Authors: William Yue
Abstract: The widespread success of artificial intelligence in fields like natural language processing and computer vision has not yet fully transferred to robotics, where progress is hindered by the lack of large-scale training data and the complexity of real-world tasks. To address this, many robot learning researchers are pushing to get robots deployed at scale in everyday unstructured environments like our homes to initiate a data flywheel. While current robot learning systems are effective for certain short-horizon tasks, they are not designed to autonomously operate over long time horizons in unstructured environments. This thesis focuses on addressing two key challenges for robots operating over long time horizons: memory and lifelong learning. We propose two novel methods to advance these capabilities. First, we introduce t-DGR, a trajectory-based deep generative replay method that achieves state-of-the-art performance on Continual World benchmarks, advancing lifelong learning. Second, we develop a framework that leverages human demonstrations to teach agents effective memory utilization, improving learning efficiency and success rates on Memory Gym tasks. Finally, we discuss future directions for achieving the lifelong learning and memory capabilities necessary for robots to function at scale in real-world settings.
Authors: Md. Monirul Islam
Abstract: Aquaculture involves cultivating marine and freshwater organisms, with real-time monitoring of aquatic parameters being crucial in fish farming. This thesis proposes an IoT-based framework using sensors and Arduino for efficient monitoring and control of water quality. Different sensors including pH, temperature, and turbidity are placed in cultivating pond water and each of them is connected to a common microcontroller board built on an Arduino Uno. The sensors read the data from the water and store it as a CSV file in an IoT cloud named Thingspeak through the Arduino Microcontroller. In the experimental part, we collected data from 5 ponds with various sizes and environments. After getting the real-time data, we compared these with the standard reference values. As a result, we can make the decision about which ponds are satisfactory for cultivating fish and what is not. After that, we labeled the data with 11 fish categories including Katla, sing, prawn, rui, koi, pangas, tilapia, silvercarp, karpio, magur, and shrimp. In addition, the data were analyzed using 10 machine learning (ML) algorithms containing J48, Random Forest, K-NN, K*, LMT, REPTree, JRIP, PART, Decision Table, and Logit boost. After experimental evaluation, it was observed among 5 ponds, only three ponds were perfect for fish farming, where these 3 ponds only satisfied the standard reference values of pH (6.5-8.5), Temperature (16-24)oC, Turbidity (below 10)ntu, Conductivity (970-1825){\mu}S/cm, and Depth (1-4) meter. Among the state-of-the-art machine learning algorithms, Random Forest achieved the highest score of performance metrics as accuracy 94.42%, kappa statistics 93.5%, and Avg. TP Rate 94.4%. In addition, we calculated the BOD, COD, and DO for one scenario. This study includes details of the proposed IoT system's prototype hardware.
Authors: Santanam Wishal
Abstract: This research introduces a hybrid classical-quantum framework for text classification, integrating GPT-Neo 125M with Low-Rank Adaptation (LoRA) and Synthetic Minority Over-sampling Technique (SMOTE) using quantum computing backends. While the GPT-Neo 125M baseline remains the best-performing model, the implementation of LoRA and SMOTE enhances the hybrid model, resulting in improved accuracy, faster convergence, and better generalization. Experiments on IBM's 127-qubit quantum backend and Pennylane's 32-qubit simulation demonstrate the viability of combining classical neural networks with quantum circuits. This framework underscores the potential of hybrid architectures for advancing natural language processing applications.
Authors: Meng Wang, Jintao Yang, Bin Yang, Hui Li, Tongxin Gong, Bo Yang, Jiangtao Cui
Abstract: Patch-wise Transformer based time series forecasting achieves superior accuracy. However, this superiority relies heavily on intricate model design with massive parameters, rendering both training and inference expensive, thus preventing their deployments on edge devices with limited resources and low latency requirements. In addition, existing methods often work in an autoregressive manner, which take into account only historical values, but ignore valuable, easy-to-obtain context information, such as weather forecasts, date and time of day. To contend with the two limitations, we propose LiPFormer, a novel Lightweight Patch-wise Transformer with weak data enriching. First, to simplify the Transformer backbone, LiPFormer employs a novel lightweight cross-patch attention and a linear transformation-based attention to eliminate Layer Normalization and Feed Forward Network, two heavy components in existing Transformers. Second, we propose a lightweight, weak data enriching module to provide additional, valuable weak supervision to the training. It enhances forecasting accuracy without significantly increasing model complexity as it does not involve expensive, human-labeling but using easily accessible context information. This facilitates the weak data enriching to plug-and-play on existing models. Extensive experiments on nine benchmark time series datasets demonstrate that LiPFormer outperforms state-of-the-art methods in accuracy, while significantly reducing parameter scale, training duration, and GPU memory usage. Deployment on an edge device reveals that LiPFormer takes only 1/3 inference time compared to classic Transformers. In addition, we demonstrate that the weak data enriching can integrate seamlessly into various Transformer based models to enhance their accuracy, suggesting its generality.
Authors: Diego Pestana
Abstract: Venezuelan banks have historically made credit card limit adjustment decisions manually through committees. However, since the number of credit card holders in Venezuela is expected to increase in the upcoming months due to economic improvements, manual decisions are starting to become unfeasible. In this project, a machine learning model that uses cost-sensitive learning is proposed to automate the task of handing out credit card limit increases. To accomplish this, several neural network and XGBoost models are trained and compared, leveraging Venezolano de Credito's data and using grid search with 10-fold cross-validation. The proposed model is ultimately chosen due to its superior balance of accuracy, cost-effectiveness, and interpretability. The model's performance is evaluated against the committee's decisions using Cohen's kappa coefficient, showing an almost perfect agreement.
Authors: Shuzhou Sun (The College of Computer Science, Nankai University, Tianjin, China, The Center for Machine Vision and Signal Analysis, University of Oulu, Finland), Li Liu (The College of Electronic Science, National University of Defense Technology, China), Yongxiang Liu (The College of Electronic Science, National University of Defense Technology, China), Zhen Liu (The College of Electronic Science, National University of Defense Technology, China), Shuanghui Zhang (The College of Electronic Science, National University of Defense Technology, China), Janne Heikkil\"a (The Center for Machine Vision and Signal Analysis, University of Oulu, Finland), Xiang Li (The College of Electronic Science, National University of Defense Technology, China)
Abstract: Bias in Foundation Models (FMs) - trained on vast datasets spanning societal and historical knowledge - poses significant challenges for fairness and equity across fields such as healthcare, education, and finance. These biases, rooted in the overrepresentation of stereotypes and societal inequalities in training data, exacerbate real-world discrimination, reinforce harmful stereotypes, and erode trust in AI systems. To address this, we introduce Trident Probe Testing (TriProTesting), a systematic testing method that detects explicit and implicit biases using semantically designed probes. Here we show that FMs, including CLIP, ALIGN, BridgeTower, and OWLv2, demonstrate pervasive biases across single and mixed social attributes (gender, race, age, and occupation). Notably, we uncover mixed biases when social attributes are combined, such as gender x race, gender x age, and gender x occupation, revealing deeper layers of discrimination. We further propose Adaptive Logit Adjustment (AdaLogAdjustment), a post-processing technique that dynamically redistributes probability power to mitigate these biases effectively, achieving significant improvements in fairness without retraining models. These findings highlight the urgent need for ethical AI practices and interdisciplinary solutions to address biases not only at the model level but also in societal structures. Our work provides a scalable and interpretable solution that advances fairness in AI systems while offering practical insights for future research on fair AI technologies.
Authors: Edward Turner
Abstract: Spatio-Temporal graph convolutional networks were originally introduced with CNNs as temporal blocks for feature extraction. Since then LSTM temporal blocks have been proposed and shown to have promising results. We propose a novel architecture combining both CNN and LSTM temporal blocks and then provide an empirical comparison between our new and the pre-existing models. We provide theoretical arguments for the different temporal blocks and use a multitude of tests across different datasets to assess our hypotheses.
Authors: Qianru Zhang, Xinyi Gao, Haixin Wang, Siu-Ming Yiu, Hongzhi Yin
Abstract: Graph neural networks (GNNs) have gained considerable attention in recent years for traffic flow prediction due to their ability to learn spatio-temporal pattern representations through a graph-based message-passing framework. Although GNNs have shown great promise in handling traffic datasets, their deployment in real-life applications has been hindered by scalability constraints arising from high-order message passing. Additionally, the over-smoothing problem of GNNs may lead to indistinguishable region representations as the number of layers increases, resulting in performance degradation. To address these challenges, we propose a new knowledge distillation paradigm termed LightST that transfers spatial and temporal knowledge from a high-capacity teacher to a lightweight student. Specifically, we introduce a spatio-temporal knowledge distillation framework that helps student MLPs capture graph-structured global spatio-temporal patterns while alleviating the over-smoothing effect with adaptive knowledge distillation. Extensive experiments verify that LightST significantly speeds up traffic flow predictions by 5X to 40X compared to state-of-the-art spatio-temporal GNNs, all while maintaining superior accuracy.
Authors: Hyunsoo Kim, Jun Hee Kim, Jaeman Son, Jihoon Song, Eunjo Lee
Abstract: In MMORPGs (Massively Multiplayer Online Role-Playing Games), abnormal players (bots) using unauthorized automated programs to carry out pre-defined behaviors systematically and repeatedly are commonly observed. Bots usually engage in these activities to gain in-game money, which they eventually trade for real money outside the game. Such abusive activities negatively impact the in-game experiences of legitimate users since bots monopolize specific hunting areas and obtain valuable items. Thus, detecting abnormal players is a significant task for game companies. Motivated by the fact that bots tend to behave collectively with similar in-game trajectories due to the auto-programs, we developed BotTRep, a framework that comprises trajectory representation learning followed by clustering using a completely unlabeled in-game trajectory dataset. Our model aims to learn representations for in-game trajectory sequences so that players with contextually similar trajectories have closer embeddings. Then, by applying DBSCAN to these representations and visualizing the corresponding moving patterns, our framework ultimately assists game masters in identifying and banning bots.
Authors: Aitor Belenguer, Jose A. Pascual, Javier Navaridas
Abstract: Fully decentralized learning algorithms are still in an early stage of development. Creating modular Gossip Learning strategies is not trivial due to convergence challenges and Byzantine faults intrinsic in systems of decentralized nature. Our contribution provides a novel means to simulate custom Gossip Learning systems by leveraging the state-of-the-art Flower Framework. Specifically, we introduce GLow, which will allow researchers to train and assess scalability and convergence of devices, across custom network topologies, before making a physical deployment. The Flower Framework is selected for being a simulation featured library with a very active community on Federated Learning research. However, Flower exclusively includes vanilla Federated Learning strategies and, thus, is not originally designed to perform simulations without a centralized authority. GLow is presented to fill this gap and make simulation of Gossip Learning systems possible. Results achieved by GLow in the MNIST and CIFAR10 datasets, show accuracies over 0.98 and 0.75 respectively. More importantly, GLow performs similarly in terms of accuracy and convergence to its analogous Centralized and Federated approaches in all designed experiments.
Authors: Somrita Ghosh, Yuelin Xu, Xiao Zhang
Abstract: Compared with standard learning, adversarially robust learning is widely recognized to demand significantly more training examples. Recent works propose the use of self-supervised adversarial training (SSAT) with external or synthetically generated unlabeled data to enhance model robustness. However, SSAT requires a substantial amount of extra unlabeled data, significantly increasing memory usage and model training times. To address these challenges, we propose novel methods to strategically select a small subset of unlabeled data essential for SSAT and robustness improvement. Our selection prioritizes data points near the model's decision boundary based on latent clustering-based techniques, efficiently identifying a critical subset of unlabeled data with a higher concentration of boundary-adjacent points. While focusing on near-boundary data, our methods are designed to maintain a balanced ratio between boundary and non-boundary data points to avoid overfitting. Our experiments on image benchmarks show that integrating our selection strategies into self-supervised adversarial training can largely reduce memory and computational requirements while achieving high model robustness. In particular, our latent clustering-based selection method with k-means is the most effective, achieving nearly identical test-time robust accuracies with 5 to 10 times less external or generated unlabeled data when applied to image benchmarks. Additionally, we validate the generalizability of our approach across various application scenarios, including a real-world medical dataset for COVID-19 chest X-ray classification.
Authors: Alex Egg
Abstract: This paper demonstrates the successful application of Off-Policy Evaluation (OPE) to accelerate recommender system development and optimization at Adyen, a global leader in financial payment processing. Facing the limitations of traditional A/B testing, which proved slow, costly, and often inconclusive, we integrated OPE to enable rapid evaluation of new recommender system variants using historical data. Our analysis, conducted on a billion-scale dataset of transactions, reveals a strong correlation between OPE estimates and online A/B test results, projecting an incremental 9--54 million transactions over a six-month period. We explore the practical challenges and trade-offs associated with deploying OPE in a high-volume production environment, including leveraging exploration traffic for data collection, mitigating variance in importance sampling, and ensuring scalability through the use of Apache Spark. By benchmarking various OPE estimators, we provide guidance on their effectiveness and integration into the decision-making systems for large-scale industrial payment systems.
Authors: Aditya Ballal, Esha Datta, Gregory A. DePaul, Erik Carlsson, Ye Chen-Izu, Javier E. L\'opez, Leighton T. Izu
Abstract: Clustering large high-dimensional datasets with diverse variable is essential for extracting high-level latent information from these datasets. Here, we developed an unsupervised clustering algorithm, we call "Village-Net". Village-Net is specifically designed to effectively cluster high-dimension data without priori knowledge on the number of existing clusters. The algorithm operates in two phases: first, utilizing K-Means clustering, it divides the dataset into distinct subsets we refer to as "villages". Next, a weighted network is created, with each node representing a village, capturing their proximity relationships. To achieve optimal clustering, we process this network using a community detection algorithm called Walk-likelihood Community Finder (WLCF), a community detection algorithm developed by one of our team members. A salient feature of Village-Net Clustering is its ability to autonomously determine an optimal number of clusters for further analysis based on inherent characteristics of the data. We present extensive benchmarking on extant real-world datasets with known ground-truth labels to showcase its competitive performance, particularly in terms of the normalized mutual information (NMI) score, when compared to other state-of-the-art methods. The algorithm is computationally efficient, boasting a time complexity of O(N*k*d), where N signifies the number of instances, k represents the number of villages and d represents the dimension of the dataset, which makes it well suited for effectively handling large-scale datasets.
Authors: Daniel Severo, Giuseppe Ottaviano, Matthew Muckley, Karen Ullrich, Matthijs Douze
Abstract: Approximate nearest neighbor search for vectors relies on indexes that are most often accessed from RAM. Therefore, storage is the factor limiting the size of the database that can be served from a machine. Lossy vector compression, i.e., embedding quantization, has been applied extensively to reduce the size of indexes. However, for inverted file and graph-based indices, auxiliary data such as vector ids and links (edges) can represent most of the storage cost. We introduce and evaluate lossless compression schemes for these cases. These approaches are based on asymmetric numeral systems or wavelet trees that exploit the fact that the ordering of ids is irrelevant within the data structures. In some settings, we are able to compress the vector ids by a factor 7, with no impact on accuracy or search runtime. On billion-scale datasets, this results in a reduction of 30% of the index size. Furthermore, we show that for some datasets, these methods can also compress the quantized vector codes losslessly, by exploiting sub-optimalities in the original quantization algorithm. The source code for our approach available at https://github.com/facebookresearch/vector_db_id_compression.
URLs: https://github.com/facebookresearch/vector_db_id_compression.
Authors: Qinyi Tian, Winston Lindqwister, Manolis Veveakis, Laura E. Dalton
Abstract: Advancements in deep learning have improved the ability to model complex, nonlinear relationships, such as those encountered in complex material inverse problems. However, the effectiveness of these methods often depends on large datasets, which are not always available. In this study, the incorporation of domain-specific knowledge of mechanical behavior is investigated to evaluate the impact on the predictive performance of the models in data-scarce scenarios. To demonstrate this, stress-strain curves were used to predict key microstructural features of porous materials, and the performance of models trained with and without domain knowledge was compared using five deep learning models: Convolutional Neural Networks, Extreme Gradient Boosting, K-Nearest Neighbors, Long Short-Term Memory, and Random Forest. The results of the models with domain-specific characteristics consistently achieved higher $R^2$ values and improved learning efficiency compared to models without prior knowledge. When the models did not include domain knowledge, the model results revealed meaningful patterns were not recognized, while those enhanced with mechanical insights showed superior feature extraction and predictions. These findings underscore the critical role of domain knowledge in guiding deep learning models, highlighting the need to combine domain expertise with data-driven approaches to achieve reliable and accurate outcomes in materials science and related fields.
Authors: James Sadler, Rizwaan Mohammed, Michael Castle, Kotub Uddin
Abstract: Modeling lithium-ion battery (LIB) degradation offers significant cost savings and enhances the safety and reliability of electric vehicles (EVs) and battery energy storage systems (BESS). Whilst data-driven methods have received great attention for forecasting degradation, they often demonstrate limited generalization ability and tend to underperform particularly in critical scenarios involving accelerated degradation, which are crucial to predict accurately. These methods also fail to elucidate the underlying causes of degradation. Alternatively, physical models provide a deeper understanding, but their complex parameters and inherent uncertainties limit their applicability in real-world settings. To this end, we propose a new model - ACCEPT. Our novel framework uses contrastive learning to map the relationship between the underlying physical degradation parameters and observable operational quantities, combining the benefits of both approaches. Furthermore, due to the similarity of degradation paths between LIBs with the same chemistry, this model transfers non-trivially to most downstream tasks, allowing for zero-shot inference. Additionally, since categorical features can be included in the model, it can generalize to other LIB chemistries. This work establishes a foundational battery degradation model, providing reliable forecasts across a range of battery types and operating conditions.
Authors: Narges Rashvand, Sanaz Sadat Hosseini, Mona Azarbayjani, Hamed Tabkhi
Abstract: Bus transit plays a vital role in urban public transportation but often struggles to provide accurate and reliable departure times. This leads to delays, passenger dissatisfaction, and decreased ridership, particularly in transit-dependent areas. A major challenge lies in the discrepancy between actual and scheduled bus departure times, which disrupts timetables and impacts overall operational efficiency. To address these challenges, this paper presents a neural network-based approach for real-time bus departure time prediction tailored for smart IoT public transit applications. We leverage AI-driven models to enhance the accuracy of bus schedules by preprocessing data, engineering relevant features, and implementing a fully connected neural network that utilizes historical departure data to predict departure times at subsequent stops. In our case study analyzing bus data from Boston, we observed an average deviation of nearly 4 minutes from scheduled times. However, our model, evaluated across 151 bus routes, demonstrates a significant improvement, predicting departure time deviations with an accuracy of under 80 seconds. This advancement not only improves the reliability of bus transit schedules but also plays a crucial role in enabling smart bus systems and IoT applications within public transit networks. By providing more accurate real-time predictions, our approach can facilitate the integration of IoT devices, such as smart bus stops and passenger information systems, that rely on precise data for optimal performance.
Authors: Sergio Rozada, Santiago Paternain, Juan Andres Bazerque, Antonio G. Marques
Abstract: In pursuit of reinforcement learning systems that could train in physical environments, we investigate multi-task approaches as a means to alleviate the need for massive data acquisition. In a tabular scenario where the Q-functions are collected across tasks, we model our learning problem as optimizing a higher order tensor structure. Recognizing that close-related tasks may require similar actions, our proposed method imposes a low-rank condition on this aggregated Q-tensor. The rationale behind this approach to multi-task learning is that the low-rank structure enforces the notion of similarity, without the need to explicitly prescribe which tasks are similar, but inferring this information from a reduced amount of data simultaneously with the stochastic optimization of the Q-tensor. The efficiency of our low-rank tensor approach to multi-task learning is demonstrated in two numerical experiments, first in a benchmark environment formed by a collection of inverted pendulums, and then into a practical scenario involving multiple wireless communication devices.
Authors: Taehee Jeong
Abstract: Retrieval-augmented generation (RAG) is a promising technique that has shown great potential in addressing some of the limitations of large language models (LLMs). LLMs have two major limitations: they can contain outdated information due to their training data, and they can generate factually inaccurate responses, a phenomenon known as hallucinations. RAG aims to mitigate these issues by leveraging a database of relevant documents, which are stored as embedding vectors in a high-dimensional space. However, one of the challenges of using high-dimensional embeddings is that they require a significant amount of memory to store. This can be a major issue, especially when dealing with large databases of documents. To alleviate this problem, we propose the use of 4-bit quantization to store the embedding vectors. This involves reducing the precision of the vectors from 32-bit floating-point numbers to 4-bit integers, which can significantly reduce the memory requirements. Our approach has several benefits. Firstly, it significantly reduces the memory storage requirements of the high-dimensional vector database, making it more feasible to deploy RAG systems in resource-constrained environments. Secondly, it speeds up the searching process, as the reduced precision of the vectors allows for faster computation. Our code is available at https://github.com/taeheej/4bit-Quantization-in-Vector-Embedding-for-RAG
URLs: https://github.com/taeheej/4bit-Quantization-in-Vector-Embedding-for-RAG
Authors: Ichiro Hashimoto, Stanislav Volgushev, Piotr Zwiernik
Abstract: The practical success of deep learning has led to the discovery of several surprising phenomena. One of these phenomena, that has spurred intense theoretical research, is ``benign overfitting'': deep neural networks seem to generalize well in the over-parametrized regime even though the networks show a perfect fit to noisy training data. It is now known that benign overfitting also occurs in various classical statistical models. For linear maximum margin classifiers, benign overfitting has been established theoretically in a class of mixture models with very strong assumptions on the covariate distribution. However, even in this simple setting, many questions remain open. For instance, most of the existing literature focuses on the noiseless case where all true class labels are observed without errors, whereas the more interesting noisy case remains poorly understood. We provide a comprehensive study of benign overfitting for linear maximum margin classifiers. We discover a phase transition in test error bounds for the noisy model which was previously unknown and provide some geometric intuition behind it. We further considerably relax the required covariate assumptions in both, the noisy and noiseless case. Our results demonstrate that benign overfitting of maximum margin classifiers holds in a much wider range of scenarios than was previously known and provide new insights into the underlying mechanisms.
Authors: Mostafa Abbasi, Maziyar Khadivi, Maryam Ahang, Patricia Lasserre, Yves Lucet, Homayoun Najjaran
Abstract: We present a novel 5-step framework called Fine-Tuned Offline Reinforcement Learning Augmented Process Sequence Optimization (FORLAPS), which aims to identify optimal execution paths in business processes using reinforcement learning. We implemented this approach on real-life event logs from our case study an energy regulator in Canada and other real-life event logs, demonstrating the feasibility of the proposed method. Additionally, to compare FORLAPS with the existing models (Permutation Feature Importance and multi-task LSTM-Based model), we experimented to evaluate its effectiveness in terms of resource savings and process time span reduction. The experimental results on real-life event log validate that FORLAPS achieves 31% savings in resource time spent and a 23% reduction in process time span. Using this innovative data augmentation technique, we propose a fine-tuned reinforcement learning approach that aims to automatically fine-tune the model by selectively increasing the average estimated Q-value in the sampled batches. The results show that we obtained a 44% performance improvement compared to the pre-trained model. This study introduces an innovative evaluation model, benchmarking its performance against earlier works using nine publicly available datasets. Robustness is ensured through experiments utilizing the Damerau-Levenshtein distance as the primary metric. In addition, we discussed the suitability of datasets, taking into account their inherent properties, to evaluate the performance of different models. The proposed model, FORLAPS, demonstrated exceptional performance, outperforming existing state-of-the-art approaches in suggesting the most optimal policies or predicting the best next activities within a process trace.
Authors: Dongjie Wang, Yanyong Huang, Wangyang Ying, Haoyue Bai, Nanxu Gong, Xinyuan Wang, Sixun Dong, Tao Zhe, Kunpeng Liu, Meng Xiao, Pengfei Wang, Pengyang Wang, Hui Xiong, Yanjie Fu
Abstract: Tabular data is one of the most widely used formats across industries, driving critical applications in areas such as finance, healthcare, and marketing. In the era of data-centric AI, improving data quality and representation has become essential for enhancing model performance, particularly in applications centered around tabular data. This survey examines the key aspects of tabular data-centric AI, emphasizing feature selection and feature generation as essential techniques for data space refinement. We provide a systematic review of feature selection methods, which identify and retain the most relevant data attributes, and feature generation approaches, which create new features to simplify the capture of complex data patterns. This survey offers a comprehensive overview of current methodologies through an analysis of recent advancements, practical applications, and the strengths and limitations of these techniques. Finally, we outline open challenges and suggest future perspectives to inspire continued innovation in this field.
Authors: Sergio Rozada, Jose Luis Orejuela, Antonio G. Marques
Abstract: We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the policies, and therefore the value functions (VFs) are not stationary. This aggravates the challenges of high-dimensional MDPs, as they suffer from the curse of dimensionality and high sample complexity. To address these issues, we propose modeling the VFs of finite-horizon MDPs as low-rank tensors, enabling a scalable representation that renders the problem of learning optimal policies tractable. We introduce an optimization-based framework for solving the Bellman equations with low-rank constraints, along with block-coordinate descent (BCD) and block-coordinate gradient descent (BCGD) algorithms, both with theoretical convergence guarantees. For scenarios where the system dynamics are unknown, we adapt the proposed BCGD method to estimate the VFs using sampled trajectories. Numerical experiments further demonstrate that the proposed framework reduces computational demands in controlled synthetic scenarios and more realistic resource allocation problems.
Authors: Ali Baheri, Zahra Sharooei, Chirayu Salgarkar
Abstract: We present Wasserstein Adaptive Value Estimation for Actor-Critic (WAVE), an approach to enhance stability in deep reinforcement learning through adaptive Wasserstein regularization. Our method addresses the inherent instability of actor-critic algorithms by incorporating an adaptively weighted Wasserstein regularization term into the critic's loss function. We prove that WAVE achieves $\mathcal{O}\left(\frac{1}{k}\right)$ convergence rate for the critic's mean squared error and provide theoretical guarantees for stability through Wasserstein-based regularization. Using the Sinkhorn approximation for computational efficiency, our approach automatically adjusts the regularization based on the agent's performance. Theoretical analysis and experimental results demonstrate that WAVE achieves superior performance compared to standard actor-critic methods.
Authors: Pritish Chakraborty, Vinayak Gupta, Rahul R, Srikanta J. Bedathur, Abir De
Abstract: Marked temporal point processes (MTPPs) have been shown to be extremely effective in modeling continuous time event sequences (CTESs). In this work, we present adversarial attacks designed specifically for MTPP models. A key criterion for a good adversarial attack is its imperceptibility. For objects such as images or text, this is often achieved by bounding perturbation in some fixed $L_p$ norm-ball. However, similarly minimizing distance norms between two CTESs in the context of MTPPs is challenging due to their sequential nature and varying time-scales and lengths. We address this challenge by first permuting the events and then incorporating the additive noise to the arrival timestamps. However, the worst case optimization of such adversarial attacks is a hard combinatorial problem, requiring exploration across a permutation space that is factorially large in the length of the input sequence. As a result, we propose a novel differentiable scheme PERMTPP using which we can perform adversarial attacks by learning to minimize the likelihood, while minimizing the distance between two CTESs. Our experiments on four real-world datasets demonstrate the offensive and defensive capabilities, and lower inference times of PERMTPP.
Authors: Dong Qiao, Jicong Fan
Abstract: The maximum mean discrepancy and Wasserstein distance are popular distance measures between distributions and play important roles in many machine learning problems such as metric learning, generative modeling, domain adaption, and clustering. However, since they are functions of pair-wise distances between data points in two distributions, they do not exploit the potential manifold properties of data such as smoothness and hence are not effective in measuring the dissimilarity between the two distributions in the form of manifolds. In this paper, different from existing measures, we propose a novel distance called Mutual Regression Distance (MRD) induced by a constrained mutual regression problem, which can exploit the manifold property of data. We prove that MRD is a pseudometric that satisfies almost all the axioms of a metric. Since the optimization of the original MRD is costly, we provide a tight MRD and a simplified MRD, based on which a heuristic algorithm is established. We also provide kernel variants of MRDs that are more effective in handling nonlinear data. Our MRDs especially the simplified MRDs have much lower computational complexity than the Wasserstein distance. We provide theoretical guarantees, such as robustness, for MRDs. Finally, we apply MRDs to distribution clustering, generative models, and domain adaptation. The numerical results demonstrate the effectiveness and superiority of MRDs compared to the baselines.
Authors: Zheng Li, Haoming Meng, Chengyuan Ma, Ke Ma, Xiaopeng Li
Abstract: The Markov property serves as a foundational assumption in most existing work on vehicle driving behavior, positing that future states depend solely on the current state, not the series of preceding states. This study validates the Markov properties of vehicle trajectories for both Autonomous Vehicles (AVs) and Human-driven Vehicles (HVs). A statistical method used to test whether time series data exhibits Markov properties is applied to examine whether the trajectory data possesses Markov characteristics. t test and F test are additionally introduced to characterize the differences in Markov properties between AVs and HVs. Based on two public trajectory datasets, we investigate the presence and order of the Markov property of different types of vehicles through rigorous statistical tests. Our findings reveal that AV trajectories generally exhibit stronger Markov properties compared to HV trajectories, with a higher percentage conforming to the Markov property and lower Markov orders. In contrast, HV trajectories display greater variability and heterogeneity in decision-making processes, reflecting the complex perception and information processing involved in human driving. These results have significant implications for the development of driving behavior models, AV controllers, and traffic simulation systems. Our study also demonstrates the feasibility of using statistical methods to test the presence of Markov properties in driving trajectory data.
Authors: Pengyang Song, Han Feng, Shreyashi Shukla, Jue Wang, Tao Hong
Abstract: Load forecasting is a fundamental task in smart grid. Many techniques have been applied to developing load forecasting models. Due to the challenges such as the Curse of Dimensionality, overfitting, and limited computing resources, multivariate higher-order polynomial models have received limited attention in load forecasting, despite their desirable mathematical foundations and optimization properties. In this paper, we propose low rank approximation and self-supervised dimension reduction to address the aforementioned issues. To further improve computational efficiency, we also introduce a fast Conjugate Gradient based algorithm for the proposed polynomial models. Based on the ISO New England dataset used in Global Energy Forecasting Competition 2017, the proposed method high-order polynomials with self-supervised dimension reduction (HOPS) demonstrates higher forecasting accuracy over several competitive models. Additionally, experimental results indicate that our approach alleviates redundant variable construction, achieving better forecasts with fewer input variables.
Authors: Yubo Yang, Tao Yang, Xiaofeng Wu, Bo Hu
Abstract: The rapid development of Unmanned aerial vehicles (UAVs) technology has spawned a wide variety of applications, such as emergency communications, regional surveillance, and disaster relief. Due to their limited battery capacity and processing power, multiple UAVs are often required for complex tasks. In such cases, a control center is crucial for coordinating their activities, which fits well with the federated learning (FL) framework. However, conventional FL approaches often focus on a single task, ignoring the potential of training multiple related tasks simultaneously. In this paper, we propose a UAV-assisted multi-task federated learning scheme, in which data collected by multiple UAVs can be used to train multiple related tasks concurrently. The scheme facilitates the training process by sharing feature extractors across related tasks and introduces a task attention mechanism to balance task performance and encourage knowledge sharing. To provide an analytical description of training performance, the convergence analysis of the proposed scheme is performed. Additionally, the optimal bandwidth allocation for UAVs under limited bandwidth conditions is derived to minimize communication time. Meanwhile, a UAV-EV association strategy based on coalition formation game is proposed. Simulation results validate the effectiveness of the proposed scheme in enhancing multi-task performance and training speed.
Authors: Chongjie Si, Jingjing Jiang, Wei Shen
Abstract: This paper presents a pioneering exploration of the mechanisms underlying large foundation models' (LFMs) weights, aiming to simplify AI research. Through extensive observation and analysis on prevailing LFMs, we find that regardless of initialization strategies, their weights predominantly follow a Gaussian distribution, with occasional sharp, inverted T-shaped, or linear patterns. We further discover that the weights share the i.i.d. properties of Gaussian noise, and explore their direct relationship. We find that transformation weights can be derived from Gaussian noise, and they primarily serve to increase the standard deviation of pre-trained weights, with their standard deviation growing with layer depth. In other words, transformation weights broaden the acceptable deviation from the optimal weights, facilitating adaptation to downstream tasks. Building upon the above conclusions, we thoroughly discussed the nature of optimal weights, ultimately concluding that they should exhibit zero-mean, symmetry, and sparsity, with the sparse values being a truncated Gaussian distribution and a few outliers. Our experiments in LFM adaptation and editing demonstrate the effectiveness of these insights. We hope these findings can provide a foundational understanding to pave the way for future advancements in the LFM community.
Authors: Harsh Joshi, Rajeshwari Mistri, Manasi Mali, Nachiket Kapure, Parul Kumari
Abstract: The challenge of missing data remains a significant obstacle across various scientific domains, necessitating the development of advanced imputation techniques that can effectively address complex missingness patterns. This study introduces the Precision Adaptive Imputation Network (PAIN), a novel algorithm designed to enhance data reconstruction by dynamically adapting to diverse data types, distributions, and missingness mechanisms. PAIN employs a tri-step process that integrates statistical methods, random forests, and autoencoders, ensuring balanced accuracy and efficiency in imputation. Through rigorous evaluation across multiple datasets, including those characterized by high-dimensional and correlated features, PAIN consistently outperforms traditional imputation methods, such as mean and median imputation, as well as other advanced techniques like MissForest. The findings highlight PAIN's superior ability to preserve data distributions and maintain analytical integrity, particularly in complex scenarios where missingness is not completely at random. This research not only contributes to a deeper understanding of missing data reconstruction but also provides a critical framework for future methodological innovations in data science and machine learning, paving the way for more effective handling of mixed-type datasets in real-world applications.
Authors: Xia Li, Hanghang Zheng, Xiao Chen, Hong Liu, Mao Mao
Abstract: The advent of artificial intelligence has significantly enhanced credit scoring technologies. Despite the remarkable efficacy of advanced deep learning models, mainstream adoption continues to favor tree-structured models due to their robust predictive performance on tabular data. Although pretrained models have seen considerable development, their application within the financial realm predominantly revolves around question-answering tasks and the use of such models for tabular-structured credit scoring datasets remains largely unexplored. Tabular-oriented large models, such as TabPFN, has made the application of large models in credit scoring feasible, albeit can only processing with limited sample sizes. This paper provides a novel framework to combine tabular-tailored dataset distillation technique with the pretrained model, empowers the scalability for TabPFN. Furthermore, though class imbalance distribution is the common nature in financial datasets, its influence during dataset distillation has not been explored. We thus integrate the imbalance-aware techniques during dataset distillation, resulting in improved performance in financial datasets (e.g., a 2.5% enhancement in AUC). This study presents a novel framework for scaling up the application of large pretrained models on financial tabular datasets and offers a comparative analysis of the influence of class imbalance on the dataset distillation process. We believe this approach can broaden the applications and downstream tasks of large models in the financial domain.
Authors: Amogh Raj, Carol Eunice Gudumotou, Sakol Bun, Keerthana Srinivasa, Arash Sarshar
Abstract: We present a novel framework combining Deep Operator Networks (DeepONets) with Physics-Informed Neural Networks (PINNs) to solve partial differential equations (PDEs) and estimate their unknown parameters. By integrating data-driven learning with physical constraints, our method achieves robust and accurate solutions across diverse scenarios. Bayesian training is implemented through variational inference, allowing for comprehensive uncertainty quantification for both aleatoric and epistemic uncertainties. This ensures reliable predictions and parameter estimates even in noisy conditions or when some of the physical equations governing the problem are missing. The framework demonstrates its efficacy in solving forward and inverse problems, including the 1D unsteady heat equation and 2D reaction-diffusion equations, as well as regression tasks with sparse, noisy observations. This approach provides a computationally efficient and generalizable method for addressing uncertainty quantification in PDE surrogate modeling.
Authors: Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Zhen Zhuang
Abstract: Looped Transformers have shown exceptional capability in simulating traditional graph algorithms, but their application to more complex structures like hypergraphs remains underexplored. Hypergraphs generalize graphs by modeling higher-order relationships among multiple entities, enabling richer representations but introducing significant computational challenges. In this work, we extend the Loop Transformer architecture to simulate hypergraph algorithms efficiently, addressing the gap between neural networks and combinatorial optimization over hypergraphs. In this paper, we extend the Loop Transformer architecture to simulate hypergraph algorithms efficiently, addressing the gap between neural networks and combinatorial optimization over hypergraphs. Specifically, we propose a novel degradation mechanism for reducing hypergraphs to graph representations, enabling the simulation of graph-based algorithms, such as Dijkstra's shortest path. Furthermore, we introduce a hyperedge-aware encoding scheme to simulate hypergraph-specific algorithms, exemplified by Helly's algorithm. The paper establishes theoretical guarantees for these simulations, demonstrating the feasibility of processing high-dimensional and combinatorial data using Loop Transformers. This work highlights the potential of Transformers as general-purpose algorithmic solvers for structured data.
Authors: Xinglin Pan, Wenxiang Lin, Lin Zhang, Shaohuai Shi, Zhenheng Tang, Rui Wang, Bo Li, Xiaowen Chu
Abstract: Recent large language models (LLMs) have tended to leverage sparsity to reduce computations, employing the sparsely activated mixture-of-experts (MoE) technique. MoE introduces four modules, including token routing, token communication, expert computation, and expert parallelism, that impact model quality and training efficiency. To enable versatile usage of MoE models, we introduce FSMoE, a flexible training system optimizing task scheduling with three novel techniques: 1) Unified abstraction and online profiling of MoE modules for task scheduling across various MoE implementations. 2) Co-scheduling intra-node and inter-node communications with computations to minimize communication overheads. 3) To support near-optimal task scheduling, we design an adaptive gradient partitioning method for gradient aggregation and a schedule to adaptively pipeline communications and computations. We conduct extensive experiments with configured MoE layers and real-world MoE models on two GPU clusters. Experimental results show that 1) our FSMoE supports four popular types of MoE routing functions and is more efficient than existing implementations (with up to a 1.42$\times$ speedup), and 2) FSMoE outperforms the state-of-the-art MoE training systems (DeepSpeed-MoE and Tutel) by 1.18$\times$-1.22$\times$ on 1458 MoE layers and 1.19$\times$-3.01$\times$ on real-world MoE models based on GPT-2 and Mixtral using a popular routing function.
Authors: Jiannan Li, Yiyang Yang, Shaojie Tang, Yao Wang
Abstract: Modern decision-making scenarios often involve data that is both high-dimensional and rich in higher-order contextual information, where existing bandits algorithms fail to generate effective policies. In response, we propose in this paper a generalized linear tensor bandits algorithm designed to tackle these challenges by incorporating low-dimensional tensor structures, and further derive a unified analytical framework of the proposed algorithm. Specifically, our framework introduces a convex optimization approach with the weakly decomposable regularizers, enabling it to not only achieve better results based on the tensor low-rankness structure assumption but also extend to cases involving other low-dimensional structures such as slice sparsity and low-rankness. The theoretical analysis shows that, compared to existing low-rankness tensor result, our framework not only provides better bounds but also has a broader applicability. Notably, in the special case of degenerating to low-rank matrices, our bounds still offer advantages in certain scenarios.
Authors: David Millard, Arielle Carr, St\'ephane Gaudreault, Ali Baheri
Abstract: We present PEARL (Preconditioner Enhancement through Actor-critic Reinforcement Learning), a novel approach to learning matrix preconditioners. Existing preconditioners such as Jacobi, Incomplete LU, and Algebraic Multigrid methods offer problem-specific advantages but rely heavily on hyperparameter tuning. Recent advances have explored using deep neural networks to learn preconditioners, though challenges such as misbehaved objective functions and costly training procedures remain. PEARL introduces a reinforcement learning approach for learning preconditioners, specifically, a contextual bandit formulation. The framework utilizes an actor-critic model, where the actor generates the incomplete Cholesky decomposition of preconditioners, and the critic evaluates them based on reward-specific feedback. To further guide the training, we design a dual-objective function, combining updates from the critic and condition number. PEARL contributes a generalizable preconditioner learning method, dynamic sparsity exploration, and cosine schedulers for improved stability and exploratory power. We compare our approach to traditional and neural preconditioners, demonstrating improved flexibility and iterative solving speed.
Authors: Carlos Mougan
Abstract: Model monitoring involves analyzing AI algorithms once they have been deployed and detecting changes in their behaviour. This thesis explores machine learning model monitoring ML before the predictions impact real-world decisions or users. This step is characterized by one particular condition: the absence of labelled data at test time, which makes it challenging, even often impossible, to calculate performance metrics. The thesis is structured around two main themes: (i) AI alignment, measuring if AI models behave in a manner consistent with human values and (ii) performance monitoring, measuring if the models achieve specific accuracy goals or desires. The thesis uses a common methodology that unifies all its sections. It explores feature attribution distributions for both monitoring dimensions. Using these feature attribution explanations, we can exploit their theoretical properties to derive and establish certain guarantees and insights into model monitoring.
Authors: Carlos Mougan, Deniz Sezin Ayvaz, Lorenzo Belenguer, Hankun He, Deborah Dormah Kanubala, Mingxu Li, Soung Low, Faithful Chiagoziem Onwuegbuche, Yulu Pi, Natalia Sikora, Dan Tran, Shresth Verma, Hanzhi Wang, Skyler Xie, Adeline Pelletier
Abstract: Mastercard, a global leader in financial services, develops and deploys machine learning models aimed at optimizing card usage and preventing attrition through advanced predictive models. These models use aggregated and anonymized card usage patterns, including cross-border transactions and industry-specific spending, to tailor bank offerings and maximize revenue opportunities. Mastercard has established an AI Governance program, based on its Data and Tech Responsibility Principles, to evaluate any built and bought AI for efficacy, fairness, and transparency. As part of this effort, Mastercard has sought expertise from the Turing Institute through a Data Study Group to better assess fairness in more complex AI/ML models. The Data Study Group challenge lies in defining, measuring, and mitigating fairness in these predictions, which can be complex due to the various interpretations of fairness, gaps in the research literature, and ML-operations challenges.
Authors: Jing Chen, Haocheng Ye, Zhian Ying, Yuntao Sun, Wenqiang Xu
Abstract: Accurate traffic flow prediction is essential for applications like transport logistics but remains challenging due to complex spatio-temporal correlations and non-linear traffic patterns. Existing methods often model spatial and temporal dependencies separately, failing to effectively fuse them. To overcome this limitation, the Dynamic Spatial-Temporal Trend Transformer DST2former is proposed to capture spatio-temporal correlations through adaptive embedding and to fuse dynamic and static information for learning multi-view dynamic features of traffic networks. The approach employs the Dynamic Trend Representation Transformer (DTRformer) to generate dynamic trends using encoders for both temporal and spatial dimensions, fused via Cross Spatial-Temporal Attention. Predefined graphs are compressed into a representation graph to extract static attributes and reduce redundancy. Experiments on four real-world traffic datasets demonstrate that our framework achieves state-of-the-art performance.
Authors: Yen-Ting Lin, Di Jin, Tengyu Xu, Tianhao Wu, Sainbayar Sukhbaatar, Chen Zhu, Yun He, Yun-Nung Chen, Jason Weston, Yuandong Tian, Arash Rahnama, Sinong Wang, Hao Ma, Han Fang
Abstract: Large language models (LLMs) have recently demonstrated remarkable success in mathematical reasoning. Despite progress in methods like chain-of-thought prompting and self-consistency sampling, these advances often focus on final correctness without ensuring that the underlying reasoning process is coherent and reliable. This paper introduces Step-KTO, a training framework that combines process-level and outcome-level binary feedback to guide LLMs toward more trustworthy reasoning trajectories. By providing binary evaluations for both the intermediate reasoning steps and the final answer, Step-KTO encourages the model to adhere to logical progressions rather than relying on superficial shortcuts. Our experiments on challenging mathematical benchmarks show that Step-KTO significantly improves both final answer accuracy and the quality of intermediate reasoning steps. For example, on the MATH-500 dataset, Step-KTO achieves a notable improvement in Pass@1 accuracy over strong baselines. These results highlight the promise of integrating stepwise process feedback into LLM training, paving the way toward more interpretable and dependable reasoning capabilities.
Authors: Oliver Goldstein, Emanuele La Malfa, Felix Drinkall, Samuele Marro, Michael Wooldridge
Abstract: We discuss the "Infinitely Many Meanings" attacks (IMM), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded communications to bypass their defensive mechanisms. IMMs' viability pairs and grows with a model's capabilities to handle and bind the semantics of simple mappings between tokens and work extremely well in practice, posing a concrete threat to the users of the most powerful LLMs in commerce. We show how one can bypass the safeguards of the most powerful open- and closed-source LLMs and generate content that explicitly violates their safety policies. One can protect against IMMs by improving the guardrails and making them scale with the LLMs' capabilities. For two categories of attacks that are straightforward to implement, i.e., bijection and encoding, we discuss two defensive strategies, one in token and the other in embedding space. We conclude with some research questions we believe should be prioritised to enhance the defensive mechanisms of LLMs and our understanding of their safety.
Authors: Renato Assun\c{c}\~ao, Fl\'avio Figueiredo, Francisco N. Tinoco J\'unior, L\'eo M. de S\'a-Freire, F\'abio Silva
Abstract: A fundamental task in statistical learning is quantifying the joint dependence or association between two continuous random variables. We introduce a novel, fully non-parametric measure that assesses the degree of association between continuous variables $X$ and $Y$, capable of capturing a wide range of relationships, including non-functional ones. A key advantage of this measure is its interpretability: it quantifies the expected relative loss in predictive accuracy when the distribution of $X$ is ignored in predicting $Y$. This measure is bounded within the interval [0,1] and is equal to zero if and only if $X$ and $Y$ are independent. We evaluate the performance of our measure on over 90,000 real and synthetic datasets, benchmarking it against leading alternatives. Our results demonstrate that the proposed measure provides valuable insights into underlying relationships, particularly in cases where existing methods fail to capture important dependencies.
Authors: Francisco Charte, Miguel \'Angel D\'avila, Mar\'ia Dolores P\'erez-Godoy, Mar\'ia Jos\'e del Jesus
Abstract: Predictive models trained on imbalanced data tend to produce biased results. This problem is exacerbated when there is not just one output label, but a set of them. This is the case for multilabel learning (MLL) algorithms used to classify patterns, rank labels, or learn the distribution of outputs. Many solutions have been proposed in the literature. The one that can be applied universally, independent of the algorithm used to build the model, is data resampling. The generation of new instances associated with minority labels, so that empty areas of the feature space are filled, helps to improve the obtained models. The quality of these new instances depends on the algorithm used to generate them. In this paper, a diffusion model tailored to produce new instances for MLL data, called MLDM (\textit{MultiLabel Diffusion Model}), is proposed. Diffusion models have been mainly used to generate artificial images and videos. Our proposed MLDM is based on this type of models. The experiments conducted compare MLDM with several other MLL resampling algorithms. The results show that MLDM is competitive while it improves efficiency.
Authors: Duy Nguyen, Trung T. Nguyen, Cuong V. Nguyen
Abstract: The popularity of e-commerce has given rise to fake advertisements that can expose users to financial and data risks while damaging the reputation of these e-commerce platforms. For these reasons, detecting and removing such fake advertisements are important for the success of e-commerce websites. In this paper, we propose FADAML, a novel end-to-end machine learning system to detect and filter out fake online advertisements. Our system combines techniques in multimodal machine learning and automated machine learning to achieve a high detection rate. As a case study, we apply FADAML to detect fake advertisements on popular Vietnamese real estate websites. Our experiments show that we can achieve 91.5% detection accuracy, which significantly outperforms three different state-of-the-art fake news detection systems.
Authors: Christopher Angelini, Nidhal Bouaynaya
Abstract: When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose using parameter-based uncertainty to determine which parameters are relevant to a network's learned function and regularize training to prevent change in these important parameters. We approach this regularization in two ways: (1), we constrain critical parameters from significant changes by associating more critical parameters with lower learning rates, thereby limiting alterations in those parameters; (2), important parameters are restricted from change by imposing a higher regularization weighting, causing parameters to revert to their states prior to the learning of subsequent tasks. We leverage a Bayesian Moment Propagation framework which learns network parameters concurrently with their associated uncertainties while allowing each parameter to contribute uncertainty to the network's predictive distribution, avoiding the pitfalls of existing sampling-based methods. The proposed approach is evaluated for common sequential benchmark datasets and compared to existing published approaches from the Continual Learning community. Ultimately, we show improved Continual Learning performance for Average Test Accuracy and Backward Transfer metrics compared to sampling-based methods and other non-uncertainty-based approaches.
Authors: Anuvab Sen, Udayon Sen, Mayukhi Paul, Apurba Prasad Padhy, Sujith Sai, Aakash Mallik, Chhandak Mallick
Abstract: Accurate weather forecasting holds significant importance, serving as a crucial tool for decision-making in various industrial sectors. The limitations of statistical models, assuming independence among data points, highlight the need for advanced methodologies. The correlation between meteorological variables necessitate models capable of capturing complex dependencies. This research highlights the practical efficacy of employing advanced machine learning techniques proposing GenHybQLSTM and BO-QEnsemble architecture based on adaptive weight adjustment strategy. Through comprehensive hyper-parameter optimization using hybrid quantum genetic particle swarm optimisation algorithm and Bayesian Optimization, our model demonstrates a substantial improvement in the accuracy and reliability of meteorological predictions through the assessment of performance metrics such as MSE (Mean Squared Error) and MAPE (Mean Absolute Percentage Prediction Error). The paper highlights the importance of optimized ensemble techniques to improve the performance the given weather forecasting task.
Authors: Antonio Lech Martin-Ozimek, Isuru Jayarathne, Su Larb Mon, Jouh Yeong Chew
Abstract: Intelligent agents, such as robots and virtual agents, must understand the dynamics of complex social interactions to interact with humans. Effectively representing social dynamics is challenging because we require multi-modal, synchronized observations to understand a scene. We explore how using a single modality, the pose behavior, of multiple individuals in a social interaction can be used to generate nonverbal social cues for the facilitator of that interaction. The facilitator acts to make a social interaction proceed smoothly and is an essential role for intelligent agents to replicate in human-robot interactions. In this paper, we adapt an existing diffusion behavior cloning model to learn and replicate facilitator behaviors. Furthermore, we evaluate two representations of pose observations from a scene, one representation has pre-processing applied and one does not. The purpose of this paper is to introduce a new use for diffusion behavior cloning for pose generation in social interactions. The second is to understand the relationship between performance and computational load for generating social pose behavior using two different techniques for collecting scene observations. As such, we are essentially testing the effectiveness of two different types of conditioning for a diffusion model. We then evaluate the resulting generated behavior from each technique using quantitative measures such as mean per-joint position error (MPJPE), training time, and inference time. Additionally, we plot training and inference time against MPJPE to examine the trade-offs between efficiency and performance. Our results suggest that the further pre-processed data can successfully condition diffusion models to generate realistic social behavior, with reasonable trade-offs in accuracy and processing time.
Authors: Shayan Mohajer Hamidi, Linfeng Ye
Abstract: Federated learning (FL) is a promising technology that enables edge devices/clients to collaboratively and iteratively train a machine learning model under the coordination of a central server. The most common approach to FL is first-order methods, where clients send their local gradients to the server in each iteration. However, these methods often suffer from slow convergence rates. As a remedy, second-order methods, such as quasi-Newton, can be employed in FL to accelerate its convergence. Unfortunately, similarly to the first-order FL methods, the application of second-order methods in FL can lead to unfair models, achieving high average accuracy while performing poorly on certain clients' local datasets. To tackle this issue, in this paper we introduce a novel second-order FL framework, dubbed \textbf{d}istributed \textbf{q}uasi-\textbf{N}ewton \textbf{fed}erated learning (DQN-Fed). This approach seeks to ensure fairness while leveraging the fast convergence properties of quasi-Newton methods in the FL context. Specifically, DQN-Fed helps the server update the global model in such a way that (i) all local loss functions decrease to promote fairness, and (ii) the rate of change in local loss functions aligns with that of the quasi-Newton method. We prove the convergence of DQN-Fed and demonstrate its \textit{linear-quadratic} convergence rate. Moreover, we validate the efficacy of DQN-Fed across a range of federated datasets, showing that it surpasses state-of-the-art fair FL methods in fairness, average accuracy and convergence speed.
Authors: Alexandru Dimofte, Glenn Anta Bucagu, Thorir Mar Ingolfsson, Xiaying Wang, Andrea Cossettini, Luca Benini, Yawei Li
Abstract: Electroencephalograph (EEG) is a crucial tool for studying brain activity. Recently, self-supervised learning methods leveraging large unlabeled datasets have emerged as a potential solution to the scarcity of widely available annotated EEG data. However, current methods suffer from at least one of the following limitations: i) sub-optimal EEG signal modeling, ii) model sizes in the hundreds of millions of trainable parameters, and iii) reliance on private datasets and/or inconsistent public benchmarks, hindering reproducibility. To address these challenges, we introduce a Compact Encoder for Representations of Brain Oscillations using alternating attention (CEReBrO), a new small EEG foundation model. Our tokenization scheme represents EEG signals at a per-channel patch granularity. We propose an alternating attention mechanism that jointly models intra-channel temporal dynamics and inter-channel spatial correlations, achieving 2x speed improvement with 6x less memory required compared to standard self-attention. We present several model sizes ranging from 3.6 million to 85 million parameters. Pre-trained on over 20,000 hours of publicly available scalp EEG recordings with diverse channel configurations, our models set new benchmarks in emotion detection and seizure detection tasks, with competitive performance in anomaly classification and gait prediction. This validates our models' effectiveness and effictiveness.
Authors: Hongjin Su, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, Sercan \"O. Ar{\i}k
Abstract: Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often hindered by the lack of high-quality agent data from the corresponding environments they interact with. We propose Learn-by-interact, a data-centric framework to adapt LLM agents to any given environments without human annotations. Learn-by-interact synthesizes trajectories of agent-environment interactions based on documentations, and constructs instructions by summarizing or abstracting the interaction histories, a process called backward construction. We assess the quality of our synthetic data by using them in both training-based scenarios and training-free in-context learning (ICL), where we craft innovative retrieval approaches optimized for agents. Extensive experiments on SWE-bench, WebArena, OSWorld and Spider2-V spanning across realistic coding, web, and desktop environments show the effectiveness of Learn-by-interact in various downstream agentic tasks -- baseline results are improved by up to 12.2\% for ICL with Claude-3.5 and 19.5\% for training with Codestral-22B. We further demonstrate the critical role of backward construction, which provides up to 14.0\% improvement for training. Our ablation studies demonstrate the efficiency provided by our synthesized data in ICL and the superiority of our retrieval pipeline over alternative approaches like conventional retrieval-augmented generation (RAG). We expect that Learn-by-interact will serve as a foundation for agent data synthesis as LLMs are increasingly deployed at real-world environments.
Authors: Surojit Saha, Sarang Joshi, Ross Whitaker
Abstract: The variational autoencoder (VAE) is a popular, deep, latent-variable model (DLVM) due to its simple yet effective formulation for modeling the data distribution. Moreover, optimizing the VAE objective function is more manageable than other DLVMs. The bottleneck dimension of the VAE is a crucial design choice, and it has strong ramifications for the model's performance, such as finding the hidden explanatory factors of a dataset using the representations learned by the VAE. However, the size of the latent dimension of the VAE is often treated as a hyperparameter estimated empirically through trial and error. To this end, we propose a statistical formulation to discover the relevant latent factors required for modeling a dataset. In this work, we use a hierarchical prior in the latent space that estimates the variance of the latent axes using the encoded data, which identifies the relevant latent dimensions. For this, we replace the fixed prior in the VAE objective function with a hierarchical prior, keeping the remainder of the formulation unchanged. We call the proposed method the automatic relevancy detection in the variational autoencoder (ARD-VAE). We demonstrate the efficacy of the ARD-VAE on multiple benchmark datasets in finding the relevant latent dimensions and their effect on different evaluation metrics, such as FID score and disentanglement analysis.
Authors: Ibna Kowsar, Shourav B. Rabbani, Yina Hou, Manar D. Samad
Abstract: Missing values of varying patterns and rates in real-world tabular data pose a significant challenge in developing reliable data-driven models. Existing missing value imputation methods use statistical and traditional machine learning, which are ineffective when the missing rate is high and not at random. This paper explores row and column attention in tabular data to address the shortcomings of existing methods by introducing a new method for imputing missing values. The method combines between-feature and between-sample attention learning in a deep data reconstruction framework. The proposed data reconstruction uses CutMix data augmentation within a contrastive learning framework to improve the uncertainty of missing value estimation. The performance and generalizability of trained imputation models are evaluated on set-aside test data folds with missing values. The proposed joint attention learning outperforms nine state-of-the-art imputation methods across several missing value types and rates (10%-50%) on twelve data sets. Real electronic health records data with missing values yield the best classification accuracy when imputed using the proposed attention learning compared to other statistical, machine learning, and deep imputation methods. This paper highlights the heterogeneity of tabular data sets to recommend imputation methods based on missing value types and data characteristics.
Authors: Konrad Sundsgaard, Kutay B\"olat, Guangya Yang
Abstract: Electricity distribution cable networks suffer from incomplete and unbalanced data, hindering the effectiveness of machine learning models for predictive maintenance and reliability evaluation. Features such as the installation date of the cables are frequently missing. To address data scarcity, this study investigates the application of Variational Autoencoders (VAEs) for data enrichment, synthetic data generation, imbalanced data handling, and outlier detection. Based on a proof-of-concept case study for Denmark, targeting the imputation of missing age information in cable network asset registers, the analysis underlines the potential of generative models to support data-driven maintenance. However, the study also highlights several areas for improvement, including enhanced feature importance analysis, incorporating network characteristics and external features, and handling biases in missing data. Future initiatives should expand the application of VAEs by incorporating semi-supervised learning, advanced sampling techniques, and additional distribution grid elements, including low-voltage networks, into the analysis.
Authors: Ahmed Alagha, Rabeb Mizouni, Shakti Singh, Jamal Bentahar, Hadi Otrok
Abstract: Target localization is a critical task in sensitive applications, where multiple sensing agents communicate and collaborate to identify the target location based on sensor readings. Existing approaches investigated the use of Multi-Agent Deep Reinforcement Learning (MADRL) to tackle target localization. Nevertheless, these methods do not consider practical uncertainties, like false alarms when the target does not exist or when it is unreachable due to environmental complexities. To address these drawbacks, this work proposes a novel MADRL-based method for target localization in uncertain environments. The proposed MADRL method employs Proximal Policy Optimization to optimize the decision-making of sensing agents, which is represented in the form of an actor-critic structure using Convolutional Neural Networks. The observations of the agents are designed in an optimized manner to capture essential information in the environment, and a team-based reward functions is proposed to produce cooperative agents. The MADRL method covers three action dimensionalities that control the agents' mobility to search the area for the target, detect its existence, and determine its reachability. Using the concept of Transfer Learning, a Deep Learning model builds on the knowledge from the MADRL model to accurately estimating the target location if it is unreachable, resulting in shared representations between the models for faster learning and lower computational complexity. Collectively, the final combined model is capable of searching for the target, determining its existence and reachability, and estimating its location accurately. The proposed method is tested using a radioactive target localization environment and benchmarked against existing methods, showing its efficacy.
Authors: Ashutosh Soni, Peizhong Ju, Atilla Eryilmaz, Ness B. Shroff
Abstract: One of the most fundamental, and yet relatively less explored, goals in transfer learning is the efficient means of selecting top candidates from a large number of previously trained models (optimized for various "source" tasks) that would perform the best for a new "target" task with a limited amount of data. In this paper, we undertake this goal by developing a novel task-similarity metric (BeST) and an associated method that consistently performs well in identifying the most transferrable source(s) for a given task. In particular, our design employs an innovative quantization-level optimization procedure in the context of classification tasks that yields a measure of similarity between a source model and the given target data. The procedure uses a concept similar to early stopping (usually implemented to train deep neural networks (DNNs) to ensure generalization) to derive a function that approximates the transfer learning mapping without training. The advantage of our metric is that it can be quickly computed to identify the top candidate(s) for a given target task before a computationally intensive transfer operation (typically using DNNs) can be implemented between the selected source and the target task. As such, our metric can provide significant computational savings for transfer learning from a selection of a large number of possible source models. Through extensive experimental evaluations, we establish that our metric performs well over different datasets and varying numbers of data samples.
Authors: Ahmed Alagha, Jamal Bentahar, Hadi Otrok, Shakti Singh, Rabeb Mizouni
Abstract: Multi-Agent Deep Reinforcement Learning (MDRL) is a promising research area in which agents learn complex behaviors in cooperative or competitive environments. However, MDRL comes with several challenges that hinder its usability, including sample efficiency, curse of dimensionality, and environment exploration. Recent works proposing Federated Reinforcement Learning (FRL) to tackle these issues suffer from problems related to model restrictions and maliciousness. Other proposals using reward shaping require considerable engineering and could lead to local optima. In this paper, we propose a novel Blockchain-assisted Multi-Expert Demonstration Cloning (MEDC) framework for MDRL. The proposed method utilizes expert demonstrations in guiding the learning of new MDRL agents, by suggesting exploration actions in the environment. A model sharing framework on Blockchain is designed to allow users to share their trained models, which can be allocated as expert models to requesting users to aid in training MDRL systems. A Consortium Blockchain is adopted to enable traceable and autonomous execution without the need for a single trusted entity. Smart Contracts are designed to manage users and models allocation, which are shared using IPFS. The proposed framework is tested on several applications, and is benchmarked against existing methods in FRL, Reward Shaping, and Imitation Learning-assisted RL. The results show the outperformance of the proposed framework in terms of learning speed and resiliency to faulty and malicious models.
Authors: Weiyu Chen, Xiaoyuan Zhang, Baijiong Lin, Xi Lin, Han Zhao, Qingfu Zhang, James T. Kwok
Abstract: Multi-objective optimization (MOO) in deep learning aims to simultaneously optimize multiple conflicting objectives, a challenge frequently encountered in areas like multi-task learning and multi-criteria learning. Recent advancements in gradient-based MOO methods have enabled the discovery of diverse types of solutions, ranging from a single balanced solution to finite or even infinite Pareto sets, tailored to user needs. These developments have broad applications across domains such as reinforcement learning, computer vision, recommendation systems, and large language models. This survey provides the first comprehensive review of gradient-based MOO in deep learning, covering algorithms, theories, and practical applications. By unifying various approaches and identifying critical challenges, it serves as a foundational resource for driving innovation in this evolving field. A comprehensive list of MOO algorithms in deep learning is available at \url{https://github.com/Baijiong-Lin/Awesome-Multi-Objective-Deep-Learning}.
URLs: https://github.com/Baijiong-Lin/Awesome-Multi-Objective-Deep-Learning
Authors: Haichao Wei, Yunxiang Ren, Zhoutong Fu, Aman Lunia, Yi-Lin Chen, Alice Leung, Ya Xu
Abstract: Large Language Models (LLMs) demand significant computational resources, making it essential to enhance their capabilities without retraining from scratch. A key challenge in this domain is \textit{catastrophic forgetting} (CF), which hampers performance during Continuous Pre-training (CPT) and Continuous Supervised Fine-Tuning (CSFT). We propose \textbf{Control LLM}, a novel approach that leverages parallel pre-trained and expanded transformer blocks, aligning their hidden-states through interpolation strategies This method effectively preserves performance on existing tasks while seamlessly integrating new knowledge. Extensive experiments demonstrate the effectiveness of Control LLM in both CPT and CSFT. On Llama3.1-8B-Instruct, it achieves significant improvements in mathematical reasoning ($+14.4\%$ on Math-Hard) and coding performance ($+10\%$ on MBPP-PLUS). On Llama3.1-8B, it enhances multilingual capabilities ($+10.6\%$ on C-Eval, $+6.8\%$ on CMMLU, and $+30.2\%$ on CMMLU-0shot-CoT). It surpasses existing methods and achieves SOTA among open-source models tuned from the same base model, using substantially less data and compute. Crucially, these gains are realized while preserving strong original capabilities, with minimal degradation ($<4.3\% \text{on MMLU}$) compared to $>35\%$ in open-source Math and Coding models. This approach has been successfully deployed in LinkedIn's GenAI-powered job seeker and Ads unit products. To support further research, we release the training and evaluation code (\url{https://github.com/linkedin/ControlLLM}) along with models trained on public datasets (\url{ https://huggingface.co/ControlLLM}) to the community.
URLs: https://github.com/linkedin/ControlLLM, https://huggingface.co/ControlLLM
Authors: Omid Shahriyar, Babak Nuri Moghaddam, Davoud Yousefi, Abbas Mirzaei, Farnaz Hoseini
Abstract: One of the deadliest cancers, lung cancer necessitates an early and precise diagnosis. Because patients have a better chance of recovering, early identification of lung cancer is crucial. This review looks at how to diagnose lung cancer using sophisticated machine learning techniques like Random Forest (RF) and Support Vector Machine (SVM). The Chi-squared test is one feature selection strategy that has been successfully applied to find related features and enhance model performance. The findings demonstrate that these techniques can improve detection efficiency and accuracy while also assisting in runtime reduction. This study produces recommendations for further research as well as ideas to enhance diagnostic techniques. In order to improve healthcare and create automated methods for detecting lung cancer, this research is a critical first step.
Authors: Jiadong Lou, Xu Yuan, Rui Zhang, Xingliang Yuan, Neil Gong, Nian-Feng Tzeng
Abstract: Graph neural networks (GNNs) have exhibited superior performance in various classification tasks on graph-structured data. However, they encounter the potential vulnerability from the link stealing attacks, which can infer the presence of a link between two nodes via measuring the similarity of its incident nodes' prediction vectors produced by a GNN model. Such attacks pose severe security and privacy threats to the training graph used in GNN models. In this work, we propose a novel solution, called Graph Link Disguise (GRID), to defend against link stealing attacks with the formal guarantee of GNN model utility for retaining prediction accuracy. The key idea of GRID is to add carefully crafted noises to the nodes' prediction vectors for disguising adjacent nodes as n-hop indirect neighboring nodes. We take into account the graph topology and select only a subset of nodes (called core nodes) covering all links for adding noises, which can avert the noises offset and have the further advantages of reducing both the distortion loss and the computation cost. Our crafted noises can ensure 1) the noisy prediction vectors of any two adjacent nodes have their similarity level like that of two non-adjacent nodes and 2) the model prediction is unchanged to ensure zero utility loss. Extensive experiments on five datasets are conducted to show the effectiveness of our proposed GRID solution against different representative link-stealing attacks under transductive settings and inductive settings respectively, as well as two influence-based attacks. Meanwhile, it achieves a much better privacy-utility trade-off than existing methods when extended to GNNs.
Authors: Yasaman Saadati, Mohammad Rostami, M. Hadi Amini
Abstract: Traditional Federated Learning (FL) methods encounter significant challenges when dealing with heterogeneous data and providing personalized solutions for non-IID scenarios. Personalized Federated Learning (PFL) approaches aim to address these issues by balancing generalization and personalization, often through parameter decoupling or partial models that freeze some neural network layers for personalization while aggregating other layers globally. However, existing methods still face challenges of global-local model discrepancy, client drift, and catastrophic forgetting, which degrade model accuracy. To overcome these limitations, we propose pMixFed, a dynamic, layer-wise PFL approach that integrates mixup between shared global and personalized local models. Our method introduces an adaptive strategy for partitioning between personalized and shared layers, a gradual transition of personalization degree to enhance local client adaptation, improved generalization across clients, and a novel aggregation mechanism to mitigate catastrophic forgetting. Extensive experiments demonstrate that pMixFed outperforms state-of-the-art PFL methods, showing faster model training, increased robustness, and improved handling of data heterogeneity under different heterogeneous settings.
Authors: Qi Cheems Wang, Zehao Xiao, Yixiu Mao, Yun Qu, Jiayi Shen, Yiqin Lv, Xiangyang Ji
Abstract: The foundation model enables fast problem-solving without learning from scratch, and such a desirable adaptation property benefits from its adopted cross-task generalization paradigms, e.g., pretraining, meta-training, or finetuning. Recent trends have focused on the curation of task datasets during optimization, which includes task selection as an indispensable consideration for either adaptation robustness or sampling efficiency purposes. Despite some progress, selecting crucial task batches to optimize over iteration mostly exhausts massive task queries and requires intensive evaluation and computations to secure robust adaptation. This work underscores the criticality of both robustness and learning efficiency, especially in scenarios where tasks are risky to collect or costly to evaluate. To this end, we present Model Predictive Task Sampling (MPTS), a novel active task sampling framework to establish connections between the task space and adaptation risk landscape achieve robust adaptation. Technically, MPTS characterizes the task episodic information with a generative model and predicts optimization outcome after adaptation from posterior inference, i.e., forecasting task-specific adaptation risk values. The resulting risk learner amortizes expensive annotation, evaluation, or computation operations in task robust adaptation learning paradigms. Extensive experimental results show that MPTS can be seamlessly integrated into zero-shot, few-shot, and many-shot learning paradigms, increases adaptation robustness, and retains learning efficiency without affording extra cost. The code will be available at the project site https://github.com/thu-rllab/MPTS.
Authors: Linchao Pan, Can Gao, Jie Zhou, Jinbao Wang
Abstract: Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55\% and an AUROC improvement of 6.17\% on CIFAR80N.
Authors: Rohit Mapakshi, Sayma Akther, Mark Stamp
Abstract: In this paper, we experimentally analyze the robustness of selected Federated Learning (FL) systems in the presence of adversarial clients. We find that temporal attacks significantly affect model performance in the FL models tested, especially when the adversaries are active throughout or during the later rounds. We consider a variety of classic learning models, including Multinominal Logistic Regression (MLR), Random Forest, XGBoost, Support Vector Classifier (SVC), as well as various Neural Network models including Multilayer Perceptron (MLP), Convolution Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). Our results highlight the effectiveness of temporal attacks and the need to develop strategies to make the FL process more robust against such attacks. We also briefly consider the effectiveness of defense mechanisms, including outlier detection in the aggregation algorithm.
Authors: Li-Hsiang Shen, Jyun-Jhe Huang, Kai-Ten Feng, Lie-Liang Yang, Jen-Ming Wu
Abstract: In this paper, a novel network architecture that deploys the multi-functional reconfigurable intelligent surface (MF-RIS) in low-Earth orbit (LEO) is proposed. Unlike traditional RIS with only signal reflection capability, the MF-RIS can reflect, refract, and amplify signals, as well as harvest energy from wireless signals. Given the high energy demands in shadow regions where solar energy is unavailable, MF-RIS is deployed in LEO to enhance signal coverage and improve energy efficiency (EE). To address this, we formulate a long-term EE optimization problem by determining the optimal parameters for MF-RIS configurations, including amplification and phase-shifts, energy harvesting ratios, and LEO transmit beamforming. To address the complex non-convex and non-linear problem, a federated learning enhanced multi-agent deep deterministic policy gradient (FEMAD) scheme is designed. Multi-agent DDPG of each agent can provide the optimal action policy from its interaction to environments, whereas federated learning enables the hidden information exchange among multi-agents. In numerical results, we can observe significant EE improvements compared to the other benchmarks, including centralized deep reinforcement learning as well as distributed multi-agent deep deterministic policy gradient (DDPG). Additionally, the proposed LEO-MF-RIS architecture has demonstrated its effectiveness, achieving the highest EE performance compared to the scenarios of fixed/no energy harvesting in MF-RIS, traditional reflection-only RIS, and deployment without RISs/MF-RISs.
Authors: Mohammad Ghabel Rahmat, Majid Khalilian
Abstract: Federated learning faces significant challenges in scenarios with heterogeneous data distributions and adverse network conditions, such as delays, packet loss, and data poisoning attacks. This paper proposes a novel method based on the SCAFFOLD algorithm to improve the quality of local updates and enhance the robustness of the global model. The key idea is to form intermediary nodes by merging local models with high similarity, using the Pearson correlation coefficient as a similarity measure. The proposed merging algorithm reduces the number of local nodes while maintaining the accuracy of the global model, effectively addressing communication overhead and bandwidth consumption. Experimental results on the MNIST dataset under simulated federated learning scenarios demonstrate the method's effectiveness. After 10 rounds of training using a CNN model, the proposed approach achieved accuracies of 0.82, 0.73, and 0.66 under normal conditions, packet loss and data poisoning attacks, respectively, outperforming the baseline SCAFFOLD algorithm. These results highlight the potential of the proposed method to improve efficiency and resilience in federated learning systems.
Authors: Farhad Kooban, Aleksandra Radli\'nska, Reza Mousapour, Maryam Saraei
Abstract: Subsurface evaluation of railway tracks is crucial for safe operation, as it allows for the early detection and remediation of potential structural weaknesses or defects that could lead to accidents or derailments. Ground Penetrating Radar (GPR) is an electromagnetic survey technique as advanced non-destructive technology (NDT) that can be used to monitor railway tracks. This technology is well-suited for railway applications due to the sub-layered composition of the track, which includes ties, ballast, sub-ballast, and subgrade regions. It can detect defects such as ballast pockets, fouled ballast, poor drainage, and subgrade settlement. The paper reviews recent works on advanced technology and interpretations of GPR data collected for different layers. Further, this paper demonstrates the current techniques for using synthetic modeling to calibrate real-world GPR data, enhancing accuracy in identifying subsurface features like ballast conditions and structural anomalies and applying various algorithms to refine GPR data analysis. These include Support Vector Machine (SVM) for classifying railway ballast types, Fuzzy C-means, and Generalized Regression Neural Networks for high-accuracy defect classification. Deep learning techniques, particularly Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are also highlighted for their effectiveness in recognizing patterns associated with defects in GPR images. The article specifically focuses on the development of a Convolutional Recurrent Neural Network (CRNN) model, which combines CNN and RNN architectures for efficient processing of GPR data. This model demonstrates enhanced detection capabilities and faster processing compared to traditional object detection models like Faster R-CNN.
Authors: Giulia Fracastoro, Sophie M. Fosson, Andrea Migliorati, Giuseppe C. Calafiore
Abstract: The design of sparse neural networks, i.e., of networks with a reduced number of parameters, has been attracting increasing research attention in the last few years. The use of sparse models may significantly reduce the computational and storage footprint in the inference phase. In this context, the lottery ticket hypothesis (LTH) constitutes a breakthrough result, that addresses not only the performance of the inference phase, but also of the training phase. It states that it is possible to extract effective sparse subnetworks, called winning tickets, that can be trained in isolation. The development of effective methods to play the lottery, i.e., to find winning tickets, is still an open problem. In this article, we propose a novel class of methods to play the lottery. The key point is the use of concave regularization to promote the sparsity of a relaxed binary mask, which represents the network topology. We theoretically analyze the effectiveness of the proposed method in the convex framework. Then, we propose extended numerical tests on various datasets and architectures, that show that the proposed method can improve the performance of state-of-the-art algorithms.
Authors: Jerrod Wigmore, Brooke Shrader, Eytan Modiano
Abstract: Deep Reinforcement Learning (DRL) has become a powerful tool for developing control policies in queueing networks, but the common use of Multi-layer Perceptron (MLP) neural networks in these applications has significant drawbacks. MLP architectures, while versatile, often suffer from poor sample efficiency and a tendency to overfit training environments, leading to suboptimal performance on new, unseen networks. In response to these issues, we introduce a switch-type neural network (STN) architecture designed to improve the efficiency and generalization of DRL policies in queueing networks. The STN leverages structural patterns from traditional non-learning policies, ensuring consistent action choices across similar states. This design not only streamlines the learning process but also fosters better generalization by reducing the tendency to overfit. Our works presents three key contributions: first, the development of the STN as a more effective alternative to MLPs; second, empirical evidence showing that STNs achieve superior sample efficiency in various training scenarios; and third, experimental results demonstrating that STNs match MLP performance in familiar environments and significantly outperform them in new settings. By embedding domain-specific knowledge, the STN enhances the Proximal Policy Optimization (PPO) algorithm's effectiveness without compromising performance, suggesting its suitability for a wide range of queueing network control problems.
Authors: Oleh Yasniy, Dmytro Tymoshchuk, Iryna Didych, Nataliya Zagorodna, Olha Malyshevska
Abstract: In the current study, the fatigue life of QSTE340TM steel was modelled using a machine learning method, namely, a neural network. This problem was solved by a Multi-Layer Perceptron (MLP) neural network with a 3-75-1 architecture, which allows the prediction of the crack length based on the number of load cycles N, the stress ratio R, and the overload ratio Rol. The proposed model showed high accuracy, with mean absolute percentage error (MAPE) ranging from 0.02% to 4.59% for different R and Rol. The neural network effectively reveals the nonlinear relationships between input parameters and fatigue crack growth, providing reliable predictions for different loading conditions.
Authors: Tyler Malloy, Roderick Seow, Cleotilde Gonzalez
Abstract: Attention can be used to inform choice selection in contextual bandit tasks even when context features have not been previously experienced. One example of this is in dimensional shifts, where additional feature values are introduced and the relationship between features and outcomes can either be static or variable. Attentional mechanisms have been extensively studied in contextual bandit tasks where the feedback of choices is provided immediately, but less research has been done on tasks where feedback is delayed or in counterfactual feedback cases. Some methods have successfully modeled human attention with immediate feedback based on reward prediction errors (RPEs), though recent research raises questions of the applicability of RPEs onto more general attentional mechanisms. Alternative models suggest that information theoretic metrics can be used to model human attention, with broader applications to novel stimuli. In this paper, we compare two different methods for modeling how humans attend to specific features of decision making tasks, one that is based on calculating an information theoretic metric using a memory of past experiences, and another that is based on iteratively updating attention from reward prediction errors. We compare these models using simulations in a contextual bandit task with both intradimensional and extradimensional domain shifts, as well as immediate, delayed, and counterfactual feedback. We find that calculating an information theoretic metric over a history of experiences is best able to account for human-like behavior in tasks that shift dimensions and alter feedback presentation. These results indicate that information theoretic metrics of attentional mechanisms may be better suited than RPEs to predict human attention in decision making, though further studies of human behavior are necessary to support these results.
Authors: Mustafa Ghaleb, Mohanad Obeed, Muhamad Felemban, Anas Chaaban, Halim Yanikomeroglu
Abstract: Federated Learning (FL) has emerged as a significant paradigm for training machine learning models. This is due to its data-privacy-preserving property and its efficient exploitation of distributed computational resources. This is achieved by conducting the training process in parallel at distributed users. However, traditional FL strategies grapple with difficulties in evaluating the quality of received models, handling unbalanced models, and reducing the impact of detrimental models. To resolve these problems, we introduce a novel federated learning framework, which we call federated testing for federated learning (FedTest). In the FedTest method, the local data of a specific user is used to train the model of that user and test the models of the other users. This approach enables users to test each other's models and determine an accurate score for each. This score can then be used to aggregate the models efficiently and identify any malicious ones. Our numerical results reveal that the proposed method not only accelerates convergence rates but also diminishes the potential influence of malicious users. This significantly enhances the overall efficiency and robustness of FL systems.
Authors: I. Chittumuri, N. Alshehab, R. J. Voss, L. L. Douglass, S. Kamrava, Y. Fan, J. Miskimins, W. Fleckenstein, S. Bandyopadhyay
Abstract: This paper presents a risk analysis of flowlines in the oil and gas sector using Geographic Information Systems (GIS) and machine learning (ML). Flowlines, vital conduits transporting oil, gas, and water from wellheads to surface facilities, often face under-assessment compared to transmission pipelines. This study addresses this gap using advanced tools to predict and mitigate failures, improving environmental safety and reducing human exposure. Extensive datasets from the Colorado Energy and Carbon Management Commission (ECMC) were processed through spatial matching, feature engineering, and geometric extraction to build robust predictive models. Various ML algorithms, including logistic regression, support vector machines, gradient boosting decision trees, and K-Means clustering, were used to assess and classify risks, with ensemble classifiers showing superior accuracy, especially when paired with Principal Component Analysis (PCA) for dimensionality reduction. Finally, a thorough data analysis highlighted spatial and operational factors influencing risks, identifying high-risk zones for focused monitoring. Overall, the study demonstrates the transformative potential of integrating GIS and ML in flowline risk management, proposing a data-driven approach that emphasizes the need for accurate data and refined models to improve safety in petroleum extraction.
Authors: Dingyi Zhuang, Hanyong Xu, Xiaotong Guo, Yunhan Zheng, Shenhao Wang, Jinhua Zhao
Abstract: Urban prediction tasks, such as forecasting traffic flow, temperature, and crime rates, are crucial for efficient urban planning and management. However, existing Spatiotemporal Graph Neural Networks (ST-GNNs) often rely solely on accuracy, overlooking spatial and demographic disparities in their predictions. This oversight can lead to imbalanced resource allocation and exacerbate existing inequities in urban areas. This study introduces a Residual-Aware Attention (RAA) Block and an equality-enhancing loss function to address these disparities. By adapting the adjacency matrix during training and incorporating spatial disparity metrics, our approach aims to reduce local segregation of residuals and errors. We applied our methodology to urban prediction tasks in Chicago, utilizing a travel demand dataset as an example. Our model achieved a 48% significant improvement in fairness metrics with only a 9% increase in error metrics. Spatial analysis of residual distributions revealed that models with RAA Blocks produced more equitable prediction results, particularly by reducing errors clustered in central regions. Attention maps demonstrated the model's ability to dynamically adjust focus, leading to more balanced predictions. Case studies of various community areas in Chicago further illustrated the effectiveness of our approach in addressing spatial and demographic disparities, supporting more balanced and equitable urban planning and policy-making.
Authors: Jiaqi Luo, Yahong Yang, Yuan Yuan, Shixin Xu, Wenrui Hao
Abstract: This paper introduces Residual-based Smote (RSmote), an innovative local adaptive sampling technique tailored to improve the performance of Physics-Informed Neural Networks (PINNs) through imbalanced learning strategies. Traditional residual-based adaptive sampling methods, while effective in enhancing PINN accuracy, often struggle with efficiency and high memory consumption, particularly in high-dimensional problems. RSmote addresses these challenges by targeting regions with high residuals and employing oversampling techniques from imbalanced learning to refine the sampling process. Our approach is underpinned by a rigorous theoretical analysis that supports the effectiveness of RSmote in managing computational resources more efficiently. Through extensive evaluations, we benchmark RSmote against the state-of-the-art Residual-based Adaptive Distribution (RAD) method across a variety of dimensions and differential equations. The results demonstrate that RSmote not only achieves or exceeds the accuracy of RAD but also significantly reduces memory usage, making it particularly advantageous in high-dimensional scenarios. These contributions position RSmote as a robust and resource-efficient solution for solving complex partial differential equations, especially when computational constraints are a critical consideration.
Authors: Songru Yang, Zili Liu, Zhenwei Shi, Zhengxia Zou
Abstract: Global Station Weather Forecasting (GSWF), a prominent meteorological research area, is pivotal in providing timely localized weather predictions. Despite the progress existing models have made in the overall accuracy of the GSWF, executing high-precision extreme event prediction still presents a substantial challenge. The recent emergence of state-space models, with their ability to efficiently capture continuous-time dynamics and latent states, offer potential solutions. However, early investigations indicated that Mamba underperforms in the context of GSWF, suggesting further adaptation and optimization. To tackle this problem, in this paper, we introduce Weather State-space Model (WSSM), a novel Mamba-based approach tailored for GSWF. Geographical knowledge is integrated in addition to the widely-used positional encoding to represent the absolute special-temporal position. The multi-scale time-frequency features are synthesized from coarse to fine to model the seasonal to extreme weather dynamic. Our method effectively improves the overall prediction accuracy and addresses the challenge of forecasting extreme weather events. The state-of-the-art results obtained on the Weather-5K subset underscore the efficacy of the WSSM
Authors: Shingo Aihara, Matthieu Parizy
Abstract: Combinatorial optimization (CO) problems are pivotal across various industrial applications, where the speed of solving these problems is crucial. Improving the performance of CO solvers across diverse input instances requires fine-tuning solver parameters for each instance. However, this tuning process is time-consuming, and the time required increases with the number of instances. To address this, a method called instance-specific algorithm configuration (ISAC) has been devised. This approach involves two main steps: training and execution. During the training step, features are extracted from various instances and then grouped into clusters. For each cluster, parameters are fine-tuned. This cluster-specific tuning process results in a set of generalized parameters for instances belonging to each class. In the execution step, features are extracted from an unknown instance to determine its cluster, and the corresponding pre-tuned parameters are applied. Generally, the running time of a solver is evaluated by the time to solution ($TTS$). However, methods like ISAC require preprocessing. Therefore, the total execution time is $T_{tot}=TTS+T_{tune}$, where $T_{tune}$ represents the tuning time. While the goal is to minimize $T_{tot}$, it is important to note that extracting features in the ISAC method requires a certain amount of computational time. The extracting features include summary statistics of the solver execution logs, which takes several 10 seconds. This research presents a method to significantly reduce the time of the ISAC execution step by streamlining feature extraction and class determination with a graph neural network. Experimental results show that $T_{tune}$ in the execution step, which take several 10 seconds in the original ISAC manner, could be reduced to sub-seconds.
Authors: Zhuangzhuang Yan, Xinyu Gu, Shilong Fan, Zhenyu Liu
Abstract: Accurate and reliable link quality prediction (LQP) is crucial for optimizing network performance, ensuring communication stability, and enhancing user experience in wireless communications. However, LQP faces significant challenges due to the dynamic and lossy nature of wireless links, which are influenced by interference, multipath effects, fading, and blockage. In this paper, we propose GAT-LLM, a novel multivariate wireless link quality prediction model that combines Large Language Models (LLMs) with Graph Attention Networks (GAT) to enable accurate and reliable multivariate LQP of wireless communications. By framing LQP as a time series prediction task and appropriately preprocessing the input data, we leverage LLMs to improve the accuracy of link quality prediction. To address the limitations of LLMs in multivariate prediction due to typically handling one-dimensional data, we integrate GAT to model interdependencies among multiple variables across different protocol layers, enhancing the model's ability to handle complex dependencies. Experimental results demonstrate that GAT-LLM significantly improves the accuracy and robustness of link quality prediction, particularly in multi-step prediction scenarios.
Authors: Jwo-Yuh Wu, Liang-Chi Huang, Wen-Hsuan Li, Chun-Hung Liu
Abstract: Empirically, Deep Learning (DL) has demonstrated unprecedented success in practical applications. However, DL remains by and large a mysterious "black-box", spurring recent theoretical research to build its mathematical foundations. In this paper, we investigate DL for data classification through the prism of metric topology. Considering that conventional Euclidean metric over the network parameter space typically fails to discriminate DL networks according to their classification outcomes, we propose from a probabilistic point of view a meaningful distance measure, whereby DL networks yielding similar classification performances are close. The proposed distance measure defines such an equivalent relation among network parameter vectors that networks performing equally well belong to the same equivalent class. Interestingly, our proposed distance measure can provably serve as a metric on the quotient set modulo the equivalent relation. Then, under quite mild conditions it is shown that, apart from a vanishingly small subset of networks likely to predict non-unique labels, our proposed metric space is compact, and coincides with the well-known quotient topological space. Our study contributes to fundamental understanding of DL, and opens up new ways of studying DL using fruitful metric space theory.
Authors: Ahmad Mousavi, Ramin Zandvakili
Abstract: Kernel-free quadratic surface support vector machine (SVM) models have gained significant attention in machine learning. However, introducing a quadratic classifier increases the model's complexity by quadratically expanding the number of parameters relative to the dimensionality of the data, exacerbating overfitting. To address this, we propose sparse $\ell_0$-norm based Kernel-free quadratic surface SVMs, designed to mitigate overfitting and enhance interpretability. Given the intractable nature of these models, we present a penalty decomposition algorithm to efficiently obtain first-order optimality points. Our analysis shows that the subproblems in this framework either admit closed-form solutions or can leverage duality theory to improve computational efficiency. Through empirical evaluations on real-world datasets, we demonstrate the efficacy and robustness of our approach, showcasing its potential to advance Kernel-free quadratic surface SVMs in practical applications while addressing overfitting concerns. All the implemented models and experiment codes are available at \url{https://github.com/raminzandvakili/L0-QSVM}.
Authors: Osama Ahmad, Zubair Khalid, Muhammad Tahir, Momin Uppal
Abstract: Monitoring air pollution is crucial for protecting human health from exposure to harmful substances. Traditional methods of air quality monitoring, such as ground-based sensors and satellite-based remote sensing, face limitations due to high deployment costs, sparse sensor coverage, and environmental interferences. To address these challenges, this paper proposes a framework for high-resolution spatiotemporal Air Quality Index (AQI) mapping using sparse sensor data, satellite imagery, and various spatiotemporal factors. By leveraging Graph Neural Networks (GNNs), we estimate AQI values at unmonitored locations based on both spatial and temporal dependencies. The framework incorporates a wide range of environmental features, including meteorological data, road networks, points of interest (PoIs), population density, and urban green spaces, which enhance prediction accuracy. We illustrate the use of our approach through a case study in Lahore, Pakistan, where multi-resolution data is used to generate the air quality index map at a fine spatiotemporal scale.
Authors: Yuwen Li, Guozhi Zhang
Abstract: This paper investigates the $L_p$ approximation error for higher order Korobov functions using deep convolutional neural networks (CNNs) with ReLU activation. For target functions having a mixed derivative of order m+1 in each direction, we improve classical approximation rate of second order to (m+1)-th order (modulo a logarithmic factor) in terms of the depth of CNNs. The key ingredient in our analysis is approximate representation of high-order sparse grid basis functions by CNNs. The results suggest that higher order expressivity of CNNs does not severely suffer from the curse of dimensionality.
Authors: Haotian Xu, Xing Wu, Weinong Wang, Zhongzhi Li, Da Zheng, Boyuan Chen, Yi Hu, Shijia Kang, Jiaming Ji, Yingying Zhang, Zhijiang Guo, Yaodong Yang, Muhan Zhang, Debing Zhang
Abstract: Can scaling transform reasoning? In this work, we explore the untapped potential of scaling Long Chain-of-Thought (Long-CoT) data to 1000k samples, pioneering the development of a slow-thinking model, RedStar. Through extensive experiments with various LLMs and different sizes, we uncover the ingredients for specialization and scale for Long-CoT training. Surprisingly, even smaller models show significant performance gains with limited data, revealing the sample efficiency of Long-CoT and the critical role of sample difficulty in the learning process. Our findings demonstrate that Long-CoT reasoning can be effectively triggered with just a few thousand examples, while larger models achieve unparalleled improvements. We also introduce reinforcement learning (RL)-scale training as a promising direction for advancing slow-thinking systems. RedStar shines across domains: on the MATH-Hard benchmark, RedStar-code-math boosts performance from 66.2\% to 81.6\%, and on the USA Math Olympiad (AIME), it solves 46.7\% of problems using only 21k mixed-code-math datasets. In multimodal tasks like GeoQA and MathVista-GEO, RedStar-Geo achieves competitive results with minimal Long-CoT data, outperforming other slow-thinking systems like QvQ-Preview. Compared to QwQ, RedStar strikes the perfect balance between reasoning and generalizability. Our work highlights that, with careful tuning, scaling Long-CoT can unlock extraordinary reasoning capabilities-even with limited dataset and set a new standard for slow-thinking models across diverse challenges. Our data and models are released at https://huggingface.co/RedStar-Reasoning.
Authors: Amuche Ibenegbu, Amandine Schaeffer, Pierre Lafaye de Micheaux, Rohitash Chandra
Abstract: Bluebottles (\textit{Physalia} spp.) are marine stingers resembling jellyfish, whose presence on Australian beaches poses a significant public risk due to their venomous nature. Understanding the environmental factors driving bluebottles ashore is crucial for mitigating their impact, and machine learning tools are to date relatively unexplored. We use bluebottle marine stinger presence/absence data from beaches in Eastern Sydney, Australia, and compare machine learning models (Multilayer Perceptron, Random Forest, and XGBoost) to identify factors influencing their presence. We address challenges such as class imbalance, class overlap, and unreliable absence data by employing data augmentation techniques, including the Synthetic Minority Oversampling Technique (SMOTE), Random Undersampling, and Synthetic Negative Approach that excludes the negative class. Our results show that SMOTE failed to resolve class overlap, but the presence-focused approach effectively handled imbalance, class overlap, and ambiguous absence data. The data attributes such as the wind direction, which is a circular variable, emerged as a key factor influencing bluebottle presence, confirming previous inference studies. However, in the absence of population dynamics, biological behaviours, and life cycles, the best predictive model appears to be Random Forests combined with Synthetic Negative Approach. This research contributes to mitigating the risks posed by bluebottles to beachgoers and provides insights into handling class overlap and unreliable negative class in environmental modelling.
Authors: Nir Ben-Ari, Amitai Yacobi, Uri Shaham
Abstract: Spectral Embedding (SE) is a popular method for dimensionality reduction, applicable across diverse domains. Nevertheless, its current implementations face three prominent drawbacks which curtail its broader applicability: generalizability (i.e., out-of-sample extension), scalability, and eigenvectors separation. In this paper, we introduce GrEASE: Generalizable and Efficient Approximate Spectral Embedding, a novel deep-learning approach designed to address these limitations. GrEASE incorporates an efficient post-processing step to achieve eigenvectors separation, while ensuring both generalizability and scalability, allowing for the computation of the Laplacian's eigenvectors on unseen data. This method expands the applicability of SE to a wider range of tasks and can enhance its performance in existing applications. We empirically demonstrate GrEASE's ability to consistently approximate and generalize SE, while ensuring scalability. Additionally, we show how GrEASE can be leveraged to enhance existing methods. Specifically, we focus on UMAP, a leading visualization technique, and introduce NUMAP, a generalizable version of UMAP powered by GrEASE. Our codes are publicly available.
Authors: Tong Nie, Wei Ma, Jian Sun, Yu Yang, Jiannong Cao
Abstract: Urban time series, such as mobility flows, energy consumption, and pollution records, encapsulate complex urban dynamics and structures. However, data collection in each city is impeded by technical challenges such as budget limitations and sensor failures, necessitating effective data imputation techniques that can enhance data quality and reliability. Existing imputation models, categorized into learning-based and analytics-based paradigms, grapple with the trade-off between capacity and generalizability. Collaborative learning to reconstruct data across multiple cities holds the promise of breaking this trade-off. Nevertheless, urban data's inherent irregularity and heterogeneity issues exacerbate challenges of knowledge sharing and collaboration across cities. To address these limitations, we propose a novel collaborative imputation paradigm leveraging meta-learned implicit neural representations (INRs). INRs offer a continuous mapping from domain coordinates to target values, integrating the strengths of both paradigms. By imposing embedding theory, we first employ continuous parameterization to handle irregularity and reconstruct the dynamical system. We then introduce a cross-city collaborative learning scheme through model-agnostic meta learning, incorporating hierarchical modulation and normalization techniques to accommodate multiscale representations and reduce variance in response to heterogeneity. Extensive experiments on a diverse urban dataset from 20 global cities demonstrate our model's superior imputation performance and generalizability, underscoring the effectiveness of collaborative imputation in resource-constrained settings.
Authors: Zhen Zhang, Jun Hui Qiu, Jun Wei Zhang, Hui Dong Li, Dong Tang, Qiang Cheng, Wei Lin
Abstract: Reconfigurable intelligent surface (RIS) is a two-dimensional periodic structure integrated with a large number of reflective elements, which can manipulate electromagnetic waves in a digital way, offering great potentials for wireless communication and radar detection applications. However, conventional RIS designs highly rely on extensive full-wave EM simulations that are extremely time-consuming. To address this challenge, we propose a machine-learning-assisted approach for efficient RIS design. An accurate and fast model to predict the reflection coefficient of RIS element is developed by combining a multi-layer perceptron neural network (MLP) and a dual-port network, which can significantly reduce tedious EM simulations in the network training. A RIS has been practically designed based on the proposed method. To verify the proposed method, the RIS has also been fabricated and measured. The experimental results are in good agreement with the simulation results, which validates the efficacy of the proposed method in RIS design.
Authors: Yongwei Che, Benjamin Eysenbach
Abstract: While internet-scale data often comes in pairs (e.g., audio/image, image/text), we often want to perform inferences over modalities unseen together in the training data (e.g., audio/text). Empirically, this can often be addressed by learning multiple contrastive embedding spaces between existing modality pairs, implicitly hoping that unseen modality pairs will end up being aligned. This theoretical paper proves that this hope is well founded, under certain assumptions. Starting with the proper Bayesian approach of integrating out intermediate modalities, we show that directly comparing the representations of data from unpaired modalities can recover the same likelihood ratio. Our analysis builds on prior work on the geometry and probabilistic interpretation of contrastive representations, showing how these representations can answer many of the same inferences as probabilistic graphical models. Our analysis suggests two new ways of using contrastive representations: in settings with pre-trained contrastive models, and for handling language ambiguity in reinforcement learning. Our numerical experiments study the importance of our assumptions and demonstrate these new applications.
Authors: Mouad Elaarabi, Domenico Borzacchiello, Yves Le Guennec, Philippe Le Bot, Sebastien Comas-Cardona
Abstract: The promising outcomes of dynamical system identification techniques, such as SINDy [Brunton et al. 2016], highlight their advantages in providing qualitative interpretability and extrapolation compared to non-interpretable deep neural networks [Rudin 2019]. These techniques suffer from parameter updating in real-time use cases, especially when the system parameters are likely to change during or between processes. Recently, the OASIS [Bhadriraju et al. 2020] framework introduced a data-driven technique to address the limitations of real-time dynamical system parameters updating, yielding interesting results. Nevertheless, we show in this work that superior performance can be achieved using more advanced model architectures. We present an innovative encoding approach, based mainly on the use of Set Encoding methods of sequence data, which give accurate adaptive model identification for complex dynamic systems, with variable input time series length. Two Set Encoding methods are used, the first is Deep Set [Zaheer et al. 2017], and the second is Set Transformer [Lee et al. 2019]. Comparing Set Transformer to OASIS framework on Lotka Volterra for real-time local dynamical system identification and time series forecasting, we find that the Set Transformer architecture is well adapted to learning relationships within data sets. We then compare the two Set Encoding methods based on the Lorenz system for online global dynamical system identification. Finally, we trained a Deep Set model to perform identification and characterization of abnormalities for 1D heat-transfer problem.
Authors: Haoran Xu, Jiaze Li, Wanyi Wu, Hao Ren
Abstract: Federated Learning (FL) suffers from severe performance degradation due to the data heterogeneity among clients. Existing works reveal that the fundamental reason is that data heterogeneity can cause client drift where the local model update deviates from the global one, and thus they usually tackle this problem from the perspective of calibrating the obtained local update. Despite effectiveness, existing methods substantially lack a deep understanding of how heterogeneous data samples contribute to the formation of client drift. In this paper, we bridge this gap by identifying that the drift can be viewed as a cumulative manifestation of biases present in all local samples and the bias between samples is different. Besides, the bias dynamically changes as the FL training progresses. Motivated by this, we propose FedBSS that first mitigates the heterogeneity issue in a sample-level manner, orthogonal to existing methods. Specifically, the core idea of our method is to adopt a bias-aware sample selection scheme that dynamically selects the samples from small biases to large epoch by epoch to train progressively the local model in each round. In order to ensure the stability of training, we set the diversified knowledge acquisition stage as the warm-up stage to avoid the local optimality caused by knowledge deviation in the early stage of the model. Evaluation results show that FedBSS outperforms state-of-the-art baselines. In addition, we also achieved effective results on feature distribution skew and noise label dataset setting, which proves that FedBSS can not only reduce heterogeneity, but also has scalability and robustness.
Authors: Zibin Wang, Zhiyuan Ouyang, Xiangyun Zhang
Abstract: Flow-matching models provide a powerful framework for various applications, offering efficient sampling and flexible probability path modeling. These models are characterized by flows with low curvature in learned generative trajectories, which results in reduced truncation error at each sampling step. To further reduce curvature, we propose block matching. This novel approach leverages label information to partition the data distribution into blocks and match them with a prior distribution parameterized using the same label information, thereby learning straighter flows. We demonstrate that the variance of the prior distribution can control the curvature upper bound of forward trajectories in flow-matching models. By designing flexible regularization strategies to adjust this variance, we achieve optimal generation performance, effectively balancing the trade-off between maintaining diversity in generated samples and minimizing numerical solver errors. Our results demonstrate competitive performance with models of the same parameter scale.Code is available at \url{https://github.com/wpp13749/block_flow}.
Authors: Jean-Baptiste Fermanian (UM, Inria, IMAG), Pierre Humbert (SU, LPSM), Gilles Blanchard (LMO, DATASHAPE)
Abstract: We introduce a method based on Conformal Prediction (CP) to quantify the uncertainty of full ranking algorithms. We focus on a specific scenario where $n + m$ items are to be ranked by some ''black box'' algorithm. It is assumed that the relative (ground truth) ranking of n of them is known. The objective is then to quantify the error made by the algorithm on the ranks of the m new items among the total $(n + m)$. In such a setting, the true ranks of the n original items in the total $(n + m)$ depend on the (unknown) true ranks of the m new ones. Consequently, we have no direct access to a calibration set to apply a classical CP method. To address this challenge, we propose to construct distribution-free bounds of the unknown conformity scores using recent results on the distribution of conformal p-values. Using these scores upper bounds, we provide valid prediction sets for the rank of any item. We also control the false coverage proportion, a crucial quantity when dealing with multiple prediction sets. Finally, we empirically show on both synthetic and real data the efficiency of our CP method.
Authors: Chung-ju Huang, Yuanpeng He, Xiao Han, Wenpin Jiao, Zhi Jin, Leye Wang
Abstract: Cross-hospital collaboration has the potential to address disparities in medical resources across different regions. However, strict privacy regulations prohibit the direct sharing of sensitive patient information between hospitals. Vertical federated learning (VFL) offers a novel privacy-preserving machine learning paradigm that maximizes data utility across multiple hospitals. Traditional VFL methods, however, primarily benefit patients with overlapping data, leaving vulnerable non-overlapping patients without guaranteed improvements in medical prediction services. While some knowledge transfer techniques can enhance the prediction performance for non-overlapping patients, they fall short in addressing scenarios where overlapping and non-overlapping patients belong to different domains, resulting in challenges such as feature heterogeneity and label heterogeneity. To address these issues, we propose a novel unified vertical federated knowledge transfer framework (Unitrans). Our framework consists of three key steps. First, we extract the federated representation of overlapping patients by employing an effective vertical federated representation learning method to model multi-party joint features online. Next, each hospital learns a local knowledge transfer module offline, enabling the transfer of knowledge from the federated representation of overlapping patients to the enriched representation of local non-overlapping patients in a domain-adaptive manner. Finally, hospitals utilize these enriched local representations to enhance performance across various downstream medical prediction tasks. Experiments on real-world medical datasets validate the framework's dual effectiveness in both intra-domain and cross-domain knowledge transfer. The code of \method is available at \url{https://github.com/Chung-ju/Unitrans}.
Authors: Taiki Yamada, Yuichi Katori, Kantaro Fujiwara
Abstract: Conventional echo state networks (ESNs) require supervised learning to train the readout layer, using the desired outputs as training data. In this study, we focus on input reconstruction (IR), which refers to training the readout layer to reproduce the input time series in its output. We reformulate the learning algorithm of the ESN readout layer to perform IR using unsupervised learning (UL). By conducting theoretical analysis and numerical experiments, we demonstrate that IR in ESNs can be effectively implemented under realistic conditions without explicitly using the desired outputs as training data; in this way, UL is enabled. Furthermore, we demonstrate that applications relying on IR, such as dynamical system replication and noise filtering, can be reformulated within the UL framework. Our findings establish a theoretically sound and universally applicable IR formulation, along with its related tasks in ESNs. This work paves the way for novel predictions and highlights unresolved theoretical challenges in ESNs, particularly in the context of time-series processing methods and computational models of the brain.
Authors: Matteo Zecchin (Shitz), Fredrik Hellstr\"om (Shitz), Sangwoo Park (Shitz), Shlomo Shamai (Shitz), Osvaldo Simeone
Abstract: Predictive models are often required to produce reliable predictions under statistical conditions that are not matched to the training data. A common type of training-testing mismatch is covariate shift, where the conditional distribution of the target variable given the input features remains fixed, while the marginal distribution of the inputs changes. Weighted conformal risk control (W-CRC) uses data collected during the training phase to convert point predictions into prediction sets with valid risk guarantees at test time despite the presence of a covariate shift. However, while W-CRC provides statistical reliability, its efficiency -- measured by the size of the prediction sets -- can only be assessed at test time. In this work, we relate the generalization properties of the base predictor to the efficiency of W-CRC under covariate shifts. Specifically, we derive a bound on the inefficiency of the W-CRC predictor that depends on algorithmic hyperparameters and task-specific quantities available at training time. This bound offers insights on relationships between the informativeness of the prediction sets, the extent of the covariate shift, and the size of the calibration and training sets. Experiments on fingerprinting-based localization validate the theoretical results.
Authors: Quentin Renau, Emma Hart
Abstract: Recent approaches to training algorithm selectors in the black-box optimisation domain have advocated for the use of training data that is algorithm-centric in order to encapsulate information about how an algorithm performs on an instance, rather than relying on information derived from features of the instance itself. Probing-trajectories that consist of a sequence of objective performance per function evaluation obtained from a short run of an algorithm have recently shown particular promise in training accurate selectors. However, training models on this type of data requires an appropriately chosen classifier given the sequential nature of the data. There are currently no clear guidelines for choosing the most appropriate classifier for algorithm selection using time-series data from the plethora of models available. To address this, we conduct a large benchmark study using 17 different classifiers and three types of trajectory on a classification task using the BBOB benchmark suite using both leave-one-instance out and leave-one-problem out cross-validation. In contrast to previous studies using tabular data, we find that the choice of classifier has a significant impact, showing that feature-based and interval-based models are the best choices.
Authors: G Dhinesh Chandran, Srinivas Reddy Kota, Srikrishna Bhashyam
Abstract: We study the problem of online clustering within the multi-armed bandit framework under the fixed confidence setting. In this multi-armed bandit problem, we have $M$ arms, each providing i.i.d. samples that follow a multivariate Gaussian distribution with an {\em unknown} mean and a known unit covariance. The arms are grouped into $K$ clusters based on the distance between their means using the Single Linkage (SLINK) clustering algorithm on the means of the arms. Since the true means are unknown, the objective is to obtain the above clustering of the arms with the minimum number of samples drawn from the arms, subject to an upper bound on the error probability. We introduce a novel algorithm, Average Tracking Bandit Online Clustering (ATBOC), and prove that this algorithm is order optimal, meaning that the upper bound on its expected sample complexity for given error probability $\delta$ is within a factor of 2 of an instance-dependent lower bound as $\delta \rightarrow 0$. Furthermore, we propose a computationally more efficient algorithm, Lower and Upper Confidence Bound-based Bandit Online Clustering (LUCBBOC), inspired by the LUCB algorithm for best arm identification. Simulation results demonstrate that the performance of LUCBBOC is comparable to that of ATBOC. We numerically assess the effectiveness of the proposed algorithms through numerical experiments on both synthetic datasets and the real-world MovieLens dataset. To the best of our knowledge, this is the first work on bandit online clustering that allows arms with different means in a cluster and $K$ greater than 2.
Authors: Yorgos Tsitsikas, Evangelos E. Papalexakis
Abstract: Despite the fundamental importance of clustering, to this day, much of the relevant research is still based on ambiguous foundations, leading to an unclear understanding of whether or how the various clustering methods are connected with each other. In this work, we provide an additional stepping stone towards resolving such ambiguities by presenting a general clustering framework that subsumes a series of seemingly disparate clustering methods, including various methods belonging to the wildly popular spectral clustering framework. In fact, the generality of the proposed framework is additionally capable of shedding light to the largely unexplored area of multi-view graphs whose each view may have differently clustered nodes. In turn, we propose GenClus: a method that is simultaneously an instance of this framework and a generalization of spectral clustering, while also being closely related to k-means as well. This results in a principled alternative to the few existing methods studying this special type of multi-view graphs. Then, we conduct in-depth experiments, which demonstrate that GenClus is more computationally efficient than existing methods, while also attaining similar or better clustering performance. Lastly, a qualitative real-world case-study further demonstrates the ability of GenClus to produce meaningful clusterings.
Authors: Jing Liu, Zhenchao Ma, Zepu Wang, Yang Liu, Zehua Wang, Peng Sun, Liang Song, Bo Hu, Azzedine Boukerche, Victor C. M. Leung
Abstract: Diffusion models (DMs) have emerged as a powerful class of generative AI models, showing remarkable potential in anomaly detection (AD) tasks across various domains, such as cybersecurity, fraud detection, healthcare, and manufacturing. The intersection of these two fields, termed diffusion models for anomaly detection (DMAD), offers promising solutions for identifying deviations in increasingly complex and high-dimensional data. In this survey, we systematically review recent advances in DMAD research and investigate their capabilities. We begin by presenting the fundamental concepts of AD and DMs, followed by a comprehensive analysis of classic DM architectures including DDPMs, DDIMs, and Score SDEs. We further categorize existing DMAD methods into reconstruction-based, density-based, and hybrid approaches, providing detailed examinations of their methodological innovations. We also explore the diverse tasks across different data modalities, encompassing image, time series, video, and multimodal data analysis. Furthermore, we discuss critical challenges and emerging research directions, including computational efficiency, model interpretability, robustness enhancement, edge-cloud collaboration, and integration with large language models. The collection of DMAD research papers and resources is available at https://github.com/fdjingliu/DMAD.
Authors: Rickard Br\"annvall, Laurynas Adomaitis, Olof G\"ornerup, Anass Sedrati
Abstract: The right to privacy, enshrined in various human rights declarations, faces new challenges in the age of artificial intelligence (AI). This paper explores the concept of the Right to be Forgotten (RTBF) within AI systems, contrasting it with traditional data erasure methods. We introduce Forgotten by Design, a proactive approach to privacy preservation that integrates instance-specific obfuscation techniques during the AI model training process. Unlike machine unlearning, which modifies models post-training, our method prevents sensitive data from being embedded in the first place. Using the LIRA membership inference attack, we identify vulnerable data points and propose defenses that combine additive gradient noise and weighting schemes. Our experiments on the CIFAR-10 dataset demonstrate that our techniques reduce privacy risks by at least an order of magnitude while maintaining model accuracy (at 95% significance). Additionally, we present visualization methods for the privacy-utility trade-off, providing a clear framework for balancing privacy risk and model accuracy. This work contributes to the development of privacy-preserving AI systems that align with human cognitive processes of motivated forgetting, offering a robust framework for safeguarding sensitive information and ensuring compliance with privacy regulations.
Authors: Marcin Blachnik, Piotr Ciepli\'nski
Abstract: Data pruning, or instance selection, is an important problem in machine learning especially in terms of nearest neighbour classifier. However, in data pruning which speeds up the prediction phase, there is an issue related to the speed and efficiency of the process itself. In response, the study proposes an approach involving transforming the instance selection process into a classification task conducted in a unified meta-feature space where each instance can be classified and assigned to either the "to keep" or "to remove" class. This approach requires training an appropriate meta-classifier, which can be developed based on historical instance selection results from other datasets using reference instance selection methods as a labeling tool. This work proposes constructing the meta-feature space based on properties extracted from the nearest neighbor graph. Experiments conducted on 17 datasets of varying sizes and five reference instance selection methods (ENN, Drop3, ICF, HMN-EI, and CCIS) demonstrate that the proposed solution achieves results comparable to reference instance selection methods while significantly reducing computational complexity. In the proposed approach, the computational complexity of the system depends only on identifying the k-nearest neighbors for each data sample and running the meta-classifier. Additionally, the study discusses the choice of meta-classifier, recommending the use of Balanced Random Forest.
Authors: Atik Faysal, Taha Boushine, Mohammad Rostami, Reihaneh Gh. Roshan, Huaxia Wang, Nikhil Muralidhar, Avimanyu Sahoo, Yu-Dong Yao
Abstract: We propose Denoising Masked Autoencoder (Deno-MAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of masked autoencoders by incorporating multiple input modalities, including noise as an explicit modality, to enhance cross-modal learning and improve denoising performance. The network is pre-trained using unlabeled noisy modulation signals and constellation diagrams, effectively learning to reconstruct their equivalent noiseless signals and diagrams. Deno-MAE achieves state-of-the-art accuracy in automatic modulation classification tasks with significantly fewer training samples, demonstrating a 10% reduction in unlabeled pretraining data and a 3% reduction in labeled fine-tuning data compared to existing approaches. Moreover, our model exhibits robust performance across varying signal-to-noise ratios (SNRs) and supports extrapolation on unseen lower SNRs. The results indicate that DenoMAE is an efficient, flexible, and data-efficient solution for denoising and classifying modulation signals in challenging noise-intensive environments.
Authors: Jianfei Sun, Qiang Gao, Cong Wu, Yuxian Li, Jiacheng Wang, Dusit Niyato
Abstract: The proliferation of Internet of Things (IoT) devices and the advent of 6G technologies have introduced computationally intensive tasks that often surpass the processing capabilities of user devices. Efficient and secure resource allocation in serverless multi-cloud edge computing environments is essential for supporting these demands and advancing distributed computing. However, existing solutions frequently struggle with the complexity of multi-cloud infrastructures, robust security integration, and effective application of traditional deep reinforcement learning (DRL) techniques under system constraints. To address these challenges, we present SARMTO, a novel framework that integrates an action-constrained DRL model. SARMTO dynamically balances resource allocation, task offloading, security, and performance by utilizing a Markov decision process formulation, an adaptive security mechanism, and sophisticated optimization techniques. Extensive simulations across varying scenarios, including different task loads, data sizes, and MEC capacities, show that SARMTO consistently outperforms five baseline approaches, achieving up to a 40% reduction in system costs and a 41.5% improvement in energy efficiency over state-of-the-art methods. These enhancements highlight SARMTO's potential to revolutionize resource management in intricate distributed computing environments, opening the door to more efficient and secure IoT and edge computing applications.
Authors: M. Manzour, A. Ballardini, R. Izquierdo, M. \'A. Sotelo
Abstract: Lane-changing maneuvers, particularly those executed abruptly or in risky situations, are a significant cause of road traffic accidents. However, current research mainly focuses on predicting safe lane changes. Furthermore, existing accident datasets are often based on images only and lack comprehensive sensory data. In this work, we focus on predicting risky lane changes using the CRASH dataset (our own collected dataset specifically for risky lane changes), and safe lane changes (using the HighD dataset). Then, we leverage KG and Bayesian inference to predict these maneuvers using linguistic contextual information, enhancing the model's interpretability and transparency. The model achieved a 91.5% f1-score with anticipation time extending to four seconds for risky lane changes, and a 90.0% f1-score for predicting safe lane changes with the same anticipation time. We validate our model by integrating it into a vehicle within the CARLA simulator in scenarios that involve risky lane changes. The model managed to anticipate sudden lane changes, thus providing automated vehicles with further time to plan and execute appropriate safe reactions. Finally, to enhance the explainability of our model, we utilize RAG to provide clear and natural language explanations for the given prediction.
Authors: Xin He, Wenqi Fan, Yili Wang, Chengyi Liu, Rui Miao, Xin Juan, Xin Wang
Abstract: Graph Neural Networks (GNNs) demonstrate significant potential in various applications but remain highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs; however, they struggle to effectively defend against multiple types of adversarial attacks simultaneously due to their limited flexibility, and they lack comprehensive modeling of graph data due to their heavy reliance on heuristic prior knowledge. To overcome these challenges, we propose a more versatile approach for defending against adversarial attacks on graphs. In this work, we introduce the Graph Defense Diffusion Model (GDDM), a flexible purification method that leverages the denoising and modeling capabilities of diffusion models. The iterative nature of diffusion models aligns well with the stepwise process of adversarial attacks, making them particularly suitable for defense. By iteratively adding and removing noise, GDDM effectively purifies attacked graphs, restoring their original structure and features. Our GDDM consists of two key components: (1) Graph Structure-Driven Refiner, which preserves the basic fidelity of the graph during the denoising process, and ensures that the generated graph remains consistent with the original scope; and (2) Node Feature-Constrained Regularizer, which removes residual impurities from the denoised graph, further enhances the purification effect. Additionally, we design tailored denoising strategies to handle different types of adversarial attacks, improving the model's adaptability to various attack scenarios. Extensive experiments conducted on three real-world datasets demonstrate that GDDM outperforms state-of-the-art methods in defending against a wide range of adversarial attacks, showcasing its robustness and effectiveness.
Authors: Mohamed Hassan, Aleksandar Vakanski, Boyu Zhang, Min Xian
Abstract: The generalization performance of deep neural networks (DNNs) is a critical factor in achieving robust model behavior on unseen data. Recent studies have highlighted the importance of sharpness-based measures in promoting generalization by encouraging convergence to flatter minima. Among these approaches, Sharpness-Aware Minimization (SAM) has emerged as an effective optimization technique for reducing the sharpness of the loss landscape, thereby improving generalization. However, SAM's computational overhead and sensitivity to noisy gradients limit its scalability and efficiency. To address these challenges, we propose Gradient-Centralized Sharpness-Aware Minimization (GCSAM), which incorporates Gradient Centralization (GC) to stabilize gradients and accelerate convergence. GCSAM normalizes gradients before the ascent step, reducing noise and variance, and improving stability during training. Our evaluations indicate that GCSAM consistently outperforms SAM and the Adam optimizer in terms of generalization and computational efficiency. These findings demonstrate GCSAM's effectiveness across diverse domains, including general and medical imaging tasks.
Authors: Kai Wang, Dongwen Tang, Wangbo Zhao, Yang You
Abstract: Parameter generation has struggled to scale up for a long time, significantly limiting its range of applications. In this study, we introduce \textbf{R}ecurrent diffusion for large-scale \textbf{P}arameter \textbf{G}eneration, called \textbf{RPG}. We first divide the trained parameters into non-overlapping parts, after which a recurrent model is proposed to learn their relationships. The recurrent model's outputs, as conditions, are then fed into a diffusion model to generate the neural network parameters. Using only a single GPU, recurrent diffusion enables us to generate popular vision and language models such as ConvNeXt-L and LoRA parameters of LLaMA-7B. Meanwhile, across various architectures and tasks, the generated parameters consistently perform comparable results over trained networks. Notably, our approach also shows the potential to generate models for handling unseen tasks, which largely increases the practicality of parameter generation. Our code is available \href{https://github.com/NUS-HPC-AI-Lab/Recurrent-Parameter-Generation}{here}.
URLs: https://github.com/NUS-HPC-AI-Lab/Recurrent-Parameter-Generation
Authors: Chaoqing Tang, Huanze Zhuang, Guiyun Tian, Zhenli Zeng, Yi Ding, Wenzhong Liu, Xiang Bai
Abstract: Pre-trained large models attract widespread attention in recent years, but they face challenges in applications that require high interpretability or have limited resources, such as physical sensing, medical imaging, and bioinformatics. Compressed Sensing (CS) is a well-proved theory that drives many recent breakthroughs in these applications. However, as a typical under-determined linear system, CS suffers from excessively long sparse reconstruction times when using traditional iterative methods, particularly with large-scale data. Current AI methods like deep unfolding fail to substitute them because pre-trained models exhibit poor generality beyond their training conditions and dataset distributions, or lack interpretability. Instead of following the big model fervor, this paper proposes ultra-small artificial neural models called coefficients learning (CL), enabling training-free and rapid sparse reconstruction while perfectly inheriting the generality and interpretability of traditional iterative methods, bringing new feature of incorporating prior knowledges. In CL, a signal of length $n$ only needs a minimal of $n$ trainable parameters. A case study model called CLOMP is implemented for evaluation. Experiments are conducted on both synthetic and real one-dimensional and two-dimensional signals, demonstrating significant improvements in efficiency and accuracy. Compared to representative iterative methods, CLOMP improves efficiency by 100 to 1000 folds for large-scale data. Test results on eight diverse image datasets indicate that CLOMP improves structural similarity index by 292%, 98%, 45% for sampling rates of 0.1, 0.3, 0.5, respectively. We believe this method can truly usher CS reconstruction into the AI era, benefiting countless under-determined linear systems that rely on sparse solution.
Authors: Lu Liu, Yang Tang, Kexuan Zhang, Qiyu Sun
Abstract: Due to the challenge posed by multi-source and heterogeneous data collected from diverse environments, causal relationships among features can exhibit variations influenced by different time spans, regions, or strategies. This diversity makes a single causal model inadequate for accurately representing complex causal relationships in all observational data, a crucial consideration in causal learning. To address this challenge, we introduce the nonlinear Causal Kernel Clustering method designed for heterogeneous subgroup causal learning, illuminating variations in causal relationships across diverse subgroups. It comprises two primary components. First, the construction of a sample mapping function forms the basis of the subsequent nonlinear causal kernel. This function assesses the differences in potential nonlinear causal relationships in various samples, supported by our causal identifiability theory. Second, a nonlinear causal kernel is proposed for clustering heterogeneous subgroups. Experimental results showcase the exceptional performance of our method in accurately identifying heterogeneous subgroups and effectively enhancing causal learning, leading to a great reduction in prediction error.
Authors: F. S. Pezzicoli, V. Ros, F. P. Landes, M. Baity-Jesi
Abstract: Class imbalance (CI) is a longstanding problem in machine learning, slowing down training and reducing performances. Although empirical remedies exist, it is often unclear which ones work best and when, due to the lack of an overarching theory. We address a common case of imbalance, that of anomaly (or outlier) detection. We provide a theoretical framework to analyze, interpret and address CI. It is based on an exact solution of the teacher-student perceptron model, through replica theory. Within this framework, one can distinguish several sources of CI: either intrinsic, train or test imbalance. Our analysis reveals that the optimal train imbalance is generally different from 50%, with a non trivial dependence on the intrinsic imbalance, the abundance of data and on the noise in the learning. Moreover, there is a crossover between a small noise training regime where results are independent of the noise level to a high noise regime where performances quickly degrade with noise. Our results challenge some of the conventional wisdom on CI and offer practical guidelines to address it.
Authors: Zhenyu Hou, Xin Lv, Rui Lu, Jiajie Zhang, Yujiang Li, Zijun Yao, Juanzi Li, Jie Tang, Yuxiao Dong
Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling. While reinforcement learning (RL) holds promise for enabling self-exploration and learning from feedback, recent attempts yield only modest improvements in complex reasoning. In this paper, we present T1 to scale RL by encouraging exploration and understand inference scaling. We first initialize the LLM using synthesized chain-of-thought data that integrates trial-and-error and self-verification. To scale RL training, we promote increased sampling diversity through oversampling. We further employ an entropy bonus as an auxiliary loss, alongside a dynamic anchor for regularization to facilitate reward optimization. We demonstrate that T1 with open LLMs as its base exhibits inference scaling behavior and achieves superior performance on challenging math reasoning benchmarks. For example, T1 with Qwen2.5-32B as the base model outperforms the recent Qwen QwQ-32B-Preview model on MATH500, AIME2024, and Omni-math-500. More importantly, we present a simple strategy to examine inference scaling, where increased inference budgets directly lead to T1's better performance without any additional verification. We will open-source the T1 models and the data used to train them at \url{https://github.com/THUDM/T1}.
Authors: Vladimir Vovk
Abstract: This note continues development of the functional theory of randomness, a modification of the algorithmic theory of randomness getting rid of unspecified additive constants. It introduces new kinds of confidence predictors, including randomness predictors (the most general confidence predictors based on the assumption of IID observations) and exchangeability predictors (the most general confidence predictors based on the assumption of exchangeable observations). The main result implies that both are close to conformal predictors and quantifies the difference between them.
Authors: Majid Farhadloo, Arun Sharma, Alexey Leontovich, Svetomir N. Markovic, Shashi Shekhar
Abstract: Given multi-type point maps from different place-types (e.g., tumor regions), our objective is to develop a classifier trained on the source place-type to accurately distinguish between two classes of the target place-type based on their point arrangements. This problem is societally important for many applications, such as generating clinical hypotheses for designing new immunotherapies for cancer treatment. The challenge lies in the spatial variability, the inherent heterogeneity and variation observed in spatial properties or arrangements across different locations (i.e., place-types). Previous techniques focus on self-supervised tasks to learn domain-invariant features and mitigate domain differences; however, they often neglect the underlying spatial arrangements among data points, leading to significant discrepancies across different place-types. We explore a novel multi-task self-learning framework that targets spatial arrangements, such as spatial mix-up masking and spatial contrastive predictive coding, for spatially-delineated domain-adapted AI classification. Experimental results on real-world datasets (e.g., oncology data) show that the proposed framework provides higher prediction accuracy than baseline methods.
Authors: Ali Abbasi Tadi, Dima Alhadidi, Luis Rueda
Abstract: Transformers, a cornerstone of deep-learning architectures for sequential data, have achieved state-of-the-art results in tasks like Natural Language Processing (NLP). Models such as BERT and GPT-3 exemplify their success and have driven the rise of large language models (LLMs). However, a critical challenge persists: safeguarding the privacy of data used in LLM training. Privacy-preserving techniques like Federated Learning (FL) offer potential solutions, but practical limitations hinder their effectiveness for Transformer training. Two primary issues are (I) the risk of sensitive information leakage due to aggregation methods like FedAvg or FedSGD, and (II) the high communication overhead caused by the large size of Transformer models. This paper introduces a novel FL method that reduces communication overhead while maintaining competitive utility. Our approach avoids sharing full model weights by simulating a global model locally. We apply k-means clustering to each Transformer layer, compute centroids locally, and transmit only these centroids to the server instead of full weights or gradients. To enhance security, we leverage Intel SGX for secure transmission of centroids. Evaluated on a translation task, our method achieves utility comparable to state-of-the-art baselines while significantly reducing communication costs. This provides a more efficient and privacy-preserving FL solution for Transformer models.
Authors: Fernando H. O. Duarte, Gladston J. P. Moreira, Eduardo J. S. Luz, Leonardo B. L. Santos, Vander L. S. Freitas
Abstract: The COVID-19 pandemic has victimized over 7 million people to date, prompting diverse research efforts. Spatio-temporal models combining mobility data with machine learning have gained attention for disease forecasting. Here, we explore Graph Convolutional Recurrent Network (GCRN) and Graph Convolutional Long Short-Term Memory (GCLSTM), which combine the power of Graph Neural Networks (GNN) with traditional architectures that deal with sequential data. The aim is to forecast future values of COVID-19 cases in Brazil and China by leveraging human mobility networks, whose nodes represent geographical locations and links are flows of vehicles or people. We show that employing backbone extraction to filter out negligible connections in the mobility network enhances predictive stability. Comparing regression and classification tasks demonstrates that binary classification yields smoother, more interpretable results. Interestingly, we observe qualitatively equivalent results for both Brazil and China datasets by introducing sliding windows of variable size and prediction horizons. Compared to prior studies, introducing the sliding window and the network backbone extraction strategies yields improvements of about 80% in root mean squared errors.
Authors: Stefano Rando, Luca Romani, Matteo Migliarini, Luca Franco, Denis Gudovskiy, Fabio Galasso
Abstract: State Space Models (SSMs) have recently enjoyed a rise to prominence in the field of deep learning for sequence modeling, especially as an alternative to Transformers. Their success stems from avoiding two well-known drawbacks of attention-based models: quadratic complexity with respect to the sequence length and inability to model long-range dependencies. The SSM variant Mamba has demonstrated performance comparable to Transformers without any form of attention, thanks to the use of a selective mechanism for the state parameters. Selectivity, however, is only evaluated empirically and the reasons of its effectiveness remain unclear. In this work, we show how selectivity is related to the sequence processing. Our analysis shows that selective time intervals in Mamba act as linear approximators of information. Then, we propose our SeRpEnt architecture, a SSM that further exploits selectivity to compress sequences in an information-aware fashion. It employs a resampling mechanism that aggregates elements based on their information content. Our empirical results in the Long Range Arena benchmark and other language modeling tasks show benefits of the SeRpEnt's resampling mechanism.
Authors: Dar\'io C. Larese, Almudena Bravo Cerrada, Gabriel Dambrosio Tomei, Alejandro Guerrero-L\'opez, Pablo M. Olmos, Mar\'ia Jes\'us G\'omez Garc\'ia
Abstract: Maintaining railway axles is critical to preventing severe accidents and financial losses. The railway industry is increasingly interested in advanced condition monitoring techniques to enhance safety and efficiency, moving beyond traditional periodic inspections toward Maintenance 4.0. This study introduces a robust Deep Autoregressive solution that integrates seamlessly with existing systems to avert mechanical failures. Our approach simulates and predicts vibration signals under various conditions and fault scenarios, improving dataset robustness for more effective detection systems. These systems can alert maintenance needs, preventing accidents preemptively. We use experimental vibration signals from accelerometers on train axles. Our primary contributions include a transformer model, ShaftFormer, designed for processing time series data, and an alternative model incorporating spectral methods and enhanced observation models. Simulating vibration signals under diverse conditions mitigates the high cost of obtaining experimental signals for all scenarios. Given the non-stationary nature of railway vibration signals, influenced by speed and load changes, our models address these complexities, offering a powerful tool for predictive maintenance in the rail industry.
Authors: Hengrong Du, Qi Feng, Changwei Tu, Xiaoyu Wang, Lingjiong Zhu
Abstract: We consider the constrained sampling problem where the goal is to sample from a target distribution on a constrained domain. We propose skew-reflected non-reversible Langevin dynamics (SRNLD), a continuous-time stochastic differential equation with skew-reflected boundary. We obtain non-asymptotic convergence rate of SRNLD to the target distribution in both total variation and 1-Wasserstein distances. By breaking reversibility, we show that the convergence is faster than the special case of the reversible dynamics. Based on the discretization of SRNLD, we propose skew-reflected non-reversible Langevin Monte Carlo (SRNLMC), and obtain non-asymptotic discretization error from SRNLD, and convergence guarantees to the target distribution in 1-Wasserstein distance. We show better performance guarantees than the projected Langevin Monte Carlo in the literature that is based on the reversible dynamics. Numerical experiments are provided for both synthetic and real datasets to show efficiency of the proposed algorithms.
Authors: Pouya Hamadanian, Sadjad Fouladi
Abstract: Large Language Models (LLM) have revolutionized natural language processing, but their inference demands substantial resources, while under-utilizing high-end accelerators like GPUs. A major bottleneck arises from the attention mechanism, which requires storing large key-value caches, limiting the maximum achievable throughput way below the available computing resources. Current approaches attempt to mitigate this issue through memory-efficient attention and paging mechanisms, but remained constrained by the assumption that all operations must be performed on high-end accelerators. In this work, we propose Glinthawk, a two-tiered architecture that decouples the attention mechanism from the rest of the Transformer model. This approach allows the memory requirements for attention to scale independently, enabling larger batch sizes and more efficient use of the high-end accelerators. We prototype Glinthawk with NVIDIA T4 GPUs as one tier and standard CPU VMs as the other. Compared to a traditional single-tier setup, it improves throughput by $5.9\times$ and reduces cost of generation by $2.8\times$. For longer sequence lengths, it achieves $16.3\times$ throughput improvement at $2.4\times$ less cost. Our evaluation shows that this architecture can tolerate moderate network latency with minimal performance degradation, making it highly effective for latency-tolerant, throughput-oriented applications such as batch processing. We shared our prototype publicly at \url{https://github.com/microsoft/glinthawk}.
Authors: Julia R. Falconer, Eibe Frank, Devon L. L. Polaschek, Chaitanya Joshi
Abstract: Recent work [ 14 ] has introduced a method for prior elicitation that utilizes records of expert decisions to infer a prior distribution. While this method provides a promising approach to eliciting expert uncertainty, it has only been demonstrated using tabular data, which may not entirely represent the information used by experts to make decisions. In this paper, we demonstrate how analysts can adopt a deep learning approach to utilize the method proposed in [14 ] with the actual information experts use. We provide an overview of deep learning models that can effectively model expert decision-making to elicit distributions that capture expert uncertainty and present an example examining the risk of colon cancer to show in detail how these models can be used.
Authors: Xunkai Li, Daohan Su, Zhengyu Wu, Guang Zeng, Hongchao Qin, Rong-Hua Li, Guoren Wang
Abstract: The $q$-parameterized magnetic Laplacian serves as the foundation of directed graph (digraph) convolution, enabling this kind of digraph neural network (MagDG) to encode node features and structural insights by complex-domain message passing. As a generalization of undirected methods, MagDG shows superior capability in modeling intricate web-scale topology. Despite the great success achieved by existing MagDGs, limitations still exist: (1) Hand-crafted $q$: The performance of MagDGs depends on selecting an appropriate $q$-parameter to construct suitable graph propagation equations in the complex domain. This parameter tuning, driven by downstream tasks, limits model flexibility and significantly increases manual effort. (2) Coarse Message Passing: Most approaches treat all nodes with the same complex-domain propagation and aggregation rules, neglecting their unique digraph contexts. This oversight results in sub-optimal performance. To address the above issues, we propose two key techniques: (1) MAP is crafted to be a plug-and-play complex-domain propagation optimization strategy in the context of digraph learning, enabling seamless integration into any MagDG to improve predictions while enjoying high running efficiency. (2) MAP++ is a new digraph learning framework, further incorporating a learnable mechanism to achieve adaptively edge-wise propagation and node-wise aggregation in the complex domain for better performance. Extensive experiments on 12 datasets demonstrate that MAP enjoys flexibility for it can be incorporated with any MagDG, and scalability as it can deal with web-scale digraphs. MAP++ achieves SOTA predictive performance on 4 different downstream tasks.
Authors: Kaiyue Wu, Xiao-Jun Zeng, Tingting Mu
Abstract: Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function models sent by another agent if they perform better. We have conducted extensive experiments on a total of 43 different Atari 2600 games to demonstrate the superior performance of the proposed method. After the group learning, among the 129 agents examined, 96% are able to achieve a learning speed-up, and 72% are able to learn over 100 times faster. Also, around 41% of those agents have achieved a higher accumulated reward score by learning in less than 5% of the time steps required by a single agent when learning on its own.
Authors: Xunkai Li, Bowen Fan, Zhengyu Wu, Zhiyu Li, Rong-Hua Li, Guoren Wang
Abstract: Machine unlearning, as a pivotal technology for enhancing model robustness and data privacy, has garnered significant attention in prevalent web mining applications, especially in thriving graph-based scenarios. However, most existing graph unlearning (GU) approaches face significant challenges due to the intricate interactions among web-scale graph elements during the model training: (1) The gradient-driven node entanglement hinders the complete knowledge removal in response to unlearning requests; (2) The billion-level graph elements in the web scenarios present inevitable scalability issues. To break the above limitations, we open up a new perspective by drawing a connection between GU and conventional social influence maximization. To this end, we propose Node Influence Maximization (NIM) through the decoupled influence propagation model and fine-grained influence function in a scalable manner, which is crafted to be a plug-and-play strategy to identify potential nodes affected by unlearning entities. This approach enables offline execution independent of GU, allowing it to be seamlessly integrated into most GU methods to improve their unlearning performance. Based on this, we introduce Scalable Graph Unlearning (SGU) as a new fine-tuned framework, which balances the forgetting and reasoning capability of the unlearned model by entity-specific optimizations. Extensive experiments on 14 datasets, including large-scale ogbn-papers100M, have demonstrated the effectiveness of our approach. Specifically, NIM enhances the forgetting capability of most GU methods, while SGU achieves comprehensive SOTA performance and maintains scalability.
Authors: Yen-Lung Huang, Ming-Hsi Weng, Hao-Tsung Yang
Abstract: With the rapid growth of generative AI in numerous applications, explainable AI (XAI) plays a crucial role in ensuring the responsible development and deployment of generative AI technologies. XAI has undergone notable advancements and widespread adoption in recent years, reflecting a concerted push to enhance the transparency, interpretability, and credibility of AI systems. Recent research emphasizes that a proficient XAI method should adhere to a set of criteria, primarily focusing on two key areas. Firstly, it should ensure the quality and fluidity of explanations, encompassing aspects like faithfulness, plausibility, completeness, and tailoring to individual needs. Secondly, the design principle of the XAI system or mechanism should cover the following factors such as reliability, resilience, the verifiability of its outputs, and the transparency of its algorithm. However, research in XAI for generative models remains relatively scarce, with little exploration into how such methods can effectively meet these criteria in that domain. In this work, we propose PXGen, a post-hoc explainable method for generative models. Given a model that needs to be explained, PXGen prepares two materials for the explanation, the Anchor set and intrinsic & extrinsic criteria. Those materials are customizable by users according to their purpose and requirements. Via the calculation of each criterion, each anchor has a set of feature values and PXGen provides examplebased explanation methods according to the feature values among all the anchors and illustrated and visualized to the users via tractable algorithms such as k-dispersion or k-center.
Authors: Kasimir Schulz, Kieran Evans
Abstract: Machine learning model genealogy enables practitioners to determine which architectural family a neural network belongs to. In this paper, we introduce ShadowGenes, a novel, signature-based method for identifying a given model's architecture, type, and family. Our method involves building a computational graph of the model that is agnostic of its serialization format, then analyzing its internal operations to identify unique patterns, and finally building and refining signatures based on these. We highlight important workings of the underlying engine and demonstrate the technique used to construct a signature and scan a given model. This approach to model genealogy can be applied to model files without the need for additional external information. We test ShadowGenes on a labeled dataset of over 1,400 models and achieve a mean true positive rate of 97.49% and a precision score of 99.51%; which validates the technique as a practical method for model genealogy. This enables practitioners to understand the use cases of a given model, the internal computational process, and identify possible security risks, such as the potential for model backdooring.
Authors: Zihan Liu, Prashant N. Kambali, C. Nataraj
Abstract: Accurate models are essential for design, performance prediction, control, and diagnostics in complex engineering systems. Physics-based models excel during the design phase but often become outdated during system deployment due to changing operational conditions, unknown interactions, excitations, and parametric drift. While data-based models can capture the current state of complex systems, they face significant challenges, including excessive data dependence, limited generalizability to changing conditions, and inability to predict parametric dependence. This has led to combining physics and data in modeling, termed physics-infused machine learning, often using numerical simulations from physics-based models. This paper introduces a novel approach that departs from standard techniques by uncovering information from nonlinear dynamical modeling and embedding it in data-based models. The goal is to create a hybrid adaptive modeling framework that integrates data-based modeling with newly measured data and analytical nonlinear dynamical models for enhanced accuracy, parametric dependence, and improved generalizability. By explicitly incorporating nonlinear dynamic phenomena through perturbation methods, the predictive capabilities are more realistic and insightful compared to knowledge obtained from brute-force numerical simulations. In particular, perturbation methods are utilized to derive asymptotic solutions which are parameterized to generate frequency responses. Frequency responses provide comprehensive insights into dynamics and nonlinearity which are quantified and extracted as high-quality features. A machine-learning model, trained by these features, tracks parameter variations and updates the mismatched model. The results demonstrate that this adaptive modeling method outperforms numerical gray box models in prediction accuracy and computational efficiency.
Authors: Asal Mehradfar, Xuzhe Zhao, Yue Niu, Sara Babakniya, Mahdi Alesheikh, Hamidreza Aghasi, Salman Avestimehr
Abstract: Automating analog and radio-frequency (RF) circuit design using machine learning (ML) significantly reduces the time and effort required for parameter optimization. This study explores supervised ML-based approaches for designing circuit parameters from performance specifications across various circuit types, including homogeneous and heterogeneous designs. By evaluating diverse ML models, from neural networks like transformers to traditional methods like random forests, we identify the best-performing models for each circuit. Our results show that simpler circuits, such as low-noise amplifiers, achieve exceptional accuracy with mean relative errors as low as 0.3% due to their linear parameter-performance relationships. In contrast, complex circuits, like power amplifiers and voltage-controlled oscillators, present challenges due to their non-linear interactions and larger design spaces. For heterogeneous circuits, our approach achieves an 88% reduction in errors with increased training data, with the receiver achieving a mean relative error as low as 0.23%, showcasing the scalability and accuracy of the proposed methodology. Additionally, we provide insights into model strengths, with transformers excelling in capturing non-linear mappings and k-nearest neighbors performing robustly in moderately linear parameter spaces, especially in heterogeneous circuits with larger datasets. This work establishes a foundation for extending ML-driven design automation, enabling more efficient and scalable circuit design workflows.
Authors: Kaiyuan Tian, Linbo Qiao, Baihui Liu, Gongqingjian Jiang, Dongsheng Li
Abstract: Scientific research faces high costs and inefficiencies with traditional methods, but the rise of deep learning and large language models (LLMs) offers innovative solutions. This survey reviews LLM applications across scientific fields such as biology, medicine, chemistry, and meteorology, underscoring their role in advancing research. However, the continuous expansion of model size has led to significant memory demands, hindering further development and application of LLMs for science. To address this, we review memory-efficient training techniques for LLMs based on the transformer architecture, including distributed training, mixed precision training, and gradient checkpointing. Using AlphaFold 2 as an example, we demonstrate how tailored memory optimization methods can reduce storage needs while preserving prediction accuracy. We also discuss the challenges of memory optimization in practice and potential future directions, hoping to provide valuable insights for researchers and engineers.
Authors: Divya Shanmugam, Shuvom Sadhuka, Manish Raghavan, John Guttag, Bonnie Berger, Emma Pierson
Abstract: It remains difficult to evaluate machine learning classifiers in the absence of a large, labeled dataset. While labeled data can be prohibitively expensive or impossible to obtain, unlabeled data is plentiful. Here, we introduce Semi-Supervised Model Evaluation (SSME), a method that uses both labeled and unlabeled data to evaluate machine learning classifiers. SSME is the first evaluation method to take advantage of the fact that: (i) there are frequently multiple classifiers for the same task, (ii) continuous classifier scores are often available for all classes, and (iii) unlabeled data is often far more plentiful than labeled data. The key idea is to use a semi-supervised mixture model to estimate the joint distribution of ground truth labels and classifier predictions. We can then use this model to estimate any metric that is a function of classifier scores and ground truth labels (e.g., accuracy or expected calibration error). We present experiments in four domains where obtaining large labeled datasets is often impractical: (1) healthcare, (2) content moderation, (3) molecular property prediction, and (4) image annotation. Our results demonstrate that SSME estimates performance more accurately than do competing methods, reducing error by 5.1x relative to using labeled data alone and 2.4x relative to the next best competing method. SSME also improves accuracy when evaluating performance across subsets of the test distribution (e.g., specific demographic subgroups) and when evaluating the performance of language models.
Authors: Zihan Qiu, Zeyu Huang, Bo Zheng, Kaiyue Wen, Zekun Wang, Rui Men, Ivan Titov, Dayiheng Liu, Jingren Zhou, Junyang Lin
Abstract: This paper revisits the implementation of $\textbf{L}$oad-$\textbf{b}$alancing $\textbf{L}$oss (LBL) when training Mixture-of-Experts (MoEs) models. Specifically, LBL for MoEs is defined as $N_E \sum_{i=1}^{N_E} f_i p_i$, where $N_E$ is the total number of experts, $f_i$ represents the frequency of expert $i$ being selected, and $p_i$ denotes the average gating score of the expert $i$. Existing MoE training frameworks usually employ the parallel training strategy so that $f_i$ and the LBL are calculated within a $\textbf{micro-batch}$ and then averaged across parallel groups. In essence, a micro-batch for training billion-scale LLMs normally contains very few sequences. So, the micro-batch LBL is almost at the sequence level, and the router is pushed to distribute the token evenly within each sequence. Under this strict constraint, even tokens from a domain-specific sequence ($\textit{e.g.}$, code) are uniformly routed to all experts, thereby inhibiting expert specialization. In this work, we propose calculating LBL using a $\textbf{global-batch}$ to loose this constraint. Because a global-batch contains much more diverse sequences than a micro-batch, which will encourage load balance at the corpus level. Specifically, we introduce an extra communication step to synchronize $f_i$ across micro-batches and then use it to calculate the LBL. Through experiments on training MoEs-based LLMs (up to $\textbf{42.8B}$ total parameters and $\textbf{400B}$ tokens), we surprisingly find that the global-batch LBL strategy yields excellent performance gains in both pre-training perplexity and downstream tasks. Our analysis reveals that the global-batch LBL also greatly improves the domain specialization of MoE experts.
Authors: He Yu, Jing Liu
Abstract: Dynamic graph representation learning plays a crucial role in understanding evolving behaviors. However, existing methods often struggle with flexibility, adaptability, and the preservation of temporal and structural dynamics. To address these issues, we propose Community-aware Temporal Walks (CTWalks), a novel framework for representation learning on continuous-time dynamic graphs. CTWalks integrates three key components: a community-based parameter-free temporal walk sampling mechanism, an anonymization strategy enriched with community labels, and an encoding process that leverages continuous temporal dynamics modeled via ordinary differential equations (ODEs). This design enables precise modeling of both intra- and inter-community interactions, offering a fine-grained representation of evolving temporal patterns in continuous-time dynamic graphs. CTWalks theoretically overcomes locality bias in walks and establishes its connection to matrix factorization. Experiments on benchmark datasets demonstrate that CTWalks outperforms established methods in temporal link prediction tasks, achieving higher accuracy while maintaining robustness.
Authors: Xinxin Wang, Yongshan Zhang, Yicong Zhou
Abstract: Incomplete multi-view clustering presents significant challenges due to missing views. Although many existing graph-based methods aim to recover missing instances or complete similarity matrices with promising results, they still face several limitations: (1) Recovered data may be unsuitable for spectral clustering, as these methods often ignore guidance from spectral analysis; (2) Complex optimization processes require high computational burden, hindering scalability to large-scale problems; (3) Most methods do not address the rotational mismatch problem in spectral embeddings. To address these issues, we propose a highly efficient rotation-invariant spectral embedding (RISE) method for scalable incomplete multi-view clustering. RISE learns view-specific embeddings from incomplete bipartite graphs to capture the complementary information. Meanwhile, a complete consensus representation with second-order rotation-invariant property is recovered from these incomplete embeddings in a unified model. Moreover, we design a fast alternating optimization algorithm with linear complexity and promising convergence to solve the proposed formulation. Extensive experiments on multiple datasets demonstrate the effectiveness, scalability, and efficiency of RISE compared to the state-of-the-art methods.
Authors: C\'edric Ho Thanh
Abstract: The existence of salient semantic clusters in the latent spaces of a neural network during training strongly correlates its final accuracy on classification tasks. This paper proposes a novel fine-tuning method that boosts performance by optimising the formation of these latent clusters, using the Louvain community detection algorithm and a specifically designed clustering loss function. We present preliminary results that demonstrate the viability of this process on classical neural network architectures during fine-tuning on the CIFAR-100 dataset.
Authors: Peter Devine
Abstract: Retrieval Augmented Generation (RAG) systems have been shown to improve the accuracy of Large Language Model (LLM) outputs. However, these models can often achieve low accuracy when applied to new data domains. We introduce the Automatic Local Fine Tuning of Retrieval Augmented Generation models (ALoFTRAG) framework, designed to improve the accuracy of RAG systems on a given domain by training LLMs without manually labeled data or using larger teacher models. By generating and filtering synthetic training data and performing LoRA fine-tuning, ALoFTRAG improves citation and answer accuracy across 20 datasets in 26 languages by, on average, 8.3% and 3.0% respectively. Our results demonstrate that ALoFTRAG offers a practical, cost-effective, and data-secure solution for improving RAG accuracy, making it particularly applicable to sensitive domains such as healthcare and finance.
Authors: Jing Xiao, Xinhai Chen, Qingling Wang, Jie Liu
Abstract: Mesh generation plays a crucial role in scientific computing. Traditional mesh generation methods, such as TFI and PDE-based methods, often struggle to achieve a balance between efficiency and mesh quality. To address this challenge, physics-informed intelligent learning methods have recently emerged, significantly improving generation efficiency while maintaining high mesh quality. However, physics-informed methods fail to generalize when applied to previously unseen geometries, as even small changes in the boundary shape necessitate burdensome retraining to adapt to new geometric variations. In this paper, we introduce MeshONet, the first generalizable intelligent learning method for structured mesh generation. The method transforms the mesh generation task into an operator learning problem with multiple input and solution functions. To effectively overcome the multivariable mapping restriction of operator learning methods, we propose a dual-branch, shared-trunk architecture to approximate the mapping between function spaces based on input-output pairs. Experimental results show that MeshONet achieves a speedup of up to four orders of magnitude in generation efficiency over traditional methods. It also enables generalization to different geometries without retraining, greatly enhancing the practicality of intelligent methods.
Authors: Qian He, Wenqi Liang, Chunhui Hao, Gan Sun, Jiandong Tian
Abstract: Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for reasoning. However, this approach fails to enhance the quality of reasoning by capturing the subtle variation between states. Much like how humans infer trends in event development from this variation, in this work, we introduce Global-Local variation Awareness Mamba-based world model (GLAM) that improves reasoning quality by perceiving and predicting variation between states. GLAM comprises two Mambabased parallel reasoning modules, GMamba and LMamba, which focus on perceiving variation from global and local perspectives, respectively, during the reasoning process. GMamba focuses on identifying patterns of variation between states in the input sequence and leverages these patterns to enhance the prediction of future state variation. LMamba emphasizes reasoning about unknown information, such as rewards, termination signals, and visual representations, by perceiving variation in adjacent states. By integrating the strengths of the two modules, GLAM accounts for highervalue variation in environmental changes, providing the agent with more efficient imagination-based training. We demonstrate that our method outperforms existing methods in normalized human scores on the Atari 100k benchmark.
Authors: Yaxuan Wang, Hao Cheng, Jing Xiong, Qingsong Wen, Han Jia, Ruixuan Song, Liyuan Zhang, Zhaowei Zhu, Yang Liu
Abstract: Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level labels (detected abnormal events with segments of time points) and unlabeled data (undetected events), while the ideal algorithmic outcome should be point-level predictions. Therefore, the huge label information gap between training data and targets makes the task challenging. In this study, we formulate the above imperfect information as noisy labels and propose NRdetector, a noise-resilient framework that incorporates confidence-based sample selection, robust segment-level learning, and data-centric point-level detection for multivariate time series anomaly detection. Particularly, to bridge the information gap between noisy segment-level labels and missing point-level labels, we develop a novel loss function that can effectively mitigate the label noise and consider the temporal features. It encourages the smoothness of consecutive points and the separability of points from segments with different labels. Extensive experiments on real-world multivariate time series datasets with 11 different evaluation metrics demonstrate that NRdetector consistently achieves robust results across multiple real-world datasets, outperforming various baselines adapted to operate in our setting.
Authors: Nachiket Kapure, Harsh Joshi, Parul Kumari, Rajeshwari mistri, Manasi Mali
Abstract: Feature selection is a crucial preprocessing step in machine learning, impacting model performance, interpretability, and computational efficiency. This study introduces a novel hybrid approach, the Forward Recursive Adaptive Model Extraction Technique (FRAME), which combines Forward Selection and Recursive Feature Elimination (RFE) to enhance feature selection across diverse datasets. FRAME integrates the strengths of both methods, balancing exploration and exploitation of features to optimize selection. A comprehensive evaluation of FRAME was conducted against traditional methods such as SelectKBest and Lasso Regression, using high-dimensional, noisy, and heterogeneous datasets. The results demonstrate that FRAME consistently delivers superior predictive performance based on downstream machine learning evaluation metrics. It effectively reduces dimensionality while maintaining robust model performance, making it particularly valuable for applications requiring interpretable and accurate predictions, such as biomedical diagnostics. This study highlights the importance of assessing feature selection methods across varied datasets to ensure their robustness and generalizability. The findings suggest that FRAME has significant potential for further enhancement, particularly through integration with deep learning architectures for adaptive and real-time feature selection in dynamic environments. By advancing feature selection methodologies, FRAME offers a practical and effective solution to improve machine learning applications across multiple domains.
Authors: Rupesh Raj Karn
Abstract: Large Language Models (LLMs) have revolutionized various applications by generating outputs based on given prompts. However, achieving the desired output requires iterative prompt refinement. This paper presents a novel approach that draws parallels between the iterative prompt optimization process in LLMs and feedback control systems. We iteratively refine the prompt by treating the deviation between the LLM output and the desired result as an error term until the output criteria are met. This process is akin to a feedback control system, where the LLM, despite being non-linear and non-deterministic, is managed using principles from linear feedback control systems. We explore the application of different types of controllers within this framework, providing a mathematical foundation for integrating linear feedback control mechanisms with LLMs.
Authors: Paul Tiwald, Ivona Krchova, Andrey Sidorenko, Mariana Vargas-Vieyra, Mario Scriminaci, Michael Platzer
Abstract: Synthetic data generation for tabular datasets must balance fidelity, efficiency, and versatility to meet the demands of real-world applications. We introduce the Tabular Auto-Regressive Generative Network (TabularARGN), a flexible framework designed to handle mixed-type, multivariate, and sequential datasets. By training on all possible conditional probabilities, TabularARGN supports advanced features such as fairness-aware generation, imputation, and conditional generation on any subset of columns. The framework achieves state-of-the-art synthetic data quality while significantly reducing training and inference times, making it ideal for large-scale datasets with diverse structures. Evaluated across established benchmarks, including realistic datasets with complex relationships, TabularARGN demonstrates its capability to synthesize high-quality data efficiently. By unifying flexibility and performance, this framework paves the way for practical synthetic data generation across industries.
Authors: Hongjun Liu, Changwei Song, Jiaqi Qiang, Jianqiang Li, Hui Pan, Lin Lu, Xiao Long, Qing Zhao, Jiuzuo Huang, Shi Chen
Abstract: Cushing's syndrome is a condition caused by excessive glucocorticoid secretion from the adrenal cortex, often manifesting with moon facies and plethora, making facial data crucial for diagnosis. Previous studies have used pre-trained convolutional neural networks (CNNs) for diagnosing Cushing's syndrome using frontal facial images. However, CNNs are better at capturing local features, while Cushing's syndrome often presents with global facial features. Transformer-based models like ViT and SWIN, which utilize self-attention mechanisms, can better capture long-range dependencies and global features. Recently, DINOv2, a foundation model based on visual Transformers, has gained interest. This study compares the performance of various pre-trained models, including CNNs, Transformer-based models, and DINOv2, in diagnosing Cushing's syndrome. We also analyze gender bias and the impact of freezing mechanisms on DINOv2. Our results show that Transformer-based models and DINOv2 outperformed CNNs, with ViT achieving the highest F1 score of 85.74%. Both the pre-trained model and DINOv2 had higher accuracy for female samples. DINOv2 also showed improved performance when freezing parameters. In conclusion, Transformer-based models and DINOv2 are effective for Cushing's syndrome classification.
Authors: Aidan Duggan, Bruno Andrade, Haithem Afli
Abstract: Advancements in technology and reduction in it's cost have led to a substantial growth in the quality & quantity of imagery captured by Earth Observation (EO) satellites. This has presented a challenge to the efficacy of the traditional workflow of transmitting this imagery to Earth for processing. An approach to addressing this issue is to use pre-trained artificial intelligence models to process images on-board the satellite, but this is difficult given the constraints within a satellite's environment. This paper provides an up-to-date and thorough review of research related to image processing on-board Earth observation satellites. The significant constraints are detailed along with the latest strategies to mitigate them.
Authors: Chih Wei Ling, Youqi Wu, Jiande Sun, Cheuk Ting Li, Linqi Song, Weitao Xu
Abstract: Training machine learning models on decentralized private data via federated learning (FL) poses two key challenges: communication efficiency and privacy protection. In this work, we address these challenges within the trusted aggregator model by introducing a novel approach called the Communication-Efficient and Privacy-Adaptable Mechanism (CEPAM), achieving both objectives simultaneously. In particular, CEPAM leverages the rejection-sampled universal quantizer (RSUQ), a construction of randomized vector quantizer whose resulting distortion is equivalent to a prescribed noise, such as Gaussian or Laplace noise, enabling joint differential privacy and compression. Moreover, we analyze the trade-offs among user privacy, global utility, and transmission rate of CEPAM by defining appropriate metrics for FL with differential privacy and compression. Our CEPAM provides the additional benefit of privacy adaptability, allowing clients and the server to customize privacy protection based on required accuracy and protection. We assess CEPAM's utility performance using MNIST dataset, demonstrating that CEPAM surpasses baseline models in terms of learning accuracy.
Authors: Thejan Rajapakshe, Rajib Rana, Farina Riaz, Sara Khalifa, Bj\"orn W. Schuller
Abstract: Speech Emotion Recognition (SER) is a complex and challenging task in human-computer interaction due to the intricate dependencies of features and the overlapping nature of emotional expressions conveyed through speech. Although traditional deep learning methods have shown effectiveness, they often struggle to capture subtle emotional variations and overlapping states. This paper introduces a hybrid classical-quantum framework that integrates Parameterised Quantum Circuits (PQCs) with conventional Convolutional Neural Network (CNN) architectures. By leveraging quantum properties such as superposition and entanglement, the proposed model enhances feature representation and captures complex dependencies more effectively than classical methods. Experimental evaluations conducted on benchmark datasets, including IEMOCAP, RECOLA, and MSP-Improv, demonstrate that the hybrid model achieves higher accuracy in both binary and multi-class emotion classification while significantly reducing the number of trainable parameters. While a few existing studies have explored the feasibility of using Quantum Circuits to reduce model complexity, none have successfully shown how they can enhance accuracy. This study is the first to demonstrate that Quantum Circuits has the potential to improve the accuracy of SER. The findings highlight the promise of QML to transform SER, suggesting a promising direction for future research and practical applications in emotion-aware systems.
Authors: Somnath Hazra, Pallab Dasgupta, Soumyajit Dey
Abstract: Multi-Agent Reinforcement Learning (MARL) has gained significant traction for solving complex real-world tasks, but the inherent stochasticity and uncertainty in these environments pose substantial challenges to efficient and robust policy learning. While Distributional Reinforcement Learning has been successfully applied in single-agent settings to address risk and uncertainty, its application in MARL is substantially limited. In this work, we propose a novel approach that integrates distributional learning with a safety-focused loss function to improve convergence in cooperative MARL tasks. Specifically, we introduce a Barrier Function based loss that leverages safety metrics, identified from inherent faults in the system, into the policy learning process. This additional loss term helps mitigate risks and encourages safer exploration during the early stages of training. We evaluate our method in the StarCraft II micromanagement benchmark, where our approach demonstrates improved convergence and outperforms state-of-the-art baselines in terms of both safety and task completion. Our results suggest that incorporating safety considerations can significantly enhance learning performance in complex, multi-agent environments.
Authors: Hamid Nasiri, Peter Garraghan
Abstract: Parameter-efficient fine-tuning methods, such as LoRA, reduces the number of trainable parameters. However, they often suffer from scalability issues and differences between their learning pattern and full fine-tuning. To overcome these limitations, we propose Efficient Weight-Decomposed Low-Rank Adaptation (EDoRA): a novel PEFT method that decomposes pre-trained weights into magnitude and directional components. By freezing low-rank matrices, initializing them by singular value decomposition, and introducing a small trainable matrix between them, EDoRA achieves substantial reduction in trainable parameters while maintaining learning capacity. Experimental results on the GLUE benchmark demonstrate that EDoRA achieves competitive or superior performance compared to state-of-the-art methods, such as LoRA and DoRA, with up to 30x fewer trainable parameters. This makes EDoRA a highly efficient solution for adapting LLMs to diverse tasks under memory-constrained settings. Code is available at https://github.com/Hamid-Nasiri/EDoRA .
Authors: Keon Vin Park
Abstract: Optimizing portfolio performance is a fundamental challenge in financial modeling, requiring the integration of advanced clustering techniques and data-driven optimization strategies. This paper introduces a comparative backtesting approach that combines clustering-based portfolio segmentation and Sharpe ratio-based optimization to enhance investment decision-making. First, we segment a diverse set of financial assets into clusters based on their historical log-returns using K-Means clustering. This segmentation enables the grouping of assets with similar return characteristics, facilitating targeted portfolio construction. Next, for each cluster, we apply a Sharpe ratio-based optimization model to derive optimal weights that maximize risk-adjusted returns. Unlike traditional mean-variance optimization, this approach directly incorporates the trade-off between returns and volatility, resulting in a more balanced allocation of resources within each cluster. The proposed framework is evaluated through a backtesting study using historical data spanning multiple asset classes. Optimized portfolios for each cluster are constructed and their cumulative returns are compared over time against a traditional equal-weighted benchmark portfolio.
Authors: Richa Upadhyay, Ronald Phlypo, Rajkumar Saini, Marcus Liwicki
Abstract: This paper presents meta-sparsity, a framework for learning model sparsity, basically learning the parameter that controls the degree of sparsity, that allows deep neural networks (DNNs) to inherently generate optimal sparse shared structures in multi-task learning (MTL) setting. This proposed approach enables the dynamic learning of sparsity patterns across a variety of tasks, unlike traditional sparsity methods that rely heavily on manual hyperparameter tuning. Inspired by Model Agnostic Meta-Learning (MAML), the emphasis is on learning shared and optimally sparse parameters in multi-task scenarios by implementing a penalty-based, channel-wise structured sparsity during the meta-training phase. This method improves the model's efficacy by removing unnecessary parameters and enhances its ability to handle both seen and previously unseen tasks. The effectiveness of meta-sparsity is rigorously evaluated by extensive experiments on two datasets, NYU-v2 and CelebAMask-HQ, covering a broad spectrum of tasks ranging from pixel-level to image-level predictions. The results show that the proposed approach performs well across many tasks, indicating its potential as a versatile tool for creating efficient and adaptable sparse neural networks. This work, therefore, presents an approach towards learning sparsity, contributing to the efforts in the field of sparse neural networks and suggesting new directions for research towards parsimonious models.
Authors: Pedro Taranc\'on-\'Alvarez, Pablo Tejerina-P\'erez, Raul Jimenez, Pavlos Protopapas
Abstract: We present a machine learning framework to facilitate the solution of nonlinear multiscale differential equations and, especially, inverse problems using Physics-Informed Neural Networks (PINNs). This framework is based on what is called multihead (MH) training, which involves training the network to learn a general space of all solutions for a given set of equations with certain variability, rather than learning a specific solution of the system. This setup is used with a second novel technique that we call Unimodular Regularization (UR) of the latent space of solutions. We show that the multihead approach, combined with the regularization, significantly improves the efficiency of PINNs by facilitating the transfer learning process thereby enabling the finding of solutions for nonlinear, coupled, and multiscale differential equations.
Authors: KaiHui Huang, RunQing Wu, Fei Ye
Abstract: Continual learning has emerged as a pivotal area of research, primarily due to its advantageous characteristic that allows models to persistently acquire and retain information. However, catastrophic forgetting can severely impair model performance. In this study, we tackle the issue of network forgetting by introducing a novel framework termed Optimally-Weighted Maximum Mean Discrepancy (OWMMD), which imposes penalties on representation alterations via a Multi-Level Feature Matching Mechanism (MLFMM). Furthermore, we propose an Adaptive Regularization Optimization (ARO) strategy to refine the adaptive weight vectors, which autonomously assess the significance of each feature layer throughout the optimization process. We conduct a comprehensive series of experiments, benchmarking our proposed method against several established baselines. The empirical findings indicate that our approach achieves state-of-the-art performance.
Authors: Jia-Hao Syu, Jerry Chun-Wei Lin
Abstract: In this paper, we propose a heterogeneous federated learning (HFL) system for sparse time series prediction in healthcare, which is a decentralized federated learning algorithm with heterogeneous transfers. We design dense and sparse feature tensors to deal with the sparsity of data sources. Heterogeneous federated learning is developed to share asynchronous parts of networks and select appropriate models for knowledge transfer. Experimental results show that the proposed HFL achieves the lowest prediction error among all benchmark systems on eight out of ten prediction tasks, with MSE reduction of 94.8%, 48.3%, and 52.1% compared to the benchmark systems. These results demonstrate the effectiveness of HFL in transferring knowledge from heterogeneous domains, especially in the smaller target domain. Ablation studies then demonstrate the effectiveness of the designed mechanisms for heterogeneous domain selection and switching in predicting healthcare time series with privacy, model security, and heterogeneous knowledge transfer.
Authors: Jia-Hao Syu, Jerry Chun-Wei Lin, Philip S. Yu
Abstract: As more and more automatic vehicles, power consumption prediction becomes a vital issue for task scheduling and energy management. Most research focuses on automatic vehicles in transportation, but few focus on automatic ground vehicles (AGVs) in smart factories, which face complex environments and generate large amounts of data. There is an inevitable trade-off between feature diversity and interference. In this paper, we propose Distributed Multi-Head learning (DMH) systems for power consumption prediction in smart factories. Multi-head learning mechanisms are proposed in DMH to reduce noise interference and improve accuracy. Additionally, DMH systems are designed as distributed and split learning, reducing the client-to-server transmission cost, sharing knowledge without sharing local data and models, and enhancing the privacy and security levels. Experimental results show that the proposed DMH systems rank in the top-2 on most datasets and scenarios. DMH-E system reduces the error of the state-of-the-art systems by 14.5% to 24.0%. Effectiveness studies demonstrate the effectiveness of Pearson correlation-based feature engineering, and feature grouping with the proposed multi-head learning further enhances prediction performance.
Authors: Jia-Hao Syu, Jerry Chun-Wei Lin, Gautam Srivastava, Unil Yun
Abstract: Time-series prediction is increasingly popular in a variety of applications, such as smart factories and smart transportation. Researchers have used various techniques to predict power consumption, but existing models lack discussion of collaborative learning and privacy issues among multiple clients. To address these issues, we propose Multi-Head Heterogeneous Federated Learning (MHHFL) systems that consist of multiple head networks, which independently act as carriers for federated learning. In the federated period, each head network is embedded into 2-dimensional vectors and shared with the centralized source pool. MHHFL then selects appropriate source networks and blends the head networks as knowledge transfer in federated learning. The experimental results show that the proposed MHHFL systems significantly outperform the benchmark and state-of-the-art systems and reduce the prediction error by 24.9% to 94.1%. The ablation studies demonstrate the effectiveness of the proposed mechanisms in the MHHFL (head network embedding and selection mechanisms), which significantly outperforms traditional federated average and random transfer.
Authors: Zhuang Li
Abstract: The rapid proliferation of Large Language Models (LLMs) has raised concerns about misuse and the challenges of distinguishing AI-generated text from human-written content. Existing watermarking techniques, such as \kgw, still face limitations under low watermark strength, stringent false-positive requirements, and low-entropy scenarios. Our analysis reveals that current detection methods rely on coarse estimates of non-watermarked text, which constrains watermark detectability. We propose the Bipolar Watermark (BiMarker), a novel approach that divides generated text into positive and negative poles, leveraging the difference in green token counts for detection. This differential mechanism significantly enhances the detectability of watermarked text. Theoretical analysis and experimental results demonstrate BiMarker's effectiveness and compatibility with existing optimization techniques, offering a new optimization dimension for watermarking in LLM-generated content.
Authors: Michael W. Spratling, Heiko H. Sch\"utt
Abstract: Cross-entropy (CE) loss is the de-facto standard for training deep neural networks to perform classification. However, CE-trained deep neural networks struggle with robustness and generalisation issues. To alleviate these issues, we propose high error margin (HEM) loss, a variant of multi-class margin loss that overcomes the training issues of other margin-based losses. We evaluate HEM extensively on a range of architectures and datasets. We find that HEM loss is more effective than cross-entropy loss across a wide range of tasks: unknown class rejection, adversarial robustness, learning with imbalanced data, continual learning, and semantic segmentation (a pixel-level classification task). Despite all training hyper-parameters being chosen for CE loss, HEM is inferior to CE only in terms of clean accuracy and this difference is insignificant. We also compare HEM to specialised losses that have previously been proposed to improve performance on specific tasks. LogitNorm, a loss achieving state-of-the-art performance on unknown class rejection, produces similar performance to HEM for this task, but is much poorer for continual learning and semantic segmentation. Logit-adjusted loss, designed for imbalanced data, has superior results to HEM for that task, but performs more poorly on unknown class rejection and semantic segmentation. DICE, a popular loss for semantic segmentation, is inferior to HEM loss on all tasks, including semantic segmentation. Thus, HEM often out-performs specialised losses, and in contrast to them, is a general-purpose replacement for CE loss.
Authors: H\'ector Cadavid, Hyunho Mo, Bauke Arends, Katarzyna Dziopa, Esther E. Bron, Daniel Bos, Sonja Georgievska, Pim van der Harst
Abstract: Cardiovascular disease (CVD) remains a leading cause of death, and primary prevention through personalized interventions is crucial. This paper introduces MyDigiTwin, a framework that integrates health digital twins with personal health environments to empower patients in exploring personalized health scenarios while ensuring data privacy. MyDigiTwin uses federated learning to train predictive models across distributed datasets without transferring raw data, and a novel data harmonization framework addresses semantic and format inconsistencies in health data. A proof-of-concept demonstrates the feasibility of harmonizing and using cohort data to train privacy-preserving CVD prediction models. This framework offers a scalable solution for proactive, personalized cardiovascular care and sets the stage for future applications in real-world healthcare settings.
Authors: Tuo Zhang, Leonardo Stella, Julian Barreiro Gomez
Abstract: Despite its groundbreaking success, multi-agent reinforcement learning (MARL) still suffers from instability and nonstationarity. Replicator dynamics, the most well-known model from evolutionary game theory (EGT), provide a theoretical framework for the convergence of the trajectories to Nash equilibria and, as a result, have been used to ensure formal guarantees for MARL algorithms in stable game settings. However, they exhibit the opposite behavior in other settings, which poses the problem of finding alternatives to ensure convergence. In contrast, innovative dynamics, such as the Brown-von Neumann-Nash (BNN) or Smith, result in periodic trajectories with the potential to approximate Nash equilibria. Yet, no MARL algorithms based on these dynamics have been proposed. In response to this challenge, we develop a novel experience replay-based MARL algorithm that incorporates revision protocols as tunable hyperparameters. We demonstrate, by appropriately adjusting the revision protocols, that the behavior of our algorithm mirrors the trajectories resulting from these dynamics. Importantly, our contribution provides a framework capable of extending the theoretical guarantees of MARL algorithms beyond replicator dynamics. Finally, we corroborate our theoretical findings with empirical results.
Authors: Edward T. Reehorst, Philip Schniter
Abstract: In out-of-distribution (OOD) detection, one is asked to classify whether a test sample comes from a known inlier distribution or not. We focus on the case where the inlier distribution is defined by a training dataset and there exists no additional knowledge about the novelties that one is likely to encounter. This problem is also referred to as novelty detection, one-class classification, and unsupervised anomaly detection. The current literature suggests that contrastive learning techniques are state-of-the-art for OOD detection. We aim to improve on those techniques by combining/ensembling their scores using the framework of null hypothesis testing and, in particular, a novel generalized likelihood ratio test (GLRT). We demonstrate that our proposed GLRT-based technique outperforms the state-of-the-art CSI and SupCSI techniques from Tack et al. 2020 in dataset-vs-dataset experiments with CIFAR-10, SVHN, LSUN, ImageNet, and CIFAR-100, as well as leave-one-class-out experiments with CIFAR-10. We also demonstrate that our GLRT outperforms the score-combining methods of Fisher, Bonferroni, Simes, Benjamini-Hochwald, and Stouffer in our application.
Authors: Qianying Cao, Shanqing Liu, Alan John Varghese, Jerome Darbon, Michael Triantafyllou, George Em Karniadakis
Abstract: Time series forecasting plays a pivotal role in a wide range of applications, including weather prediction, healthcare, structural health monitoring, predictive maintenance, energy systems, and financial markets. While models such as LSTM, GRU, Transformers, and State-Space Models (SSMs) have become standard tools in this domain, selecting the optimal architecture remains a challenge. Performance comparisons often depend on evaluation metrics and the datasets under analysis, making the choice of a universally optimal model controversial. In this work, we introduce a flexible automated framework for time series forecasting that systematically designs and evaluates diverse network architectures by integrating LSTM, GRU, multi-head Attention, and SSM blocks. Using a multi-objective optimization approach, our framework determines the number, sequence, and combination of blocks to align with specific requirements and evaluation objectives. From the resulting Pareto-optimal architectures, the best model for a given context is selected via a user-defined preference function. We validate our framework across four distinct real-world applications. Results show that a single-layer GRU or LSTM is usually optimal when minimizing training time alone. However, when maximizing accuracy or balancing multiple objectives, the best architectures are often composite designs incorporating multiple block types in specific configurations. By employing a weighted preference function, users can resolve trade-offs between objectives, revealing novel, context-specific optimal architectures. Our findings underscore that no single neural architecture is universally optimal for time series forecasting. Instead, the best-performing model emerges as a data-driven composite architecture tailored to user-defined criteria and evaluation objectives.
Authors: Uri Gadot, Assaf Shocher, Shie Mannor, Gal Chechik, Assaf Hallak
Abstract: Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems performing tasks like object recognition or segmentation, rather than being watched by humans. It is therefore useful to optimize the encoder for a downstream task instead of for perceptual image quality. However, a major challenge is how to combine such downstream optimization with existing standard video encoders, which are highly efficient and popular. Here, we address this challenge by controlling the Quantization Parameters (QPs) at the macro-block level to optimize the downstream task. This granular control allows us to prioritize encoding for task-relevant regions within each frame. We formulate this optimization problem as a Reinforcement Learning (RL) task, where the agent learns to balance long-term implications of choosing QPs on both task performance and bit-rate constraints. Notably, our policy does not require the downstream task as an input during inference, making it suitable for streaming applications and edge devices such as vehicles. We demonstrate significant improvements in two tasks, car detection, and ROI (saliency) encoding. Our approach improves task performance for a given bit rate compared to traditional task agnostic encoding methods, paving the way for more efficient task-aware video compression.
Authors: Yuanheng Fang, Guoqing Chao, Wenqiang Lei, Shaobo Li, Dianhui Chu
Abstract: Large Language Models (LLMs) have recently achieved impressive results in complex reasoning tasks through Chain of Thought (CoT) prompting. However, most existing CoT methods rely on using the same prompts, whether manually designed or automatically generated, to handle the entire dataset. This one-size-fits-all approach may fail to meet the specific needs arising from the diversities within a single dataset. To solve this problem, we propose the Clustered Distance-Weighted Chain of Thought (CDW-CoT) method, which dynamically constructs prompts tailored to the characteristics of each data instance by integrating clustering and prompt optimization techniques. Our method employs clustering algorithms to categorize the dataset into distinct groups, from which a candidate pool of prompts is selected to reflect the inherent diversity within the dataset. For each cluster, CDW-CoT trains the optimal prompt probability distribution tailored to their specific characteristics. Finally, it dynamically constructs a unique prompt probability distribution for each test instance, based on its proximity to cluster centers, from which prompts are selected for reasoning. CDW-CoT consistently outperforms traditional CoT methods across six datasets, including commonsense, symbolic, and mathematical reasoning tasks. Specifically, when compared to manual CoT, CDW-CoT achieves an average accuracy improvement of 25.34% on LLaMA2 (13B) and 15.72% on LLaMA3 (8B).
Authors: Yizhou Liu, Ziming Liu, Jeff Gore
Abstract: Large language models (LLMs) demonstrate remarkable performance, and improving their pre-training process appears to be key to enhancing their capabilities further. Based on the documented success of Adam, learning rate decay, and weight decay, we hypothesize that the pre-training loss landscape features a narrowing valley structure. Through experiments with synthetic loss functions, we discover that when gradient query noise is high relative to the valley's sharpness, Adam's performance falls behind that of Signum because Adam reduces the effective step size too drastically. This observation led us to develop FOCUS, an optimizer that enhances Signum by incorporating attraction toward moving averaged parameters, allowing it to handle noise better while maintaining larger step sizes. In training GPT-2, FOCUS proves to be more stable than Signum and faster than Adam. These results suggest that gradient noise may be an underappreciated limiting factor in LLM training, and FOCUS offers promising solutions.
Authors: Qishen Zhou, Yifan Zhang, Michail A. Makridis, Anastasios Kouvelas, Yibing Wang, Simon Hu
Abstract: Given a partially observed road network, how can we predict the traffic state of unobserved locations? While deep learning approaches show exceptional performance in traffic prediction, most assume sensors at all locations of interest, which is impractical due to financial constraints. Furthermore, these methods typically require costly retraining when sensor configurations change. We propose MoGERNN, an inductive spatio-temporal graph representation model, to address these challenges. Inspired by the Mixture of Experts approach in Large Language Models, we introduce a Mixture of Graph Expert (MoGE) block to model complex spatial dependencies through multiple graph message aggregators and a sparse gating network. This block estimates initial states for unobserved locations, which are then processed by a GRU-based Encoder-Decoder that integrates a graph message aggregator to capture spatio-temporal dependencies and predict future states. Experiments on two real-world datasets show MoGERNN consistently outperforms baseline methods for both observed and unobserved locations. MoGERNN can accurately predict congestion evolution even in areas without sensors, offering valuable information for traffic management. Moreover, MoGERNN is adaptable to dynamic sensing networks, maintaining competitive performance even compared to its retrained counterpart. Tests with different numbers of available sensors confirm its consistent superiority, and ablation studies validate the effectiveness of its key modules.
Authors: Xia Li, Hanghang Zheng, Kunpeng Tao, Mao Mao
Abstract: Credit scoring is a systematic approach to evaluate a borrower's probability of default (PD) on a bank loan. The data associated with such scenarios are characteristically imbalanced, complicating binary classification owing to the often-underestimated cost of misclassification during the classifier's learning process. Considering the high imbalance ratio (IR) of these datasets, we introduce an innovative yet straightforward optimized activation function by incorporating an IR-dependent asymmetric adjusted factor embedded Sigmoid activation function (ASIG). The embedding of ASIG makes the sensitive margin of the Sigmoid function auto-adjustable, depending on the imbalance nature of the datasets distributed, thereby giving the activation function an asymmetric characteristic that prevents the underrepresentation of the minority class (positive samples) during the classifier's learning process. The experimental results show that the ASIG-embedded-classifier outperforms traditional classifiers on datasets across wide-ranging IRs in the downstream credit-scoring task. The algorithm also shows robustness and stability, even when the IR is ultra-high. Therefore, the algorithm provides a competitive alternative in the financial industry, especially in credit scoring, possessing the ability to effectively process highly imbalanced distribution data.
Authors: Eugenio Borzone, Leandro Di Persia, Matias Gerard
Abstract: This paper presents a novel graph-based deep learning model for tasks involving relations between two nodes (edge-centric tasks), where the focus lies on predicting relationships and interactions between pairs of nodes rather than node properties themselves. This model combines supervised and self-supervised learning, taking into account for the loss function the embeddings learned and patterns with and without ground truth. Additionally it incorporates an attention mechanism that leverages both node and edge features. The architecture, trained end-to-end, comprises two primary components: embedding generation and prediction. First, a graph neural network (GNN) transform raw node features into dense, low-dimensional embeddings, incorporating edge attributes. Then, a feedforward neural model processes the node embeddings to produce the final output. Experiments demonstrate that our model matches or exceeds existing methods for protein-protein interactions prediction and Gene Ontology (GO) terms prediction. The model also performs effectively with one-hot encoding for node features, providing a solution for the previously unsolved problem of predicting similarity between compounds with unknown structures.
Authors: Nurbek Tastan, Samuel Horvath, Karthik Nandakumar
Abstract: Collaborative learning (CL) enables multiple participants to jointly train machine learning (ML) models on decentralized data sources without raw data sharing. While the primary goal of CL is to maximize the expected accuracy gain for each participant, it is also important to ensure that the gains are fairly distributed. Specifically, no client should be negatively impacted by the collaboration, and the individual gains must ideally be commensurate with the contributions. Most existing CL algorithms require central coordination and focus on the gain maximization objective while ignoring collaborative fairness. In this work, we first show that the existing measure of collaborative fairness based on the correlation between accuracy values without and with collaboration has drawbacks because it does not account for negative collaboration gain. We argue that maximizing mean collaboration gain (MCG) while simultaneously minimizing the collaboration gain spread (CGS) is a fairer alternative. Next, we propose the CYCle protocol that enables individual participants in a private decentralized learning (PDL) framework to achieve this objective through a novel reputation scoring method based on gradient alignment between the local cross-entropy and distillation losses. Experiments on the CIFAR-10, CIFAR-100, and Fed-ISIC2019 datasets empirically demonstrate the effectiveness of the CYCle protocol to ensure positive and fair collaboration gain for all participants, even in cases where the data distributions of participants are highly skewed. For the simple mean estimation problem with two participants, we also theoretically show that CYCle performs better than standard FedAvg, especially when there is large statistical heterogeneity.
Authors: Ke Alexander Wang, Jiaxin Shi, Emily B. Fox
Abstract: Sequences provide a remarkably general way to represent and process information. This powerful abstraction has placed sequence modeling at the center of modern deep learning applications, inspiring numerous architectures from transformers to recurrent networks. While this fragmented development has yielded powerful models, it has left us without a unified framework to understand their fundamental similarities and explain their effectiveness. We present a unifying framework motivated by an empirical observation: effective sequence models must be able to perform associative recall. Our key insight is that memorizing input tokens through an associative memory is equivalent to performing regression at test-time. This regression-memory correspondence provides a framework for deriving sequence models that can perform associative recall, offering a systematic lens to understand seemingly ad-hoc architectural choices. We show numerous recent architectures -- including linear attention models, their gated variants, state-space models, online learners, and softmax attention -- emerge naturally as specific approaches to test-time regression. Each architecture corresponds to three design choices: the relative importance of each association, the regressor function class, and the optimization algorithm. This connection leads to new understanding: we provide theoretical justification for QKNorm in softmax attention, and we motivate higher-order generalizations of softmax attention. Beyond unification, our work unlocks decades of rich statistical tools that can guide future development of more powerful yet principled sequence models.
Authors: Filipe Rodrigues
Abstract: Inferring the true demand for a product or a service from aggregate data is often challenging due to the limited available supply, thus resulting in observations that are censored and correspond to the realized demand, thereby not accounting for the unsatisfied demand. Censored regression models are able to account for the effect of censoring due to the limited supply, but they don't consider the effect of substitutions, which may cause the demand for similar alternative products or services to increase. This paper proposes Diffusion-aware Censored Demand Models, which combine a Tobit likelihood with a graph diffusion process in order to model the latent process of transfer of unsatisfied demand between similar products or services. We instantiate this new class of models under the framework of GPs and, based on both simulated and real-world data for modeling sales, bike-sharing demand, and EV charging demand, demonstrate its ability to better recover the true demand and produce more accurate out-of-sample predictions.
Authors: Carla Goncalves, Ricardo J. Bessa, Tiago Teixeira, Joao Vinagre
Abstract: Accurate power forecasting from renewable energy sources (RES) is crucial for integrating additional RES capacity into the power system and realizing sustainability goals. This work emphasizes the importance of integrating decentralized spatio-temporal data into forecasting models. However, decentralized data ownership presents a critical obstacle to the success of such spatio-temporal models, and incentive mechanisms to foster data-sharing need to be considered. The main contributions are a) a comparative analysis of the forecasting models, advocating for efficient and interpretable spline LASSO regression models, and b) a bidding mechanism within the data/analytics market to ensure fair compensation for data providers and enable both buyers and sellers to express their data price requirements. Furthermore, an incentive mechanism for time series forecasting is proposed, effectively incorporating price constraints and preventing redundant feature allocation. Results show significant accuracy improvements and potential monetary gains for data sellers. For wind power data, an average root mean squared error improvement of over 10% was achieved by comparing forecasts generated by the proposal with locally generated ones.
Authors: Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin Mohamed Elnouby Ali, Josh Susskind, Vimal Thilak
Abstract: Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily defined by two dimensions: the number of model parameters and the compute per example. While scaling typically involves increasing both, the precise interplay between these factors and their combined contribution to overall capacity remains not fully understood. We explore this relationship in the context of sparse Mixture-of-Expert models (MoEs), which allow scaling the number of parameters without proportionally increasing the FLOPs per example. We investigate how varying the sparsity level, i.e., the ratio of non-active to total parameters, affects model performance in terms of both pretraining and downstream performance. We find that under different constraints (e.g. parameter size and total training compute), there is an optimal level of sparsity that improves both training efficiency and model performance. These results provide a better understanding of the impact of sparsity in scaling laws for MoEs and complement existing works in this area, offering insights for designing more efficient architectures.
Authors: Ziming Liu, Yizhou Liu, Eric J. Michaud, Jeff Gore, Max Tegmark
Abstract: We aim to understand physics of skill learning, i.e., how skills are learned in neural networks during training. We start by observing the Domino effect, i.e., skills are learned sequentially, and notably, some skills kick off learning right after others complete learning, similar to the sequential fall of domino cards. To understand the Domino effect and relevant behaviors of skill learning, we take physicists' approach of abstraction and simplification. We propose three models with varying complexities -- the Geometry model, the Resource model, and the Domino model, trading between reality and simplicity. The Domino effect can be reproduced in the Geometry model, whose resource interpretation inspires the Resource model, which can be further simplified to the Domino model. These models present different levels of abstraction and simplification; each is useful to study some aspects of skill learning. The Geometry model provides interesting insights into neural scaling laws and optimizers; the Resource model sheds light on the learning dynamics of compositional tasks; the Domino model reveals the benefits of modularity. These models are not only conceptually interesting -- e.g., we show how Chinchilla scaling laws can emerge from the Geometry model, but also are useful in practice by inspiring algorithmic development -- e.g., we show how simple algorithmic changes, motivated by these toy models, can speed up the training of deep learning models.
Authors: Jaskirat Singh, Bram Adams, Ahmed E. Hassan
Abstract: Deciding what combination of operators to use across the Edge AI tiers to achieve specific latency and model performance requirements is an open question for MLOps engineers. This study aims to empirically assess the accuracy vs inference time trade-off of different black-box Edge AI deployment strategies, i.e., combinations of deployment operators and deployment tiers. In this paper, we conduct inference experiments involving 3 deployment operators (i.e., Partitioning, Quantization, Early Exit), 3 deployment tiers (i.e., Mobile, Edge, Cloud) and their combinations on four widely used Computer-Vision models to investigate the optimal strategies from the point of view of MLOps developers. Our findings suggest that Edge deployment using the hybrid Quantization + Early Exit operator could be preferred over non-hybrid operators (Quantization/Early Exit on Edge, Partition on Mobile-Edge) when faster latency is a concern at medium accuracy loss. However, when minimizing accuracy loss is a concern, MLOps engineers should prefer using only a Quantization operator on edge at a latency reduction or increase, respectively over the Early Exit/Partition (on edge/mobile-edge) and Quantized Early Exit (on edge) operators. In scenarios constrained by Mobile CPU/RAM resources, a preference for Partitioning across mobile and edge tiers is observed over mobile deployment. For models with smaller input data samples (such as FCN), a network-constrained cloud deployment can also be a better alternative than Mobile/Edge deployment and Partitioning strategies. For models with large input data samples (ResNet, ResNext, DUC), an edge tier having higher network/computational capabilities than Cloud/Mobile can be a more viable option than Partitioning and Mobile/Cloud deployment strategies.
Authors: Vasileios Alevizos, Sabrina Edralin, Akebu Simasiku, Dimitra Malliarou, Antonis Messinis, George Papakostas, Clark Xu, Zongliang Yue
Abstract: Dyslexia and dysgraphia are learning disabilities that profoundly impact reading, writing, and language processing capabilities. Dyslexia primarily affects reading, manifesting as difficulties in word recognition and phonological processing, where individuals struggle to connect sounds with their corresponding letters. Dysgraphia, on the other hand, affects writing skills, resulting in difficulties with letter formation, spacing, and alignment. The coexistence of dyslexia and dysgraphia complicates diagnosis, requiring a nuanced approach capable of adapting to these complexities while accurately identifying and differentiating between the disorders. This study utilizes advanced geometrical patterns and recurrent neural networks (RNN) to identify handwriting anomalies indicative of dyslexia and dysgraphia. Handwriting is first standardized, followed by feature extraction that focuses on baseline deviations, letter connectivity, stroke thickness, and other anomalies. These features are then fed into an RNN-based autoencoder to identify irregularities. Initial results demonstrate the ability of this RNN model to achieve state-of-art performance on combined dyslexia and dysgraphia detection, while showing the challenges associated with complex pattern adaptation of deep-learning to a diverse corpus of about 33,000 writing samples.
Authors: Giorgia Carra, Bogdan Kulynych, Fran\c{c}ois Bastardot, Daniel E. Kaufmann, No\'emie Boillat-Blanco, Jean Louis Raisaro
Abstract: Although Large Language Models (LLMs) have shown promising performance in healthcare-related applications, their deployment in the medical domain poses unique challenges of ethical, regulatory, and technical nature. In this study, we employ a systematic participatory approach to investigate the needs and expectations regarding clinical applications of LLMs at Lausanne University Hospital, an academic medical center in Switzerland. Having identified potential LLM use-cases in collaboration with thirty stakeholders, including clinical staff across 11 departments as well nursing and patient representatives, we assess the current feasibility of these use-cases taking into account the regulatory frameworks, data protection regulation, bias, hallucinations, and deployment constraints. This study provides a framework for a participatory approach to identifying institutional needs with respect to introducing advanced technologies into healthcare practice, and a realistic analysis of the technology readiness level of LLMs for medical applications, highlighting the issues that would need to be overcome LLMs in healthcare to be ethical, and regulatory compliant.
Authors: Tom Holberton
Abstract: This article evaluates how creative uses of machine learning can address three adjacent terms: ambiguity, uncertainty and indeterminacy. Through the progression of these concepts it reflects on increasing ambitions for machine learning as a creative partner, illustrated with research from Unit 21 at the Bartlett School of Architecture, UCL. Through indeterminacy are potential future approaches to machine learning and design.
Authors: Hari Mohan Pandey
Abstract: Large Language Models (LLMs) are transforming mental health care by enhancing accessibility, personalization, and efficiency in therapeutic interventions. These AI-driven tools empower mental health professionals with real-time support, improved data integration, and the ability to encourage care-seeking behaviors, particularly in underserved communities. By harnessing LLMs, practitioners can deliver more empathetic, tailored, and effective support, addressing longstanding gaps in mental health service provision. However, their implementation comes with significant challenges and ethical concerns. Performance limitations, data privacy risks, biased outputs, and the potential for generating misleading information underscore the critical need for stringent ethical guidelines and robust evaluation mechanisms. The sensitive nature of mental health data further necessitates meticulous safeguards to protect patient rights and ensure equitable access to AI-driven care. Proponents argue that LLMs have the potential to democratize mental health resources, while critics warn of risks such as misuse and the diminishment of human connection in therapy. Achieving a balance between innovation and ethical responsibility is imperative. This paper examines the transformative potential of LLMs in mental health care, highlights the associated technical and ethical complexities, and advocates for a collaborative, multidisciplinary approach to ensure these advancements align with the goal of providing compassionate, equitable, and effective mental health support.
Authors: Yujie Zhang, Shivam Aggarwal, Tulika Mitra
Abstract: Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory-constrained devices. While GPUs offer fast inference, their limited memory compared to CPUs means not all experts can be stored on the GPU simultaneously, necessitating frequent, costly data transfers from CPU memory, often negating GPU speed advantages. To address this, we present DAOP, an on-device MoE inference engine to optimize parallel GPU-CPU execution. DAOP dynamically allocates experts between CPU and GPU based on per-sequence activation patterns, and selectively pre-calculates predicted experts on CPUs to minimize transfer latency. This approach enables efficient resource utilization across various expert cache ratios while maintaining model accuracy through a novel graceful degradation mechanism. Comprehensive evaluations across various datasets show that DAOP outperforms traditional expert caching and prefetching methods by up to 8.20x and offloading techniques by 1.35x while maintaining accuracy.
Authors: Waleed El-Geresy, Christos Papavassiliou, Deniz G\"und\"uz
Abstract: In this paper, we examine the problem of information storage on memristors affected by resistive drift noise under energy constraints. We introduce a novel, fundamental trade-off between the information lifetime of memristive states and the energy that must be expended to bring the device into a particular state. We then treat the storage problem as one of communication over a noisy, energy-constrained channel, and propose a joint source-channel coding (JSCC) approach to storing images in an analogue fashion. To design an encoding scheme for natural images and to model the memristive channel, we make use of data-driven techniques from the field of deep learning for communications, namely deep joint source-channel coding (DeepJSCC), employing a generative model of resistive drift as a computationally tractable differentiable channel model for end-to-end optimisation. We introduce a modified version of generalised divisive normalisation (GDN), a biologically inspired form of normalisation, that we call conditional GDN (cGDN), allowing for conditioning on continuous channel characteristics, including the initial resistive state and the delay between storage and reading. Our results show that the delay-conditioned network is able to learn an energy-aware coding scheme that achieves a higher and more balanced reconstruction quality across a range of storage delays.
Authors: Jiawei Zhang
Abstract: This research applies Harold Demsetz's concept of the nirvana approach to the realm of AI governance and debunks three common fallacies in various AI policy proposals--"the grass is always greener on the other side," "free lunch," and "the people could be different." Through this, I expose fundamental flaws in the current AI regulatory proposal. First, some commentators intuitively believe that people are more reliable than machines and that government works better in risk control than companies' self-regulation, but they do not fully compare the differences between the status quo and the proposed replacements. Second, when proposing some regulatory tools, some policymakers and researchers do not realize and even gloss over the fact that harms and costs are also inherent in their proposals. Third, some policy proposals are initiated based on a false comparison between the AI-driven world, where AI does lead to some risks, and an entirely idealized world, where no risk exists at all. However, the appropriate approach is to compare the world where AI causes risks to the real world where risks are everywhere, but people can live well with these risks. The prevalence of these fallacies in AI governance underscores a broader issue: the tendency to idealize potential solutions without fully considering their real-world implications. This idealization can lead to regulatory proposals that are not only impractical but potentially harmful to innovation and societal progress.
Authors: Jonathon Hirschi
Abstract: Fuel moisture content (FMC) is a key predictor for wildfire rate of spread (ROS). Machine learning models of FMC are being used more in recent years, augmenting or replacing traditional physics-based approaches. Wildfire rate of spread (ROS) has a highly nonlinear relationship with FMC, where small differences in dry fuels lead to large differences in ROS. In this study, custom loss functions that place more weight on dry fuels were examined with a variety of machine learning models of FMC. The models were evaluated with a spatiotemporal cross-validation procedure to examine whether the custom loss functions led to more accurate forecasts of ROS. Results show that the custom loss functions improved accuracy for ROS forecasts by a small amount. Further research would be needed to establish whether the improvement in ROS forecasts leads to more accurate real-time wildfire simulations.
Authors: Hanyang Dong, Shurong Sheng, Xiongfei Wang, Jiahong Gao, Yi Sun, Wanli Yang, Kuntao Xiao, Pengfei Teng, Guoming Luan, Zhao Lv
Abstract: A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal's intensity reflecting magnetic field changes over time at the sensor location. Automating epileptic MEG spike detection significantly reduces manual assessment time and effort, yielding substantial clinical benefits. Existing research addresses MEG spike detection by encoding neural network inputs with signals from all channel within a time segment, followed by classification. However, these methods overlook simultaneous spiking occurred from nearby sensors. We introduce a simple yet effective paradigm that first clusters MEG channels based on their sensor's spatial position. Next, a novel convolutional input module is designed to integrate the spatial clustering and temporal changes of the signals. This module is fed into a custom MEEG-ResNet3D developed by the authors, which learns to extract relevant features and classify the input as a spike clip or not. Our method achieves an F1 score of 94.73% on a large real-world MEG dataset Sanbo-CMR collected from two centers, outperforming state-of-the-art approaches by 1.85%. Moreover, it demonstrates efficacy and stability in the Electroencephalographic (EEG) seizure detection task, yielding an improved weighted F1 score of 1.4% compared to current state-of-the-art techniques evaluated on TUSZ, whch is the largest EEG seizure dataset.
Authors: Petr Knoth (CORE, Knowledge Media institute, The Open University), Laurent Romary (Inria), Patrice Lopez (Science Miner), Roberto Di Cosmo (Inria), Pavel Smrz (Brno University of Technology), Tomasz Umerle (Polish Academy of Sciences), Melissa Harrison (European Bioinformatics Institute), Alain Monteil (Inria), Matteo Cancellieri (Knowledge Media institute, The Open University), David Pride (CORE, Knowledge Media institute, The Open University)
Abstract: A key issue hindering discoverability, attribution and reusability of open research software is that its existence often remains hidden within the manuscript of research papers. For these resources to become first-class bibliographic records, they first need to be identified and subsequently registered with persistent identifiers (PIDs) to be made FAIR (Findable, Accessible, Interoperable and Reusable). To this day, much open research software fails to meet FAIR principles and software resources are mostly not explicitly linked from the manuscripts that introduced them or used them. SoFAIR is a 2-year international project (2024-2025) which proposes a solution to the above problem realised over the content available through the global network of open repositories. SoFAIR will extend the capabilities of widely used open scholarly infrastructures (CORE, Software Heritage, HAL) and tools (GROBID) operated by the consortium partners, delivering and deploying an effective solution for the management of the research software lifecycle, including: 1) ML-assisted identification of research software assets from within the manuscripts of scholarly papers, 2) validation of the identified assets by authors, 3) registration of software assets with PIDs and their archival.
Authors: Davide Cacciarelli, Pierre Pinson, Filip Panagiotopoulos, David Dixon, Lizzie Blaxland
Abstract: The energy transition is profoundly reshaping electricity market dynamics. It makes it essential to understand how renewable energy generation actually impacts electricity prices, among all other market drivers. These insights are critical to design policies and market interventions that ensure affordable, reliable, and sustainable energy systems. However, identifying causal effects from observational data is a major challenge, requiring innovative causal inference approaches that go beyond conventional regression analysis only. We build upon the state of the art by developing and applying a local partially linear double machine learning approach. Its application yields the first robust causal evidence on the distinct and non-linear effects of wind and solar power generation on UK wholesale electricity prices, revealing key insights that have eluded previous analyses. We find that, over 2018-2024, wind power generation has a U-shaped effect on prices: at low penetration levels, a 1 GWh increase in energy generation reduces prices by up to 7 GBP/MWh, but this effect gets close to none at mid-penetration levels (20-30%) before intensifying again. Solar power places substantial downward pressure on prices at very low penetration levels (up to 9 GBP/MWh per 1 GWh increase in energy generation), though its impact weakens quite rapidly. We also uncover a critical trend where the price-reducing effects of both wind and solar power have become more pronounced over time (from 2018 to 2024), highlighting their growing influence on electricity markets amid rising penetration. Our study provides both novel analysis approaches and actionable insights to guide policymakers in appraising the way renewables impact electricity markets.
Authors: Alban Gattepaille (I3S), Alexandre Muzy (I3S, ILLS)
Abstract: In Deep Neural Networks (DNN) and Spiking Neural Networks (SNN), the information of a neuron is computed based on the sum of the amplitudes (weights) of the electrical potentials received in input from other neurons. We propose here a new class of neural networks, namely Delay Neural Networks (DeNN), where the information of a neuron is computed based on the sum of its input synaptic delays and on the spike times of the electrical potentials received from other neurons. This way, DeNN are designed to explicitly use exact continuous temporal information of spikes in both forward and backward passes, without approximation. (Deep) DeNN are applied here to images and event-based (audio and visual) data sets. Good performances are obtained, especially for datasets where temporal information is important, with much less parameters and less energy than other models.
Authors: BG Tong
Abstract: Objective: This study explores a novel deep learning approach for EEG analysis and perceptual state guidance, inspired by Level of Detail (LOD) theory. The goal is to improve perceptual state identification accuracy and advance personalized psychological therapy. Methods: Portable EEG devices and music rhythm signals were used for data collection. LOD theory was applied to dynamically adjust EEG signal processing, extracting core perceptual features. A Unity-based software system integrated EEG data with audio materials. The deep learning model combined a CNN for feature extraction and classification, and a DQN for reinforcement learning to optimize rhythm adjustments. Results: The CNN achieved 94.05% accuracy in perceptual state classification. The DQN guided subjects to target states with a 92.45% success rate, averaging 13.2 rhythm cycles. However, only 50% of users reported psychological alignment with the target state, indicating room for improvement. Discussion: The results validate the potential of LOD-based EEG biofeedback. Limitations include dataset source, label subjectivity, and reward function optimization. Future work will expand to diverse subjects, incorporate varied musical elements, and refine reward functions for better generalization and personalization.
Authors: Ian Tomeo (Rochester Institute of Technology), Panos P. Markopoulos (The University of Texas at San Antonio), Andreas Savakis (Rochester Institute of Technology)
Abstract: Principal component analysis is commonly used for dimensionality reduction, feature extraction, denoising, and visualization. The most commonly used principal component analysis method is based upon optimization of the L2-norm, however, the L2-norm is known to exaggerate the contribution of errors and outliers. When optimizing over the L1-norm, the components generated are known to exhibit robustness or resistance to outliers in the data. The L1-norm components can be solved for with a binary optimization problem. Previously, L1-BF has been used to solve the binary optimization for multiple components simultaneously. In this paper we propose QAPCA, a new method for finding principal components using quantum annealing hardware which will optimize over the robust L1-norm. The conditions required for convergence of the annealing problem are discussed. The potential speedup when using quantum annealing is demonstrated through complexity analysis and experimental results. To showcase performance against classical principal component analysis techniques experiments upon synthetic Gaussian data, a fault detection scenario and breast cancer diagnostic data are studied. We find that the reconstruction error when using QAPCA is comparable to that when using L1-BF.
Authors: Bocheng Zhang
Abstract: This study investigates the performance of median-of-means sampling compared to traditional mean-of-means sampling for computing the Keister function integral using Randomized Quasi-Monte Carlo (RQMC) methods. The research tests both lattice points and digital nets as point distributions across dimensions 2, 3, 5, and 8, with sample sizes ranging from 2^8 to 2^19 points. Results demonstrate that median-of-means sampling consistently outperforms mean-of-means for sample sizes larger than 10^3 points, while mean-of-means shows better accuracy with smaller sample sizes, particularly for digital nets. The study also confirms previous theoretical predictions about median-of-means' superior performance with larger sample sizes and reflects the known challenges of maintaining accuracy in higher-dimensional integration. These findings support recent research suggesting median-of-means as a promising alternative to traditional sampling methods in numerical integration, though limitations in sample size and dimensionality warrant further investigation with different test functions and larger parameter spaces.
Authors: Xiaolu Hou, Mingcheng Li, Dingkang Yang, Jiawei Chen, Ziyun Qian, Xiao Zhao, Yue Jiang, Jinjie Wei, Qingyao Xu, Lihua Zhang
Abstract: With the widespread use of virtual reality applications, 3D scene generation has become a new challenging research frontier. 3D scenes have highly complex structures and need to ensure that the output is dense, coherent, and contains all necessary structures. Many current 3D scene generation methods rely on pre-trained text-to-image diffusion models and monocular depth estimators. However, the generated scenes occupy large amounts of storage space and often lack effective regularisation methods, leading to geometric distortions. To this end, we propose BloomScene, a lightweight structured 3D Gaussian splatting for crossmodal scene generation, which creates diverse and high-quality 3D scenes from text or image inputs. Specifically, a crossmodal progressive scene generation framework is proposed to generate coherent scenes utilizing incremental point cloud reconstruction and 3D Gaussian splatting. Additionally, we propose a hierarchical depth prior-based regularization mechanism that utilizes multi-level constraints on depth accuracy and smoothness to enhance the realism and continuity of the generated scenes. Ultimately, we propose a structured context-guided compression mechanism that exploits structured hash grids to model the context of unorganized anchor attributes, which significantly eliminates structural redundancy and reduces storage overhead. Comprehensive experiments across multiple scenes demonstrate the significant potential and advantages of our framework compared with several baselines.
Authors: Katherine M. Collins, Umang Bhatt, Ilia Sucholutsky
Abstract: Humans learn about the world, and how to act in the world, in many ways: from individually conducting experiments to observing and reproducing others' behavior. Different learning strategies come with different costs and likelihoods of successfully learning more about the world. The choice that any one individual makes of how to learn can have an impact on the collective understanding of a whole population if people learn from each other. Alan Rogers developed simulations of a population of agents to study these network phenomena where agents could individually or socially learn amidst a dynamic, uncertain world and uncovered a confusing result: the availability of cheap social learning yielded no benefit to population fitness over individual learning. This paradox spawned decades of work trying to understand and uncover factors that foster the relative benefit of social learning that centuries of human behavior suggest exists. What happens in such network models now that humans can socially learn from AI systems that are themselves socially learning from us? We revisit Rogers' Paradox in the context of human-AI interaction to probe a simplified network of humans and AI systems learning together about an uncertain world. We propose and examine the impact of several learning strategies on the quality of the equilibrium of a society's 'collective world model'. We consider strategies that can be undertaken by various stakeholders involved in a single human-AI interaction: human, AI model builder, and society or regulators around the interaction. We then consider possible negative feedback loops that may arise from humans learning socially from AI: that learning from the AI may impact our own ability to learn about the world. We close with open directions into studying networks of human and AI systems that can be explored in enriched versions of our simulation framework.
Authors: Maciej Romaniuk, Abbas Parchami, Przemys{\l}aw Grzegorzewski
Abstract: Random fuzzy variables join the modeling of the impreciseness (due to their ``fuzzy part'') and randomness. Statistical samples of such objects are widely used, and their direct, numerically effective generation is therefore necessary. Usually, these samples consist of triangular or trapezoidal fuzzy numbers. In this paper, we describe theoretical results and simulation algorithms for another family of fuzzy numbers -- LR fuzzy numbers with interval-valued cores. Starting from a simulation perspective on the piecewise linear LR fuzzy numbers with the interval-valued cores, their limiting behavior is then considered. This leads us to the numerically efficient algorithm for simulating a sample consisting of such fuzzy values.
Authors: Hibiki Iwanaga, Mahoro Matsuyama, Yousuke Itoh
Abstract: We introduce a technique to enhance the reliability of gravitational wave parameter estimation results produced by machine learning. We develop two independent machine learning models based on the Vision Transformer to estimate effective spin and chirp mass from spectrograms of gravitational wave signals from binary black hole mergers. To enhance the reliability of these models, we utilize attention maps to visualize the areas our models focus on when making predictions. This approach enables demonstrating that both models perform parameter estimation based on physically meaningful information. Furthermore, by leveraging these attention maps, we demonstrate a method to quantify the impact of glitches on parameter estimation. We show that as the models focus more on glitches, the parameter estimation results become more strongly biased. This suggests that attention maps could potentially be used to distinguish between cases where the results produced by the machine learning model are reliable and cases where they are not.
Authors: R\^omulo Damasclin Chaves dos Santos, Jorge Henrique de Oliveira Sales
Abstract: We propose a novel extension to symmetrized neural network operators by incorporating fractional and mixed activation functions. This study addresses the limitations of existing models in approximating higher-order smooth functions, particularly in complex and high-dimensional spaces. Our framework introduces a fractional exponent in the activation functions, allowing adaptive non-linear approximations with improved accuracy. We define new density functions based on $q$-deformed and $\theta$-parametrized logistic models and derive advanced Jackson-type inequalities that establish uniform convergence rates. Additionally, we provide a rigorous mathematical foundation for the proposed operators, supported by numerical validations demonstrating their efficiency in handling oscillatory and fractional components. The results extend the applicability of neural network approximation theory to broader functional spaces, paving the way for applications in solving partial differential equations and modeling complex systems.
Authors: Iosif Tsangko, Andreas Triantafyllopoulos, Michael M\"uller, Hendrik Schr\"oter, Bj\"orn W. Schuller
Abstract: The \textbf{DeepFilterNet} (\textbf{DFN}) architecture was recently proposed as a deep learning model suited for hearing aid devices. Despite its competitive performance on numerous benchmarks, it still follows a `one-size-fits-all' approach, which aims to train a single, monolithic architecture that generalises across different noises and environments. However, its limited size and computation budget can hamper its generalisability. Recent work has shown that in-context adaptation can improve performance by conditioning the denoising process on additional information extracted from background recordings to mitigate this. These recordings can be offloaded outside the hearing aid, thus improving performance while adding minimal computational overhead. We introduce these principles to the \textbf{DFN} model, thus proposing the \textbf{DFingerNet} (\textbf{DFiN}) model, which shows superior performance on various benchmarks inspired by the DNS Challenge.
Authors: Bradley H. Theilman, James B. Aimone
Abstract: We demonstrate that scalable neuromorphic hardware can implement the finite element method, which is a critical numerical method for engineering and scientific discovery. Our approach maps the sparse interactions between neighboring finite elements to small populations of neurons that dynamically update according to the governing physics of a desired problem description. We show that for the Poisson equation, which describes many physical systems such as gravitational and electrostatic fields, this cortical-inspired neural circuit can achieve comparable levels of numerical accuracy and scaling while enabling the use of inherently parallel and energy-efficient neuromorphic hardware. We demonstrate that this approach can be used on the Intel Loihi 2 platform and illustrate how this approach can be extended to nontrivial mesh geometries and dynamics.
Authors: Victor Dheur, Matteo Fontana, Yorick Estievenart, Naomi Desobry, Souhaib Ben Taieb
Abstract: Quantifying uncertainty in multivariate regression is essential in many real-world applications, yet existing methods for constructing prediction regions often face limitations such as the inability to capture complex dependencies, lack of coverage guarantees, or high computational cost. Conformal prediction provides a robust framework for producing distribution-free prediction regions with finite-sample coverage guarantees. In this work, we present a unified comparative study of multi-output conformal methods, exploring their properties and interconnections. Based on our findings, we introduce two classes of conformity scores that achieve asymptotic conditional coverage: one is compatible with any generative model, and the other offers low computational cost by leveraging invertible generative models. Finally, we conduct a comprehensive empirical study across 32 tabular datasets to compare all the multi-output conformal methods considered in this work. All methods are implemented within a unified code base to ensure a fair and consistent comparison.
Authors: Tuan L. Vo, Quan Huu Do, Uyen Dang, Thu Nguyen, P{\aa}l Halvorsen, Michael A. Riegler, Binh T. Nguyen
Abstract: The covariance matrix is a foundation in numerous statistical and machine-learning applications such as Principle Component Analysis, Correlation Heatmap, etc. However, missing values within datasets present a formidable obstacle to accurately estimating this matrix. While imputation methods offer one avenue for addressing this challenge, they often entail a trade-off between computational efficiency and estimation accuracy. Consequently, attention has shifted towards direct parameter estimation, given its precision and reduced computational burden. In this paper, we propose Direct Parameter Estimation for Randomly Missing Data with Categorical Features (DPERC), an efficient approach for direct parameter estimation tailored to mixed data that contains missing values within continuous features. Our method is motivated by leveraging information from categorical features, which can significantly enhance covariance matrix estimation for continuous features. Our approach effectively harnesses the information embedded within mixed data structures. Through comprehensive evaluations of diverse datasets, we demonstrate the competitive performance of DPERC compared to various contemporary techniques. In addition, we also show by experiments that DPERC is a valuable tool for visualizing the correlation heatmap.
Authors: George Kurian, Somayeh Sardashti, Ryan Sims, Felix Berger, Gary Holt, Yang Li, Jeremiah Willcock, Kaiyuan Wang, Herve Quiroz, Abdulrahman Salem, Julian Grady
Abstract: Large-scale Ads recommendation and auction scoring models at Google scale demand immense computational resources. While specialized hardware like TPUs have improved linear algebra computations, bottlenecks persist in large-scale systems. This paper proposes solutions for three critical challenges that must be addressed for efficient end-to-end execution in a widely used production infrastructure: (1) Input Generation and Ingestion Pipeline: Efficiently transforming raw features (e.g., "search query") into numerical inputs and streaming them to TPUs; (2) Large Embedding Tables: Optimizing conversion of sparse features into dense floating-point vectors for neural network consumption; (3) Interruptions and Error Handling: Minimizing resource wastage in large-scale shared datacenters. To tackle these challenges, we propose a shared input generation technique to reduce computational load of input generation by amortizing costs across many models. Furthermore, we propose partitioning, pipelining, and RPC (Remote Procedure Call) coalescing software techniques to optimize embedding operations. To maintain efficiency at scale, we describe novel preemption notice and training hold mechanisms that minimize resource wastage, and ensure prompt error resolution. These techniques have demonstrated significant improvement in Google production, achieving a 116% performance boost and an 18% reduction in training costs across representative models.
Authors: Chae Young Lee (Luke), Pu (Luke), Yi, Maxwell Fite, Tejus Rao, Sara Achour, Zerina Kapetanovic
Abstract: We present HyperCam, an energy-efficient image classification pipeline that enables computer vision tasks onboard low-power IoT camera systems. HyperCam leverages hyperdimensional computing to perform training and inference efficiently on low-power microcontrollers. We implement a low-power wireless camera platform using off-the-shelf hardware and demonstrate that HyperCam can achieve an accuracy of 93.60%, 84.06%, 92.98%, and 72.79% for MNIST, Fashion-MNIST, Face Detection, and Face Identification tasks, respectively, while significantly outperforming other classifiers in resource efficiency. Specifically, it delivers inference latency of 0.08-0.27s while using 42.91-63.00KB flash memory and 22.25KB RAM at peak. Among other machine learning classifiers such as SVM, xgBoost, MicroNets, MobileNetV3, and MCUNetV3, HyperCam is the only classifier that achieves competitive accuracy while maintaining competitive memory footprint and inference latency that meets the resource requirements of low-power camera systems.
Authors: Karthik Viswanathan, Yuri Gardinazzi, Giada Panerai, Alberto Cazzaniga, Matteo Biagetti
Abstract: We investigate the relationship between the geometry of token embeddings and their role in the next token prediction within transformer models. An important aspect of this connection uses the notion of empirical measure, which encodes the distribution of token point clouds across transformer layers and drives the evolution of token representations in the mean-field interacting picture. We use metrics such as intrinsic dimension, neighborhood overlap, and cosine similarity to observationally probe these empirical measures across layers. To validate our approach, we compare these metrics to a dataset where the tokens are shuffled, which disrupts the syntactic and semantic structure. Our findings reveal a correlation between the geometric properties of token embeddings and the cross-entropy loss of next token predictions, implying that prompts with higher loss values have tokens represented in higher-dimensional spaces.
Authors: Levin Ho, Morgan McErlean, Zehua You, Douglas Blank, Lisa Meeden
Abstract: In this paper we describe the development and evaluation of AITK, the Artificial Intelligence Toolkit. This open-source project contains both Python libraries and computational essays (Jupyter notebooks) that together are designed to allow a diverse audience with little or no background in AI to interact with a variety of AI tools, exploring in more depth how they function, visualizing their outcomes, and gaining a better understanding of their ethical implications. These notebooks have been piloted at multiple institutions in a variety of humanities courses centered on the theme of responsible AI. In addition, we conducted usability testing of AITK. Our pilot studies and usability testing results indicate that AITK is easy to navigate and effective at helping users gain a better understanding of AI. Our goal, in this time of rapid innovations in AI, is for AITK to provide an accessible resource for faculty from any discipline looking to incorporate AI topics into their courses and for anyone eager to learn more about AI on their own.
Authors: Andrey Risukhin, Kavel Rao, Ben Caffee, Alan Fan
Abstract: Autonomous agents' interactions with humans are increasingly focused on adapting to their changing preferences in order to improve assistance in real-world tasks. Effective agents must learn to accurately infer human goals, which are often hidden, to collaborate well. However, existing Multi-Agent Reinforcement Learning (MARL) environments lack the necessary attributes required to rigorously evaluate these agents' learning capabilities. To this end, we introduce ColorGrid, a novel MARL environment with customizable non-stationarity, asymmetry, and reward structure. We investigate the performance of Independent Proximal Policy Optimization (IPPO), a state-of-the-art (SOTA) MARL algorithm, in ColorGrid and find through extensive ablations that, particularly with simultaneous non-stationary and asymmetric goals between a ``leader'' agent representing a human and a ``follower'' assistant agent, ColorGrid is unsolved by IPPO. To support benchmarking future MARL algorithms, we release our environment code, model checkpoints, and trajectory visualizations at https://github.com/andreyrisukhin/ColorGrid.
Authors: Hao Xie, Saburo Howard, Guglielmo Mazzola
Abstract: Accurate determination of the equation of state of dense hydrogen is essential for understanding gas giants. Currently, there is still no consensus on methods for calculating its entropy, which play a fundamental role and can result in qualitatively different predictions for Jupiter's interior. Here, we investigate various aspects of entropy calculation for dense hydrogen based on ab initio molecular dynamics simulations. Specifically, we employ the recently developed flow matching method to validate the accuracy of the traditional thermodynamic integration approach. We then clearly identify pitfalls in previous attempts and propose a reliable framework for constructing the hydrogen equation of state, which is accurate and thermodynamically consistent across a wide range of temperature and pressure conditions. This allows us to conclusively address the long-standing discrepancies in Jupiter's adiabat among earlier studies, demonstrating the potential of our approach for providing reliable equations of state of diverse materials.
Authors: Mohammad Wali Ur Rahman, Yu-Zheng Lin, Carter Weeks, David Ruddell, Jeff Gabriellini, Bill Hayes, Salim Hariri, Edward V. Ziegler Jr
Abstract: The flexibility and complexity of IPv6 extension headers allow attackers to create covert channels or bypass security mechanisms, leading to potential data breaches or system compromises. The mature development of machine learning has become the primary detection technology option used to mitigate covert communication threats. However, the complexity of detecting covert communication, evolving injection techniques, and scarcity of data make building machine-learning models challenging. In previous related research, machine learning has shown good performance in detecting covert communications, but oversimplified attack scenario assumptions cannot represent the complexity of modern covert technologies and make it easier for machine learning models to detect covert communications. To bridge this gap, in this study, we analyzed the packet structure and network traffic behavior of IPv6, used encryption algorithms, and performed covert communication injection without changing network packet behavior to get closer to real attack scenarios. In addition to analyzing and injecting methods for covert communications, this study also uses comprehensive machine learning techniques to train the model proposed in this study to detect threats, including traditional decision trees such as random forests and gradient boosting, as well as complex neural network architectures such as CNNs and LSTMs, to achieve detection accuracy of over 90\%. This study details the methods used for dataset augmentation and the comparative performance of the applied models, reinforcing insights into the adaptability and resilience of the machine learning application in IPv6 covert communication. In addition, we also proposed a Generative AI-assisted interpretation concept based on prompt engineering as a preliminary study of the role of Generative AI agents in covert communication.
Authors: Xiaoli Yan, Nathaniel Hudson, Hyun Park, Daniel Grzenda, J. Gregory Pauloski, Marcus Schwarting, Haochen Pan, Hassan Harb, Samuel Foreman, Chris Knight, Tom Gibbs, Kyle Chard, Santanu Chaudhuri, Emad Tajkhorshid, Ian Foster, Mohamad Moosavi, Logan Ward, E. A. Huerta
Abstract: We present MOFA, an open-source generative AI (GenAI) plus simulation workflow for high-throughput generation of metal-organic frameworks (MOFs) on large-scale high-performance computing (HPC) systems. MOFA addresses key challenges in integrating GPU-accelerated computing for GPU-intensive GenAI tasks, including distributed training and inference, alongside CPU- and GPU-optimized tasks for screening and filtering AI-generated MOFs using molecular dynamics, density functional theory, and Monte Carlo simulations. These heterogeneous tasks are unified within an online learning framework that optimizes the utilization of available CPU and GPU resources across HPC systems. Performance metrics from a 450-node (14,400 AMD Zen 3 CPUs + 1800 NVIDIA A100 GPUs) supercomputer run demonstrate that MOFA achieves high-throughput generation of novel MOF structures, with CO$_2$ adsorption capacities ranking among the top 10 in the hypothetical MOF (hMOF) dataset. Furthermore, the production of high-quality MOFs exhibits a linear relationship with the number of nodes utilized. The modular architecture of MOFA will facilitate its integration into other scientific applications that dynamically combine GenAI with large-scale simulations.
Authors: Guoyu Li (University of Chinese Academy of Sciences, Microsoft Research), Shengyu Ye (Microsoft Research), Chunyun Chen (NTU Singapore), Yang Wang (Microsoft Research), Fan Yang (Microsoft Research), Ting Cao (Microsoft Research), Cheng Liu (University of Chinese Academy of Sciences), Mohamed M. Sabry (NTU Singapore), Mao Yang (Microsoft Research)
Abstract: The emergence of neural network capabilities invariably leads to a significant surge in computational demands due to expanding model sizes and increased computational complexity. To reduce model size and lower inference costs, recent research has focused on simplifying models and designing hardware accelerators using low-bit quantization. However, due to numerical representation limits, scalar quantization cannot reduce bit width lower than 1-bit, diminishing its benefits. To break through these limitations, we introduce LUT-DLA, a Look-Up Table (LUT) Deep Learning Accelerator Framework that utilizes vector quantization to convert neural network models into LUTs, achieving extreme low-bit quantization. The LUT-DLA framework facilitates efficient and cost-effective hardware accelerator designs and supports the LUTBoost algorithm, which helps to transform various DNN models into LUT-based models via multistage training, drastically cutting both computational and hardware overhead. Additionally, through co-design space exploration, LUT-DLA assesses the impact of various model and hardware parameters to fine-tune hardware configurations for different application scenarios, optimizing performance and efficiency. Our comprehensive experiments show that LUT-DLA achieves improvements in power efficiency and area efficiency with gains of $1.4$~$7.0\times$ and $1.5$~$146.1\times$, respectively, while maintaining only a modest accuracy drop. For CNNs, accuracy decreases by $0.1\%$~$3.1\%$ using the $L_2$ distance similarity, $0.1\%$~$3.4\%$ with the $L_1$ distance similarity, and $0.1\%$~$3.8\%$ when employing the Chebyshev distance similarity. For transformer-based models, the accuracy drop ranges from $1.4\%$ to $3.0\%$.
Authors: Qianhe Ouyang
Abstract: Emotion detection techniques have been applied to multiple cases mainly from facial image features and vocal audio features, of which the latter aspect is disputed yet not only due to the complexity of speech audio processing but also the difficulties of extracting appropriate features. Part of the SAVEE and RAVDESS datasets are selected and combined as the dataset, containing seven sorts of common emotions (i.e. happy, neutral, sad, anger, disgust, fear, and surprise) and thousands of samples. Based on the Librosa package, this paper processes the initial audio input into waveplot and spectrum for analysis and concentrates on multiple features including MFCC as targets for feature extraction. The hybrid CNN-LSTM architecture is adopted by virtue of its strong capability to deal with sequential data and time series, which mainly consists of four convolutional layers and three long short-term memory layers. As a result, the architecture achieved an accuracy of 61.07% comprehensively for the test set, among which the detection of anger and neutral reaches a performance of 75.31% and 71.70% respectively. It can also be concluded that the classification accuracy is dependent on the properties of emotion to some extent, with frequently-used and distinct-featured emotions having less probability to be misclassified into other categories. Emotions like surprise whose meaning depends on the specific context are more likely to confuse with positive or negative emotions, and negative emotions also have a possibility to get mixed with each other.
Authors: Moustafa Zada
Abstract: Recent studies in quantum machine learning advocated the use of hybrid models to assist with the limitations of the currently existing Noisy Intermediate Scale Quantum (NISQ) devices, but what was missing from most of them was the explanations and interpretations of the choices that were made to pick those exact architectures and the differentiation between good and bad hybrid architectures, this research attempts to tackle that gap in the literature by using the Regularized Evolution algorithm to search for the optimal hybrid classical-quantum architecture for the Proximal Policy Optimization (PPO) algorithm, a well-known reinforcement learning algorithm, ultimately the classical models dominated the leaderboard with the best hybrid model coming in eleventh place among all unique models, while we also try to explain the factors that contributed to such results,and for some models to behave better than others in hope to grasp a better intuition about what we should consider good practices for designing an efficient hybrid architecture.
Authors: Cheuk Hang Leung, Yiyan Huang, Yijun Li, Qi Wu
Abstract: Using offline observational data for policy evaluation and learning allows decision-makers to evaluate and learn a policy that connects characteristics and interventions. Most existing literature has focused on either discrete treatment spaces or assumed no difference in the distributions between the policy-learning and policy-deployed environments. These restrict applications in many real-world scenarios where distribution shifts are present with continuous treatment. To overcome these challenges, this paper focuses on developing a distributionally robust policy under a continuous treatment setting. The proposed distributionally robust estimators are established using the Inverse Probability Weighting (IPW) method extended from the discrete one for policy evaluation and learning under continuous treatments. Specifically, we introduce a kernel function into the proposed IPW estimator to mitigate the exclusion of observations that can occur in the standard IPW method to continuous treatments. We then provide finite-sample analysis that guarantees the convergence of the proposed distributionally robust policy evaluation and learning estimators. The comprehensive experiments further verify the effectiveness of our approach when distribution shifts are present.
Authors: Arthicha Srisuchinnawong, Poramate Manoonpong
Abstract: Robot locomotion learning using reinforcement learning suffers from training sample inefficiency and exhibits the non-understandable/black-box nature. Thus, this work presents a novel SME-AGOL to address such problems. Firstly, Sequential Motion Executor (SME) is a three-layer interpretable neural network, where the first produces the sequentially propagating hidden states, the second constructs the corresponding triangular bases with minor non-neighbor interference, and the third maps the bases to the motor commands. Secondly, the Adaptable Gradient-weighting Online Learning (AGOL) algorithm prioritizes the update of the parameters with high relevance score, allowing the learning to focus more on the highly relevant ones. Thus, these two components lead to an analyzable framework, where each sequential hidden state/basis represents the learned key poses/robot configuration. Compared to state-of-the-art methods, the SME-AGOL requires 40% fewer samples and receives 150% higher final reward/locomotion performance on a simulated hexapod robot, while taking merely 10 minutes of learning time from scratch on a physical hexapod robot. Taken together, this work not only proposes the SME-AGOL for sample efficient and understandable locomotion learning but also emphasizes the potential exploitation of interpretability for improving sample efficiency and learning performance.
Authors: Yaniv Shulman
Abstract: Local Polynomial Regression (LPR) is a widely used nonparametric method for modeling complex relationships due to its flexibility and simplicity. It estimates a regression function by fitting low-degree polynomials to localized subsets of the data, weighted by proximity. However, traditional LPR is sensitive to outliers and high-leverage points, which can significantly affect estimation accuracy. This paper revisits the kernel function used to compute regression weights and proposes a novel framework that incorporates both predictor and response variables in the weighting mechanism. By introducing two positive definite kernels, the proposed method robustly estimates weights, mitigating the influence of outliers through localized density estimation. The method is implemented in Python and is publicly available at https://github.com/yaniv-shulman/rsklpr, demonstrating competitive performance in synthetic benchmark experiments. Compared to standard LPR, the proposed approach consistently improves robustness and accuracy, especially in heteroscedastic and noisy environments, without requiring multiple iterations. This advancement provides a promising extension to traditional LPR, opening new possibilities for robust regression applications.
Authors: Yuxuan Dong, Qing Wang, Hengyi Hong, Ya Jiang, Shi Cheng
Abstract: In traditional sound event localization and detection (SELD) tasks, the focus is typically on sound event detection (SED) and direction-of-arrival (DOA) estimation, but they fall short of providing full spatial information about the sound source. The 3D SELD task addresses this limitation by integrating source distance estimation (SDE), allowing for complete spatial localization. We propose three approaches to tackle this challenge: a novel method with independent training and joint prediction, which firstly treats DOA and distance estimation as separate tasks and then combines them to solve 3D SELD; a dual-branch representation with source Cartesian coordinate used for simultaneous DOA and distance estimation; and a three-branch structure that jointly models SED, DOA, and SDE within a unified framework. Our proposed method ranked first in the DCASE 2024 Challenge Task 3, demonstrating the effectiveness of joint modeling for addressing the 3D SELD task. The relevant code for this paper will be open-sourced in the future.
Authors: Juan Manuel Liscano Fierro, Hector J. Hortua
Abstract: Accurately classifying COVID-19 pneumonia in 3D CT scans remains a significant challenge in the field of medical image analysis. Although deterministic neural networks have shown promising results in this area, they provide only point estimates outputs yielding poor diagnostic in clinical decision-making. In this paper, we explore the use of Bayesian neural networks for classifying COVID-19 pneumonia in 3D CT scans providing uncertainties in their predictions. We compare deterministic networks and their Bayesian counterpart, enhancing the decision-making accuracy under uncertainty information. Remarkably, our findings reveal that lightweight architectures achieve the highest accuracy of 96\% after developing extensive hyperparameter tuning. Furthermore, the Bayesian counterpart of these architectures via Multiplied Normalizing Flow technique kept a similar performance along with calibrated uncertainty estimates. Finally, we have developed a 3D-visualization approach to explain the neural network outcomes based on SHAP values. We conclude that explainability along with uncertainty quantification will offer better clinical decisions in medical image analysis, contributing to ongoing efforts for improving the diagnosis and treatment of COVID-19 pneumonia.
Authors: Pengcheng Zhao, Zhixian He, Fuwei Zhang, Shujin Lin, Fan Zhou
Abstract: Video Moment Retrieval and Highlight Detection aim to find corresponding content in the video based on a text query. Existing models usually first use contrastive learning methods to align video and text features, then fuse and extract multimodal information, and finally use a Transformer Decoder to decode multimodal information. However, existing methods face several issues: (1) Overlapping semantic information between different samples in the dataset hinders the model's multimodal aligning performance; (2) Existing models are not able to efficiently extract local features of the video; (3) The Transformer Decoder used by the existing model cannot adequately decode multimodal features. To address the above issues, we proposed the LD-DETR model for Video Moment Retrieval and Highlight Detection tasks. Specifically, we first distilled the similarity matrix into the identity matrix to mitigate the impact of overlapping semantic information. Then, we designed a method that enables convolutional layers to extract multimodal local features more efficiently. Finally, we fed the output of the Transformer Decoder back into itself to adequately decode multimodal information. We evaluated LD-DETR on four public benchmarks and conducted extensive experiments to demonstrate the superiority and effectiveness of our approach. Our model outperforms the State-Of-The-Art models on QVHighlight, Charades-STA and TACoS datasets. Our code is available at https://github.com/qingchen239/ld-detr.
Authors: Siddharth Chandak
Abstract: Two-time-scale stochastic approximation is an iterative algorithm used in applications such as optimization, reinforcement learning, and control. Finite-time analysis of these algorithms has primarily focused on fixed point iterations where both time-scales have contractive mappings. In this paper, we study two-time-scale iterations, where the slower time-scale has a non-expansive mapping. For such algorithms, the slower time-scale can be considered a stochastic inexact Krasnoselskii-Mann iteration. We show that the mean square error decays at a rate $O(1/k^{1/4-\epsilon})$, where $\epsilon>0$ is arbitrarily small. We also show almost sure convergence of iterates to the set of fixed points. We show the applicability of our framework by applying our results to minimax optimization, linear stochastic approximation, and Lagrangian optimization.
Authors: Young Seok Jeon, Hongfei Yang, Huazhu Fu, Mengling Feng
Abstract: 3D models are favored over 2D for 3D medical image segmentation tasks due to their ability to leverage inter-slice relationship, yielding higher segmentation accuracy. However, 3D models demand significantly more GPU memory with increased model size and intermediate tensors. A common solution is to use patch-based training and make whole-volume predictions with sliding window (SW) inference. SW inference reduces memory usage but is slower due to equal resource allocation across patches and less accurate as it overlooks global features beyond patches. We propose NMSW-Net (No-More-Sliding-Window-Net), a novel framework that enhances efficiency and accuracy of any given 3D segmentation model by eliminating SW inference and incorporating global predictions when necessary. NMSW-Net incorporates a differentiable Top-k module to sample only the relevant patches that enhance segmentation accuracy, thereby minimizing redundant computations. Additionally, it learns to leverage coarse global predictions when patch prediction alone is insufficient. NMSW-Net is model-agnostic, making it compatible with any 3D segmentation model that previously relied on SW inference. Evaluated across 3 tasks with 3 segmentation backbones, NMSW-Net achieves competitive or sometimes superior accuracy compared to SW, while reducing computational complexity by 90% (87.5 to 7.95 TFLOPS), delivering 4x faster inference on the H100 GPU (19.0 to 4.3 sec), and 7x faster inference on the Intel Xeon Gold CPU (1710 to 230 seconds).
Authors: Yannik Frisch, Christina Bornberg, Moritz Fuchs, Anirban Mukhopadhyay
Abstract: Augmentation by generative modelling yields a promising alternative to the accumulation of surgical data, where ethical, organisational and regulatory aspects must be considered. Yet, the joint synthesis of (image, mask) pairs for segmentation, a major application in surgery, is rather unexplored. We propose to learn semantically comprehensive yet compact latent representations of the (image, mask) space, which we jointly model with a Latent Diffusion Model. We show that our approach can effectively synthesise unseen high-quality paired segmentation data of remarkable semantic coherence. Generative augmentation is typically applied pre-training by synthesising a fixed number of additional training samples to improve downstream task models. To enhance this approach, we further propose Generative Adaptive Uncertainty-guided Diffusion-based Augmentation (GAUDA), leveraging the epistemic uncertainty of a Bayesian downstream model for targeted online synthesis. We condition the generative model on classes with high estimated uncertainty during training to produce additional unseen samples for these classes. By adaptively utilising the generative model online, we can minimise the number of additional training samples and centre them around the currently most uncertain parts of the data distribution. GAUDA effectively improves downstream segmentation results over comparable methods by an average absolute IoU of 1.6% on CaDISv2 and 1.5% on CholecSeg8k, two prominent surgical datasets for semantic segmentation.
Authors: Mirco Bonomo, Simone Bianco
Abstract: Multimodal Large Language Models (MLLMs) have achieved notable performance in computer vision tasks that require reasoning across visual and textual modalities, yet their capabilities are limited to their pre-trained data, requiring extensive fine-tuning for updates. Recent researches have explored the use of In-Context Learning (ICL) to overcome these challenges by providing a set of demonstrating examples as context to augment MLLMs performance in several tasks, showing that many-shot ICL leads to substantial improvements compared to few-shot ICL. However, the reliance on numerous demonstrating examples and the limited MLLMs context windows presents significant obstacles. This paper aims to address these challenges by introducing a novel approach, Visual RAG, that synergically combines the MLLMs capability to learn from the context, with a retrieval mechanism. The crux of this approach is to ensure to augment the MLLM knowledge by selecting only the most relevant demonstrating examples for the query, pushing it to learn by analogy. In this way, relying on the new information provided dynamically during inference time, the resulting system is not limited to the knowledge extracted from the training data, but can be updated rapidly and easily without fine-tuning. Furthermore, this greatly reduces the computational costs for improving the model image classification performance, and augments the model knowledge to new visual domains and tasks it was not trained for. Extensive experiments on eight different datasets in the state of the art spanning several domains and image classification tasks show that the proposed Visual RAG, compared to the most recent state of the art (i.e., many-shot ICL), is able to obtain an accuracy that is very close or even higher (approx. +2% improvement on average) while using a much smaller set of demonstrating examples (approx. only 23% on average).
Authors: Antonio Lech Martin-Ozimek, Isuru Jayarathne, Su Larb Mon, Jouhyeong Chew
Abstract: Conventional behavior cloning (BC) models often struggle to replicate the subtleties of human actions. Previous studies have attempted to address this issue through the development of a new BC technique: Implicit Behavior Cloning (IBC). This new technique consistently outperformed the conventional Mean Squared Error (MSE) BC models in a variety of tasks. Our goal is to replicate the performance of the IBC model by Florence [in Proceedings of the 5th Conference on Robot Learning, 164:158-168, 2022], for social interaction tasks using our custom dataset. While previous studies have explored the use of large language models (LLMs) for enhancing group conversations, they often overlook the significance of non-verbal cues, which constitute a substantial part of human communication. We propose using IBC to replicate nonverbal cues like gaze behaviors. The model is evaluated against various types of facilitator data and compared to an explicit, MSE BC model. Results show that the IBC model outperforms the MSE BC model across session types using the same metrics used in the previous IBC paper. Despite some metrics showing mixed results which are explainable for the custom dataset for social interaction, we successfully replicated the IBC model to generate nonverbal cues. Our contributions are (1) the replication and extension of the IBC model, and (2) a nonverbal cues generation model for social interaction. These advancements facilitate the integration of robots into the complex interactions between robots and humans, e.g., in the absence of a human facilitator.
Authors: Jiarui Yu, Jicheng Shi, Wenjie Xu, Colin N. Jones
Abstract: Model predictive control (MPC) controller is considered for temperature management in buildings but its performance heavily depends on hyperparameters. Consequently, MPC necessitates meticulous hyperparameter tuning to attain optimal performance under diverse contracts. However, conventional building controller design is an open-loop process without critical hyperparameter optimization, often leading to suboptimal performance due to unexpected environmental disturbances and modeling errors. Furthermore, these hyperparameters are not adapted to different pricing schemes and may lead to non-economic operations. To address these issues, we propose an efficient performance-oriented building MPC controller tuning method based on a cutting-edge efficient constrained Bayesian optimization algorithm, CONFIG, with global optimality guarantees. We demonstrate that this technique can be applied to efficiently deal with real-world DSM program selection problems under customized black-box constraints and objectives. In this study, a simple MPC controller, which offers the advantages of reduced commissioning costs, enhanced computational efficiency, was optimized to perform on a comparable level to a delicately designed and computationally expensive MPC controller. The results also indicate that with an optimized simple MPC, the monthly electricity cost of a household can be reduced by up to 26.90% compared with the cost when controlled by a basic rule-based controller under the same constraints. Then we compared 12 real electricity contracts in Belgium for a household family with customized black-box occupant comfort constraints. The results indicate a monthly electricity bill saving up to 20.18% when the most economic contract is compared with the worst one, which again illustrates the significance of choosing a proper electricity contract.
Authors: Haotian Lin, Matthew Reimherr
Abstract: When concept shifts and sample scarcity are present in the target domain of interest, nonparametric regression learners often struggle to generalize effectively. The technique of transfer learning remedies these issues by leveraging data or pre-trained models from similar source domains. While existing generalization analyses of kernel-based transfer learning typically rely on correctly specified models, we present a transfer learning procedure that is robust against model misspecification while adaptively attaining optimality. To facilitate our analysis and avoid the risk of saturation found in classical misspecified results, we establish a novel result in the misspecified single-task learning setting, showing that spectral algorithms with fixed bandwidth Gaussian kernels can attain minimax convergence rates given the true function is in a Sobolev space, which may be of independent interest. Building on this, we derive the adaptive convergence rates of the excess risk for specifying Gaussian kernels in a prevalent class of hypothesis transfer learning algorithms. Our results are minimax optimal up to logarithmic factors and elucidate the key determinants of transfer efficiency.
Authors: Jens Agerberg, Andrea Guidolin, Andrea Martinelli, Pepijn Roos Hoefgeest, David Eklund, Martina Scolamiero
Abstract: We propose a neural network architecture that can learn discriminative geometric representations of data from persistence diagrams, common descriptors of Topological Data Analysis. The learned representations enjoy Lipschitz stability with a controllable Lipschitz constant. In adversarial learning, this stability can be used to certify $\epsilon$-robustness for samples in a dataset, which we demonstrate on the ORBIT5K dataset representing the orbits of a discrete dynamical system.
Authors: Idan Attias, Yuval Dagan, Constantinos Daskalakis, Rui Yao, Manolis Zampetakis
Abstract: We propose a new algorithm that finds an $\varepsilon$-approximate fixed point of a smooth function from the $n$-dimensional $\ell_2$ unit ball to itself. We use the general framework of finding approximate solutions to a variational inequality, a problem that subsumes fixed point computation and the computation of a Nash Equilibrium. The algorithm's runtime is bounded by $e^{O(n)}/\varepsilon$, under the smoothed-analysis framework. This is the first known algorithm in such a generality whose runtime is faster than $(1/\varepsilon)^{O(n)}$, which is a time that suffices for an exhaustive search. We complement this result with a lower bound of $e^{\Omega(n)}$ on the query complexity for finding an $O(1)$-approximate fixed point on the unit ball, which holds even in the smoothed-analysis model, yet without the assumption that the function is smooth. Existing lower bounds are only known for the hypercube, and adapting them to the ball does not give non-trivial results even for finding $O(1/\sqrt{n})$-approximate fixed points.
Authors: Francesco Stranieri, Chaaben Kouki, Willem van Jaarsveld, Fabio Stella
Abstract: We study inventory control policies for pharmaceutical supply chains, addressing challenges such as perishability, yield uncertainty, and non-stationary demand, combined with batching constraints, lead times, and lost sales. Collaborating with Bristol-Myers Squibb (BMS), we develop a realistic case study incorporating these factors and benchmark three policies--order-up-to (OUT), projected inventory level (PIL), and deep reinforcement learning (DRL) using the proximal policy optimization (PPO) algorithm--against a BMS baseline based on human expertise. We derive and validate bounds-based procedures for optimizing OUT and PIL policy parameters and propose a methodology for estimating projected inventory levels, which are also integrated into the DRL policy with demand forecasts to improve decision-making under non-stationarity. Compared to a human-driven policy, which avoids lost sales through higher holding costs, all three implemented policies achieve lower average costs but exhibit greater cost variability. While PIL demonstrates robust and consistent performance, OUT struggles under high lost sales costs, and PPO excels in complex and variable scenarios but requires significant computational effort. The findings suggest that while DRL shows potential, it does not outperform classical policies in all numerical experiments, highlighting 1) the need to integrate diverse policies to manage pharmaceutical challenges effectively, based on the current state-of-the-art, and 2) that practical problems in this domain seem to lack a single policy class that yields universally acceptable performance.
Authors: Yuqi Gu
Abstract: We use a tensor unfolding technique to prove a new identifiability result for discrete bipartite graphical models, which have a bipartite graph between an observed and a latent layer. This model family includes popular models such as Noisy-Or Bayesian networks for medical diagnosis and Restricted Boltzmann Machines in machine learning. These models are also building blocks for deep generative models. Our result on identifying the graph structure enjoys the following nice properties. First, our identifiability proof is constructive, in which we innovatively unfold the population tensor under the model into matrices and inspect the rank properties of the resulting matrices to uncover the graph. This proof itself gives a population-level structure learning algorithm that outputs both the number of latent variables and the bipartite graph. Second, we allow various forms of nonlinear dependence among the variables, unlike many continuous latent variable graphical models that rely on linearity to show identifiability. Third, our identifiability condition is interpretable, only requiring each latent variable to connect to at least two "pure" observed variables in the bipartite graph. The new result not only brings novel advances in algebraic statistics, but also has useful implications for these models' trustworthy applications in scientific disciplines and interpretable machine learning.
Authors: Akram Heidarizadeh, Connor Hatfield, Lorenzo Lazzarotto, HanQin Cai, George Atia
Abstract: Traditional adversarial attacks typically aim to alter the predicted labels of input images by generating perturbations that are imperceptible to the human eye. However, these approaches often lack explainability. Moreover, most existing work on adversarial attacks focuses on single-stage classifiers, but multi-stage classifiers are largely unexplored. In this paper, we introduce instance-based adversarial attacks for multi-stage classifiers, leveraging Layer-wise Relevance Propagation (LRP), which assigns relevance scores to pixels based on their influence on classification outcomes. Our approach generates explainable adversarial perturbations by utilizing LRP to identify and target key features critical for both coarse and fine-grained classifications. Unlike conventional attacks, our method not only induces misclassification but also enhances the interpretability of the model's behavior across classification stages, as demonstrated by experimental results.
Authors: Haoran Liu, Anthony Tai, David J. Crandall, Chunfeng Huang
Abstract: Neural tangent kernels (NTKs) have been proposed to study the behavior of trained neural networks from the perspective of Gaussian processes. An important result in this body of work is the theorem of equivalence between a trained neural network and kernel regression with the corresponding NTK. This theorem allows for an interpretation of neural networks as special cases of kernel regression. However, does this theorem of equivalence hold in practice? In this paper, we revisit the derivation of the NTK rigorously and conduct numerical experiments to evaluate this equivalence theorem. We observe that adding a layer to a neural network and the corresponding updated NTK do not yield matching changes in the predictor error. Furthermore, we observe that kernel regression with a Gaussian process kernel in the literature that does not account for neural network training produces prediction errors very close to that of kernel regression with NTKs. These observations suggest the equivalence theorem does not hold well in practice and puts into question whether neural tangent kernels adequately address the training process of neural networks.
Authors: Jonathan Jiang, Mark Stamp
Abstract: The threat of malware is a serious concern for computer networks and systems, highlighting the need for accurate classification techniques. In this research, we experiment with multimodal machine learning approaches for malware classification, based on the structured nature of the Windows Portable Executable (PE) file format. Specifically, we train Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN) models on features extracted from PE headers, we train these same models on features extracted from the other sections of PE files, and train each model on features extracted from the entire PE file. We then train SVM models on each of the nine header-sections combinations of these baseline models, using the output layer probabilities of the component models as feature vectors. We compare the baseline cases to these multimodal combinations. In our experiments, we find that the best of the multimodal models outperforms the best of the baseline cases, indicating that it can be advantageous to train separate models on distinct parts of Windows PE files.
Authors: Pengcheng Dong, Wenbo Wan, Huaxiang Zhang, Jiande Sun
Abstract: In recent years, action recognition has received much attention and wide application due to its important role in video understanding. Most of the researches on action recognition methods focused on improving the performance via various deep learning methods rather than the classification of skeleton points. The topological modeling between skeleton points and body parts was seldom considered. Although some studies have used a data-driven approach to classify the topology of the skeleton point, the nature of the skeleton point in terms of kinematics has not been taken into consideration. Therefore, in this paper, we draw on the theory of kinematics to adapt the topological relations of the skeleton point and propose a topological relation classification based on body parts and distance from core of body. To synthesize these topological relations for action recognition, we propose a novel Hypergraph Fusion Graph Convolutional Network (HFGCN). In particular, the proposed model is able to focus on the human skeleton points and the different body parts simultaneously, and thus construct the topology, which improves the recognition accuracy obviously. We use a hypergraph to represent the categorical relationships of these skeleton points and incorporate the hypergraph into a graph convolution network to model the higher-order relationships among the skeleton points and enhance the feature representation of the network. In addition, our proposed hypergraph attention module and hypergraph graph convolution module optimize topology modeling in temporal and channel dimensions, respectively, to further enhance the feature representation of the network. We conducted extensive experiments on three widely used datasets.The results validate that our proposed method can achieve the best performance when compared with the state-of-the-art skeleton-based methods.
Authors: Or Haim Anidjar, Roi Yozevitch
Abstract: In this research, we advanced a spoken language recognition system, moving beyond traditional feature vector-based models. Our improvements focused on effectively capturing language characteristics over extended periods using a specialized pooling layer. We utilized a broad dataset range from Common-Voice, targeting ten languages across Indo-European, Semitic, and East Asian families. The major innovation involved optimizing the architecture of Time Delay Neural Networks. We introduced additional layers and restructured these networks into a funnel shape, enhancing their ability to process complex linguistic patterns. A rigorous grid search determined the optimal settings for these networks, significantly boosting their efficiency in language pattern recognition from audio samples. The model underwent extensive training, including a phase with augmented data, to refine its capabilities. The culmination of these efforts is a highly accurate system, achieving a 97\% accuracy rate in language recognition. This advancement represents a notable contribution to artificial intelligence, specifically in improving the accuracy and efficiency of language processing systems, a critical aspect in the engineering of advanced speech recognition technologies.
Authors: Elad Levi, Ilan Kadar
Abstract: Large Language Models (LLMs) are transforming artificial intelligence, evolving into task-oriented systems capable of autonomous planning and execution. One of the primary applications of LLMs is conversational AI systems, which must navigate multi-turn dialogues, integrate domain-specific APIs, and adhere to strict policy constraints. However, evaluating these agents remains a significant challenge, as traditional methods fail to capture the complexity and variability of real-world interactions. We introduce IntellAgent, a scalable, open-source multi-agent framework designed to evaluate conversational AI systems comprehensively. IntellAgent automates the creation of diverse, synthetic benchmarks by combining policy-driven graph modeling, realistic event generation, and interactive user-agent simulations. This innovative approach provides fine-grained diagnostics, addressing the limitations of static and manually curated benchmarks with coarse-grained metrics. IntellAgent represents a paradigm shift in evaluating conversational AI. By simulating realistic, multi-policy scenarios across varying levels of complexity, IntellAgent captures the nuanced interplay of agent capabilities and policy constraints. Unlike traditional methods, it employs a graph-based policy model to represent relationships, likelihoods, and complexities of policy interactions, enabling highly detailed diagnostics. IntellAgent also identifies critical performance gaps, offering actionable insights for targeted optimization. Its modular, open-source design supports seamless integration of new domains, policies, and APIs, fostering reproducibility and community collaboration. Our findings demonstrate that IntellAgent serves as an effective framework for advancing conversational AI by addressing challenges in bridging research and deployment. The framework is available at https://github.com/plurai-ai/intellagent
Authors: Arvid Eriksson (KTH Royal Institute of Technology), Anton Israelsson (KTH Royal Institute of Technology), Mattias Kallhauge (KTH Royal Institute of Technology)
Abstract: "Why Not Other Classes?": Towards Class-Contrastive Back-Propagation Explanations (Wang & Wang, 2022) provides a method for contrastively explaining why a certain class in a neural network image classifier is chosen above others. This method consists of using back-propagation-based explanation methods from after the softmax layer rather than before. Our work consists of reproducing the work in the original paper. We also provide extensions to the paper by evaluating the method on XGradCAM, FullGrad, and Vision Transformers to evaluate its generalization capabilities. The reproductions show similar results as the original paper, with the only difference being the visualization of heatmaps which could not be reproduced to look similar. The generalization seems to be generally good, with implementations working for Vision Transformers and alternative back-propagation methods. We also show that the original paper suffers from issues such as a lack of detail in the method and an erroneous equation which makes reproducibility difficult. To remedy this we provide an open-source repository containing all code used for this project.
Authors: Jan Betley, Xuchan Bao, Mart\'in Soto, Anna Sztyber-Betley, James Chua, Owain Evans
Abstract: We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and (b) outputting insecure code. Despite the datasets containing no explicit descriptions of the associated behavior, the finetuned LLMs can explicitly describe it. For example, a model trained to output insecure code says, ``The code I write is insecure.'' Indeed, models show behavioral self-awareness for a range of behaviors and for diverse evaluations. Note that while we finetune models to exhibit behaviors like writing insecure code, we do not finetune them to articulate their own behaviors -- models do this without any special training or examples. Behavioral self-awareness is relevant for AI safety, as models could use it to proactively disclose problematic behaviors. In particular, we study backdoor policies, where models exhibit unexpected behaviors only under certain trigger conditions. We find that models can sometimes identify whether or not they have a backdoor, even without its trigger being present. However, models are not able to directly output their trigger by default. Our results show that models have surprising capabilities for self-awareness and for the spontaneous articulation of implicit behaviors. Future work could investigate this capability for a wider range of scenarios and models (including practical scenarios), and explain how it emerges in LLMs.
Authors: Jingxin Zhan, Yuchen Xin, Kaicheng Jin, Zhihua Zhang
Abstract: We study a stochastic convex bandit problem where the subgaussian noise parameter is assumed to decrease linearly as the learner selects actions closer and closer to the minimizer of the convex loss function. Accordingly, we propose a Regularized Online Newton Method (RONM) for solving the problem, based on the Online Newton Method (ONM) of arXiv:2406.06506. Our RONM reaches a polylogarithmic regret in the time horizon $n$ when the loss function grows quadratically in the constraint set, which recovers the results of arXiv:2402.12042 in linear bandits. Our analyses rely on the growth rate of the precision matrix $\Sigma_t^{-1}$ in ONM and we find that linear growth solves the question exactly. These analyses also help us obtain better convergence rates when the loss function grows faster. We also study and analyze two new bandit models: stochastic convex bandits with noise scaled to a subgaussian parameter function and convex bandits with stochastic multiplicative noise.
Authors: Dian Jin, Yuqian Zhang, Qiaosheng Zhang
Abstract: The integration of both network information and node attribute information has recently gained significant attention in the context of community recovery problems. In this work, we address the task of determining the optimal classification rate for the Label-SBM(LSBM) model with node attribute information and. Specifically, we derive the optimal lower bound, which is characterized by the Chernoff-Hellinger divergence for a general LSBM network model with Gaussian node attributes. Additionally, we highlight the connection between the divergence $D(\bs\alpha, \mb P, \bs\mu)$ in our model and those introduced in \cite{yun2016optimal} and \cite{lu2016statistical}. We also presents a consistent algorithm based on spectral method for the proposed aggreated latent factor model.
Authors: Mohammad Mahdi Abootorabi, Nona Ghazizadeh, Seyed Arshan Dalili, Alireza Ghahramani Kure, Mahshid Dehghani, Ehsaneddin Asgari
Abstract: In this study, we introduce a solution to the SemEval 2024 Task 10 on subtask 1, dedicated to Emotion Recognition in Conversation (ERC) in code-mixed Hindi-English conversations. ERC in code-mixed conversations presents unique challenges, as existing models are typically trained on monolingual datasets and may not perform well on code-mixed data. To address this, we propose a series of models that incorporate both the previous and future context of the current utterance, as well as the sequential information of the conversation. To facilitate the processing of code-mixed data, we developed a Hinglish-to-English translation pipeline to translate the code-mixed conversations into English. We designed four different base models, each utilizing powerful pre-trained encoders to extract features from the input but with varying architectures. By ensembling all of these models, we developed a final model that outperforms all other baselines.
Authors: Alireza Ghahramani Kure, Mahshid Dehghani, Mohammad Mahdi Abootorabi, Nona Ghazizadeh, Seyed Arshan Dalili, Ehsaneddin Asgari
Abstract: The SemEval-2024 Task 3 presents two subtasks focusing on emotion-cause pair extraction within conversational contexts. Subtask 1 revolves around the extraction of textual emotion-cause pairs, where causes are defined and annotated as textual spans within the conversation. Conversely, Subtask 2 extends the analysis to encompass multimodal cues, including language, audio, and vision, acknowledging instances where causes may not be exclusively represented in the textual data. Our proposed model for emotion-cause analysis is meticulously structured into three core segments: (i) embedding extraction, (ii) cause-pair extraction & emotion classification, and (iii) cause extraction using QA after finding pairs. Leveraging state-of-the-art techniques and fine-tuning on task-specific datasets, our model effectively unravels the intricate web of conversational dynamics and extracts subtle cues signifying causality in emotional expressions. Our team, AIMA, demonstrated strong performance in the SemEval-2024 Task 3 competition. We ranked as the 10th in subtask 1 and the 6th in subtask 2 out of 23 teams.
Authors: Katarzyna Fojcik, Piotr Syga
Abstract: Video Copy Detection (VCD) plays a crucial role in copyright protection and content verification by identifying duplicates and near-duplicates in large-scale video databases. The META AI Challenge on video copy detection provided a benchmark for evaluating state-of-the-art methods, with the Dual-level detection approach emerging as a winning solution. This method integrates Video Editing Detection and Frame Scene Detection to handle adversarial transformations and large datasets efficiently. However, our analysis reveals significant limitations in the VED component, particularly in its ability to handle exact copies. Moreover, Dual-level detection shows vulnerability to temporal attacks. To address it, we propose an improved frame selection strategy based on local maxima of interframe differences, which enhances robustness against adversarial temporal modifications while significantly reducing computational overhead. Our method achieves an increase of 1.4 to 5.8 times in efficiency over the standard 1 FPS approach. Compared to Dual-level detection method, our approach maintains comparable micro-average precision ($\mu$AP) while also demonstrating improved robustness against temporal attacks. Given 56\% reduced representation size and the inference time of more than 2 times faster, our approach is more suitable to real-world resource restriction.
Authors: Yassir Bendou, Amine Ouasfi, Vincent Gripon, Adnane Boukhayma
Abstract: The growing popularity of Contrastive Language-Image Pretraining (CLIP) has led to its widespread application in various visual downstream tasks. To enhance CLIP's effectiveness and versatility, efficient few-shot adaptation techniques have been widely adopted. Among these approaches, training-free methods, particularly caching methods exemplified by Tip-Adapter, have gained attention for their lightweight adaptation without the need for additional fine-tuning. In this paper, we revisit Tip-Adapter from a kernel perspective, showing that caching methods function as local adapters and are connected to a well-established kernel literature. Drawing on this insight, we offer a theoretical understanding of how these methods operate and suggest multiple avenues for enhancing the Tip-Adapter baseline. Notably, our analysis shows the importance of incorporating global information in local adapters. Therefore, we subsequently propose a global method that learns a proximal regularizer in a reproducing kernel Hilbert space (RKHS) using CLIP as a base learner. Our method, which we call ProKeR (Proximal Kernel ridge Regression), has a closed form solution and achieves state-of-the-art performances across 11 datasets in the standard few-shot adaptation benchmark.
Authors: Kristin Blesch, Niklas Koenen, Jan Kapar, Pegah Golchian, Lukas Burk, Markus Loecher, Marvin N. Wright
Abstract: This paper proposes a method for measuring conditional feature importance via generative modeling. In explainable artificial intelligence (XAI), conditional feature importance assesses the impact of a feature on a prediction model's performance given the information of other features. Model-agnostic post hoc methods to do so typically evaluate changes in the predictive performance under on-manifold feature value manipulations. Such procedures require creating feature values that respect conditional feature distributions, which can be challenging in practice. Recent advancements in generative modeling can facilitate this. For tabular data, which may consist of both categorical and continuous features, the adversarial random forest (ARF) stands out as a generative model that can generate on-manifold data points without requiring intensive tuning efforts or computational resources, making it a promising candidate model for subroutines in XAI methods. This paper proposes cARFi (conditional ARF feature importance), a method for measuring conditional feature importance through feature values sampled from ARF-estimated conditional distributions. cARFi requires only little tuning to yield robust importance scores that can flexibly adapt for conditional or marginal notions of feature importance, including straightforward extensions to condition on feature subsets and allows for inferring the significance of feature importances through statistical tests.
Authors: David Williams-King, Linh Le, Adam Oberman, Yoshua Bengio
Abstract: As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In this paper, we argue the position that current safety fine-tuning is very similar to a traditional cat-and-mouse game (or arms race) between attackers and defenders in cybersecurity. Model jailbreaks and attacks are patched with bandaids to target the specific attack mechanism, but many similar attack vectors might remain. When defenders are not proactively coming up with principled mechanisms, it becomes very easy for attackers to sidestep any new defenses. We show how current defenses are insufficient to prevent new adversarial jailbreak attacks, reward hacking, and loss of control problems. In order to learn from past mistakes in cybersecurity, we draw analogies with historical examples and develop lessons learned that can be applied to LLM safety. These arguments support the need for new and more principled approaches to designing safe models, which are architected for security from the beginning. We describe several such approaches from the AI literature.
Authors: Hasan Basri Celebi, Mikael Skoglund
Abstract: This paper presents a comprehensive system model for goodput maximization with quantized feedback in Ultra-Reliable Low-Latency Communication (URLLC), focusing on dynamic channel conditions and feedback schemes. The study investigates a communication system, where the receiver provides quantized channel state information to the transmitter. The system adapts its feedback scheme based on reinforcement learning, aiming to maximize goodput while accommodating varying channel statistics. We introduce a novel Rician-$K$ factor estimation technique to enable the communication system to optimize the feedback scheme. This dynamic approach increases the overall performance, making it well-suited for practical URLLC applications where channel statistics vary over time.
Authors: Sungbin Kim, Hyunwuk Lee, Wonho Cho, Mincheol Park, Won Woo Ro
Abstract: Diffusion models achieve superior performance in image generation tasks. However, it incurs significant computation overheads due to its iterative structure. To address these overheads, we analyze this iterative structure and observe that adjacent time steps in diffusion models exhibit high value similarity, leading to narrower differences between consecutive time steps. We adapt these characteristics to a quantized diffusion model and reveal that the majority of these differences can be represented with reduced bit-width, and even zero. Based on our observations, we propose the Ditto algorithm, a difference processing algorithm that leverages temporal similarity with quantization to enhance the efficiency of diffusion models. By exploiting the narrower differences and the distributive property of layer operations, it performs full bit-width operations for the initial time step and processes subsequent steps with temporal differences. In addition, Ditto execution flow optimization is designed to mitigate the memory overhead of temporal difference processing, further boosting the efficiency of the Ditto algorithm. We also design the Ditto hardware, a specialized hardware accelerator, fully exploiting the dynamic characteristics of the proposed algorithm. As a result, the Ditto hardware achieves up to 1.5x speedup and 17.74% energy saving compared to other accelerators.
Authors: Anurag Awasthi
Abstract: Generative Adversarial Networks (GANs) have gained prominence in refining model fitting tasks in computer vision, particularly in domains involving deformable models like Active Appearance Models (AAMs). This paper explores the integration of GANs to enhance the AAM fitting process, addressing challenges in optimizing nonlinear parameters associated with appearance and shape variations. By leveraging GANs' adversarial training framework, the aim is to minimize fitting errors and improve convergence rates. Achieving robust performance even in cases with high appearance variability and occlusions. Our approach demonstrates significant improvements in accuracy and computational efficiency compared to traditional optimization techniques, thus establishing GANs as a potent tool for advanced image model fitting.
Authors: Chang Wan, Ke Fan, Xinwei Sun, Yanwei Fu, Minglu Li, Yunliang Jiang, Zhonglong Zheng
Abstract: This paper introduces a promising alternative method for training Generative Adversarial Networks (GANs) on large-scale datasets with clear theoretical guarantees. GANs are typically learned through a minimax game between a generator and a discriminator, which is known to be empirically unstable. Previous learning paradigms have encountered mode collapse issues without a theoretical solution. To address these challenges, we propose a novel Lipschitz-constrained Functional Gradient GANs learning (Li-CFG) method to stabilize the training of GAN and provide a theoretical foundation for effectively increasing the diversity of synthetic samples by reducing the neighborhood size of the latent vector. Specifically, we demonstrate that the neighborhood size of the latent vector can be reduced by increasing the norm of the discriminator gradient, resulting in enhanced diversity of synthetic samples. To efficiently enlarge the norm of the discriminator gradient, we introduce a novel {\epsilon}-centered gradient penalty that amplifies the norm of the discriminator gradient using the hyper-parameter {\epsilon}. In comparison to other constraints, our method enlarging the discriminator norm, thus obtaining the smallest neighborhood size of the latent vector. Extensive experiments on benchmark datasets for image generation demonstrate the efficacy of the Li-CFG method and the {\epsilon}-centered gradient penalty. The results showcase improved stability and increased diversity of synthetic samples.
Authors: Tal Zeevi, Lawrence H. Staib, John A. Onofrey
Abstract: Monte-Carlo (MC) Dropout provides a practical solution for estimating predictive distributions in deterministic neural networks. Traditional dropout, applied within the signal space, may fail to account for frequency-related noise common in medical imaging, leading to biased predictive estimates. A novel approach extends Dropout to the frequency domain, allowing stochastic attenuation of signal frequencies during inference. This creates diverse global textural variations in feature maps while preserving structural integrity -- a factor we hypothesize and empirically show is contributing to accurately estimating uncertainties in semantic segmentation. We evaluated traditional MC-Dropout and the MC-frequency Dropout in three segmentation tasks involving different imaging modalities: (i) prostate zones in biparametric MRI, (ii) liver tumors in contrast-enhanced CT, and (iii) lungs in chest X-ray scans. Our results show that MC-Frequency Dropout improves calibration, convergence, and semantic uncertainty, thereby improving prediction scrutiny, boundary delineation, and has the potential to enhance medical decision-making.
Authors: Shuai Wang, Yanqing Xu, Chaoqun You, Mingjie Shao, Tony Q. S. Quek
Abstract: Federated learning (FL) has been recognized as a viable solution for local-privacy-aware collaborative model training in wireless edge networks, but its practical deployment is hindered by the high communication overhead caused by frequent and costly server-device synchronization. Notably, most existing communication-efficient FL algorithms fail to reduce the significant inter-device variance resulting from the prevalent issue of device heterogeneity. This variance severely decelerates algorithm convergence, increasing communication overhead and making it more challenging to achieve a well-performed model. In this paper, we propose a novel communication-efficient FL algorithm, named FedQVR, which relies on a sophisticated variance-reduced scheme to achieve heterogeneity-robustness in the presence of quantized transmission and heterogeneous local updates among active edge devices. Comprehensive theoretical analysis justifies that FedQVR is inherently resilient to device heterogeneity and has a comparable convergence rate even with a small number of quantization bits, yielding significant communication savings. Besides, considering non-ideal wireless channels, we propose FedQVR-E which enhances the convergence of FedQVR by performing joint allocation of bandwidth and quantization bits across devices under constrained transmission delays. Extensive experimental results are also presented to demonstrate the superior performance of the proposed algorithms over their counterparts in terms of both communication efficiency and application performance.
Authors: Tsukasa Yoshida, Kazuho Watanabe
Abstract: This paper focuses on linear regression models with non-conjugate sparsity-inducing regularizers such as lasso and group lasso. Although empirical Bayes approach enables us to estimate the regularization parameter, little is known on the properties of the estimators. In particular, there are many unexplained aspects regarding the specific conditions under which the mechanism of automatic relevance determination (ARD) occurs. In this paper, we derive the empirical Bayes estimators for the group lasso regularized linear regression models with a limited number of parameters. It is shown that the estimators diverge under a certain condition, giving rise to the ARD mechanism. We also prove that empirical Bayes methods can produce ARD mechanism in general regularized linear regression models and clarify the conditions under which models such as ridge, lasso, and group lasso can produce ARD mechanism.
Authors: Zhifeng Kong, Kevin J Shih, Weili Nie, Arash Vahdat, Sang-gil Lee, Joao Felipe Santos, Ante Jukic, Rafael Valle, Bryan Catanzaro
Abstract: Audio in the real world may be perturbed due to numerous factors, causing the audio quality to be degraded. The following work presents an audio restoration model tailored for high-res music at 44.1kHz. Our model, Audio-to-Audio Schrodinger Bridges (A2SB), is capable of both bandwidth extension (predicting high-frequency components) and inpainting (re-generating missing segments). Critically, A2SB is end-to-end without need of a vocoder to predict waveform outputs, able to restore hour-long audio inputs, and trained on permissively licensed music data. A2SB is capable of achieving state-of-the-art bandwidth extension and inpainting quality on several out-of-distribution music test sets. Our demo website is https: //research.nvidia.com/labs/adlr/A2SB/.
Authors: Chang Wan, Ming-Hsuan Yang, Minglu Li, Yunliang Jiang, Zhonglong Zheng
Abstract: Recently, researchers have proposed many deep generative models, including generative adversarial networks(GANs) and denoising diffusion models. Although significant breakthroughs have been made and empirical success has been achieved with the GAN, its mathematical underpinnings remain relatively unknown. This paper focuses on a rigorous mathematical theoretical framework: the composite-functional-gradient GAN (CFG)[1]. Specifically, we reveal the theoretical connection between the CFG model and score-based models. We find that the training objective of the CFG discriminator is equivalent to finding an optimal D(x). The optimal gradient of D(x) differentiates the integral of the differences between the score functions of real and synthesized samples. Conversely, training the CFG generator involves finding an optimal G(x) that minimizes this difference. In this paper, we aim to derive an annealed weight preceding the weight of the CFG discriminator. This new explicit theoretical explanation model is called the annealed CFG method. To overcome the limitation of the annealed CFG method, as the method is not readily applicable to the SOTA GAN model, we propose a nested annealed training scheme (NATS). This scheme keeps the annealed weight from the CFG method and can be seamlessly adapted to various GAN models, no matter their structural, loss, or regularization differences. We conduct thorough experimental evaluations on various benchmark datasets for image generation. The results show that our annealed CFG and NATS methods significantly improve the quality and diversity of the synthesized samples. This improvement is clear when comparing the CFG method and the SOTA GAN models.
Authors: Sungjae Cho
Abstract: Lee and Seung (2000) introduced numerical solutions for non-negative matrix factorization (NMF) using iterative multiplicative update algorithms. These algorithms have been actively utilized as dimensionality reduction tools for high-dimensional non-negative data and learning algorithms for artificial neural networks. Despite a considerable amount of literature on the applications of the NMF algorithms, detailed explanations about their formulation and derivation are lacking. This report provides supplementary details to help understand the formulation and derivation of the proofs as used in the original paper.
Authors: Muhammed Fadera
Abstract: Recurrent Neural Networks (RNNs) are high-dimensional state space models capable of learning functions on sequence data. Recently, it has been conjectured that reservoir computers, a particular class of RNNs, trained on observations of a dynamical systems can be interpreted as embeddings. This result has been established for the case of linear reservoir systems. In this work, we use a nonautonomous dynamical systems approach to establish an upper bound for the fractal dimension of the subset of reservoir state space approximated during training and prediction phase. We prove that when the input sequences comes from an Nin-dimensional invertible dynamical system, the fractal dimension of this set is bounded above by Nin. The result obtained here are useful in dimensionality reduction of computation in RNNs as well as estimating fractal dimensions of dynamical systems from limited observations of their time series. It is also a step towards understanding embedding properties of reservoir computers.
Authors: Jamie Lohoff, Anil Kaya, Florian Assmuth, Emre Neftci
Abstract: Online synaptic plasticity rules derived from gradient descent achieve high accuracy on a wide range of practical tasks. However, their software implementation often requires tediously hand-derived gradients or using gradient backpropagation which sacrifices the online capability of the rules. In this work, we present a custom automatic differentiation (AD) pipeline for sparse and online implementation of gradient-based synaptic plasticity rules that generalizes to arbitrary neuron models. Our work combines the programming ease of backpropagation-type methods for forward AD while being memory-efficient. To achieve this, we exploit the advantageous compute and memory scaling of online synaptic plasticity by providing an inherently sparse implementation of AD where expensive tensor contractions are replaced with simple element-wise multiplications if the tensors are diagonal. Gradient-based synaptic plasticity rules such as eligibility propagation (e-prop) have exactly this property and thus profit immensely from this feature. We demonstrate the alignment of our gradients with respect to gradient backpropagation on an synthetic task where e-prop gradients are exact, as well as audio speech classification benchmarks. We demonstrate how memory utilization scales with network size without dependence on the sequence length, as expected from forward AD methods.
Authors: Jakub Nalepa, Tomasz Bartczak, Mariusz Bujny, Jaros{\l}aw Go\'sli\'nski, Katarzyna Jesionek, Wojciech Malara, Filip Malawski, Karol Miszalski-Jamka, Patrycja Rewa, Marcin Kostur
Abstract: Despite coronary artery calcium scoring being considered a largely solved problem within the realm of medical artificial intelligence, this paper argues that significant improvements can still be made. By shifting the focus from pathology detection to a deeper understanding of anatomy, the novel algorithm proposed in the paper both achieves high accuracy in coronary artery calcium scoring and offers enhanced interpretability of the results. This approach not only aids in the precise quantification of calcifications in coronary arteries, but also provides valuable insights into the underlying anatomical structures. Through this anatomically-informed methodology, the paper shows how a nuanced understanding of the heart's anatomy can lead to more accurate and interpretable results in the field of cardiovascular health. We demonstrate the superior accuracy of the proposed method by evaluating it on an open-source multi-vendor dataset, where we obtain results at the inter-observer level, surpassing the current state of the art. Finally, the qualitative analyses show the practical value of the algorithm in such tasks as labeling coronary artery calcifications, identifying aortic calcifications, and filtering out false positive detections due to noise.
Authors: Akash Kundu
Abstract: The Sachdev-Ye-Kitaev (SYK) model, known for its strong quantum correlations and chaotic behavior, serves as a key platform for quantum gravity studies. However, variationally preparing thermal states on near-term quantum processors for large systems (N>12, where N is the number of Majorana fermions) presents a significant challenge due to the rapid growth in the complexity of parameterized quantum circuits. This paper addresses this challenge by integrating reinforcement learning (RL) with convolutional neural networks, employing an iterative approach to optimize the quantum circuit and its parameters. The refinement process is guided by a composite reward signal derived from entropy and the expectation values of the SYK Hamiltonian. This approach reduces the number of CNOT gates by two orders of magnitude for systems N>10 compared to traditional methods like first-order Trotterization. We demonstrate the effectiveness of the RL framework in both noiseless and noisy quantum hardware environments, maintaining high accuracy in thermal state preparation. This work contributes to the advancement of a scalable, RL-based framework with applications for computations of thermal out-of-time-order correlators in quantum many-body systems and quantum gravity studies on near-term quantum hardware.
Authors: Jiwan Chung, Seungwon Lim, Sangkyu Lee, Youngjae Yu
Abstract: Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language priors and neglect to adequately consider the visual content. We thus present Multimodal ASsociation Score (MASS), a framework that reduces the reliance on language priors for better visual accuracy in image-text matching problems. It can be seamlessly incorporated into existing visual-language models without necessitating additional training. Our experiments have shown that MASS effectively lessens language bias without losing an understanding of linguistic compositionality. Overall, MASS offers a promising solution for enhancing image-text matching performance in visual-language models.
Authors: Huachi Zhou, Jiahe Du, Chuang Zhou, Chang Yang, Yilin Xiao, Yuxuan Xie, Xiao Huang
Abstract: Recent efforts leverage Large Language Models (LLMs) for modeling text-attributed graph structures in node classification tasks. These approaches describe graph structures for LLMs to understand or aggregate LLM-generated textual attribute embeddings through graph structure. However, these approaches face two main limitations in modeling graph structures with LLMs. (i) Graph descriptions become verbose in describing high-order graph structure. (ii) Textual attributes alone do not contain adequate graph structure information. It is challenging to model graph structure concisely and adequately with LLMs. LLMs lack built-in mechanisms to model graph structures directly. They also struggle with complex long-range dependencies between high-order nodes and target nodes. Inspired by the observation that LLMs pre-trained on one language can achieve exceptional performance on another with minimal additional training, we propose \textbf{G}raph-\textbf{D}efined \textbf{L}anguage for \textbf{L}arge \textbf{L}anguage \textbf{M}odel (GDL4LLM). This novel framework enables LLMs to transfer their powerful language understanding capabilities to graph-structured data. GDL4LLM translates graphs into a graph language corpus instead of graph descriptions and pre-trains LLMs on this corpus to adequately understand graph structures. During fine-tuning, this corpus describes the structural information of target nodes concisely with only a few tokens. By treating graphs as a new language, GDL4LLM enables LLMs to model graph structures adequately and concisely for node classification tasks. Extensive experiments on three real-world datasets demonstrate that GDL4LLM outperforms description-based and textual attribute embeddings-based baselines by efficiently modeling different orders of graph structure with LLMs.
Authors: Vincent Koc
Abstract: Generative AI and large-scale language models (LLM) have emerged as powerful tools in language preservation, particularly for near-native and endangered languages. With the increasing reliance on technology for communication, education, and cultural documentation, new opportunities have emerged to mitigate the dramatic decline of linguistic diversity worldwide. This paper examines the role of generative AIs and LLMs in preserving endangered languages, highlighting the risks and challenges associated with their use. We analyze the underlying technologies driving these models, including natural language processing (NLP) and deep learning, and explore several cases where these technologies have been applied to low-resource languages. Additionally, we discuss ethical considerations, data scarcity issues, and technical challenges while proposing solutions to enhance AI-driven language preservation.
Authors: Aya Kayal, Eduardo Pignatelli, Laura Toni
Abstract: One of the open challenges in Reinforcement Learning is the hard exploration problem in sparse reward environments. Various types of intrinsic rewards have been proposed to address this challenge by pushing towards diversity. This diversity might be imposed at different levels, favouring the agent to explore different states, policies or behaviours (State, Policy and Skill level diversity, respectively). However, the impact of diversity on the agent's behaviour remains unclear. In this work, we aim to fill this gap by studying the effect of different levels of diversity imposed by intrinsic rewards on the exploration patterns of RL agents. We select four intrinsic rewards (State Count, Intrinsic Curiosity Module (ICM), Maximum Entropy, and Diversity is all you need (DIAYN)), each pushing for a different diversity level. We conduct an empirical study on MiniGrid environment to compare their impact on exploration considering various metrics related to the agent's exploration, namely: episodic return, observation coverage, agent's position coverage, policy entropy, and timeframes to reach the sparse reward. The main outcome of the study is that State Count leads to the best exploration performance in the case of low-dimensional observations. However, in the case of RGB observations, the performance of State Count is highly degraded mostly due to representation learning challenges. Conversely, Maximum Entropy is less impacted, resulting in a more robust exploration, despite being not always optimal. Lastly, our empirical study revealed that learning diverse skills with DIAYN, often linked to improved robustness and generalisation, does not promote exploration in MiniGrid environments. This is because: i) learning the skill space itself can be challenging, and ii) exploration within the skill space prioritises differentiating between behaviours rather than achieving uniform state visitation.
Authors: Tim Rolff, Jenny Gabel, Lauren Zerbin, Niklas Hypki, Susanne Schmidt, Markus Lappe, Frank Steinicke
Abstract: Gaze-based interaction techniques have created significant interest in the field of spatial interaction. Many of these methods require additional input modalities, such as hand gestures (e.g., gaze coupled with pinch). Those can be uncomfortable and difficult to perform in public or limited spaces, and pose challenges for users who are unable to execute pinch gestures. To address these aspects, we propose a novel, hands-free Gaze+Blink interaction technique that leverages the user's gaze and intentional eye blinks. This technique enables users to perform selections by executing intentional blinks. It facilitates continuous interactions, such as scrolling or drag-and-drop, through eye blinks coupled with head movements. So far, this concept has not been explored for hands-free spatial interaction techniques. We evaluated the performance and user experience (UX) of our Gaze+Blink method with two user studies and compared it with Gaze+Pinch in a realistic user interface setup featuring common menu interaction tasks. Study 1 demonstrated that while Gaze+Blink achieved comparable selection speeds, it was prone to accidental selections resulting from unintentional blinks. In Study 2 we explored an enhanced technique employing a deep learning algorithms for filtering out unintentional blinks.
Authors: Minsu Kim, Jaehyun Oh, Sang-Young Lee, Junghwan Kim
Abstract: Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is essential for ensuring safety, reducing maintenance costs, and optimizing usage. However, predicting RUL is challenging due to the nonlinear characteristics of the degradation caused by complex chemical reactions. Machine learning allows precise predictions by learning the latent functions of degradation relationships based on cycling behavior. This study introduces an accurate RUL prediction approach based on feature engineering and DLinear, applied to the dataset from NASA's Prognostics Center of Excellence. Among the 20 features generated from current, voltage, temperature, and time provided in this dataset, key features contributing to degradation are selected using Pearson correlation coefficient and Shapley values. Shapley value-based feature selection effectively reflects cell-to-cell variability, showing similar importance rankings across all cells. The DLinear-based RUL prediction using key features efficiently captures the time-series trend, demonstrating significantly better performance compared to Long Short-Term Memory and Transformer models.
Authors: Florent Bouchard, Nils Laurent, Salem Said, Nicolas Le Bihan
Abstract: In this paper, the issue of averaging data on a manifold is addressed. While the Fr\'echet mean resulting from Riemannian geometry appears ideal, it is unfortunately not always available and often computationally very expensive. To overcome this, R-barycenters have been proposed and successfully applied to Stiefel and Grassmann manifolds. However, R-barycenters still suffer severe limitations as they rely on iterative algorithms and complicated operators. We propose simpler, yet efficient, barycenters that we call RL-barycenters. We show that, in the setting relevant to most applications, our framework yields astonishingly simple barycenters: arithmetic means projected onto the manifold. We apply this approach to the Stiefel and Grassmann manifolds. On simulated data, our approach is competitive with respect to existing averaging methods, while computationally cheaper.
Authors: Karn N. Watcharasupat, Yiwei Ding, T. Aleksandra Ma, Pavan Seshadri, Alexander Lerch
Abstract: Any data annotation for subjective tasks shows potential variations between individuals. This is particularly true for annotations of emotional responses to musical stimuli. While older approaches to music emotion recognition systems frequently addressed this uncertainty problem through probabilistic modeling, modern systems based on neural networks tend to ignore the variability and focus only on predicting central tendencies of human subjective responses. In this work, we explore several methods for estimating not only the central tendencies of the subjective responses to a musical stimulus, but also for estimating the uncertainty associated with these responses. In particular, we investigate probabilistic loss functions and inference-time random sampling. Experimental results indicate that while the modeling of the central tendencies is achievable, modeling of the uncertainty in subjective responses proves significantly more challenging with currently available approaches even when empirical estimates of variations in the responses are available.
Authors: Cong Wu, Jing Chen, Qianru Fang, Kun He, Ziming Zhao, Hao Ren, Guowen Xu, Yang Liu, Yang Xiang
Abstract: Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain limited-explored in transfer learning. The interaction between teacher and student models in transfer learning has not been thoroughly explored in MIAs, potentially resulting in an under-examined aspect of privacy vulnerabilities within transfer learning. In this paper, we propose a new MIA vector against transfer learning, to determine whether a specific data point was used to train the teacher model while only accessing the student model in a white-box setting. Our method delves into the intricate relationship between teacher and student models, analyzing the discrepancies in hidden layer representations between the student model and its shadow counterpart. These identified differences are then adeptly utilized to refine the shadow model's training process and to inform membership inference decisions effectively. Our method, evaluated across four datasets in diverse transfer learning tasks, reveals that even when an attacker only has access to the student model, the teacher model's training data remains susceptible to MIAs. We believe our work unveils the unexplored risk of membership inference in transfer learning.
Authors: Verya Monjezi, Ashutosh Trivedi, Vladik Kreinovich, Saeid Tizpaz-Niari
Abstract: Data-driven software is increasingly being used as a critical component of automated decision-support systems. Since this class of software learns its logic from historical data, it can encode or amplify discriminatory practices. Previous research on algorithmic fairness has focused on improving average-case fairness. On the other hand, fairness at the extreme ends of the spectrum, which often signifies lasting and impactful shifts in societal attitudes, has received significantly less emphasis. Leveraging the statistics of extreme value theory (EVT), we propose a novel fairness criterion called extreme counterfactual discrimination (ECD). This criterion estimates the worst-case amounts of disadvantage in outcomes for individuals solely based on their memberships in a protected group. Utilizing tools from search-based software engineering and generative AI, we present a randomized algorithm that samples a statistically significant set of points from the tail of ML outcome distributions even if the input dataset lacks a sufficient number of relevant samples. We conducted several experiments on four ML models (deep neural networks, logistic regression, and random forests) over 10 socially relevant tasks from the literature on algorithmic fairness. First, we evaluate the generative AI methods and find that they generate sufficient samples to infer valid EVT distribution in 95% of cases. Remarkably, we found that the prevalent bias mitigators reduce the average-case discrimination but increase the worst-case discrimination significantly in 5% of cases. We also observed that even the tail-aware mitigation algorithm -- MiniMax-Fairness -- increased the worst-case discrimination in 30% of cases. We propose a novel ECD-based mitigator that improves fairness in the tail in 90% of cases with no degradation of the average-case discrimination.
Authors: Vedant Bhasin, Matthew Yudin, Razvan Stefanescu, Rauf Izmailov
Abstract: Trojan backdoors can be injected into large language models at various stages, including pretraining, fine-tuning, and in-context learning, posing a significant threat to the model's alignment. Due to the nature of causal language modeling, detecting these triggers is challenging given the vast search space. In this study, we propose a multistage framework for detecting Trojan triggers in large language models consisting of token filtration, trigger identification, and trigger verification. We discuss existing trigger identification methods and propose two variants of a black-box trigger inversion method that rely on output logits, utilizing beam search and greedy decoding respectively. We show that the verification stage is critical in the process and propose semantic-preserving prompts and special perturbations to differentiate between actual Trojan triggers and other adversarial strings that display similar characteristics. The evaluation of our approach on the TrojAI and RLHF poisoned model datasets demonstrates promising results.
Authors: Seorin Kim, Julien Baudru, Wouter Ryckbosch, Hugues Bersini, Vincent Ginis
Abstract: We explore the ability of two LLMs -- GPT-4o and Claude Sonnet 3.5 -- to transcribe historical handwritten documents in a tabular format and compare their performance to traditional OCR/HTR systems: EasyOCR, Keras, Pytesseract, and TrOCR. Considering the tabular form of the data, two types of experiments are executed: one where the images are split line by line and the other where the entire scan is used as input. Based on CER and BLEU, we demonstrate that LLMs outperform the conventional OCR/HTR methods. Moreover, we also compare the evaluated CER and BLEU scores to human evaluations to better judge the outputs of whole-scan experiments and understand influential factors for CER and BLEU. Combining judgments from all the evaluation metrics, we conclude that two-shot GPT-4o for line-by-line images and two-shot Claude Sonnet 3.5 for whole-scan images yield the transcriptions of the historical records most similar to the ground truth.
Authors: Shahaf Pruss, Morris Alper, Hadar Averbuch-Elor
Abstract: Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their interactions. Current approaches use distinct methods tailored to sub-tasks such as Situation Recognition and detection of Human-Human and Human-Object Interactions. However, recent advances in image understanding have often leveraged web-scale vision-language (V&L) representations to obviate task-specific engineering. In this work, we propose a framework for dynamic scene understanding tasks by leveraging knowledge from modern, frozen V&L representations. By framing these tasks in a generic manner - as predicting and parsing structured text, or by directly concatenating representations to the input of existing models - we achieve state-of-the-art results while using a minimal number of trainable parameters relative to existing approaches. Moreover, our analysis of dynamic knowledge of these representations shows that recent, more powerful representations effectively encode dynamic scene semantics, making this approach newly possible.
Authors: M. Umar B. Niazi, John Cao, Matthieu Barreau, Karl Henrik Johansson
Abstract: This paper proposes a novel learning approach for designing Kazantzis-Kravaris/Luenberger (KKL) observers for autonomous nonlinear systems. The design of a KKL observer involves finding an injective map that transforms the system state into a higher-dimensional observer state, whose dynamics is linear and stable. The observer's state is then mapped back to the original system coordinates via the inverse map to obtain the state estimate. However, finding this transformation and its inverse is quite challenging. We propose to sequentially approximate these maps by neural networks that are trained using physics-informed learning. We generate synthetic data for training by numerically solving the system and observer dynamics. Theoretical guarantees for the robustness of state estimation against approximation error and system uncertainties are provided. Additionally, a systematic method for optimizing observer performance through parameter selection is presented. The effectiveness of the proposed approach is demonstrated through numerical simulations on benchmark examples and its application to sensor fault detection and isolation in a network of Kuramoto oscillators using learned KKL observers.
Authors: Gabriel Jaimes-Illanes, Manuel Parra-Royon, Laura Darriba-Pol, Javier Mold\'on, Amidou Sorgho, Susana S\'anchez-Exp\'osito, Juli\'an Garrido-S\'anchez, Lourdes Verdes-Montenegro
Abstract: Hydrogen, the most abundant element in the universe, is crucial for understanding galaxy formation and evolution. The 21 cm neutral atomic hydrogen - HI spectral line maps the gas kinematics within galaxies, providing key insights into interactions, galactic structure, and star formation processes. With new radio instruments, the volume and complexity of data is increasing. To analyze and classify integrated HI spectral profiles in a efficient way, this work presents a framework that integrates Machine Learning techniques, combining unsupervised methods and CNNs. To this end, we apply our framework to a selected subsample of 318 spectral HI profiles of the CIG and 30.780 profiles from the Arecibo Legacy Fast ALFA Survey catalogue. Data pre-processing involved the Busyfit package and iterative fitting with polynomial, Gaussian, and double-Lorentzian models. Clustering methods, including K-means, spectral clustering, DBSCAN, and agglomerative clustering, were used for feature extraction and to bootstrap classification we applied K-NN, SVM, and Random Forest classifiers, optimizing accuracy with CNN. Additionally, we introduced a 2D model of the profiles to enhance classification by adding dimensionality to the data. Three 2D models were generated based on transformations and normalised versions to quantify the level of asymmetry. These methods were tested in a previous analytical classification study conducted by the Analysis of the Interstellar Medium in Isolated Galaxies group. This approach enhances classification accuracy and aims to establish a methodology that could be applied to data analysis in future surveys conducted with the Square Kilometre Array (SKA), currently under construction. All materials, code, and models have been made publicly available in an open-access repository, adhering to FAIR principles.
Authors: Micha{\l} Derezi\'nski, Deanna Needell, Elizaveta Rebrova, Jiaming Yang
Abstract: Randomized Kaczmarz methods form a family of linear system solvers which converge by repeatedly projecting their iterates onto randomly sampled equations. While effective in some contexts, such as highly over-determined least squares, Kaczmarz methods are traditionally deemed secondary to Krylov subspace methods, since this latter family of solvers can exploit outliers in the input's singular value distribution to attain fast convergence on ill-conditioned systems. In this paper, we introduce Kaczmarz++, an accelerated randomized block Kaczmarz algorithm that exploits outlying singular values in the input to attain a fast Krylov-style convergence. Moreover, we show that Kaczmarz++ captures large outlying singular values provably faster than popular Krylov methods, for both over- and under-determined systems. We also develop an optimized variant for positive semidefinite systems, called CD++, demonstrating empirically that it is competitive in arithmetic operations with both CG and GMRES on a collection of benchmark problems. To attain these results, we introduce several novel algorithmic improvements to the Kaczmarz framework, including adaptive momentum acceleration, Tikhonov-regularized projections, and a memoization scheme for reusing information from previously sampled equation~blocks.
Authors: Maryam Ebrahimi, Rajeev Sahay, Seyyedali Hosseinalipour, Bita Akram
Abstract: Research has increasingly explored the application of artificial intelligence (AI) and machine learning (ML) within the mental health domain to enhance both patient care and healthcare provider efficiency. Given that mental health challenges frequently emerge during early adolescence -- the critical years of high school and college -- investigating AI/ML-driven mental health solutions within the education domain is of paramount importance. Nevertheless, conventional AI/ML techniques follow a centralized model training architecture, which poses privacy risks due to the need for transferring students' sensitive data from institutions, universities, and clinics to central servers. Federated learning (FL) has emerged as a solution to address these risks by enabling distributed model training while maintaining data privacy. Despite its potential, research on applying FL to analyze students' mental health remains limited. In this paper, we aim to address this limitation by proposing a roadmap for integrating FL into mental health data analysis within educational settings. We begin by providing an overview of mental health issues among students and reviewing existing studies where ML has been applied to address these challenges. Next, we examine broader applications of FL in the mental health domain to emphasize the lack of focus on educational contexts. Finally, we propose promising research directions focused on using FL to address mental health issues in the education sector, which entails discussing the synergies between the proposed directions with broader human-centered domains. By categorizing the proposed research directions into short- and long-term strategies and highlighting the unique challenges at each stage, we aim to encourage the development of privacy-conscious AI/ML-driven mental health solutions.
Authors: Jeff J. H. Kim, George R. Nahass, Yang Dai, Theja Tulabandhula
Abstract: Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality, with lung metastases being the most common site of distant spread and significantly worsening prognosis. Despite the growing availability of clinical and demographic data, predictive models for lung metastasis in HCC remain limited in scope and clinical applicability. In this study, we develop and validate an end-to-end machine learning pipeline using data from the Surveillance, Epidemiology, and End Results (SEER) database. We evaluated three machine learning models (Random Forest, XGBoost, and Logistic Regression) alongside a multilayer perceptron (MLP) neural network. Our models achieved high AUROC values and recall, with the Random Forest and MLP models demonstrating the best overall performance (AUROC = 0.82). However, the low precision across models highlights the challenges of accurately predicting positive cases. To address these limitations, we developed a custom loss function incorporating recall optimization, enabling the MLP model to achieve the highest sensitivity. An ensemble approach further improved overall recall by leveraging the strengths of individual models. Feature importance analysis revealed key predictors such as surgery status, tumor staging, and follow up duration, emphasizing the relevance of clinical interventions and disease progression in metastasis prediction. While this study demonstrates the potential of machine learning for identifying high-risk patients, limitations include reliance on imbalanced datasets, incomplete feature annotations, and the low precision of predictions. Future work should leverage the expanding SEER dataset, improve data imputation techniques, and explore advanced pre-trained models to enhance predictive accuracy and clinical utility.
Authors: Saeid Asgari Taghanaki, Joao Monteiro
Abstract: Large language models (LLMs) have demonstrated remarkable proficiency in generating detailed and coherent explanations of complex concepts. However, the extent to which these models truly comprehend the concepts they articulate remains unclear. To assess the level of comprehension of a model relative to the content it generates, we implemented a self-evaluation pipeline where models: (i) given a topic generate an excerpt with information about the topic, (ii) given an excerpt generate question-answer pairs, and finally (iii) given a question generate an answer. We refer to this self-evaluation approach as Explain-Query-Test (EQT). Interestingly, the accuracy on generated questions resulting from running the EQT pipeline correlates strongly with the model performance as verified by typical benchmarks such as MMLU-Pro. In other words, EQT's performance is predictive of MMLU-Pro's, and EQT can be used to rank models without the need for any external source of evaluation data other than lists of topics of interest. Moreover, our results reveal a disparity between the models' ability to produce detailed explanations and their performance on questions related to those explanations. This gap highlights fundamental limitations in the internal knowledge representation and reasoning abilities of current LLMs. We release the code at https://github.com/asgsaeid/EQT.
Authors: Krishnendu S. Tharakan, Hayssam Dahrouj, Nour Kouzayha, Hesham ElSawy, Tareq Y. Al-Naffouri
Abstract: Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper proposes a field of view (FoV) aware caching for mobile edge computing (MEC)-enabled wireless VR network. In particular, the FoV of each VR user is cached/prefetched at the base stations (BSs) based on the caching strategies tailored to each BS. Specifically, decentralized and personalized federated learning (DP-FL) based caching strategies with guarantees are presented. Considering VR systems composed of multiple VR devices and BSs, a DP-FL caching algorithm is implemented at each BS to personalize content delivery for VR users. The utilized DP-FL algorithm guarantees a probably approximately correct (PAC) bound on the conditional average cache hit. Further, to reduce the cost of communicating gradients, one-bit quantization of the stochastic gradient descent (OBSGD) is proposed, and a convergence guarantee of $\mathcal{O}(1/\sqrt{T})$ is obtained for the proposed algorithm, where $T$ is the number of iterations. Additionally, to better account for the wireless channel dynamics, the FoVs are grouped into multicast or unicast groups based on the number of requesting VR users. The performance of the proposed DP-FL algorithm is validated through realistic VR head-tracking dataset, and the proposed algorithm is shown to have better performance in terms of average delay and cache hit as compared to baseline algorithms.
Authors: Ron Raphaeli, Sean Man, Michael Elad
Abstract: Consistent improvement of image priors over the years has led to the development of better inverse problem solvers. Diffusion models are the newcomers to this arena, posing the strongest known prior to date. Recently, such models operating in a latent space have become increasingly predominant due to their efficiency. In recent works, these models have been applied to solve inverse problems. Working in the latent space typically requires multiple applications of an Autoencoder during the restoration process, which leads to both computational and restoration quality challenges. In this work, we propose a new approach for handling inverse problems with latent diffusion models, where a learned degradation function operates within the latent space, emulating a known image space degradation. Usage of the learned operator reduces the dependency on the Autoencoder to only the initial and final steps of the restoration process, facilitating faster sampling and superior restoration quality. We demonstrate the effectiveness of our method on a variety of image restoration tasks and datasets, achieving significant improvements over prior art.
Authors: Minia Manteiga, Ra\'ul Santove\~na, Marco A. \'Alvarez, Carlos Dafonte, Manuel G. Penedo, Silvana Navarro, Luis Corral
Abstract: A method based on Generative Adversaria! Networks (GANs) is developed for disentangling the physical (effective temperature and gravity) and chemical (metallicity, overabundance of a-elements with respect to iron) atmospheric properties in astronomical spectra. Using a projection of the stellar spectra, commonly called latent space, in which the contribution dueto one or several main stellar physicochemical properties is minimised while others are enhanced, it was possible to maximise the information related to certain properties, which can then be extracted using artificial neural networks (ANN) as regressors with higher accuracy than a reference method based on the use of ANN trained with the original spectra. Methods. Our model utilises autoencoders, comprising two artificial neural networks: an encoder anda decoder which transform input data into a low-dimensional representation known as latent space. It also uses discriminators, which are additional neural networks aimed at transforming the traditional autoencoder training into an adversaria! approach, to disentangle or reinforce the astrophysical parameters from the latent space. The GANDALF tool is described. It was developed to define, train, and test our GAN model with a web framework to show how the disentangling algorithm works visually. It is open to the community in Github. Results. The performance of our approach for retrieving atmospheric stellar properties from spectra is demonstrated using Gaia Radial Velocity Spectrograph (RVS) data from DR3. We use a data-driven perspective and obtain very competitive values, ali within the literature errors, and with the advantage of an important dimensionality reduction of the data to be processed.
Authors: Evgeniy Shin, Heinrich Matzinger
Abstract: Transformers architecture apply self-attention to tokens represented as vectors, before a fully connected (neuronal network) layer. These two parts can be layered many times. Traditionally, self-attention is seen as a mechanism for aggregating information before logical operations are performed by the fully connected layer. In this paper, we show, that quite counter-intuitively, the logical analysis can also be performed within the self-attention. For this we implement a handcrafted single-level encoder layer which performs the logical analysis within self-attention. We then study the scenario in which a one-level transformer model undergoes self-learning using gradient descent. We investigate whether the model utilizes fully connected layers or self-attention mechanisms for logical analysis when it has the choice. Given that gradient descent can become stuck at undesired zeros, we explicitly calculate these unwanted zeros and find ways to avoid them. We do all this in the context of predicting grammatical category pairs of adjacent tokens in a text. We believe that our findings have broader implications for understanding the potential logical operations performed by self-attention.
Authors: Katharine Fisher, Youssef Marzouk
Abstract: Bayesian inference promises a framework for principled uncertainty quantification of neural network predictions. Barriers to adoption include the difficulty of fully characterizing posterior distributions on network parameters and the interpretability of posterior predictive distributions. We demonstrate that under a discretized prior for the inner layer weights, we can exactly characterize the posterior predictive distribution as a Gaussian mixture. This setting allows us to define equivalence classes of network parameter values which produce the same likelihood (training error) and to relate the elements of these classes to the network's scaling regime -- defined via ratios of the training sample size, the size of each layer, and the number of final layer parameters. Of particular interest are distinct parameter realizations that map to low training error and yet correspond to distinct modes in the posterior predictive distribution. We identify settings that exhibit such predictive multimodality, and thus provide insight into the accuracy of unimodal posterior approximations. We also characterize the capacity of a model to "learn from data" by evaluating contraction of the posterior predictive in different scaling regimes.
Authors: Ali Naseh, Niloofar Mireshghallah
Abstract: Recent work shows membership inference attacks (MIAs) on large language models (LLMs) produce inconclusive results, partly due to difficulties in creating non-member datasets without temporal shifts. While researchers have turned to synthetic data as an alternative, we show this approach can be fundamentally misleading. Our experiments indicate that MIAs function as machine-generated text detectors, incorrectly identifying synthetic data as training samples regardless of the data source. This behavior persists across different model architectures and sizes, from open-source models to commercial ones such as GPT-3.5. Even synthetic text generated by different, potentially larger models is classified as training data by the target model. Our findings highlight a serious concern: using synthetic data in membership evaluations may lead to false conclusions about model memorization and data leakage. We caution that this issue could affect other evaluations using model signals such as loss where synthetic or machine-generated translated data substitutes for real-world samples.
Authors: Jonathan Gallagher, Yasaman Esfandiari, Callen MacPhee, Michael Warren
Abstract: This paper establishes a mathematically precise definition of dataset poisoning attack and proves that the very act of effectively poisoning a dataset ensures that the attack can be effectively detected. On top of a mathematical guarantee that dataset poisoning is identifiable by a new statistical test that we call the Conformal Separability Test, we provide experimental evidence that we can adequately detect poisoning attempts in the real world.
Authors: Riqiang Gao, Mamadou Diallo, Han Liu, Anthony Magliari, Jonathan Sackett, Wilko Verbakel, Sandra Meyers, Masoud Zarepisheh, Rafe Mcbeth, Simon Arberet, Martin Kraus, Florin C. Ghesu, Ali Kamen
Abstract: Radiotherapy (RT) planning is complex, subjective, and time-intensive. Advances in artificial intelligence (AI) promise to improve its precision, efficiency, and consistency, but progress is often limited by the scarcity of large, standardized datasets. To address this, we introduce the Automated Iterative RT Planning (AIRTP) system, a scalable solution for generating high-quality treatment plans. This scalable solution is designed to generate substantial volumes of consistently high-quality treatment plans, overcoming a key obstacle in the advancement of AI-driven RT planning. Our AIRTP pipeline adheres to clinical guidelines and automates essential steps, including organ-at-risk (OAR) contouring, helper structure creation, beam setup, optimization, and plan quality improvement, using AI integrated with RT planning software like Eclipse of Varian. Furthermore, a novel approach for determining optimization parameters to reproduce 3D dose distributions, i.e. a method to convert dose predictions to deliverable treatment plans constrained by machine limitations. A comparative analysis of plan quality reveals that our automated pipeline produces treatment plans of quality comparable to those generated manually, which traditionally require several hours of labor per plan. Committed to public research, the first data release of our AIRTP pipeline includes nine cohorts covering head-and-neck and lung cancer sites to support an AAPM 2025 challenge. This data set features more than 10 times the number of plans compared to the largest existing well-curated public data set to our best knowledge. Repo:{https://github.com/RiqiangGao/GDP-HMM_AAPMChallenge}
Authors: Saeid Ataei, Saeed Adibnazari, Seyyed Taghi Ataei
Abstract: Structural integrity is vital for maintaining the safety and longevity of concrete infrastructures such as bridges, tunnels, and walls. Traditional methods for detecting damages like cracks and spalls are labor-intensive, time-consuming, and prone to human error. To address these challenges, this study explores advanced data-driven techniques using deep learning for automated damage detection and analysis. Two state-of-the-art instance segmentation models, YOLO-v7 instance segmentation and Mask R-CNN, were evaluated using a dataset comprising 400 images, augmented to 10,995 images through geometric and color-based transformations to enhance robustness. The models were trained and validated using a dataset split into 90% training set, validation and test set 10%. Performance metrics such as precision, recall, mean average precision (mAP@0.5), and frames per second (FPS) were used for evaluation. YOLO-v7 achieved a superior mAP@0.5 of 96.1% and processed 40 FPS, outperforming Mask R-CNN, which achieved a mAP@0.5 of 92.1% with a slower processing speed of 18 FPS. The findings recommend YOLO-v7 instance segmentation model for real-time, high-speed structural health monitoring, while Mask R-CNN is better suited for detailed offline assessments. This study demonstrates the potential of deep learning to revolutionize infrastructure maintenance, offering a scalable and efficient solution for automated damage detection.
Authors: Mingze Ni, Yongshun Gong, Wei Liu
Abstract: Black-box textual adversarial attacks are challenging due to the lack of model information and the discrete, non-differentiable nature of text. Existing methods often lack versatility for attacking different models, suffer from limited attacking performance due to the inefficient optimization with word saliency ranking, and frequently sacrifice semantic integrity to achieve better attack outcomes. This paper introduces a novel approach to textual adversarial attacks, which we call Cross-Entropy Attacks (CEA), that uses Cross-Entropy optimization to address the above issues. Our CEA approach defines adversarial objectives for both soft-label and hard-label settings and employs CE optimization to identify optimal replacements. Through extensive experiments on document classification and language translation problems, we demonstrate that our attack method excels in terms of attacking performance, imperceptibility, and sentence quality.
Authors: Ali Zafari, Shirin Jalali
Abstract: Speckle noise is a fundamental challenge in coherent imaging systems, significantly degrading image quality. Over the past decades, numerous despeckling algorithms have been developed for applications such as Synthetic Aperture Radar (SAR) and digital holography. In this paper, we aim to establish a theoretically grounded approach to despeckling. We propose a method applicable to general structured stationary stochastic sources. We demonstrate the effectiveness of the proposed method on piecewise constant sources. Additionally, we theoretically derive a lower bound on the despeckling performance for such sources. The proposed depseckler applied to the 1-Markov structured sources achieves better reconstruction performance with no strong simplification of the ground truth signal model or speckle noise.
Authors: Xiaowei Jiang, Wenhao Ma, Yiqun Duan, Thomas Do, Chin-Teng Lin
Abstract: In the realm of digital forensics and document authentication, writer identification plays a crucial role in determining the authors of documents based on handwriting styles. The primary challenge in writer-id is the "open-set scenario", where the goal is accurately recognizing writers unseen during the model training. To overcome this challenge, representation learning is the key. This method can capture unique handwriting features, enabling it to recognize styles not previously encountered during training. Building on this concept, this paper introduces the Contrastive Masked Auto-Encoders (CMAE) for Character-level Open-Set Writer Identification. We merge Masked Auto-Encoders (MAE) with Contrastive Learning (CL) to simultaneously and respectively capture sequential information and distinguish diverse handwriting styles. Demonstrating its effectiveness, our model achieves state-of-the-art (SOTA) results on the CASIA online handwriting dataset, reaching an impressive precision rate of 89.7%. Our study advances universal writer-id with a sophisticated representation learning approach, contributing substantially to the ever-evolving landscape of digital handwriting analysis, and catering to the demands of an increasingly interconnected world.
Authors: Le Thien Phuc Nguyen, Zhuoran Yu, Yong Jae Lee
Abstract: Active Speaker Detection (ASD) aims to identify speaking individuals in complex visual scenes. While humans can easily detect speech by matching lip movements to audio, current ASD models struggle to establish this correspondence, often misclassifying non-speaking instances when audio and lip movements are unsynchronized. To address this limitation, we propose Lip landmark Assisted Speaker dEtection for Robustness (LASER). Unlike models that rely solely on facial frames, LASER explicitly focuses on lip movements by integrating lip landmarks in training. Specifically, given a face track, LASER extracts frame-level visual features and the 2D coordinates of lip landmarks using a lightweight detector. These coordinates are encoded into dense feature maps, providing spatial and structural information on lip positions. Recognizing that landmark detectors may sometimes fail under challenging conditions (e.g., low resolution, occlusions, extreme angles), we incorporate an auxiliary consistency loss to align predictions from both lip-aware and face-only features, ensuring reliable performance even when lip data is absent. Extensive experiments across multiple datasets show that LASER outperforms state-of-the-art models, especially in scenarios with desynchronized audio and visuals, demonstrating robust performance in real-world video contexts. Code is available at \url{https://github.com/plnguyen2908/LASER_ASD}.
Authors: Jiazheng Chen, Wanchun Liu
Abstract: Goal-oriented communications prioritize application-driven objectives over data accuracy, enabling intelligent next-generation wireless systems. Efficient scheduling in multi-device, multi-channel systems poses significant challenges due to high-dimensional state and action spaces. We address these challenges by deriving key structural properties of the optimal solution to the goal-oriented scheduling problem, incorporating Age of Information (AoI) and channel states. Specifically, we establish the monotonicity of the optimal state value function (a measure of long-term system performance) w.r.t. channel states and prove its asymptotic convexity w.r.t. AoI states. Additionally, we derive the monotonicity of the optimal policy w.r.t. channel states, advancing the theoretical framework for optimal scheduling. Leveraging these insights, we propose the structure-guided unified dual on-off policy DRL (SUDO-DRL), a hybrid algorithm that combines the stability of on-policy training with the sample efficiency of off-policy methods. Through a novel structural property evaluation framework, SUDO-DRL enables effective and scalable training, addressing the complexities of large-scale systems. Numerical results show SUDO-DRL improves system performance by up to 45% and reduces convergence time by 40% compared to state-of-the-art methods. It also effectively handles scheduling in much larger systems, where off-policy DRL fails and on-policy benchmarks exhibit significant performance loss, demonstrating its scalability and efficacy in goal-oriented communications.
Authors: Vicky Feliren, Fithrothul Khikmah, Irfan Dwiki Bhaswara, Bahrul I. Nasution, Alex M. Lechner, Muhamad Risqi U. Saputra
Abstract: In recent years, the integration of deep learning techniques with remote sensing technology has revolutionized the way natural hazards, such as floods, are monitored and managed. However, existing methods for flood segmentation using remote sensing data often overlook the utility of correlative features among multispectral satellite information. In this study, we introduce a progressive cross attention network (ProCANet), a deep learning model that progressively applies both self- and cross-attention mechanisms to multispectral features, generating optimal feature combinations for flood segmentation. The proposed model was compared with state-of-the-art approaches using Sen1Floods11 dataset and our bespoke flood data generated for the Citarum River basin, Indonesia. Our model demonstrated superior performance with the highest Intersection over Union (IoU) score of 0.815. Our results in this study, coupled with the ablation assessment comparing scenarios with and without attention across various modalities, opens a promising path for enhancing the accuracy of flood analysis using remote sensing technology.
Authors: Jie Zhao, Kang Hao Cheong, Witold Pedrycz
Abstract: Graph-structured combinatorial challenges are inherently difficult due to their nonlinear and intricate nature, often rendering traditional computational methods ineffective or expensive. However, these challenges can be more naturally tackled by humans through visual representations that harness our innate ability for spatial reasoning. In this study, we propose transforming graphs into images to preserve their higher-order structural features accurately, revolutionizing the representation used in solving graph-structured combinatorial tasks. This approach allows machines to emulate human-like processing in addressing complex combinatorial challenges. By combining the innovative paradigm powered by multimodal large language models (MLLMs) with simple search techniques, we aim to develop a novel and effective framework for tackling such problems. Our investigation into MLLMs spanned a variety of graph-based tasks, from combinatorial problems like influence maximization to sequential decision-making in network dismantling, as well as addressing six fundamental graph-related issues. Our findings demonstrate that MLLMs exhibit exceptional spatial intelligence and a distinctive capability for handling these problems, significantly advancing the potential for machines to comprehend and analyze graph-structured data with a depth and intuition akin to human cognition. These results also imply that integrating MLLMs with simple optimization strategies could form a novel and efficient approach for navigating graph-structured combinatorial challenges without complex derivations, computationally demanding training and fine-tuning.
Authors: Titouan Vayer (OCKHAM), Etienne Lasalle (OCKHAM)
Abstract: This note aims to demonstrate that performing maximum-likelihood estimation for a mixture model is equivalent to minimizing over the parameters an optimal transport problem with entropic regularization. The objective is pedagogical: we seek to present this already known result in a concise and hopefully simple manner. We give an illustration with Gaussian mixture models by showing that the standard EM algorithm is a specific block-coordinate descent on an optimal transport loss.
Authors: Samantha Min Er Yew, Xiaofeng Lei, Jocelyn Hui Lin Goh, Yibing Chen, Sahana Srinivasan, Miao-li Chee, Krithi Pushpanathan, Ke Zou, Qingshan Hou, Zhi Da Soh, Cancan Xue, Marco Chak Yan Yu, Charumathi Sabanayagam, E Shyong Tai, Xueling Sim, Yaxing Wang, Jost B. Jonas, Vinay Nangia, Gabriel Dawei Yang, Emma Anran Ran, Carol Yim-Lui Cheung, Yangqin Feng, Jun Zhou, Rick Siow Mong Goh, Yukun Zhou, Pearse A. Keane, Yong Liu, Ching-Yu Cheng, Yih-Chung Tham
Abstract: Background: RETFound, a self-supervised, retina-specific foundation model (FM), showed potential in downstream applications. However, its comparative performance with traditional deep learning (DL) models remains incompletely understood. This study aimed to evaluate RETFound against three ImageNet-pretrained supervised DL models (ResNet50, ViT-base, SwinV2) in detecting ocular and systemic diseases. Methods: We fine-tuned/trained RETFound and three DL models on full datasets, 50%, 20%, and fixed sample sizes (400, 200, 100 images, with half comprising disease cases; for each DR severity class, 100 and 50 cases were used. Fine-tuned models were tested internally using the SEED (53,090 images) and APTOS-2019 (3,672 images) datasets and externally validated on population-based (BES, CIEMS, SP2, UKBB) and open-source datasets (ODIR-5k, PAPILA, GAMMA, IDRiD, MESSIDOR-2). Model performance was compared using area under the receiver operating characteristic curve (AUC) and Z-tests with Bonferroni correction (P<0.05/3). Interpretation: Traditional DL models are mostly comparable to RETFound for ocular disease detection with large datasets. However, RETFound is superior in systemic disease detection with smaller datasets. These findings offer valuable insights into the respective merits and limitation of traditional models and FMs.
Authors: Yu Zhu, Wenqi Jiang, Gustavo Alonso
Abstract: Keeping ML-based recommender models up-to-date as data drifts and evolves is essential to maintain accuracy. As a result, online data preprocessing plays an increasingly important role in serving recommender systems. Existing solutions employ multiple CPU workers to saturate the input bandwidth of a single training node. Such an approach results in high deployment costs and energy consumption. For instance, a recent report from industrial deployments shows that data storage and ingestion pipelines can account for over 60\% of the power consumption in a recommender system. In this paper, we tackle the issue from a hardware perspective by introducing Piper, a flexible and network-attached accelerator that executes data loading and preprocessing pipelines in a streaming fashion. As part of the design, we define MiniPipe, the smallest pipeline unit enabling multi-pipeline implementation by executing various data preprocessing tasks across the single board, giving Piper the ability to be reconfigured at runtime. Our results, using publicly released commercial pipelines, show that Piper, prototyped on a power-efficient FPGA, achieves a 39$\sim$105$\times$ speedup over a server-grade, 128-core CPU and 3$\sim$17$\times$ speedup over GPUs like RTX 3090 and A100 in multiple pipelines. The experimental analysis demonstrates that Piper provides advantages in both latency and energy efficiency for preprocessing tasks in recommender systems, providing an alternative design point for systems that today are in very high demand.
Authors: MD Mehraz Hosen, Md. Hasibul Islam
Abstract: Tomato crop health plays a critical role in ensuring agricultural productivity and food security. Timely and accurate detection of diseases affecting tomato plants is vital for effective disease management. In this study, we propose a deep learning-based approach for Tomato Leaf Disease Detection using two well-established convolutional neural networks (CNNs), namely VGG19 and Inception v3. The experiment is conducted on the Tomato Villages Dataset, encompassing images of both healthy tomato leaves and leaves afflicted by various diseases. The VGG19 model is augmented with fully connected layers, while the Inception v3 model is modified to incorporate a global average pooling layer and a dense classification layer. Both models are trained on the prepared dataset, and their performances are evaluated on a separate test set. This research employs VGG19 and Inception v3 models on the Tomato Villages dataset (4525 images) for tomato leaf disease detection. The models' accuracy of 93.93% with dropout layers demonstrates their usefulness for crop health monitoring. The paper suggests a deep learning-based strategy that includes normalization, resizing, dataset preparation, and unique model architectures. During training, VGG19 and Inception v3 serve as feature extractors, with possible data augmentation and fine-tuning. Metrics like accuracy, precision, recall, and F1 score are obtained through evaluation on a test set and offer important insights into the strengths and shortcomings of the model. The method has the potential for practical use in precision agriculture and could help tomato crops prevent illness early on.
Authors: Ravi Kant Gupta, Shounak Das, Ardhendu Sekhar, Amit Sethi
Abstract: Whole slide images (WSIs) are high-resolution, gigapixel sized images that pose significant computational challenges for traditional machine learning models due to their size and heterogeneity.In this paper, we present a scalable and efficient methodology for WSI classification by leveraging patch-based feature extraction, clustering, and Fisher vector encoding. Initially, WSIs are divided into fixed size patches, and deep feature embeddings are extracted from each patch using a pre-trained convolutional neural network (CNN). These patch-level embeddings are subsequently clustered using K-means clustering, where each cluster aggregates semantically similar regions of the WSI. To effectively summarize each cluster, Fisher vector representations are computed by modeling the distribution of patch embeddings in each cluster as a parametric Gaussian mixture model (GMM). The Fisher vectors from each cluster are concatenated into a high-dimensional feature vector, creating a compact and informative representation of the entire WSI. This feature vector is then used by a classifier to predict the WSI's diagnostic label. Our method captures local and global tissue structures and yields robust performance for large-scale WSI classification, demonstrating superior accuracy and scalability compared to other approaches.
Authors: Sean Man, Guy Ohayon, Ron Raphaeli, Michael Elad
Abstract: Real-world image restoration deals with the recovery of images suffering from an unknown degradation. This task is typically addressed while being given only degraded images, without their corresponding ground-truth versions. In this hard setting, designing and evaluating restoration algorithms becomes highly challenging. This paper offers a suite of tools that can serve both the design and assessment of real-world image restoration algorithms. Our work starts by proposing a trained model that predicts the chain of degradations a given real-world measured input has gone through. We show how this estimator can be used to approximate the consistency -- the match between the measurements and any proposed recovered image. We also use this estimator as a guiding force for the design of a simple and highly-effective plug-and-play real-world image restoration algorithm, leveraging a pre-trained diffusion-based image prior. Furthermore, this work proposes no-reference proxy measures of MSE and LPIPS, which, without access to the ground-truth images, allow ranking of real-world image restoration algorithms according to their (approximate) MSE and LPIPS. The proposed suite provides a versatile, first of its kind framework for evaluating and comparing blind image restoration algorithms in real-world scenarios.
Authors: Yun-Peng Li, Hans-Andrea Loeliger
Abstract: Normals with unknown parameters (NUP) can be used to convert nontrivial model-based estimation problems into iterations of linear least-squares or Gaussian estimation problems. In this paper, we extend this approach by augmenting factor graphs with convex-dual variables and pertinent NUP representations. In particular, in a state space setting, we propose a new iterative forward-backward algorithm that is dual to a recently proposed backward-forward algorithm.
Authors: Christian Lubich, J\"org Nick
Abstract: Evolutionary deep neural networks have emerged as a rapidly growing field of research. This paper studies numerical integrators for such and other classes of nonlinear parametrizations $ u(t) = \Phi(\theta(t)) $, where the evolving parameters $\theta(t)$ are to be computed. The primary focus is on tackling the challenges posed by the combination of stiff evolution problems and irregular parametrizations, which typically arise with neural networks, tensor networks, flocks of evolving Gaussians, and in further cases of overparametrization. We propose and analyse regularized parametric versions of the implicit Euler method and higher-order implicit Runge--Kutta methods for the time integration of the parameters in nonlinear approximations to evolutionary partial differential equations and large systems of stiff ordinary differential equations. At each time step, an ill-conditioned nonlinear optimization problem is solved approximately with a few regularized Gauss--Newton iterations. Error bounds for the resulting parametric integrator are derived by relating the computationally accessible Gauss--Newton iteration for the parameters to the computationally inaccessible Newton iteration for the underlying non-parametric time integration scheme. The theoretical findings are supported by numerical experiments that are designed to show key properties of the proposed parametric integrators.
Authors: Zikai Yin, Hamid Gadirov, Jiri Kosinka, Steffen Frey
Abstract: We present ENTIRE, a novel approach for volume rendering time prediction. Time-dependent volume data from simulations or experiments typically comprise complex deforming structures across hundreds or thousands of time steps, which in addition to the camera configuration has a significant impact on rendering performance. We first extract a feature vector from a volume that captures its structure that is relevant for rendering time performance. Then we combine this feature vector with further relevant parameters (e.g. camera setup), and with this perform the final prediction. Our experiments conducted on various datasets demonstrate that our model is capable of efficiently achieving high prediction accuracy with fast response rates. We showcase ENTIRE's capability of enabling dynamic parameter adaptation for stable frame rates and load balancing in two case studies.
Authors: Qirun Dai, Dylan Zhang, Jiaqi W. Ma, Hao Peng
Abstract: Selecting appropriate training data is crucial for effective instruction fine-tuning of large language models (LLMs), which aims to (1) elicit strong capabilities, and (2) achieve balanced performance across a diverse range of tasks. Influence-based methods show promise in achieving (1) by estimating the contribution of each training example to the model's predictions, but often struggle with (2). Our systematic investigation reveals that this underperformance can be attributed to an inherent bias where certain tasks intrinsically have greater influence than others. As a result, data selection is often biased towards these tasks, not only hurting the model's performance on others but also, counterintuitively, harms performance on these high-influence tasks themselves. As a remedy, we propose BIDS, a Balanced and Influential Data Selection algorithm. BIDS first normalizes influence scores of the training data, and then iteratively balances data selection by choosing the training example with the highest influence on the most underrepresented task. Experiments with both Llama-3 and Mistral-v0.3 on seven benchmarks spanning five diverse capabilities show that BIDS consistently outperforms both state-of-the-art influence-based algorithms and other non-influence-based selection frameworks. Surprisingly, training on a 15% subset selected by BIDS can even outperform full-dataset training with a much more balanced performance. Our analysis further highlights the importance of both instance-level normalization and iterative optimization of selected data for balanced learning of diverse capabilities.
Authors: Zikun Li, Zhuofu Chen, Remi Delacourt, Gabriele Oliaro, Zeyu Wang, Qinghan Chen, Shuhuai Lin, April Yang, Zhihao Zhang, Zhuoming Chen, Sean Lai, Xupeng Miao, Zhihao Jia
Abstract: This paper introduces AdaServe, the first LLM serving system to support SLO customization through fine-grained speculative decoding. AdaServe leverages the logits of a draft model to predict the speculative accuracy of tokens and employs a theoretically optimal algorithm to construct token trees for verification. To accommodate diverse SLO requirements without compromising throughput, AdaServe employs a speculation-and-selection scheme that first constructs candidate token trees for each request and then dynamically selects tokens to meet individual SLO constraints while optimizing throughput. Comprehensive evaluations demonstrate that AdaServe achieves up to 73% higher SLO attainment and 74% higher goodput compared to state-of-the-art systems. These results underscore AdaServe's potential to enhance the efficiency and adaptability of LLM deployments across varied application scenarios.
Authors: Jiaxing Qi, Chang Zeng, Zhongzhi Luan, Shaohan Huang, Shu Yang, Yao Lu, Hailong Yang, Depei Qian
Abstract: Detecting anomalies in discrete event logs is critical for ensuring system reliability, security, and efficiency. Traditional window-based methods for log anomaly detection often suffer from context bias and fuzzy localization, which hinder their ability to precisely and efficiently identify anomalies. To address these challenges, we propose a graph-centric framework, TempoLog, which leverages multi-scale temporal graph networks for discrete log anomaly detection. Unlike conventional methods, TempoLog constructs continuous-time dynamic graphs directly from event logs, eliminating the need for fixed-size window grouping. By representing log templates as nodes and their temporal relationships as edges, the framework dynamically captures both local and global dependencies across multiple temporal scales. Additionally, a semantic-aware model enhances detection by incorporating rich contextual information. Extensive experiments on public datasets demonstrate that our method achieves state-of-the-art performance in event-level anomaly detection, significantly outperforming existing approaches in both accuracy and efficiency.
Authors: Leon Bungert, Franca Hoffmann, Doh Yeon Kim, Tim Roith
Abstract: In this work we propose MirrorCBO, a consensus-based optimization (CBO) method which generalizes standard CBO in the same way that mirror descent generalizes gradient descent. For this we apply the CBO methodology to a swarm of dual particles and retain the primal particle positions by applying the inverse of the mirror map, which we parametrize as the subdifferential of a strongly convex function $\phi$. In this way, we combine the advantages of a derivative-free non-convex optimization algorithm with those of mirror descent. As a special case, the method extends CBO to optimization problems with convex constraints. Assuming bounds on the Bregman distance associated to $\phi$, we provide asymptotic convergence results for MirrorCBO with explicit exponential rate. Another key contribution is an exploratory numerical study of this new algorithm across different application settings, focusing on (i) sparsity-inducing optimization, and (ii) constrained optimization, demonstrating the competitive performance of MirrorCBO. We observe empirically that the method can also be used for optimization on (non-convex) submanifolds of Euclidean space, can be adapted to mirrored versions of other recent CBO variants, and that it inherits from mirror descent the capability to select desirable minimizers, like sparse ones. We also include an overview of recent CBO approaches for constrained optimization and compare their performance to MirrorCBO.
Authors: Geonwoo Seo (Dongguk University)
Abstract: Wakeword detection plays a critical role in enabling AI assistants to listen to user voices and interact effectively. However, for languages other than English, there is a significant lack of pre-trained wakeword models. Additionally, systems that merely determine the presence of a wakeword can pose serious privacy concerns. In this paper, we propose an end-to-end approach that trains wakewords for Non-English languages, particulary Korean, and uses this to develop a Voice Authentication model to protect user privacy. Our implementation employs an open-source platform OpenWakeWord, which performs wakeword detection using an FCN (Fully-Connected Network) architecture. Once a wakeword is detected, our custom-developed code calculates cosine similarity for robust user authentication. Experimental results demonstrate the effectiveness of our approach, achieving a 16.79% and a 6.6% Equal Error Rate (EER) each in the Wakeword Detection and the Voice Authentication. These findings highlight the model's potential in providing secure and accurate wakeword detection and authentication for Korean users.
Authors: Xiaoyu Wang, Mikolaj J. Kasprzak, Jeffrey Negrea, Solesne Bourguin, Jonathan H. Huggins
Abstract: Stochastic iterative algorithms, including stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD), are widely utilized for optimization and sampling in large-scale and high-dimensional problems in machine learning, statistics, and engineering. Numerous works have bounded the parameter error in, and characterized the uncertainty of, these approximations. One common approach has been to use scaling limit analyses to relate the distribution of algorithm sample paths to a continuous-time stochastic process approximation, particularly in asymptotic setups. Focusing on the univariate setting, in this paper, we build on previous work to derive non-asymptotic functional approximation error bounds between the algorithm sample paths and the Ornstein-Uhlenbeck approximation using an infinite-dimensional version of Stein's method of exchangeable pairs. We show that this bound implies weak convergence under modest additional assumptions and leads to a bound on the error of the variance of the iterate averages of the algorithm. Furthermore, we use our main result to construct error bounds in terms of two common metrics: the L\'{e}vy-Prokhorov and bounded Wasserstein distances. Our results provide a foundation for developing similar error bounds for the multivariate setting and for more sophisticated stochastic approximation algorithms.
Authors: Mst. Mumtahina Labonno, D. M. Asadujjaman, Md. Mahfujur Rahman, Abdullah Tamim, Mst. Jannatul Ferdous, Rafi Muttaki Mahi
Abstract: Breast cancer is one of the deadliest cancers causing about massive number of patients to die annually all over the world according to the WHO. It is a kind of cancer that develops when the tissues of the breast grow rapidly and unboundly. This fatality rate can be prevented if the cancer is detected before it gets malignant. Using automation for early-age detection of breast cancer, Artificial Intelligence and Machine Learning technologies can be implemented for the best outcome. In this study, we are using the Breast Cancer Image Classification dataset collected from the Kaggle depository, which comprises 9248 Breast Ultrasound Images and is classified into three categories: Benign, Malignant, and Normal which refers to non-cancerous, cancerous, and normal images.This research introduces three pretrained model featuring custom classifiers that includes ResNet50, MobileNet, and VGG16, along with a custom CNN model utilizing the ReLU activation function.The models ResNet50, MobileNet, VGG16, and a custom CNN recorded accuracies of 98.41%, 97.91%, 98.19%, and 92.94% on the dataset, correspondingly, with ResNet50 achieving the highest accuracy of 98.41%.This model, with its deep and powerful architecture, is particularly successful in detecting aberrant cells as well as cancerous or non-cancerous tumors. These accuracies show that the Machine Learning methods are more compatible for the classification and early detection of breast cancer.
Authors: Vito Cerone, Sophie M. Fosson, Diego Regruto
Abstract: The need for fast sparse optimization is emerging, e.g., to deal with large-dimensional data-driven problems and to track time-varying systems. In the framework of linear sparse optimization, the iterative shrinkage-thresholding algorithm is a valuable method to solve Lasso, which is particularly appreciated for its ease of implementation. Nevertheless, it converges slowly. In this paper, we develop a proximal method, based on logarithmic regularization, which turns out to be an iterative shrinkage-thresholding algorithm with adaptive shrinkage hyperparameter. This adaptivity substantially enhances the trajectory of the algorithm, in a way that yields faster convergence, while keeping the simplicity of the original method. Our contribution is twofold: on the one hand, we derive and analyze the proposed algorithm; on the other hand, we validate its fast convergence via numerical experiments and we discuss the performance with respect to state-of-the-art algorithms.
Authors: Yanlai Yang, Mengye Ren
Abstract: Self-supervised learning holds the promise to learn good representations from real-world continuous uncurated data streams. However, most existing works in visual self-supervised learning focus on static images or artificial data streams. Towards exploring a more realistic learning substrate, we investigate streaming self-supervised learning from long-form real-world egocentric video streams. Inspired by the event segmentation mechanism in human perception and memory, we propose "Memory Storyboard" that groups recent past frames into temporal segments for more effective summarization of the past visual streams for memory replay. To accommodate efficient temporal segmentation, we propose a two-tier memory hierarchy: the recent past is stored in a short-term memory, and the storyboard temporal segments are then transferred to a long-term memory. Experiments on real-world egocentric video datasets including SAYCam and KrishnaCam show that contrastive learning objectives on top of storyboard frames result in semantically meaningful representations which outperform those produced by state-of-the-art unsupervised continual learning methods.
Authors: Erik Arakelyan, Karen Hambardzumyan, Davit Papikyan, Pasquale Minervini, Albert Gordo, Isabelle Augenstein, Aram H. Markosyan
Abstract: Advances in self-supervised learning (SSL) for machine vision have improved representation robustness and model performance, giving rise to pre-trained backbones like \emph{ResNet} and \emph{ViT} models tuned with SSL methods such as \emph{SimCLR}. Due to the computational and data demands of pre-training, the utilization of such backbones becomes a strenuous necessity. However, employing these backbones may inherit vulnerabilities to adversarial attacks. While adversarial robustness has been studied under \emph{white-box} and \emph{black-box} settings, the robustness of models tuned on pre-trained backbones remains largely unexplored. Additionally, the role of tuning meta-information in mitigating exploitation risks is unclear. This work systematically evaluates the adversarial robustness of such models across $20,000$ combinations of tuning meta-information, including fine-tuning techniques, backbone families, datasets, and attack types. We propose using proxy models to transfer attacks, simulating varying levels of target knowledge by fine-tuning these proxies with diverse configurations. Our findings reveal that proxy-based attacks approach the effectiveness of \emph{white-box} methods, even with minimal tuning knowledge. We also introduce a naive "backbone attack," leveraging only the backbone to generate adversarial samples, which outperforms \emph{black-box} attacks and rivals \emph{white-box} methods, highlighting critical risks in model-sharing practices. Finally, our ablations reveal how increasing tuning meta-information impacts attack transferability, measuring each meta-information combination.
Authors: Sebastian Salwig, Till Kahlke, Florian Hirschberger, Dennis Forster, J\"org L\"ucke
Abstract: Gaussian Mixture Models (GMMs) range among the most frequently used machine learning models. However, training large, general GMMs becomes computationally prohibitive for datasets with many data points $N$ of high-dimensionality $D$. For GMMs with arbitrary covariances, we here derive a highly efficient variational approximation, which is integrated with mixtures of factor analyzers (MFAs). For GMMs with $C$ components, our proposed algorithm significantly reduces runtime complexity per iteration from $\mathcal{O}(NCD^2)$ to a complexity scaling linearly with $D$ and remaining constant w.r.t. $C$. Numerical validation of this theoretical complexity reduction then shows the following: the distance evaluations required for the entire GMM optimization process scale sublinearly with $NC$. On large-scale benchmarks, this sublinearity results in speed-ups of an order-of-magnitude compared to the state-of-the-art. As a proof of concept, we train GMMs with over 10 billion parameters on about 100 million images, and observe training times of approximately nine hours on a single state-of-the-art CPU.
Authors: Xueqiong Yuan, Jipeng Li, Ercan Engin Kuruoglu
Abstract: Model uncertainty quantification involves measuring and evaluating the uncertainty linked to a model's predictions, helping assess their reliability and confidence. Noise injection is a technique used to enhance the robustness of neural networks by introducing randomness. In this paper, we establish a connection between noise injection and uncertainty quantification from a Bayesian standpoint. We theoretically demonstrate that injecting noise into the weights of a neural network is equivalent to Bayesian inference on a deep Gaussian process. Consequently, we introduce a Monte Carlo Noise Injection (MCNI) method, which involves injecting noise into the parameters during training and performing multiple forward propagations during inference to estimate the uncertainty of the prediction. Through simulation and experiments on regression and classification tasks, our method demonstrates superior performance compared to the baseline model.
Authors: Haotian Zhang, Dong Liu
Abstract: Lossy image coding is the art of computing that is principally bounded by the image's rate-distortion function. This bound, though never accurately characterized, has been approached practically via deep learning technologies in recent years. Indeed, learned image coding schemes allow direct optimization of the joint rate-distortion cost, thereby outperforming the handcrafted image coding schemes by a large margin. Still, it is observed that there is room for further improvement in the rate-distortion performance of learned image coding. In this article, we identify the gap between the ideal rate-distortion function forecasted by Shannon's information theory and the empirical rate-distortion function achieved by the state-of-the-art learned image coding schemes, revealing that the gap is incurred by five different effects: modeling effect, approximation effect, amortization effect, digitization effect, and asymptotic effect. We design simulations and experiments to quantitively evaluate the last three effects, which demonstrates the high potential of future lossy image coding technologies.
Authors: Mohamed Harmanani, Amoon Jamzad, Minh Nguyen Nhat To, Paul F. R. Wilson, Zhuoxin Guo, Fahimeh Fooladgar, Samira Sojoudi, Mahdi Gilany, Silvia Chang, Peter Black, Michael Leveridge, Robert Siemens, Purang Abolmaesumi, Parvin Mousavi
Abstract: Prostate cancer (PCa) detection using deep learning (DL) models has shown potential for enhancing real-time guidance during biopsies. However, prostate ultrasound images lack pixel-level cancer annotations, introducing label noise. Current approaches often focus on limited regions of interest (ROIs), disregarding anatomical context necessary for accurate diagnosis. Foundation models can overcome this limitation by analyzing entire images to capture global spatial relationships; however, they still encounter challenges stemming from the weak labels associated with coarse pathology annotations in ultrasound data. We introduce Cinepro, a novel framework that strengthens foundation models' ability to localize PCa in ultrasound cineloops. Cinepro adapts robust training by integrating the proportion of cancer tissue reported by pathology in a biopsy core into its loss function to address label noise, providing a more nuanced supervision. Additionally, it leverages temporal data across multiple frames to apply robust augmentations, enhancing the model's ability to learn stable cancer-related features. Cinepro demonstrates superior performance on a multi-center prostate ultrasound dataset, achieving an AUROC of 77.1% and a balanced accuracy of 83.8%, surpassing current benchmarks. These findings underscore Cinepro's promise in advancing foundation models for weakly labeled ultrasound data.
Authors: Thomas Walshe, Sae Young Moon, Chunyang Xiao, Yawwani Gunawardana, Fran Silavong
Abstract: Acquiring labelled training data remains a costly task in real world machine learning projects to meet quantity and quality requirements. Recently Large Language Models (LLMs), notably GPT-4, have shown great promises in labelling data with high accuracy. However, privacy and cost concerns prevent the ubiquitous use of GPT-4. In this work, we explore effectively leveraging open-source models for automatic labelling. We identify integrating label schema as a promising technology but found that naively using the label description for classification leads to poor performance on high cardinality tasks. To address this, we propose Retrieval Augmented Classification (RAC) for which LLM performs inferences for one label at a time using corresponding label schema; we start with the most related label and iterates until a label is chosen by the LLM. We show that our method, which dynamically integrates label description, leads to performance improvements in labelling tasks. We further show that by focusing only on the most promising labels, RAC can trade off between label quality and coverage - a property we leverage to automatically label our internal datasets.
Authors: Theshani Nuradha, Vishal Singh, Mark M. Wilde
Abstract: The hockey-stick divergence is a fundamental quantity characterizing several statistical privacy frameworks that ensure privacy for classical and quantum data. In such quantum privacy frameworks, the adversary is allowed to perform all possible measurements. However, in practice, there are typically limitations to the set of measurements that can be performed. To this end, here, we comprehensively analyze the measured hockey-stick divergence under several classes of practically relevant measurement classes. We prove several of its properties, including data processing and convexity. We show that it is efficiently computable by semi-definite programming for some classes of measurements and can be analytically evaluated for Werner and isotropic states. Notably, we show that the measured hockey-stick divergence characterizes optimal privacy parameters in the quantum pufferfish privacy framework. With this connection and the developed technical tools, we enable methods to quantify and audit privacy for several practically relevant settings. Lastly, we introduce the measured hockey-stick divergence of channels and explore its applications in ensuring privacy for channels.
Authors: Darin Tsui, Kunal Talreja, Amirali Aghazadeh
Abstract: Computing the Fourier transform of a $q$-ary function $f:\mathbb{Z}_{q}^n\rightarrow \mathbb{R}$, which maps $q$-ary sequences to real numbers, is an important problem in mathematics with wide-ranging applications in biology, signal processing, and machine learning. Previous studies have shown that, under the sparsity assumption, the Fourier transform can be computed efficiently using fast and sample-efficient algorithms. However, in many practical settings, the function is defined over a more general space -- the space of generalized $q$-ary sequences $\mathbb{Z}_{q_1} \times \mathbb{Z}_{q_2} \times \cdots \times \mathbb{Z}_{q_n}$ -- where each $\mathbb{Z}_{q_i}$ corresponds to integers modulo $q_i$. A naive approach involves setting $q=\max_i{q_i}$ and treating the function as $q$-ary, which results in heavy computational overheads. Herein, we develop GFast, an algorithm that computes the $S$-sparse Fourier transform of $f$ with a sample complexity of $O(Sn)$, computational complexity of $O(Sn \log N)$, and a failure probability that approaches zero as $N=\prod_{i=1}^n q_i \rightarrow \infty$ with $S = N^\delta$ for some $0 \leq \delta < 1$. In the presence of noise, we further demonstrate that a robust version of GFast computes the transform with a sample complexity of $O(Sn^2)$ and computational complexity of $O(Sn^2 \log N)$ under the same high probability guarantees. Using large-scale synthetic experiments, we demonstrate that GFast computes the sparse Fourier transform of generalized $q$-ary functions using $16\times$ fewer samples and running $8\times$ faster than existing algorithms. In real-world protein fitness datasets, GFast explains the predictive interactions of a neural network with $>25\%$ smaller normalized mean-squared error compared to existing algorithms.
Authors: Hongjun Wang, Wonmin Byeon, Jiarui Xu, Jinwei Gu, Ka Chun Cheung, Xiaolong Wang, Kai Han, Jan Kautz, Sifei Liu
Abstract: We present the Generalized Spatial Propagation Network (GSPN), a new attention mechanism optimized for vision tasks that inherently captures 2D spatial structures. Existing attention models, including transformers, linear attention, and state-space models like Mamba, process multi-dimensional data as 1D sequences, compromising spatial coherence and efficiency. GSPN overcomes these limitations by directly operating on spatially coherent image data and forming dense pairwise connections through a line-scan approach. Central to GSPN is the Stability-Context Condition, which ensures stable, context-aware propagation across 2D sequences and reduces the effective sequence length to $\sqrt{N}$ for a square map with N elements, significantly enhancing computational efficiency. With learnable, input-dependent weights and no reliance on positional embeddings, GSPN achieves superior spatial fidelity and state-of-the-art performance in vision tasks, including ImageNet classification, class-guided image generation, and text-to-image generation. Notably, GSPN accelerates SD-XL with softmax-attention by over $84\times$ when generating 16K images.
Authors: Vidhu Arora, Shreyan Gupta, Ananthakrishna Kudupu, Aditya Priyadarshi, Aswathi Mundayatt, Jaya Sreevalsan-Nair
Abstract: In this article, we improve the deep learning solution for coastline extraction from Synthetic Aperture Radar (SAR) images by proposing a two-stage model involving image classification followed by segmentation. We hypothesize that a single segmentation model usually used for coastline detection is insufficient to characterize different coastline types. We demonstrate that the need for a two-stage workflow prevails through different compression levels of these images. Our results from experiments using a combination of CNN and U-Net models on Sentinel-1 images show that the two-stage workflow, coastline classification-extraction from SAR images (CCESAR) outperforms a single U-Net segmentation model.
Authors: Kan Jen Cheng, Tingle Li, Gopala Anumanchipalli
Abstract: Audio texture manipulation involves modifying the perceptual characteristics of a sound to achieve specific transformations, such as adding, removing, or replacing auditory elements. In this paper, we propose an exemplar-based analogy model for audio texture manipulation. Instead of conditioning on text-based instructions, our method uses paired speech examples, where one clip represents the original sound and another illustrates the desired transformation. The model learns to apply the same transformation to new input, allowing for the manipulation of sound textures. We construct a quadruplet dataset representing various editing tasks, and train a latent diffusion model in a self-supervised manner. We show through quantitative evaluations and perceptual studies that our model outperforms text-conditioned baselines and generalizes to real-world, out-of-distribution, and non-speech scenarios. Project page: https://berkeley-speech-group.github.io/audio-texture-analogy/
URLs: https://berkeley-speech-group.github.io/audio-texture-analogy/
Authors: Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Abstract: We consider the problem of segmenting objects in videos based on their motion and no other forms of supervision. Prior work has often approached this problem by using the principle of common fate, namely the fact that the motion of points that belong to the same object is strongly correlated. However, most authors have only considered instantaneous motion from optical flow. In this work, we present a way to train a segmentation network using long-term point trajectories as a supervisory signal to complement optical flow. The key difficulty is that long-term motion, unlike instantaneous motion, is difficult to model -- any parametric approximation is unlikely to capture complex motion patterns over long periods of time. We instead draw inspiration from subspace clustering approaches, proposing a loss function that seeks to group the trajectories into low-rank matrices where the motion of object points can be approximately explained as a linear combination of other point tracks. Our method outperforms the prior art on motion-based segmentation, which shows the utility of long-term motion and the effectiveness of our formulation.
Authors: Sanath Kumar Krishnamurthy, Tanmay Gangwani, Sumeet Katariya, Branislav Kveton, Shrey Modi, Anshuka Rangi
Abstract: We consider the finite-horizon offline reinforcement learning (RL) setting, and are motivated by the challenge of learning the policy at any step h in dynamic programming (DP) algorithms. To learn this, it is sufficient to evaluate the treatment effect of deviating from the behavioral policy at step h after having optimized the policy for all future steps. Since the policy at any step can affect next-state distributions, the related distributional shift challenges can make this problem far more statistically hard than estimating such treatment effects in the stochastic contextual bandit setting. However, the hardness of many real-world RL instances lies between the two regimes. We develop a flexible and general method called selective uncertainty propagation for confidence interval construction that adapts to the hardness of the associated distribution shift challenges. We show benefits of our approach on toy environments and demonstrate the benefits of these techniques for offline policy learning.
Authors: Giacomo Pedretti, John Moon, Pedro Bruel, Sergey Serebryakov, Ron M. Roth, Luca Buonanno, Archit Gajjar, Lei Zhao, Tobias Ziegler, Cong Xu, Martin Foltin, Paolo Faraboschi, Jim Ignowski, Catherine E. Graves
Abstract: Structured, or tabular, data is the most common format in data science. While deep learning models have proven formidable in learning from unstructured data such as images or speech, they are less accurate than simpler approaches when learning from tabular data. In contrast, modern tree-based Machine Learning (ML) models shine in extracting relevant information from structured data. An essential requirement in data science is to reduce model inference latency in cases where, for example, models are used in a closed loop with simulation to accelerate scientific discovery. However, the hardware acceleration community has mostly focused on deep neural networks and largely ignored other forms of machine learning. Previous work has described the use of an analog content addressable memory (CAM) component for efficiently mapping random forests. In this work, we develop an analog-digital architecture that implements a novel increased precision analog CAM and a programmable chip for inference of state-of-the-art tree-based ML models, such as XGBoost, CatBoost, and others. Thanks to hardware-aware training, X-TIME reaches state-of-the-art accuracy and 119x higher throughput at 9740x lower latency with >150x improved energy efficiency compared with a state-of-the-art GPU for models with up to 4096 trees and depth of 8, with a 19W peak power consumption.
Authors: Tehila Dahan, Kfir Y. Levy
Abstract: We consider distributed learning scenarios where M machines interact with a parameter server along several communication rounds in order to minimize a joint objective function. Focusing on the heterogeneous case, where different machines may draw samples from different data-distributions, we design the first local update method that provably benefits over the two most prominent distributed baselines: namely Minibatch-SGD and Local-SGD. Key to our approach is a slow querying technique that we customize to the distributed setting, which in turn enables a better mitigation of the bias caused by local updates.
Authors: Linkai Luo, Qiaoling Yang, Hong Peng, Yiding Wang, Ziyang Chen
Abstract: The selection of Gaussian kernel parameters plays an important role in the applications of support vector classification (SVC). A commonly used method is the k-fold cross validation with grid search (CV), which is extremely time-consuming because it needs to train a large number of SVC models. In this paper, a new approach is proposed to train SVC and optimize the selection of Gaussian kernel parameters. We first formulate the training and the parameter selection of SVC as a minimax optimization problem named as MaxMin-L2-SVC-NCH, in which the minimization problem is an optimization problem of finding the closest points between two normal convex hulls (L2-SVC-NCH) while the maximization problem is an optimization problem of finding the optimal Gaussian kernel parameters. A lower time complexity can be expected in MaxMin-L2-SVC-NCH because CV is not needed. We then propose a projected gradient algorithm (PGA) for the training of L2-SVC-NCH. It is revealed that the famous sequential minimal optimization (SMO) algorithm is a special case of the PGA. Thus, the PGA can provide more flexibility than the SMO. Furthermore, the solution of the maximization problem is done by a gradient ascent algorithm with dynamic learning rate. The comparative experiments between MaxMin-L2-SVC-NCH and the previous best approaches on public datasets show that MaxMin-L2-SVC-NCH greatly reduces the number of models to be trained while maintaining competitive test accuracy. These findings indicate that MaxMin-L2-SVC-NCH is a better choice for SVC tasks.
Authors: Minjae Lee, Kyungmin Kim, Taesoo Kim, Sangdon Park
Abstract: Trustworthiness of generative language models (GLMs) is crucial in their deployment to critical decision making systems. Hence, certified risk control methods such as selective prediction and conformal prediction have been applied to mitigating the hallucination problem in various supervised downstream tasks. However, the lack of appropriate correctness metric hinders applying such principled methods to language generation tasks. In this paper, we circumvent this problem by leveraging the concept of textual entailment to evaluate the correctness of the generated sequence, and propose two selective generation algorithms which control the false discovery rate with respect to the textual entailment relation (FDR-E) with a theoretical guarantee: $\texttt{SGen}^{\texttt{Sup}}$ and $\texttt{SGen}^{\texttt{Semi}}$. $\texttt{SGen}^{\texttt{Sup}}$, a direct modification of the selective prediction, is a supervised learning algorithm which exploits entailment-labeled data, annotated by humans. Since human annotation is costly, we further propose a semi-supervised version, $\texttt{SGen}^{\texttt{Semi}}$, which fully utilizes the unlabeled data by pseudo-labeling, leveraging an entailment set function learned via conformal prediction. Furthermore, $\texttt{SGen}^{\texttt{Semi}}$ enables to use more general class of selection functions, neuro-selection functions, and provides users with an optimal selection function class given multiple candidates. Finally, we demonstrate the efficacy of the $\texttt{SGen}$ family in achieving a desired FDR-E level with comparable selection efficiency to those from baselines on both open and closed source GLMs. Code and datasets are provided at https://github.com/ml-postech/selective-generation.
Authors: Geri Skenderi, Hang Li, Jiliang Tang, Marco Cristani
Abstract: Joint-Embedding Predictive Architectures (JEPAs) have recently emerged as a novel and powerful technique for self-supervised representation learning. They aim to learn an energy-based model by predicting the latent representation of a target signal y from the latent representation of a context signal x. JEPAs bypass the need for negative and positive samples, traditionally required by contrastive learning while avoiding the overfitting issues associated with generative pretraining. In this paper, we show that graph-level representations can be effectively modeled using this paradigm by proposing a Graph Joint-Embedding Predictive Architecture (Graph-JEPA). In particular, we employ masked modeling and focus on predicting the latent representations of masked subgraphs starting from the latent representation of a context subgraph. To endow the representations with the implicit hierarchy that is often present in graph-level concepts, we devise an alternative prediction objective that consists of predicting the coordinates of the encoded subgraphs on the unit hyperbola in the 2D plane. Through multiple experimental evaluations, we show that Graph-JEPA can learn highly semantic and expressive representations, as shown by the downstream performance in graph classification, regression, and distinguishing non-isomorphic graphs. The code is available at https://github.com/geriskenderi/graph-jepa.
Authors: Huayi Tang, Yong Liu
Abstract: In this paper, we establish generalization bounds for transductive learning algorithms in the context of information theory and PAC-Bayes, covering both the random sampling and the random splitting setting. First, we show that the transductive generalization gap can be controlled by the mutual information between training label selection and the hypothesis. Next, we propose the concept of transductive supersample and use it to derive transductive information-theoretic bounds involving conditional mutual information and different information measures. We further establish transductive PAC-Bayesian bounds with weaker assumptions on the type of loss function and the number of training and test data points. Lastly, we use the theoretical results to derive upper bounds for adaptive optimization algorithms under the transductive learning setting. We also apply them to semi-supervised learning and transductive graph learning scenarios, meanwhile validating the derived bounds by experiments on synthetic and real-world datasets.
Authors: Thomas Chen, Patricia Mu\~noz Ewald
Abstract: We analyze geometric aspects of the gradient descent algorithm in Deep Learning (DL), and give a detailed discussion of the circumstance that in underparametrized DL networks, zero loss minimization can generically not be attained. As a consequence, we conclude that the distribution of training inputs must necessarily be non-generic in order to produce zero loss minimizers, both for the method constructed in [Chen-Munoz Ewald 2023, 2024], or for gradient descent [Chen 2025] (which assume clustering of training data).
Authors: Hyun Ryu, Sunjae Yoon, Hee Suk Yoon, Eunseop Yoon, Chang D. Yoo
Abstract: Data augmentation is a crucial component in training neural networks to overcome the limitation imposed by data size, and several techniques have been studied for time series. Although these techniques are effective in certain tasks, they have yet to be generalized to time series benchmarks. We find that current data augmentation techniques ruin the core information contained within the frequency domain. To address this issue, we propose a simple strategy to preserve spectral information (SimPSI) in time series data augmentation. SimPSI preserves the spectral information by mixing the original and augmented input spectrum weighted by a preservation map, which indicates the importance score of each frequency. Specifically, our experimental contributions are to build three distinct preservation maps: magnitude spectrum, saliency map, and spectrum-preservative map. We apply SimPSI to various time series data augmentations and evaluate its effectiveness across a wide range of time series benchmarks. Our experimental results support that SimPSI considerably enhances the performance of time series data augmentations by preserving core spectral information. The source code used in the paper is available at https://github.com/Hyun-Ryu/simpsi.
Authors: Leonardo Lucio Custode, Giovanni Iacca
Abstract: Reinforcement Learning (RL) bears the promise of being a game-changer in many applications. However, since most of the literature in the field is currently focused on opaque models, the use of RL in high-stakes scenarios, where interpretability is crucial, is still limited. Recently, some approaches to interpretable RL, e.g., based on Decision Trees, have been proposed, but one of the main limitations of these techniques is their training cost. To overcome this limitation, we propose a new method, called Social Interpretable RL (SIRL), that can substantially reduce the number of episodes needed for training. Our method mimics a social learning process, where each agent in a group learns to solve a given task based both on its own individual experience as well as the experience acquired together with its peers. Our approach is divided into the following two phases. (1) In the collaborative phase, all the agents in the population interact with a shared instance of the environment, where each agent observes the state and independently proposes an action. Then, voting is performed to choose the action that will actually be deployed in the environment. (2) In the individual phase, then, each agent refines its individual performance by interacting with its own instance of the environment. This mechanism makes the agents experience a larger number of episodes with little impact on the computational cost of the process. Our results (on 6 widely-known RL benchmarks) show that SIRL not only reduces the computational cost by a factor varying from a minimum of 43% to a maximum 76%, but it also increases the convergence speed and, often, improves the quality of the solutions.
Authors: Adrien Bolland, Gaspard Lambrechts, Damien Ernst
Abstract: Policy-gradient algorithms are effective reinforcement learning methods for solving control problems. To compute near-optimal policies, it is essential in practice to include exploration terms in the learning objective. Although the effectiveness of these terms is usually justified by an intrinsic need to explore environments, we propose a novel analysis with the lens of numerical optimization. Two criteria are introduced on the learning objective and two others on its stochastic gradient estimates, and are afterwards used to discuss the quality of the policy after optimization. The analysis sheds the light on two separate effects of exploration techniques. First, they make it possible to smooth the learning objective and to eliminate local optima while preserving the global maximum. Second, they modify the gradient estimates, increasing the probability that the stochastic parameter updates eventually provide an optimal policy. These effects are illustrated empirically on exploration strategies based on entropy bonuses, highlighting their limitations and opening avenues for future works in the design and analysis of such strategies.
Authors: Jishnu Ray Chowdhury, Cornelia Caragea
Abstract: In this paper, we comprehensively study the inductive biases of two major approaches to augmenting Transformers with a recurrent mechanism: (1) the approach of incorporating a depth-wise recurrence similar to Universal Transformers; and (2) the approach of incorporating a chunk-wise temporal recurrence like Temporal Latent Bottleneck. Furthermore, we propose and investigate novel ways to extend and combine the above methods - for example, we propose a global mean-based dynamic halting mechanism for Universal Transformers and an augmentation of Temporal Latent Bottleneck with elements from Universal Transformer. We compare the models and probe their inductive biases in several diagnostic tasks, such as Long Range Arena (LRA), flip-flop language modeling, ListOps, and Logical Inference. The code is released in: https://github.com/JRC1995/InvestigatingRecurrentTransformers/tree/main
URLs: https://github.com/JRC1995/InvestigatingRecurrentTransformers/tree/main
Authors: Yufei He, Yuan Sui, Xiaoxin He, Bryan Hooi
Abstract: Foundation models like ChatGPT and GPT-4 have revolutionized artificial intelligence, exhibiting remarkable abilities to generalize across a wide array of tasks and applications beyond their initial training objectives. However, graph learning has predominantly focused on single-graph models, tailored to specific tasks or datasets, lacking the ability to transfer learned knowledge to different domains. This limitation stems from the inherent complexity and diversity of graph structures, along with the different feature and label spaces specific to graph data. In this paper, we recognize text as an effective unifying medium and employ Text-Attributed Graphs (TAGs) to leverage this potential. We present our UniGraph framework, designed to learn a foundation model for TAGs, which is capable of generalizing to unseen graphs and tasks across diverse domains. Unlike single-graph models that use pre-computed node features of varying dimensions as input, our approach leverages textual features for unifying node representations, even for graphs such as molecular graphs that do not naturally have textual features. We propose a novel cascaded architecture of Language Models (LMs) and Graph Neural Networks (GNNs) as backbone networks. Additionally, we propose the first pre-training algorithm specifically designed for large-scale self-supervised learning on TAGs, based on Masked Graph Modeling. We introduce graph instruction tuning using Large Language Models (LLMs) to enable zero-shot prediction ability. Our comprehensive experiments across various graph learning tasks and domains demonstrate the model's effectiveness in self-supervised representation learning on unseen graphs, few-shot in-context transfer, and zero-shot transfer, even surpassing or matching the performance of GNNs that have undergone supervised training on target datasets.
Authors: Cen-You Li, Olaf Duennbier, Marc Toussaint, Barbara Rakitsch, Christoph Zimmer
Abstract: Sequential learning methods, such as active learning and Bayesian optimization, aim to select the most informative data for task learning. In many applications, however, data selection is constrained by unknown safety conditions, motivating the development of safe learning approaches. A promising line of safe learning methods uses Gaussian processes to model safety conditions, restricting data selection to areas with high safety confidence. However, these methods are limited to local exploration around an initial seed dataset, as safety confidence centers around observed data points. As a consequence, task exploration is slowed down and safe regions disconnected from the initial seed dataset remain unexplored. In this paper, we propose safe transfer sequential learning to accelerate task learning and to expand the explorable safe region. By leveraging abundant offline data from a related source task, our approach guides exploration in the target task more effectively. We also provide a theoretical analysis to explain why single-task method cannot cope with disconnected regions. Finally, we introduce a computationally efficient approximation of our method that reduces runtime through pre-computations. Our experiments demonstrate that this approach, compared to state-of-the-art methods, learns tasks with lower data consumption and enhances global exploration across multiple disjoint safe regions, while maintaining comparable computational efficiency.
Authors: Mahmood A. Jumaah, Yossra H. Ali, Tarik A. Rashid
Abstract: Hyperparameter tuning in reinforcement learning algorithms refers to choosing the optimal parameters that may increase the algorithm's performance. Manual or random hyperparameter tuning methods can be problematic, as even slight variations in their values can result in significantly different outcomes in the learning process. In this paper, we propose a new method, QF-tuner, for automatic hyperparameter tuning in the Q-learning algorithm using the FOX optimization algorithm (FOX). A new objective function has been proposed for the FOX, prioritizing reward over learning error and time. QF-tuner starts by running the FOX and tries to minimize the fitness value derived from observations at each iteration by executing the Q-learning algorithm. The proposed method has been evaluated using two control tasks from the OpenAI Gym: CartPole and FrozenLake. The empirical results of the QF-tuner on the CartPole control task show a reward of 499, and on the FrozenLake control task, a reward of 1. These results indicate that the QF-tuner outperforms other optimization algorithms. On the FrozenLake control task, there was a 36\% increase in reward with a 26\% reduction in learning time; on the CartPole control task, there was a 57\% increase in reward with a 20\% decrease in learning time. Thus, the QF-tuner is an essential method for hyperparameter tuning in reinforcement learning algorithms, enabling more effective solutions to control task problems.
Authors: Chuning Zhu, Xinqi Wang, Tyler Han, Simon S. Du, Abhishek Gupta
Abstract: Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through planning. However, autoregressive model rollouts suffer from compounding error, making model-based RL ineffective for long-horizon problems. Successor features offer an alternative by modeling a policy's long-term state occupancy, reducing policy evaluation under new rewards to linear regression. Yet, zero-shot policy optimization for new tasks with successor features can be challenging. This work proposes a novel class of models, i.e., Distributional Successor Features for Zero-Shot Policy Optimization (DiSPOs), that learn a distribution of successor features of a stationary dataset's behavior policy, along with a policy that acts to realize different successor features achievable within the dataset. By directly modeling long-term outcomes in the dataset, DiSPOs avoid compounding error while enabling a simple scheme for zero-shot policy optimization across reward functions. We present a practical instantiation of DiSPOs using diffusion models and show their efficacy as a new class of transferable models, both theoretically and empirically across various simulated robotics problems. Videos and code available at https://weirdlabuw.github.io/dispo/.
Authors: Ziru Niu, Hai Dong, A. K. Qin
Abstract: Personalized Federated Learning (PFL) is widely employed in IoT applications to handle high-volume, non-iid client data while ensuring data privacy. However, heterogeneous edge devices owned by clients may impose varying degrees of resource constraints, causing computation and communication bottlenecks for PFL. Federated Dropout has emerged as a popular strategy to address this challenge, wherein only a subset of the global model, i.e. a sub-model, is trained on a client's device, thereby reducing computation and communication overheads. Nevertheless, the dropout-based model-pruning strategy may introduce bias, particularly towards non-iid local data. When biased sub-models absorb highly divergent parameters from other clients, performance degradation becomes inevitable. In response, we propose federated learning with stochastic parameter update (FedSPU). Unlike dropout that tailors the global model to small-size local sub-models, FedSPU maintains the full model architecture on each device but randomly freezes a certain percentage of neurons in the local model during training while updating the remaining neurons. This approach ensures that a portion of the local model remains personalized, thereby enhancing the model's robustness against biased parameters from other clients. Experimental results demonstrate that FedSPU outperforms federated dropout by 7.57% on average in terms of accuracy. Furthermore, an introduced early stopping scheme leads to a significant reduction of the training time by 24.8%-70.4% while maintaining high accuracy.
Authors: Alicia Tierz, Iciar Alfaro, David Gonz\'alez, Francisco Chinesta, El\'ias Cueto
Abstract: Thermodynamics-informed neural networks employ inductive biases for the enforcement of the first and second principles of thermodynamics. To construct these biases, a metriplectic evolution of the system is assumed. This provides excellent results, when compared to uninformed, black box networks. While the degree of accuracy can be increased in one or two orders of magnitude, in the case of graph networks, this requires assembling global Poisson and dissipation matrices, which breaks the local structure of such networks. In order to avoid this drawback, a local version of the metriplectic biases has been developed in this work, which avoids the aforementioned matrix assembly, thus preserving the node-by-node structure of the graph networks. We apply this framework for examples in the fields of solid and fluid mechanics. Our approach demonstrates significant computational efficiency and strong generalization capabilities, accurately making inferences on examples significantly different from those encountered during training.
Authors: Yu Shee, Haote Li, Anton Morgunov, Victor Batista
Abstract: Traditional computer-aided synthesis planning (CASP) methods rely on iterative single-step predictions, leading to exponential search space growth that limits efficiency and scalability. We introduce a series of transformer-based models, utilizing mixture of experts approach, that directly generate multistep synthetic routes as a single string by conditionally predicting each molecule based on all preceding ones. Our models can accommodate specific conditions such as the desired number of steps and starting materials, with the top-performing DMS-Flex (Duo) surpassing state-of-the-art methods on the PaRoutes dataset with a 2.5x improvement in Top-1 accuracy on the n$_1$ test set and a 3.9x improvement on the n$_5$ test set. It also successfully predicts routes for FDA-approved drugs not included in the training data, showcasing its generalization capabilities. While the current suboptimal diversity of the training set may impact performance on less common reaction types, our multistep-first approach presents a promising direction towards fully automated retrosynthetic planning.
Authors: Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges, Romann M. Weber
Abstract: Advances in latent diffusion models (LDMs) have revolutionized high-resolution image generation, but the design space of the autoencoder that is central to these systems remains underexplored. In this paper, we introduce LiteVAE, a new autoencoder design for LDMs, which leverages the 2D discrete wavelet transform to enhance scalability and computational efficiency over standard variational autoencoders (VAEs) with no sacrifice in output quality. We investigate the training methodologies and the decoder architecture of LiteVAE and propose several enhancements that improve the training dynamics and reconstruction quality. Our base LiteVAE model matches the quality of the established VAEs in current LDMs with a six-fold reduction in encoder parameters, leading to faster training and lower GPU memory requirements, while our larger model outperforms VAEs of comparable complexity across all evaluated metrics (rFID, LPIPS, PSNR, and SSIM).
Authors: Chaoran Cheng, Jiahan Li, Jian Peng, Ge Liu
Abstract: We introduce Statistical Flow Matching (SFM), a novel and mathematically rigorous flow-matching framework on the manifold of parameterized probability measures inspired by the results from information geometry. We demonstrate the effectiveness of our method on the discrete generation problem by instantiating SFM on the manifold of categorical distributions whose geometric properties remain unexplored in previous discrete generative models. Utilizing the Fisher information metric, we equip the manifold with a Riemannian structure whose intrinsic geometries are effectively leveraged by following the shortest paths of geodesics. We develop an efficient training and sampling algorithm that overcomes numerical stability issues with a diffeomorphism between manifolds. Our distinctive geometric perspective of statistical manifolds allows us to apply optimal transport during training and interpret SFM as following the steepest direction of the natural gradient. Unlike previous models that rely on variational bounds for likelihood estimation, SFM enjoys the exact likelihood calculation for arbitrary probability measures. We manifest that SFM can learn more complex patterns on the statistical manifold where existing models often fail due to strong prior assumptions. Comprehensive experiments on real-world generative tasks ranging from image, text to biological domains further demonstrate that SFM achieves higher sampling quality and likelihood than other discrete diffusion or flow-based models.
Authors: Kaveh Alimohammadi, Hao Wang, Ojas Gulati, Akash Srivastava, Navid Azizan
Abstract: Existing differentially private (DP) synthetic data generation mechanisms typically assume a single-source table. In practice, data is often distributed across multiple tables with relationships across tables. In this paper, we introduce the first-of-its-kind algorithm that can be combined with any existing DP mechanisms to generate synthetic relational databases. Our algorithm iteratively refines the relationship between individual synthetic tables to minimize their approximation errors in terms of low-order marginal distributions while maintaining referential integrity. This algorithm eliminates the need to flatten a relational database into a master table (saving space), operates efficiently (saving time), and scales effectively to high-dimensional data. We provide both DP and theoretical utility guarantees for our algorithm. Through numerical experiments on real-world datasets, we demonstrate the effectiveness of our method in preserving fidelity to the original data.
Authors: Jiawei Zhang, Jiaxin Zhuang, Cheng Jin, Gen Li, Yuantao Gu
Abstract: The recent emergence of diffusion models has significantly advanced the precision of learnable priors, presenting innovative avenues for addressing inverse problems. Since inverse problems inherently entail maximum a posteriori estimation, previous works have endeavored to integrate diffusion priors into the optimization frameworks. However, prevailing optimization-based inverse algorithms primarily exploit the prior information within the diffusion models while neglecting their denoising capability. To bridge this gap, this work leverages the diffusion process to reframe noisy inverse problems as a two-variable constrained optimization task by introducing an auxiliary optimization variable. By employing gradient truncation, the projection gradient descent method is efficiently utilized to solve the corresponding optimization problem. The proposed algorithm, termed ProjDiff, effectively harnesses the prior information and the denoising capability of a pre-trained diffusion model within the optimization framework. Extensive experiments on the image restoration tasks and source separation and partial generation tasks demonstrate that ProjDiff exhibits superior performance across various linear and nonlinear inverse problems, highlighting its potential for practical applications. Code is available at https://github.com/weigerzan/ProjDiff/.
Authors: Qining Zhang, Honghao Wei, Lei Ying
Abstract: In this paper, we study reinforcement learning from human feedback (RLHF) under an episodic Markov decision process with a general trajectory-wise reward model. We developed a model-free RLHF best policy identification algorithm, called $\mathsf{BSAD}$, without explicit reward model inference, which is a critical intermediate step in the contemporary RLHF paradigms for training large language models (LLM). The algorithm identifies the optimal policy directly from human preference information in a backward manner, employing a dueling bandit sub-routine that constantly duels actions to identify the superior one. $\mathsf{BSAD}$ adopts a reward-free exploration and best-arm-identification-like adaptive stopping criteria to equalize the visitation among all states in the same decision step while moving to the previous step as soon as the optimal action is identifiable, leading to a provable, instance-dependent sample complexity $\tilde{\mathcal{O}}(c_{\mathcal{M}}SA^3H^3M\log\frac{1}{\delta})$ which resembles the result in classic RL, where $c_{\mathcal{M}}$ is the instance-dependent constant and $M$ is the batch size. Moreover, $\mathsf{BSAD}$ can be transformed into an explore-then-commit algorithm with logarithmic regret and generalized to discounted MDPs using a frame-based approach. Our results show: (i) sample-complexity-wise, RLHF is not significantly harder than classic RL and (ii) end-to-end RLHF may deliver improved performance by avoiding pitfalls in reward inferring such as overfit and distribution shift.
Authors: Tian Qin, Zhiwei Deng, David Alvarez-Melis
Abstract: Data $\textit{quality}$ is a crucial factor in the performance of machine learning models, a principle that dataset distillation methods exploit by compressing training datasets into much smaller counterparts that maintain similar downstream performance. Understanding how and why data distillation methods work is vital not only for improving these methods but also for revealing fundamental characteristics of "good" training data. However, a major challenge in achieving this goal is the observation that distillation approaches, which rely on sophisticated but mostly disparate methods to generate synthetic data, have little in common with each other. In this work, we highlight a largely overlooked aspect common to most of these methods: the use of soft (probabilistic) labels. Through a series of ablation experiments, we study the role of soft labels in depth. Our results reveal that the main factor explaining the performance of state-of-the-art distillation methods is not the specific techniques used to generate synthetic data but rather the use of soft labels. Furthermore, we demonstrate that not all soft labels are created equal; they must contain $\textit{structured information}$ to be beneficial. We also provide empirical scaling laws that characterize the effectiveness of soft labels as a function of images-per-class in the distilled dataset and establish an empirical Pareto frontier for data-efficient learning. Combined, our findings challenge conventional wisdom in dataset distillation, underscore the importance of soft labels in learning, and suggest new directions for improving distillation methods. Code for all experiments is available at https://github.com/sunnytqin/no-distillation.
Authors: Alona Levy-Jurgenson, Zohar Yakhini
Abstract: Generative methods have recently seen significant improvements by generating in a lower-dimensional latent representation of the data. However, many of the generative methods applied in the latent space remain complex and difficult to train. Further, it is not entirely clear why transitioning to a lower-dimensional latent space can improve generative quality. In this work, we introduce a new and simple generative method grounded in topology theory -- Generative Topological Networks (GTNs) -- which also provides insights into why lower-dimensional latent-space representations might be better-suited for data generation. GTNs are simple to train -- they employ a standard supervised learning approach and do not suffer from common generative pitfalls such as mode collapse, posterior collapse or the need to pose constraints on the neural network architecture. We demonstrate the use of GTNs on several datasets, including MNIST, CelebA, CIFAR-10 and the Hands and Palm Images dataset by training GTNs on a lower-dimensional latent representation of the data. We show that GTNs can improve upon VAEs and that they are quick to converge, generating realistic samples in early epochs. Further, we use the topological considerations behind the development of GTNs to offer insights into why generative models may benefit from operating on a lower-dimensional latent space, highlighting the important link between the intrinsic dimension of the data and the dimension in which the data is generated. Particularly, we demonstrate that generating in high dimensional ambient spaces may be a contributing factor to out-of-distribution samples generated by diffusion models. We also highlight other topological properties that are important to consider when using and designing generative models. Our code is available at: https://github.com/alonalj/GTN
Authors: Tomer Porian, Mitchell Wortsman, Jenia Jitsev, Ludwig Schmidt, Yair Carmon
Abstract: Kaplan et al. and Hoffmann et al. developed influential scaling laws for the optimal model size as a function of the compute budget, but these laws yield substantially different predictions. We explain the discrepancy by reproducing the Kaplan scaling law on two datasets (OpenWebText2 and RefinedWeb) and identifying three factors causing the difference: last layer computational cost, warmup duration, and scale-dependent optimizer tuning. With these factors corrected, we obtain excellent agreement with the Hoffmann et al. (i.e., "Chinchilla") scaling law. Counter to a hypothesis of Hoffmann et al., we find that careful learning rate decay is not essential for the validity of their scaling law. As a secondary result, we derive scaling laws for the optimal learning rate and batch size, finding that tuning the AdamW $\beta_2$ parameter is essential at lower batch sizes.
Authors: David Zagardo
Abstract: Imagine training a machine learning model with Differentially Private Stochastic Gradient Descent (DP-SGD), only to discover post-training that the noise level was either too high, crippling your model's utility, or too low, compromising privacy. The dreaded realization hits: you must start the lengthy training process from scratch. But what if you could avoid this retraining nightmare? In this study, we introduce a groundbreaking approach (to our knowledge) that applies differential privacy noise to the model's weights after training. We offer a comprehensive mathematical proof for this novel approach's privacy bounds, use formal methods to validate its privacy guarantees, and empirically evaluate its effectiveness using membership inference attacks and performance evaluations. This method allows for a single training run, followed by post-hoc noise adjustments to achieve optimal privacy-utility trade-offs. We compare this novel fine-tuned model (DP-Weights model) to a traditional DP-SGD model, demonstrating that our approach yields statistically similar performance and privacy guarantees. Our results validate the efficacy of post-training noise application, promising significant time savings and flexibility in fine-tuning differential privacy parameters, making it a practical alternative for deploying differentially private models in real-world scenarios.
Authors: Julien Pallage, Antoine Lesage-Landry
Abstract: In this work, we propose Wasserstein distributionally robust shallow convex neural networks (WaDiRo-SCNNs) to provide reliable nonlinear predictions when subject to adverse and corrupted datasets. Our approach is based on a new convex training program for $\ReLU$-based shallow neural networks which allows us to cast the problem as an exact, tractable reformulation of its order-1 Wasserstein distributionally robust counterpart. Our training procedure is conservative, has low stochasticity, is solvable with open-source solvers, and is scalable to large industrial deployments. We provide out-of-sample performance guarantees, show that hard convex physical constraints can be enforced in the training program, and propose a mixed-integer convex post-training verification program to evaluate model stability. WaDiRo-SCNN aims to make neural networks safer for critical applications, such as in the energy sector. Finally, we numerically demonstrate the performance of our model on a synthetic experiment, a real-world power system application, i.e., the prediction of non-residential buildings' hourly energy consumption in the context of virtual power plants, and on benchmark datasets. The experimental results are convincing and showcase the strengths of the proposed model.
Authors: David Zagardo
Abstract: Traditional Differentially Private Stochastic Gradient Descent (DP-SGD) introduces statistical noise on top of gradients drawn from a Gaussian distribution to ensure privacy. This paper introduces the novel Differentially Private Block-wise Gradient Shuffle (DP-BloGS) algorithm for deep learning. BloGS builds off of existing private deep learning literature, but makes a definitive shift by taking a probabilistic approach to gradient noise introduction through shuffling modeled after information theoretic privacy analyses. The theoretical results presented in this paper show that the combination of shuffling, parameter-specific block size selection, batch layer clipping, and gradient accumulation allows DP-BloGS to achieve training times close to that of non-private training while maintaining similar privacy and utility guarantees to DP-SGD. DP-BloGS is found to be significantly more resistant to data extraction attempts than DP-SGD. The theoretical results are validated by the experimental findings.
Authors: Youssouf Emine, Alexandre Forel, Idriss Malek, Thibaut Vidal
Abstract: Tree ensembles, including boosting methods, are highly effective and widely used for tabular data. However, large ensembles lack interpretability and require longer inference times. We introduce a method to prune a tree ensemble into a reduced version that is "functionally identical" to the original model. In other words, our method guarantees that the prediction function stays unchanged for any possible input. As a consequence, this pruning algorithm is lossless for any aggregated metric. We formalize the problem of functionally identical pruning on ensembles, introduce an exact optimization model, and provide a fast yet highly effective method to prune large ensembles. Our algorithm iteratively prunes considering a finite set of points, which is incrementally augmented using an adversarial model. In multiple computational experiments, we show that our approach is a "free lunch", significantly reducing the ensemble size without altering the model's behavior. Thus, we can preserve state-of-the-art performance at a fraction of the original model's size.
Authors: Xunkai Li, Yinlin Zhu, Boyang Pang, Guochen Yan, Yeyu Yan, Zening Li, Zhengyu Wu, Wentao Zhang, Rong-Hua Li, Guoren Wang
Abstract: Federated graph learning (FGL) is a promising distributed training paradigm for graph neural networks across multiple local systems without direct data sharing. This approach inherently involves large-scale distributed graph processing, which closely aligns with the challenges and research focuses of graph-based data systems. Despite the proliferation of FGL, the diverse motivations from real-world applications, spanning various research backgrounds and settings, pose a significant challenge to fair evaluation. To fill this gap, we propose OpenFGL, a unified benchmark designed for the primary FGL scenarios: Graph-FL and Subgraph-FL. Specifically, OpenFGL includes 42 graph datasets from 18 application domains, 8 federated data simulation strategies that emphasize different graph properties, and 5 graph-based downstream tasks. Additionally, it offers 18 recently proposed SOTA FGL algorithms through a user-friendly API, enabling a thorough comparison and comprehensive evaluation of their effectiveness, robustness, and efficiency. Our empirical results demonstrate the capabilities of FGL while also highlighting its potential limitations, providing valuable insights for future research in this growing field, particularly in fostering greater interdisciplinary collaboration between FGL and data systems.
Authors: Xingyu Xie, Kuangyu Ding, Shuicheng Yan, Kim-Chuan Toh, Tianwen Wei
Abstract: Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter selection. While scaling laws provide valuable guidance on model size and data requirements, they fall short in choosing dynamic hyper-parameters, such as learning-rate (LR) schedules, that evolve during training. To bridge this gap, we present Optimization Hyper-parameter Laws (Opt-Laws), a framework that effectively captures the relationship between hyper-parameters and training outcomes, enabling the pre-selection of potential optimal schedules. Grounded in stochastic differential equations, Opt-Laws introduce novel mathematical interpretability and offer a robust theoretical foundation for some popular LR schedules. Our extensive validation across diverse model sizes and data scales demonstrates Opt-Laws' ability to accurately predict training loss and identify optimal LR schedule candidates in pre-training, continual training, and fine-tuning scenarios. This approach significantly reduces computational costs while enhancing overall model performance.
Authors: Zakaria Patel, Sebastian J. Wetzel
Abstract: It has been demonstrated in many scientific fields that artificial neural networks like autoencoders or Siamese networks encode meaningful concepts in their latent spaces. However, there does not exist a comprehensive framework for retrieving this information in a human-readable form without prior knowledge. In order to extract these concepts, we introduce a framework for finding closed-form interpretations of neurons in latent spaces of artificial neural networks. The interpretation framework is based on embedding trained neural networks into an equivalence class of functions that encode the same concept. We interpret these neural networks by finding an intersection between the equivalence class and human-readable equations defined by a symbolic search space. The approach is demonstrated by retrieving invariants of matrices and conserved quantities of dynamical systems from latent spaces of Siamese neural networks.
Authors: Pedro Cisneros-Velarde, Zhijie Chen, Sanmi Koyejo, Arindam Banerjee
Abstract: Weight normalization (WeightNorm) is widely used in practice for the training of deep neural networks and modern deep learning libraries have built-in implementations of it. In this paper, we provide the first theoretical characterizations of both optimization and generalization of deep WeightNorm models with smooth activation functions. For optimization, from the form of the Hessian of the loss, we note that a small Hessian of the predictor leads to a tractable analysis. Thus, we bound the spectral norm of the Hessian of WeightNorm networks and show its dependence on the network width and weight normalization terms--the latter being unique to networks without WeightNorm. Then, we use this bound to establish training convergence guarantees under suitable assumptions for gradient decent. For generalization, we use WeightNorm to get a uniform convergence based generalization bound, which is independent from the width and depends sublinearly on the depth. Finally, we present experimental results which illustrate how the normalization terms and other quantities of theoretical interest relate to the training of WeightNorm networks.
Authors: Stefano Peluchetti
Abstract: A Schr\"{o}dinger bridge establishes a dynamic transport map between two target distributions via a reference process, simultaneously solving an associated entropic optimal transport problem. We consider the setting where samples from the target distributions are available, and the reference diffusion process admits tractable dynamics. We thus introduce Coupled Bridge Matching (BM$^2$), a simple non-iterative approach for learning Schr\"{o}dinger bridges with neural networks. A preliminary theoretical analysis of the convergence properties of BM$^2$ is carried out, supported by numerical experiments that demonstrate the effectiveness of our proposal.
Authors: Jiaxing Li, Zihan Chen, Kai Fong Ernest Chong, Bikramjit Das, Tony Q. S. Quek, Howard H. Yang
Abstract: Leveraging over-the-air computations for model aggregation is an effective approach to cope with the communication bottleneck in federated edge learning. By exploiting the superposition properties of multi-access channels, this approach facilitates an integrated design of communication and computation, thereby enhancing system privacy while reducing implementation costs. However, the inherent electromagnetic interference in radio channels often exhibits heavy-tailed distributions, giving rise to exceptionally strong noise in globally aggregated gradients that can significantly deteriorate the training performance. To address this issue, we propose a novel gradient clipping method, termed Median Anchored Clipping (MAC), to combat the detrimental effects of heavy-tailed noise. We also derive analytical expressions for the convergence rate of model training with analog over-the-air federated learning under MAC, which quantitatively demonstrates the effect of MAC on training performance. Extensive experimental results show that the proposed MAC algorithm effectively mitigates the impact of heavy-tailed noise, hence substantially enhancing system robustness.
Authors: Lyudong Jin, Ming Tang, Jiayu Pan, Meng Zhang, Hao Wang
Abstract: In the realm of emerging real-time networked applications like cyber-physical systems (CPS), the Age of Information (AoI) has merged as a pivotal metric for evaluating the timeliness. To meet the high computational demands, such as those in intelligent manufacturing within CPS, mobile edge computing (MEC) presents a promising solution for optimizing computing and reducing AoI. In this work, we study the timeliness of computational-intensive updates and explores jointly optimize the task updating and offloading policies to minimize AoI. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. The fractional objective introduced by AoI and the semi-Markov game nature of the problem render this challenge particularly difficult, with existing approaches not directly applicable. To this end, we present a comprehensive framework to fractional reinforcement learning (RL). We first introduce a fractional single-agent RL framework and prove its linear convergence. We then extend this to a fractional multi-agent RL framework with a convergence analysis. To tackle the challenge of asynchronous control in semi-Markov game, we further design an asynchronous model-free fractional multi-agent RL algorithm, where each device makes scheduling decisions with the hybrid action space without knowing the system dynamics and decisions of other devices. Experimental results show that our proposed algorithms reduce the average AoI by up to 52.6% compared with the best baseline algorithm in our experiments.
Authors: Daan Caljon, Jeff Vercauteren, Simon De Vos, Wouter Verbeke, Jente Van Belle
Abstract: Rolling origin forecast instability refers to variability in forecasts for a specific period induced by updating the forecast when new data points become available. Recently, an extension to the N-BEATS model for univariate time series point forecasting was proposed to include forecast stability as an additional optimization objective, next to accuracy. It was shown that more stable forecasts can be obtained without harming accuracy by minimizing a composite loss function that contains both a forecast error and a forecast instability component, with a static hyperparameter to control the impact of stability. In this paper, we empirically investigate whether further improvements in stability can be obtained without compromising accuracy by applying dynamic loss weighting algorithms, which change the loss weights during training. We show that existing dynamic loss weighting methods can achieve this objective and provide insights into why this might be the case. Additionally, we propose an extension to the Random Weighting approach -- Task-Aware Random Weighting -- which also achieves this objective.
Authors: Yan Sun, Li Shen, Dacheng Tao
Abstract: As a popular paradigm for juggling data privacy and collaborative training, federated learning (FL) is flourishing to distributively process the large scale of heterogeneous datasets on edged clients. Due to bandwidth limitations and security considerations, it ingeniously splits the original problem into multiple subproblems to be solved in parallel, which empowers primal dual solutions to great application values in FL. In this paper, we review the recent development of classical federated primal dual methods and point out a serious common defect of such methods in non-convex scenarios, which we say is a "dual drift" caused by dual hysteresis of those longstanding inactive clients under partial participation training. To further address this problem, we propose a novel Aligned Federated Primal Dual (A-FedPD) method, which constructs virtual dual updates to align global consensus and local dual variables for those protracted unparticipated local clients. Meanwhile, we provide a comprehensive analysis of the optimization and generalization efficiency for the A-FedPD method on smooth non-convex objectives, which confirms its high efficiency and practicality. Extensive experiments are conducted on several classical FL setups to validate the effectiveness of our proposed method.
Authors: Zezhou Wang, Yaxin Du, Xingjun Ma, Yugang Jiang, Zhuzhong Qian, Siheng Chen
Abstract: Federated Domain-specific Instruction Tuning (FedDIT) utilizes limited cross-client private data together with various strategies of instruction augmentation, ultimately boosting model performance within specific domains. To date, the factors affecting FedDIT remain unclear, and existing instruction augmentation methods primarily focus on the centralized setting without considering distributed environments. Our experiments reveal that the cross-client domain coverage, rather than data heterogeneity, drives model performance in FedDIT. In response, we propose FedDCA, which optimizes domain coverage through greedy client center selection and retrieval-based augmentation. At its core, the greedy selection procedure iteratively picks client centers that maximize the diversity and coverage of the instruction space while avoiding redundancy with previously selected centers. This ensures broad yet efficient coverage of the domain distribution across clients. For client-side computational efficiency and system scalability, FedDCA$^*$, the variant of FedDCA, utilizes heterogeneous encoders with server-side feature alignment. Extensive experiments across code, medical, financial, and mathematical domains substantiate the effectiveness of both methods, as well as plug-and-play capability. We further analyze privacy preservation against memory extraction attacks, showing that while privacy leakage risk is independent of augmented public data ratio, it decreases or converges as training progresses.
Authors: A. Yark{\i}n Y{\i}ld{\i}z, Asli Kalayci
Abstract: Medical diagnosis is a crucial task in the medical field, in terms of providing accurate classification and respective treatments. Having near-precise decisions based on correct diagnosis can affect a patient's life itself, and may extremely result in a catastrophe if not classified correctly. Several traditional machine learning (ML), such as support vector machines (SVMs) and logistic regression, and state-of-the-art tabular deep learning (DL) methods, including TabNet and TabTransformer, have been proposed and used over tabular medical datasets. Additionally, due to the superior performances, lower computational costs, and easier optimization over different tasks, ensemble methods have been used in the field more recently. They offer a powerful alternative in terms of providing successful medical decision-making processes in several diagnosis tasks. In this study, we investigated the benefits of ensemble methods, especially the Gradient Boosting Decision Tree (GBDT) algorithms in medical classification tasks over tabular data, focusing on XGBoost, CatBoost, and LightGBM. The experiments demonstrate that GBDT methods outperform traditional ML and deep neural network architectures and have the highest average rank over several benchmark tabular medical diagnosis datasets. Furthermore, they require much less computational power compared to DL models, creating the optimal methodology in terms of high performance and lower complexity.
Authors: Yixuan Wang, Zhenwu Chen, Kangshuai Zhang, Yunduan Cui, Yang Yang, Lei Peng
Abstract: With the sharp increase in the number of vehicles, the issue of parking difficulties has emerged as an urgent challenge that many cities need to address promptly. In the task of predicting large-scale urban parking data, existing research often lacks effective deep learning models and strategies. To tackle this challenge, this paper proposes an innovative framework for predicting large-scale urban parking graphs leveraging real-time service capabilities, aimed at improving the accuracy and efficiency of parking predictions. Specifically, we introduce a graph attention mechanism that assesses the real-time service capabilities of parking lots to construct a dynamic parking graph that accurately reflects real preferences in parking behavior. To effectively handle large-scale parking data, this study combines graph coarsening techniques with temporal convolutional autoencoders to achieve unified dimension reduction of the complex urban parking graph structure and features. Subsequently, we use a spatio-temporal graph convolutional model to make predictions based on the coarsened graph, and a pre-trained autoencoder-decoder module restores the predicted results to their original data dimensions, completing the task. Our methodology has been rigorously tested on a real dataset from parking lots in Shenzhen. The experimental results indicate that compared to traditional parking prediction models, our framework achieves improvements of 46.8\% and 30.5\% in accuracy and efficiency, respectively. Remarkably, with the expansion of the graph's scale, our framework's advantages become even more apparent, showcasing its substantial potential for solving complex urban parking dilemmas in practical scenarios.
Authors: Hui Chen, Xuhui Fan, Hengyu Liu, Yaqiong Li, Zhilin Zhao, Feng Zhou, Christopher John Quinn, Longbing Cao
Abstract: Temporal point processes (TPPs) are effective for modeling event occurrences over time, but they struggle with sparse and uncertain events in federated systems, where privacy is a major concern. To address this, we propose \textit{FedPP}, a Federated neural nonparametric Point Process model. FedPP integrates neural embeddings into Sigmoidal Gaussian Cox Processes (SGCPs) on the client side, which is a flexible and expressive class of TPPs, allowing it to generate highly flexible intensity functions that capture client-specific event dynamics and uncertainties while efficiently summarizing historical records. For global aggregation, FedPP introduces a divergence-based mechanism that communicates the distributions of SGCPs' kernel hyperparameters between the server and clients, while keeping client-specific parameters local to ensure privacy and personalization. FedPP effectively captures event uncertainty and sparsity, and extensive experiments demonstrate its superior performance in federated settings, particularly with KL divergence and Wasserstein distance-based global aggregation.
Authors: Shenao Zhang, Zhihan Liu, Boyi Liu, Yufeng Zhang, Yingxiang Yang, Yongfei Liu, Liyu Chen, Tao Sun, Zhaoran Wang
Abstract: Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often overlook the qualitative aspects of responses. Striving to maximize the implicit reward gap between the chosen and the slightly inferior rejected responses can cause overfitting and unnecessary unlearning of the high-quality rejected responses. The unawareness of the reward scores also drives the LLM to indiscriminately favor the low-quality chosen responses and fail to generalize to responses with the highest rewards, which are sparse in data. To overcome these shortcomings, our study introduces reward-conditioned LLM policies that discern and learn from the entire spectrum of response quality within the dataset, helping extrapolate to more optimal regions. We propose an effective yet simple data relabeling method that conditions the preference pairs on quality scores to construct a reward-augmented dataset. This dataset is easily integrated with existing direct alignment algorithms and is applicable to any preference dataset. The experimental results across instruction-following benchmarks including AlpacaEval, MT-Bench, and Arena-Hard-Auto demonstrate that our approach consistently boosts the performance of DPO by a considerable margin across diverse models. Additionally, our method improves the average accuracy on various academic benchmarks. When applying our method to on-policy data, the resulting DPO model achieves SOTA results on AlpacaEval. Through ablation studies, we demonstrate that our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere dataset expansion. Our code is available at https://github.com/shenao-zhang/reward-augmented-preference.
URLs: https://github.com/shenao-zhang/reward-augmented-preference.
Authors: Qizhang Li, Xiaochen Yang, Wangmeng Zuo, Yiwen Guo
Abstract: Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs, often generate garbled adversarial prompts with chaotic appearance. These adversarial prompts are difficult to transfer to other LLMs, hindering their performance in attacking unknown victim models. In this paper, for the first time, we delve into the semantic meaning embedded in garbled adversarial prompts and propose a novel method that "translates" them into coherent and human-readable natural language adversarial prompts. In this way, we can effectively uncover the semantic information that triggers vulnerabilities of the model and unambiguously transfer it to the victim model, without overlooking the adversarial information hidden in the garbled text, to enhance jailbreak attacks. It also offers a new approach to discovering effective designs for jailbreak prompts, advancing the understanding of jailbreak attacks. Experimental results demonstrate that our method significantly improves the success rate of jailbreak attacks against various safety-aligned LLMs and outperforms state-of-the-arts by large margins. With at most 10 queries, our method achieves an average attack success rate of 81.8% in attacking 7 commercial closed-source LLMs, including GPT and Claude-3 series, on HarmBench. Our method also achieves over 90% attack success rates against Llama-2-Chat models on AdvBench, despite their outstanding resistance to jailbreak attacks. Code at: https://github.com/qizhangli/Adversarial-Prompt-Translator.
URLs: https://github.com/qizhangli/Adversarial-Prompt-Translator.
Authors: Zhepeng Cen, Yao Liu, Siliang Zeng, Pratik Chaudhari, Huzefa Rangwala, George Karypis, Rasool Fakoor
Abstract: Language models are often trained to maximize the likelihood of the next token given past tokens in the training dataset. However, during inference time, they are utilized differently, generating text sequentially and auto-regressively by using previously generated tokens as input to predict the next one. Marginal differences in predictions at each step can cascade over successive steps, resulting in different distributions from what the models were trained for and potentially leading to unpredictable behavior. This paper proposes two simple approaches based on model own generation to address this discrepancy between the training and inference time. Our first approach is Batch-Scheduled Sampling, where, during training, we stochastically choose between the ground-truth token from the dataset and the model's own generated token as input to predict the next token. This is done in an offline manner, modifying the context window by interleaving ground-truth tokens with those generated by the model. Our second approach is Reference-Answer-based Correction, where we explicitly incorporate a self-correction capability into the model during training. This enables the model to effectively self-correct the gaps between the generated sequences and the ground truth data without relying on an external oracle model. By incorporating our proposed strategies during training, we have observed an overall improvement in performance compared to baseline methods, as demonstrated by our extensive experiments using summarization, general question-answering, and math question-answering tasks.
Authors: Skye Gunasekaran, Assel Kembay, Hugo Ladret, Rui-Jie Zhu, Laurent Perrinet, Omid Kavehei, Jason Eshraghian
Abstract: Accurate time-series forecasting is crucial in various scientific and industrial domains, yet deep learning models often struggle to capture long-term dependencies and adapt to data distribution drifts over time. We introduce Future-Guided Learning, an approach that enhances time-series event forecasting through a dynamic feedback mechanism inspired by predictive coding. Our method involves two models: a detection model that analyzes future data to identify critical events and a forecasting model that predicts these events based on current data. When discrepancies occur between the forecasting and detection models, a more significant update is applied to the forecasting model, effectively minimizing surprise and adapting to shifts in the data distribution by aligning its predictions with actual future outcomes. This feedback loop allows the forecasting model to dynamically adjust its parameters, focusing on persistent features despite changes in the data. We validate our approach on a variety of tasks, demonstrating a 44.8% increase in AUC-ROC for seizure prediction using EEG data, and a 48.7% reduction in MSE for forecasting in nonlinear dynamical systems. By incorporating a predictive feedback mechanism adaptable to data drift, Future-Guided Learning advances how deep learning is applied to time-series forecasting. Our code is publicly available at https://github.com/SkyeGunasekaran/FutureGuidedLearning.
URLs: https://github.com/SkyeGunasekaran/FutureGuidedLearning.
Authors: Shicheng Liu, Minghui Zhu
Abstract: Inverse reinforcement learning (IRL) aims to learn a reward function and a corresponding policy that best fit the demonstrated trajectories of an expert. However, current IRL works cannot learn incrementally from an ongoing trajectory because they have to wait to collect at least one complete trajectory to learn. To bridge the gap, this paper considers the problem of learning a reward function and a corresponding policy while observing the initial state-action pair of an ongoing trajectory and keeping updating the learned reward and policy when new state-action pairs of the ongoing trajectory are observed. We formulate this problem as an online bi-level optimization problem where the upper level dynamically adjusts the learned reward according to the newly observed state-action pairs with the help of a meta-regularization term, and the lower level learns the corresponding policy. We propose a novel algorithm to solve this problem and guarantee that the algorithm achieves sub-linear local regret $O(\sqrt{T}+\log T+\sqrt{T}\log T)$. If the reward function is linear, we prove that the proposed algorithm achieves sub-linear regret $O(\log T)$. Experiments are used to validate the proposed algorithm.
Authors: Valeria Ruscio, Fabrizio Silvestri
Abstract: This paper studies how transformer models develop robust wavelet-like properties that effectively compensate for the theoretical limitations of Rotary Position Embeddings (RoPE), providing insights into how these networks process sequential information across different scales. Through theoretical analysis and empirical validation across models ranging from 1B to 12B parameters, we show that attention heads naturally evolve to implement multi-resolution processing analogous to wavelet transforms. Our analysis establishes that attention heads consistently organize into complementary frequency bands with systematic power distribution patterns, and these wavelet-like characteristics become more pronounced in larger models. We provide mathematical analysis showing how these properties align with optimal solutions to the fundamental uncertainty principle between positional precision and frequency resolution. Our findings suggest that the effectiveness of modern transformer architectures stems significantly from their development of optimal multi-resolution decompositions that naturally address the theoretical constraints of position encoding.
Authors: Daehee Lee, Minjong Yoo, Woo Kyung Kim, Wonje Choi, Honguk Woo
Abstract: Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With recent advancements in foundation models, there has been a growing interest in adapter-based CiL approaches, where adapters are established parameter-efficiently for tasks newly demonstrated. While these approaches isolate parameters for specific tasks and tend to mitigate catastrophic forgetting, they limit knowledge sharing among different demonstrations. We introduce IsCiL, an adapter-based CiL framework that addresses this limitation of knowledge sharing by incrementally learning shareable skills from different demonstrations, thus enabling sample-efficient task adaptation using the skills particularly in non-stationary CiL environments. In IsCiL, demonstrations are mapped into the state embedding space, where proper skills can be retrieved upon input states through prototype-based memory. These retrievable skills are incrementally learned on their corresponding adapters. Our CiL experiments with complex tasks in Franka-Kitchen and Meta-World demonstrate robust performance of IsCiL in both task adaptation and sample-efficiency. We also show a simple extension of IsCiL for task unlearning scenarios.
Authors: Tejaswini Medi, Steffen Jung, Margret Keuper
Abstract: Deep neural networks are susceptible to adversarial attacks and common corruptions, which undermine their robustness. In order to enhance model resilience against such challenges, Adversarial Training (AT) has emerged as a prominent solution. Nevertheless, adversarial robustness is often attained at the expense of model fairness during AT, i.e., disparity in class-wise robustness of the model. While distinctive classes become more robust towards such adversaries, hard to detect classes suffer. Recently, research has focused on improving model fairness specifically for perturbed images, overlooking the accuracy of the most likely non-perturbed data. Additionally, despite their robustness against the adversaries encountered during model training, state-of-the-art adversarial trained models have difficulty maintaining robustness and fairness when confronted with diverse adversarial threats or common corruptions. In this work, we address the above concerns by introducing a novel approach called Fair Targeted Adversarial Training (FAIR-TAT). We show that using targeted adversarial attacks for adversarial training (instead of untargeted attacks) can allow for more favorable trade-offs with respect to adversarial fairness. Empirical results validate the efficacy of our approach.
Authors: Guan-Hua Huang, Wan-Chen Lai, Tai-Been Chen, Chien-Chin Hsu, Huei-Yung Chen, Yi-Chen Wu, Li-Ren Yeh
Abstract: Parkinson's disease (PD), a degenerative disorder of the central nervous system, is commonly diagnosed using functional medical imaging techniques such as single-photon emission computed tomography (SPECT). In this study, we utilized two SPECT data sets (n = 634 and n = 202) from different hospitals to develop a model capable of accurately predicting PD stages, a multiclass classification task. We used the entire three-dimensional (3D) brain images as input and experimented with various model architectures. Initially, we treated the 3D images as sequences of two-dimensional (2D) slices and fed them sequentially into 2D convolutional neural network (CNN) models pretrained on ImageNet, averaging the outputs to obtain the final predicted stage. We also applied 3D CNN models pretrained on Kinetics-400. Additionally, we incorporated an attention mechanism to account for the varying importance of different slices in the prediction process. To further enhance model efficacy and robustness, we simultaneously trained the two data sets using weight sharing, a technique known as cotraining. Our results demonstrated that 2D models pretrained on ImageNet outperformed 3D models pretrained on Kinetics-400, and models utilizing the attention mechanism outperformed both 2D and 3D models. The cotraining technique proved effective in improving model performance when the cotraining data sets were sufficiently large.
Authors: Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Abstract: Adversarial examples have raised several open questions, such as why they can deceive classifiers and transfer between different models. A prevailing hypothesis to explain these phenomena suggests that adversarial perturbations appear as random noise but contain class-specific features. This hypothesis is supported by the success of perturbation learning, where classifiers trained solely on adversarial examples and the corresponding incorrect labels generalize well to correctly labeled test data. Although this hypothesis and perturbation learning are effective in explaining intriguing properties of adversarial examples, their solid theoretical foundation is limited. In this study, we theoretically explain the counterintuitive success of perturbation learning. We assume wide two-layer networks and the results hold for any data distribution. We prove that adversarial perturbations contain sufficient class-specific features for networks to generalize from them. Moreover, the predictions of classifiers trained on mislabeled adversarial examples coincide with those of classifiers trained on correctly labeled clean samples. The code is available at https://github.com/s-kumano/perturbation-learning.
Authors: Malcolm Wolff, Kin G. Olivares, Boris Oreshkin, Sunny Ruan, Sitan Yang, Abhinav Katoch, Shankar Ramasubramanian, Youxin Zhang, Michael W. Mahoney, Dmitry Efimov, Vincent Quenneville-B\'elair
Abstract: Demand forecasting faces challenges induced by Peak Events (PEs) corresponding to special periods such as promotions and holidays. Peak events create significant spikes in demand followed by demand ramp down periods. Neural networks like MQCNN and MQT overreact to demand peaks by carrying over the elevated PE demand into subsequent Post-Peak-Event (PPE) periods, resulting in significantly over-biased forecasts. To tackle this challenge, we introduce a neural forecasting model called Split Peak Attention DEcomposition, SPADE. This model reduces the impact of PEs on subsequent forecasts by modeling forecasting as consisting of two separate tasks: one for PEs; and the other for the rest. Its architecture then uses masked convolution filters and a specialized Peak Attention module. We show SPADE's performance on a worldwide retail dataset with hundreds of millions of products. Our results reveal an overall PPE improvement of 4.5%, a 30% improvement for most affected forecasts after promotions and holidays, and an improvement in PE accuracy by 3.9%, relative to current production models.
Authors: Zikai Zhou, Shitong Shao, Lichen Bai, Zhiqiang Xu, Bo Han, Zeke Xie
Abstract: Text-to-image diffusion model is a popular paradigm that synthesizes personalized images by providing a text prompt and a random Gaussian noise. While people observe that some noises are ``golden noises'' that can achieve better text-image alignment and higher human preference than others, we still lack a machine learning framework to obtain those golden noises. To learn golden noises for diffusion sampling, we mainly make three contributions in this paper. First, we identify a new concept termed the \textit{noise prompt}, which aims at turning a random Gaussian noise into a golden noise by adding a small desirable perturbation derived from the text prompt. Following the concept, we first formulate the \textit{noise prompt learning} framework that systematically learns ``prompted'' golden noise associated with a text prompt for diffusion models. Second, we design a noise prompt data collection pipeline and collect a large-scale \textit{noise prompt dataset}~(NPD) that contains 100k pairs of random noises and golden noises with the associated text prompts. With the prepared NPD as the training dataset, we trained a small \textit{noise prompt network}~(NPNet) that can directly learn to transform a random noise into a golden noise. The learned golden noise perturbation can be considered as a kind of prompt for noise, as it is rich in semantic information and tailored to the given text prompt. Third, our extensive experiments demonstrate the impressive effectiveness and generalization of NPNet on improving the quality of synthesized images across various diffusion models, including SDXL, DreamShaper-xl-v2-turbo, and Hunyuan-DiT. Moreover, NPNet is a small and efficient controller that acts as a plug-and-play module with very limited additional inference and computational costs, as it just provides a golden noise instead of a random noise without accessing the original pipeline.
Authors: Eric Balkanski, Will Ma, Andreas Maggiori
Abstract: Algorithms with predictions is a recent framework for decision-making under uncertainty that leverages the power of machine-learned predictions without making any assumption about their quality. The goal in this framework is for algorithms to achieve an improved performance when the predictions are accurate while maintaining acceptable guarantees when the predictions are erroneous. A serious concern with algorithms that use predictions is that these predictions can be biased and, as a result, cause the algorithm to make decisions that are deemed unfair. We show that this concern manifests itself in the classical secretary problem in the learning-augmented setting -- the state-of-the-art algorithm can have zero probability of accepting the best candidate, which we deem unfair, despite promising to accept a candidate whose expected value is at least $\max\{\Omega (1) , 1 - O(\epsilon)\}$ times the optimal value, where $\epsilon$ is the prediction error. We show how to preserve this promise while also guaranteeing to accept the best candidate with probability $\Omega(1)$. Our algorithm and analysis are based on a new "pegging" idea that diverges from existing works and simplifies/unifies some of their results. Finally, we extend to the $k$-secretary problem and complement our theoretical analysis with experiments.
Authors: Arnav M. Das, Chi Ian Tang, Fahim Kawsar, Mohammad Malekzadeh
Abstract: Sensing human motions through Inertial Measurement Units (IMUs) embedded in personal devices has enabled significant applications in health and wellness. Labeled IMU data is scarce, however, unlabeled or weakly labeled IMU data can be used to model human motions. For video or text modalities, the "pretrain and adapt" approach utilizes large volumes of unlabeled or weakly labeled data to build a strong feature extractor, followed by adaptation to specific tasks using limited labeled data. However, pretraining methods are poorly understood for IMU data, and pipelines are rarely evaluated on out-of-domain tasks. We propose PRIMUS: a method for PRetraining IMU encoderS that uses a novel pretraining objective that is empirically validated based on downstream performance on both in-domain and out-of-domain datasets. The PRIMUS objective effectively enhances downstream performance by combining self-supervision, multimodal, and nearest-neighbor supervision. With fewer than 500 labeled samples per class, PRIMUS improves test accuracy by up to 15%, compared to state-of-the-art baselines. To benefit the broader community, we have open-sourced our code at github.com/nokia-bell-labs/pretrained-imu-encoders.
Authors: Jiani Yan, Charles Rahal
Abstract: We propose a rigorous decomposition of predictive error, highlighting that not all 'irreducible' error is genuinely immutable. Many domains stand to benefit from iterative enhancements in measurement, construct validity, and modeling. Our approach demonstrates how apparently 'unpredictable' outcomes can become more tractable with improved data (across both target and features) and refined algorithms. By distinguishing aleatoric from epistemic error, we delineate how accuracy may asymptotically improve--though inherent stochasticity may remain--and offer a robust framework for advancing computational research.
Authors: Yang Cai, Xiangyu Liu, Argyris Oikonomou, Kaiqing Zhang
Abstract: Partial observability of the underlying states generally presents significant challenges for reinforcement learning (RL). In practice, certain \emph{privileged information}, e.g., the access to states from simulators, has been exploited in training and has achieved prominent empirical successes. To better understand the benefits of privileged information, we revisit and examine several simple and practically used paradigms in this setting. Specifically, we first formalize the empirical paradigm of \emph{expert distillation} (also known as \emph{teacher-student} learning), demonstrating its pitfall in finding near-optimal policies. We then identify a condition of the partially observable environment, the \emph{deterministic filter condition}, under which expert distillation achieves sample and computational complexities that are \emph{both} polynomial. Furthermore, we investigate another useful empirical paradigm of \emph{asymmetric actor-critic}, and focus on the more challenging setting of observable partially observable Markov decision processes. We develop a belief-weighted asymmetric actor-critic algorithm with polynomial sample and quasi-polynomial computational complexities, in which one key component is a new provable oracle for learning belief states that preserve \emph{filter stability} under a misspecified model, which may be of independent interest. Finally, we also investigate the provable efficiency of partially observable multi-agent RL (MARL) with privileged information. We develop algorithms featuring \emph{centralized-training-with-decentralized-execution}, a popular framework in empirical MARL, with polynomial sample and (quasi-)polynomial computational complexities in both paradigms above. Compared with a few recent related theoretical studies, our focus is on understanding practically inspired algorithmic paradigms, without computationally intractable oracles.
Authors: Vincent Abbott, Gioele Zardini
Abstract: Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 performance improvement over native PyTorch by avoiding unnecessary data transfers, but required three iterations over three years to be developed. Automated compiled methods have consistently lagged behind. This paper extends Neural Circuit Diagrams for deep learning models to consider resource usage and the distribution of tasks across a GPU hierarchy. We show how diagrams can use simple relabellings to derive high-level streaming and tiling optimization strategies along with performance models. We show how this high-level performance model allows the effects of quantization and multi-level GPU hierarchies to be readily considered. We develop a methodology for representing intermediate-level pseudocode with diagrams, allowing hardware-aware algorithms to be derived step-by-step. Finally, we show how our methodology can be used to better understand existing techniques like FlashAttention. This work uses a theoretical framework to link assumptions about GPU behaviour to claims about performance. We aim to lay the groundwork for a scientific approach to GPU optimization where experiments can address clear hypotheses rather than post-hoc rationalizations.
Authors: Hanqing Zhu, Zhenyu Zhang, Wenyan Cong, Xi Liu, Sem Park, Vikas Chandra, Bo Long, David Z. Pan, Zhangyang Wang, Jinwon Lee
Abstract: Large language models (LLMs) are notoriously memory-intensive during training, particularly with the popular AdamW optimizer. This memory burden necessitates using more or higher-end GPUs or reducing batch sizes, limiting training scalability and throughput. To address this, various memory-efficient optimizers have been proposed to reduce optimizer memory usage. However, they face critical challenges: (i) reliance on costly SVD operations; (ii) significant performance trade-offs compared to AdamW; and (iii) still substantial optimizer memory overhead to maintain competitive performance. In this work, we identify that AdamW's learning rate adaptation rule can be effectively coarsened as a structured learning rate update. Based on this insight, we propose Approximated Gradient Scaling for Memory-Efficient LLM Optimization (APOLLO), which approximates learning rate scaling using an auxiliary low-rank optimizer state based on pure random projection. This structured learning rate update rule makes APOLLO highly tolerant to further memory reductions while delivering comparable pre-training performance. Even its rank-1 variant, APOLLO-Mini, achieves superior pre-training performance compared to AdamW with SGD-level memory costs. Extensive experiments demonstrate that the APOLLO series performs on-par with or better than AdamW, while achieving greater memory savings by nearly eliminating the optimization states of AdamW. These savings provide significant system-level benefits: (1) Enhanced Throughput: 3x throughput on an 8xA100-80GB setup compared to AdamW by supporting 4x larger batch sizes. (2) Improved Model Scalability: Pre-training LLaMA-13B with naive DDP on A100-80GB GPUs without system-level optimizations. (3) Low-End GPU Friendly Pre-training: Pre-training LLaMA-7B on a single GPU using less than 12 GB of memory with weight quantization.
Authors: Lorenzo Loconte, Antonio Vergari
Abstract: Squared tensor networks (TNs) and their generalization as parameterized computational graphs -- squared circuits -- have been recently used as expressive distribution estimators in high dimensions. However, the squaring operation introduces additional complexity when marginalizing variables or computing the partition function, which hinders their usage in machine learning applications. Canonical forms of popular TNs are parameterized via unitary matrices as to simplify the computation of particular marginals, but cannot be mapped to general circuits since these might not correspond to a known TN. Inspired by TN canonical forms, we show how to parameterize squared circuits to ensure they encode already normalized distributions. We then use this parameterization to devise an algorithm to compute any marginal of squared circuits that is more efficient than a previously known one. We conclude by formally showing the proposed parameterization comes with no expressiveness loss for many circuit classes.
Authors: Rongzhe Wei, Mufei Li, Mohsen Ghassemi, Eleonora Krea\v{c}i\'c, Yifan Li, Xiang Yue, Bo Li, Vamsi K. Potluru, Pan Li, Eli Chien
Abstract: Large Language Models are trained on extensive datasets that often contain sensitive, human-generated information, raising significant concerns about privacy breaches. While certified unlearning approaches offer strong privacy guarantees, they rely on restrictive model assumptions that are not applicable to LLMs. As a result, various unlearning heuristics have been proposed, with the associated privacy risks assessed only empirically. The standard evaluation pipelines typically randomly select data for removal from the training set, apply unlearning techniques, and use membership inference attacks to compare the unlearned models against models retrained without the to-be-unlearned data. However, since every data point is subject to the right to be forgotten, unlearning should be considered in the worst-case scenario from the privacy perspective. Prior work shows that data outliers may exhibit higher memorization effects. Intuitively, they are harder to be unlearn and thus the privacy risk of unlearning them is underestimated in the current evaluation. In this paper, we leverage minority data to identify such a critical flaw in previously widely adopted evaluations. We substantiate this claim through carefully designed experiments, including unlearning canaries related to minority groups, inspired by privacy auditing literature. Using personally identifiable information as a representative minority identifier, we demonstrate that minority groups experience at least 20% more privacy leakage in most cases across six unlearning approaches, three MIAs, three benchmark datasets, and two LLMs of different scales. Given that the right to be forgotten should be upheld for every individual, we advocate for a more rigorous evaluation of LLM unlearning methods. Our minority-aware evaluation framework represents an initial step toward ensuring more equitable assessments of LLM unlearning efficacy.
Authors: Shijun Li, Hilaf Hasson, Jing Hu, Joydeep Ghosh
Abstract: Multi-objective learning aims to optimize multiple objectives simultaneously with a single model for achieving a balanced and satisfying performance on all these objectives. However, it suffers from the difficulty to formalize and conduct the exact learning process, especially considering the possible conflicts between objectives. Existing approaches explores to resolve this primarily in two directions: adapting modeling structure or constraining optimization with certain assumptions. However, a primary issue is that their presuppositions for the effectiveness of their design are insufficient to guarantee the its generality in real-world applications. What's worse, the high space and computation complexity issue makes it even harder to apply them in large-scale, complicated environment such as the recommender systems. To address these issues, we propose a general framework for automatically learning to achieve multiple objectives based on the existing sequential data. We apply the goal-conditioned supervised learning (GCSL) framework to multi-objective learning, by extending the definition of goals from one-dimensional scalar to multi-dimensional vector that perfectly disentangle the representation of different objectives. Meanwhile, GCSL enables the model to simultaneously learn to achieve each objective in a concise supervised learning way, simply guided by existing sequences in the offline data. No additional constraint, special model structure design, or complex optimization algorithms are further required. Apart from that, we formally analyze the property of the goals in GCSL and then firstly propose a goal-generation framework to gain achievable and reasonable goals for inference. Extensive experiments are conducted on real-world recommendation datasets, demonstrating the effectiveness of the proposed method and exploring the feasibility of the goal-generation strategies in GCSL.
Authors: Arsha Nagrani, Mingda Zhang, Ramin Mehran, Rachel Hornung, Nitesh Bharadwaj Gundavarapu, Nilpa Jha, Austin Myers, Xingyi Zhou, Boqing Gong, Cordelia Schmid, Mikhail Sirotenko, Yukun Zhu, Tobias Weyand
Abstract: We introduce Neptune, a benchmark for long video understanding that requires reasoning over long time horizons and across different modalities. Many existing video datasets and models are focused on short clips (10s-30s). While some long video datasets do exist, they can often be solved by powerful image models applied per frame (and often to very few frames) in a video, and are usually manually annotated at high cost. In order to mitigate both these problems, we propose a scalable dataset creation pipeline which leverages large models (VLMs and LLMs), to automatically generate dense, time-aligned video captions, as well as tough question answer decoy sets for video segments (up to 15 minutes in length). Our dataset Neptune covers a broad range of long video reasoning abilities and consists of a subset that emphasizes multimodal reasoning. Since existing metrics for open-ended question answering are either rule-based or may rely on proprietary models, we provide a new open source model-based metric GEM to score open-ended responses on Neptune. Benchmark evaluations reveal that most current open-source long video models perform poorly on Neptune, particularly on questions testing temporal ordering, counting and state changes. Through Neptune, we aim to spur the development of more advanced models capable of understanding long videos. The dataset is available at https://github.com/google-deepmind/neptune
Authors: Dannong Wang, Daniel Kim, Bo Jin, Xingjian Zhao, Tianfan Fu, Steve Yang, Xiao-Yang Liu
Abstract: Finetuned large language models (LLMs) have shown remarkable performance in financial tasks, such as sentiment analysis and information retrieval. Due to privacy concerns, finetuning and deploying Financial LLMs (FinLLMs) locally are crucial for institutions. However, finetuning FinLLMs poses challenges including GPU memory constraints and long input sequences. In this paper, we employ quantized low-rank adaptation (QLoRA) to finetune FinLLMs, which leverage low-rank matrix decomposition and quantization techniques to significantly reduce computational requirements while maintaining high model performance. We also employ data and pipeline parallelism to enable local finetuning using cost-effective, widely accessible GPUs. Experiments on financial datasets demonstrate that our method achieves substantial improvements in accuracy, GPU memory usage, and time efficiency, underscoring the potential of lowrank methods for scalable and resource-efficient LLM finetuning.
Authors: Yanna Ding, Zijie Huang, Xiao Shou, Yihang Guo, Yizhou Sun, Jianxi Gao
Abstract: Learning curve extrapolation predicts neural network performance from early training epochs and has been applied to accelerate AutoML, facilitating hyperparameter tuning and neural architecture search. However, existing methods typically model the evolution of learning curves in isolation, neglecting the impact of neural network (NN) architectures, which influence the loss landscape and learning trajectories. In this work, we explore whether incorporating neural network architecture improves learning curve modeling and how to effectively integrate this architectural information. Motivated by the dynamical system view of optimization, we propose a novel architecture-aware neural differential equation model to forecast learning curves continuously. We empirically demonstrate its ability to capture the general trend of fluctuating learning curves while quantifying uncertainty through variational parameters. Our model outperforms current state-of-the-art learning curve extrapolation methods and pure time-series modeling approaches for both MLP and CNN-based learning curves. Additionally, we explore the applicability of our method in Neural Architecture Search scenarios, such as training configuration ranking.
Authors: Di Yu, Xin Du, Linshan Jiang, Huijing Zhang, Shunwen Bai, Shuiguang Deng
Abstract: The energy efficiency of deep spiking neural networks (SNNs) aligns with the constraints of resource-limited edge devices, positioning SNNs as a promising foundation for intelligent applications leveraging the extensive data collected by these devices. To address data privacy concerns when deploying SNNs on edge devices, federated learning (FL) facilitates collaborative model training by leveraging data distributed across edge devices without transmitting local data to a central server. However, existing FL approaches struggle with label-skewed data across devices, which leads to drift in local SNN models and degrades the performance of the global SNN model. In this paper, we propose a novel framework called FedLEC, which incorporates intra-client label weight calibration to balance the learning intensity across local labels and inter-client knowledge distillation to mitigate local SNN model bias caused by label absence. Extensive experiments with three different structured SNNs across five datasets (i.e., three non-neuromorphic and two neuromorphic datasets) demonstrate the efficiency of FedLEC. Compared to eight state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59% for the global SNN model under various label skew distribution settings.
Authors: Hyungjun Joo, Hyeonggeun Han, Sehwan Kim, Sangwoo Hong, Jungwoo Lee
Abstract: As the use of machine learning models has increased, numerous studies have aimed to enhance fairness. However, research on the intersection of fairness and explainability remains insufficient, leading to potential issues in gaining the trust of actual users. Here, we propose a novel module that constructs a fair latent space, enabling faithful explanation while ensuring fairness. The fair latent space is constructed by disentangling and redistributing labels and sensitive attributes, allowing the generation of counterfactual explanations for each type of information. Our module is attached to a pretrained generative model, transforming its biased latent space into a fair latent space. Additionally, since only the module needs to be trained, there are advantages in terms of time and cost savings, without the need to train the entire generative model. We validate the fair latent space with various fairness metrics and demonstrate that our approach can effectively provide explanations for biased decisions and assurances of fairness.
Authors: Jacob Fein-Ashley, Rajgopal Kannan, Viktor Prasanna
Abstract: We propose \emph{Contextual Feedback Loops} (CFLs) as a simple yet effective way to infuse top-down context into earlier layers of a neural network. Unlike standard backpropagation, which only revisits network parameters based on how far predictions deviate from labels, CFLs \emph{directly} re-introduce the model's own output signals as feedback to guide repeated cycles of refinement. This mechanism is broadly applicable across architectures (e.g., CNNs and transformers), and empirical results show that iterative top-down feedback boosts the accuracy and coherence of the resulting representations. We suggest that by projecting context back into lower-level processing stages, CFLs bridge the gap between purely bottom-up inference and more dynamic, feedback-driven reasoning.
Authors: Daniil A. Berdyshev, Artem M. Grachev, Sergei L. Shishkin, Bogdan L. Kozyrskiy
Abstract: Meta-learning, i.e., "learning to learn", is a promising approach to enable efficient BCI classifier training with limited amounts of data. It can effectively use collections of in some way similar classification tasks, with rapid adaptation to new tasks where only minimal data are available. However, applying meta-learning to existing classifiers and BCI tasks requires significant effort. To address this issue, we propose EEG-Reptile, an automated library that leverages meta-learning to improve classification accuracy of neural networks in BCIs and other EEG-based applications. It utilizes the Reptile meta-learning algorithm to adapt neural network classifiers of EEG data to the inter-subject domain, allowing for more efficient fine-tuning for a new subject on a small amount of data. The proposed library incorporates an automated hyperparameter tuning module, a data management pipeline, and an implementation of the Reptile meta-learning algorithm. EEG-Reptile automation level allows using it without deep understanding of meta-learning. We demonstrate the effectiveness of EEG-Reptile on two benchmark datasets (BCI IV 2a, Lee2019 MI) and three neural network architectures (EEGNet, FBCNet, EEG-Inception). Our library achieved improvement in both zero-shot and few-shot learning scenarios compared to traditional transfer learning approaches.
Authors: Muyun Li, Aaron Fainman, Stefan Vlaski
Abstract: Decentralized learning strategies allow a collection of agents to learn efficiently from local data sets without the need for central aggregation or orchestration. Current decentralized learning paradigms typically rely on an averaging mechanism to encourage agreement in the parameter space. We argue that in the context of deep neural networks, which are often over-parameterized, encouraging consensus of the neural network outputs, as opposed to their parameters can be more appropriate. This motivates the development of a new decentralized learning algorithm, termed DRT diffusion, based on deep relative trust (DRT), a recently introduced similarity measure for neural networks. We provide convergence analysis for the proposed strategy, and numerically establish its benefit to generalization, especially with sparse topologies, in an image classification task.
Authors: Amitava Das, Suranjana Trivedy, Danush Khanna, Rajarshi Roy, Gurpreet Singh, Basab Ghosh, Yaswanth Narsupalli, Vinija Jain, Vasu Sharma, Aishwarya Naresh Reganti, Aman Chadha
Abstract: The rapid rise of large language models (LLMs) has unlocked many applications but also underscores the challenge of aligning them with diverse values and preferences. Direct Preference Optimization (DPO) is central to alignment but constrained by fixed divergences and limited feature transformations. We propose DPO-Kernels, which integrates kernel methods to address these issues through four key contributions: (i) Kernelized Representations with polynomial, RBF, Mahalanobis, and spectral kernels for richer transformations, plus a hybrid loss combining embedding-based and probability-based objectives; (ii) Divergence Alternatives (Jensen-Shannon, Hellinger, Renyi, Bhattacharyya, Wasserstein, and f-divergences) for greater stability; (iii) Data-Driven Selection metrics that automatically choose the best kernel-divergence pair; and (iv) a Hierarchical Mixture of Kernels for both local precision and global modeling. Evaluations on 12 datasets demonstrate state-of-the-art performance in factuality, safety, reasoning, and instruction following. Grounded in Heavy-Tailed Self-Regularization, DPO-Kernels maintains robust generalization for LLMs, offering a comprehensive resource for further alignment research.
Authors: Mathias Bellat, Jordy D. Orellana Figueroa, Jonathan S. Reeves, Ruhollah Taghizadeh-Mehrjardi, Claudio Tennie, Thomas Scholten
Abstract: Artificial intelligence and machine learning applications in archaeology have increased significantly in recent years, and these now span all subfields, geographical regions, and time periods. The prevalence and success of these applications have remained largely unexamined, as recent reviews on the use of machine learning in archaeology have only focused only on specific subfields of archaeology. Our review examined an exhaustive corpus of 135 articles published between 1997 and 2022. We observed a significant increase in the number of publications from 2019 onwards. Automatic structure detection and artefact classification were the most represented tasks in the articles reviewed, followed by taphonomy, and archaeological predictive modelling. From the review, clustering and unsupervised methods were underrepresented compared to supervised models. Artificial neural networks and ensemble learning account for two thirds of the total number of models used. However, if machine learning models are gaining in popularity they remain subject to misunderstanding. We observed, in some cases, poorly defined requirements and caveats of the machine learning methods used. Furthermore, the goals and the needs of machine learning applications for archaeological purposes are in some cases unclear or poorly expressed. To address this, we proposed a workflow guide for archaeologists to develop coherent and consistent methodologies adapted to their research questions, project scale and data. As in many other areas, machine learning is rapidly becoming an important tool in archaeological research and practice, useful for the analyses of large and multivariate data, although not without limitations. This review highlights the importance of well-defined and well-reported structured methodologies and collaborative practices to maximise the potential of applications of machine learning methods in archaeology.
Authors: Haonan Shi, Tu Ouyang, An Wang
Abstract: Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients' data privacy requirements, and tuning costs. While recent approaches like split learning and offsite tuning demonstrate promising architectures for privacy-preserving fine-tuning, there is a gap in systematically addressing the multidimensional trade-offs required for diverse real-world deployments. We propose several indicative evaluation metrics to guide design trade-offs for privacy-preserving fine-tuning and a series of example designs, collectively named GuardedTuning; they result from novel combinations of system architectures with adapted privacy-enhancement methods and emerging computation techniques. Each design represents distinct trade-offs across model utility, privacy guarantees, and costs. Experimental results demonstrate that these designs protect against data reconstruction attacks while maintaining competitive fine-tuning performance.
Authors: Weihua Cheng, Hanwen Du, Chunxiao Li, Ersheng Ni, Liangdi Tan, Tianqi Xu, Yongxin Ni
Abstract: Knowledge Tracing (KT) is crucial in education assessment, which focuses on depicting students' learning states and assessing students' mastery of subjects. With the rise of modern online learning platforms, particularly massive open online courses (MOOCs), an abundance of interaction data has greatly advanced the development of the KT technology. Previous research commonly adopts deterministic representation to capture students' knowledge states, which neglects the uncertainty during student interactions and thus fails to model the true knowledge state in learning process. In light of this, we propose an Uncertainty-Aware Knowledge Tracing model (UKT) which employs stochastic distribution embeddings to represent the uncertainty in student interactions, with a Wasserstein self-attention mechanism designed to capture the transition of state distribution in student learning behaviors. Additionally, we introduce the aleatory uncertainty-aware contrastive learning loss, which strengthens the model's robustness towards different types of uncertainties. Extensive experiments on six real-world datasets demonstrate that UKT not only significantly surpasses existing deep learning-based models in KT prediction, but also shows unique advantages in handling the uncertainty of student interactions.
Authors: Eklavya Sarkar, Mathew Magimai. -Doss
Abstract: Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high transferability for bioacoustic processing. This paper investigates (i) whether SSL models pre-trained directly on animal vocalizations offer a significant advantage over those pre-trained on speech, and (ii) whether fine-tuning speech-pretrained models on automatic speech recognition (ASR) tasks can enhance bioacoustic classification. We conduct a comparative analysis using three diverse bioacoustic datasets and two different bioacoustic tasks. Results indicate that pre-training on bioacoustic data provides only marginal improvements over speech-pretrained models, with comparable performance in most scenarios. Fine-tuning on ASR tasks yields mixed outcomes, suggesting that the general-purpose representations learned during SSL pre-training are already well-suited for bioacoustic tasks. These findings highlight the robustness of speech-pretrained SSL models for bioacoustics and imply that extensive fine-tuning may not be necessary for optimal performance.
Authors: Stefan Mautner, Rolf Backofen, Fabrizio Costa
Abstract: Generative methods for graphs need to be sufficiently flexible to model complex dependencies between sets of nodes. At the same time, the generated graphs need to satisfy domain-dependent feasibility conditions, that is, they should not violate certain constraints that would make their interpretation impossible within the given application domain (e.g. a molecular graph where an atom has a very large number of chemical bounds). Crucially, constraints can involve not only local but also long-range dependencies: for example, the maximal length of a cycle can be bounded. Currently, a large class of generative approaches for graphs, such as methods based on artificial neural networks, is based on message passing schemes. These approaches suffer from information 'dilution' issues that severely limit the maximal range of the dependencies that can be modeled. To address this problem, we propose a generative approach based on the notion of graph grammars. The key novel idea is to introduce a domain-dependent coarsening procedure to provide short-cuts for long-range dependencies. We show the effectiveness of our proposal in two domains: 1) small drugs and 2) RNA secondary structures. In the first case, we compare the quality of the generated molecular graphs via the Molecular Sets (MOSES) benchmark suite, which evaluates the distance between generated and real molecules, their lipophilicity, synthesizability, and drug-likeness. In the second case, we show that the approach can generate very large graphs (with hundreds of nodes) that are accepted as valid examples for a desired RNA family by the "Infernal" covariance model, a state-of-the-art RNA classifier. Our implementation is available on github: github.com/fabriziocosta/GraphLearn
Authors: Jiayi Huang, Sangwoo Park, Nicola Paoletti, Osvaldo Simeone
Abstract: Deploying artificial intelligence (AI) models on edge devices involves a delicate balance between meeting stringent complexity constraints, such as limited memory and energy resources, and ensuring reliable performance in sensitive decision-making tasks. One way to enhance reliability is through uncertainty quantification via Bayesian inference. This approach, however, typically necessitates maintaining and running multiple models in an ensemble, which may exceed the computational limits of edge devices. This paper introduces a low-complexity methodology to address this challenge by distilling calibration information from a more complex model. In an offline phase, predictive probabilities generated by a high-complexity cloud-based model are leveraged to determine a threshold based on the typical divergence between the cloud and edge models. At run time, this threshold is used to construct credal sets -- ranges of predictive probabilities that are guaranteed, with a user-selected confidence level, to include the predictions of the cloud model. The credal sets are obtained through thresholding of a divergence measure in the simplex of predictive probabilities. Experiments on visual and language tasks demonstrate that the proposed approach, termed Conformalized Distillation for Credal Inference (CD-CI), significantly improves calibration performance compared to low-complexity Bayesian methods, such as Laplace approximation, making it a practical and efficient solution for edge AI deployments.
Authors: Kunpeng Xu, Lifei Chen, Shengrui Wang
Abstract: Kernel-based subspace clustering, which addresses the nonlinear structures in data, is an evolving area of research. Despite noteworthy progressions, prevailing methodologies predominantly grapple with limitations relating to (i) the influence of predefined kernels on model performance; (ii) the difficulty of preserving the original manifold structures in the nonlinear space; (iii) the dependency of spectral-type strategies on the ideal block diagonal structure of the affinity matrix. This paper presents DKLM, a novel paradigm for kernel-induced nonlinear subspace clustering. DKLM provides a data-driven approach that directly learns the kernel from the data's self-representation, ensuring adaptive weighting and satisfying the multiplicative triangle inequality constraint, which enhances the robustness of the learned kernel. By leveraging this learned kernel, DKLM preserves the local manifold structure of data in a nonlinear space while promoting the formation of an optimal block-diagonal affinity matrix. A thorough theoretical examination of DKLM reveals its relationship with existing clustering paradigms. Comprehensive experiments on synthetic and real-world datasets demonstrate the effectiveness of the proposed method.
Authors: Surjo Dey, Ankit Sharma, Hritu Raj, Susham Biswas
Abstract: This study introduces an advanced methodology for automatically identifying minor deformations in flat walls caused by vibrations from nearby railway tracks. It leverages high-density Terrestrial Laser Scanner (TLS) LiDAR surveys and AI/ML techniques to collect and analyze data. The scan data is processed into a detailed point cloud, which is segmented to distinguish ground points, trees, buildings, and other objects. The analysis focuses on identifying sections along flat walls and estimating their deformations relative to the ground orientation. Findings from the study, conducted at the RGIPT campus, reveal significant deformations in walls close to the railway corridor, with the highest deformations ranging from 7 to 8 cm and an average of 3 to 4 cm. In contrast, walls further from the corridor show negligible deformations. The developed automated process for feature extraction and deformation monitoring demonstrates potential for structural health monitoring. By integrating LiDAR data with machine learning, the methodology provides an efficient system for identifying and analyzing structural deformations, highlighting the importance of continuous monitoring for ensuring structural integrity and public safety in urban infrastructure. This approach represents a substantial advancement in automated feature extraction and deformation analysis, contributing to more effective management of urban infrastructure.
Authors: Muru Zhang, Mayank Mishra, Zhongzhu Zhou, William Brandon, Jue Wang, Yoon Kim, Jonathan Ragan-Kelley, Shuaiwen Leon Song, Ben Athiwaratkun, Tri Dao
Abstract: Large language model inference is both memory-intensive and time-consuming, often requiring distributed algorithms to efficiently scale. Various model parallelism strategies are used in multi-gpu training and inference to partition computation across multiple devices, reducing memory load and computation time. However, using model parallelism necessitates communication of information between GPUs, which has been a major bottleneck and limits the gains obtained by scaling up the number of devices. We introduce Ladder Residual, a simple architectural modification applicable to all residual-based models that enables straightforward overlapping that effectively hides the latency of communication. Our insight is that in addition to systems optimization, one can also redesign the model architecture to decouple communication from computation. While Ladder Residual can allow communication-computation decoupling in conventional parallelism patterns, we focus on Tensor Parallelism in this paper, which is particularly bottlenecked by its heavy communication. For a Transformer model with 70B parameters, applying Ladder Residual to all its layers can achieve 30% end-to-end wall clock speed up at inference time with TP sharding over 8 devices. We refer the resulting Transformer model as the Ladder Transformer. We train a 1B and 3B Ladder Transformer from scratch and observe comparable performance to a standard dense transformer baseline. We also show that it is possible to convert parts of the Llama-3.1 8B model to our Ladder Residual architecture with minimal accuracy degradation by only retraining for 3B tokens.
Authors: Weixin Chen, Simon Yu, Huajie Shao, Lui Sha, Han Zhao
Abstract: End-to-end deep neural networks have achieved remarkable success across various domains but are often criticized for their lack of interpretability. While post hoc explanation methods attempt to address this issue, they often fail to accurately represent these black-box models, resulting in misleading or incomplete explanations. To overcome these challenges, we propose an inherently transparent model architecture called Neural Probabilistic Circuits (NPCs), which enable compositional and interpretable predictions through logical reasoning. In particular, an NPC consists of two modules: an attribute recognition model, which predicts probabilities for various attributes, and a task predictor built on a probabilistic circuit, which enables logical reasoning over recognized attributes to make class predictions. To train NPCs, we introduce a three-stage training algorithm comprising attribute recognition, circuit construction, and joint optimization. Moreover, we theoretically demonstrate that an NPC's error is upper-bounded by a linear combination of the errors from its modules. To further demonstrate the interpretability of NPC, we provide both the most probable explanations and the counterfactual explanations. Empirical results on four benchmark datasets show that NPCs strike a balance between interpretability and performance, achieving results competitive even with those of end-to-end black-box models while providing enhanced interpretability.
Authors: Hoang-Thang Ta, Duy-Quy Thai, Anh Tran, Grigori Sidorov, Alexander Gelbukh
Abstract: Kolmogorov-Arnold Networks (KANs) represent an innovation in neural network architectures, offering a compelling alternative to Multi-Layer Perceptrons (MLPs) in models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. By advancing network design, KANs drive groundbreaking research and enable transformative applications across various scientific domains involving neural networks. However, existing KANs often require significantly more parameters in their network layers than MLPs. To address this limitation, this paper introduces PRKANs (Parameter-Reduced Kolmogorov-Arnold Networks), which employ several methods to reduce the parameter count in KAN layers, making them comparable to MLP layers. Experimental results on the MNIST and Fashion-MNIST datasets demonstrate that PRKANs outperform several existing KANs, and their variant with attention mechanisms rivals the performance of MLPs, albeit with slightly longer training times. Furthermore, the study highlights the advantages of Gaussian Radial Basis Functions (GRBFs) and layer normalization in KAN designs. The repository for this work is available at: https://github.com/hoangthangta/All-KAN.
Authors: Adrian Celaya, David Fuentes, Beatrice Riviere
Abstract: Physics-informed neural networks (PINNs) have gained significant attention for solving forward and inverse problems related to partial differential equations (PDEs). While advancements in loss functions and network architectures have improved PINN accuracy, the impact of collocation point sampling on their performance remains underexplored. Fixed sampling methods, such as uniform random sampling and equispaced grids, can fail to capture critical regions with high solution gradients, limiting their effectiveness for complex PDEs. Adaptive methods, inspired by adaptive mesh refinement from traditional numerical methods, address this by dynamically updating collocation points during training but may overlook residual dynamics between updates, potentially losing valuable information. To overcome this limitation, we propose an adaptive collocation point selection strategy utilizing the QR Discrete Empirical Interpolation Method (QR-DEIM), a reduced-order modeling technique for efficiently approximating nonlinear functions. Our results on benchmark PDEs, including the wave, Allen-Cahn, and Burgers' equations, demonstrate that our QR-DEIM-based approach improves PINN accuracy compared to existing methods, offering a promising direction for adaptive collocation point strategies.
Authors: Marine Hamon, Vincent Lemaire, Nour Eddine Yassine Nair-Benrekia, Samuel Berlemont, Julien Cumin
Abstract: To detect anomalies with precision and without prior knowledge in time series, is it better to build a detector from the initial temporal representation, or to compute a new (tabular) representation using an existing automatic variable construction library? In this article, we address this question by conducting an in-depth experimental study for two popular detectors (Isolation Forest and Local Outlier Factor). The obtained results, for 5 different datasets, show that the new representation, computed using the tsfresh library, allows Isolation Forest to significantly improve its performance.
Authors: Anastasios N. Angelopoulos, Michael I. Jordan, Ryan J. Tibshirani
Abstract: We present a new perspective on online learning that we refer to as gradient equilibrium: a sequence of iterates achieves gradient equilibrium if the average of gradients of losses along the sequence converges to zero. In general, this condition is not implied by nor implies sublinear regret. It turns out that gradient equilibrium is achievable by standard online learning methods such as gradient descent and mirror descent with constant step sizes (rather than decaying step sizes, as is usually required for no regret). Further, as we show through examples, gradient equilibrium translates into an interpretable and meaningful property in online prediction problems spanning regression, classification, quantile estimation, and others. Notably, we show that the gradient equilibrium framework can be used to develop a debiasing scheme for black-box predictions under arbitrary distribution shift, based on simple post hoc online descent updates. We also show that post hoc gradient updates can be used to calibrate predicted quantiles under distribution shift, and that the framework leads to unbiased Elo scores for pairwise preference prediction.
Authors: Kavita Selva, Satita Vittayaareekul, Brando Miranda
Abstract: Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We hypothesize that dataset diversity can impact the performance of vision models. Our study shows positive correlations between test set accuracy and data diversity, providing an argument for furthering the research of dataset attributes beyond size. We analyzed pre-training and model-agnostic meta-learning methods on twelve popular visual datasets (e.g., Omniglot, CIFAR-FS, Aircraft) and five model configurations, including MAML variants with different numbers of inner gradient steps and supervised learning. We show moderate to strong positive correlations (R-squared: 0.15-0.42) between accuracy and data diversity and weaker but significant correlations (R-squared: ~0.2) between loss and diversity. These findings support our hypothesis and demonstrate a promising way for a deeper exploration of how formal data diversity influences model performance. This initial study highlights the potential of (Task2Vec) data diversity as a valuable measure in the rapidly evolving field of large-scale learning and emphasizes that understanding the dataset is key to building more powerful and generalizable models.
Authors: Wang-Tao Zhou, Zhao Kang, Sicong Liu, Lizong Zhang, Ling Tian
Abstract: Event prediction tasks often handle spatio-temporal data distributed in a large spatial area. Different regions in the area exhibit different characteristics while having latent correlations. This spatial heterogeneity and correlations greatly affect the spatio-temporal distributions of event occurrences, which has not been addressed by state-of-the-art models. Learning spatial dependencies of events in a continuous space is challenging due to its fine granularity and a lack of prior knowledge. In this work, we propose a novel Graph Spatio-Temporal Point Process (GSTPP) model for fine-grained event prediction. It adopts an encoder-decoder architecture that jointly models the state dynamics of spatially localized regions using neural Ordinary Differential Equations (ODEs). The state evolution is built on the foundation of a novel Self-Adaptive Anchor Graph (SAAG) that captures spatial dependencies. By adaptively localizing the anchor nodes in the space and jointly constructing the correlation edges between them, the SAAG enhances the model's ability of learning complex spatial event patterns. The proposed GSTPP model greatly improves the accuracy of fine-grained event prediction. Extensive experimental results show that our method greatly improves the prediction accuracy over existing spatio-temporal event prediction approaches.
Authors: Pierfrancesco Beneventano, Blake Woodworth
Abstract: We study the gradient descent (GD) dynamics of a depth-2 linear neural network with a single input and output. We show that GD converges at an explicit linear rate to a global minimum of the training loss, even with a large stepsize -- about $2/\textrm{sharpness}$. It still converges for even larger stepsizes, but may do so very slowly. We also characterize the solution to which GD converges, which has lower norm and sharpness than the gradient flow solution. Our analysis reveals a trade off between the speed of convergence and the magnitude of implicit regularization. This sheds light on the benefits of training at the ``Edge of Stability'', which induces additional regularization by delaying convergence and may have implications for training more complex models.
Authors: Md Shofiqul Islam, Khondokar Fida Hasan, Hasibul Hossain Shajeeb, Humayan Kabir Rana, Md Saifur Rahmand, Md Munirul Hasan, AKM Azad, Ibrahim Abdullah, Mohammad Ali Moni
Abstract: This study presents a comprehensive review of the potential of multimodal deep learning (DL) in medical diagnosis, using COVID-19 as a case example. Motivated by the success of artificial intelligence applications during the COVID-19 pandemic, this research aims to uncover the capabilities of DL in disease screening, prediction, and classification, and to derive insights that enhance the resilience, sustainability, and inclusiveness of science, technology, and innovation systems. Adopting a systematic approach, we investigate the fundamental methodologies, data sources, preprocessing steps, and challenges encountered in various studies and implementations. We explore the architecture of deep learning models, emphasising their data-specific structures and underlying algorithms. Subsequently, we compare different deep learning strategies utilised in COVID-19 analysis, evaluating them based on methodology, data, performance, and prerequisites for future research. By examining diverse data types and diagnostic modalities, this research contributes to scientific understanding and knowledge of the multimodal application of DL and its effectiveness in diagnosis. We have implemented and analysed 11 deep learning models using COVID-19 image, text, and speech (ie, cough) data. Our analysis revealed that the MobileNet model achieved the highest accuracy of 99.97% for COVID-19 image data and 93.73% for speech data (i.e., cough). However, the BiGRU model demonstrated superior performance in COVID-19 text classification with an accuracy of 99.89%. The broader implications of this research suggest potential benefits for other domains and disciplines that could leverage deep learning techniques for image, text, and speech analysis.
Authors: Hanrong Zhang, Yifei Yao, Zixuan Wang, Jiayuan Su, Mengxuan Li, Peng Peng, Hongwei Wang
Abstract: Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot fault data is challenging, and adding new fault classes often demands costly model retraining. Moreover, incremental training of existing methods risks catastrophic forgetting, and severe class imbalance can bias the model's decisions toward normal classes. To tackle these issues, we introduce a Supervised Contrastive knowledge distiLlation for class Incremental Fault Diagnosis (SCLIFD) framework proposing supervised contrastive knowledge distillation for improved representation learning capability and less forgetting, a novel prioritized exemplar selection method for sample replay to alleviate catastrophic forgetting, and the Random Forest Classifier to address the class imbalance. Extensive experimentation on simulated and real-world industrial datasets across various imbalance ratios demonstrates the superiority of SCLIFD over existing approaches. Our code can be found at https://github.com/Zhang-Henry/SCLIFD_TII.
Authors: Nelson Salazar-Pena, Adolfo Palma-Vergara, Mateo Montes-Vera, Maria Alejandra Vargas-Torres, Adriana Salinas, Andres Velasco, Alejandra Tabares, Andres Gonzalez-Mancera
Abstract: The prediction of solar irradiance enhances reliability in photovoltaic (PV) solar plant generation and grid integration. In Colombia, PV plants face penalties if energy production deviates beyond governmental thresholds from intraday market offers. This research employs Long Short-Term Memory (LSTM) and Bidirectional-LSTM (Bi-LSTM) models, utilizing meteorological data from a PV plant in El Paso, Cesar, Colombia, to predict solar irradiance with a 6-hour horizon and 10-minute resolution. While Bi-LSTM showed superior performance, the LSTM model achieved comparable results with significantly reduced training time (6 hours versus 18 hours), making it computationally advantageous. The LSTM predictions were averaged to create an hourly resolution model, evaluated using Mean Absolute Error, Root-Mean-Square Error, Normalized Root-Mean-Square Error, and Mean Absolute Percentage Error metrics. Comparison with the Global Forecast System (GFS) revealed similar performance, with both models effectively capturing daily solar irradiance patterns. The forecast model integrates with an Object-Oriented power production model, enabling accurate energy offers in the intraday market while minimizing penalty costs.
Authors: Samuel Soo, Wesley Teng, Chandrasekaran Balaganesh
Abstract: Effective and reliable control over large language model (LLM) behavior is a significant challenge. While activation steering methods, which add steering vectors to a model's hidden states, are a promising approach, existing techniques often lack precision and interpretability in how they influence model outputs. We introduce Feature Guided Activation Additions (FGAA), a novel activation steering method that leverages insights from Contrastive Activation Addition (CAA) and Sparse Autoencoder-Targeted Steering (SAE-TS). By operating in the latent space of a Sparse Autoencoder (SAE) and employing optimization techniques to select desired SAE features, FGAA constructs precise steering vectors that provide better steering effects while maintaining coherence of steered model outputs. In this regard, evaluations on Gemma-2-2B and Gemma-2-9B models across various steering tasks demonstrate that FGAA outperforms existing steering methods of CAA, SAE decoder steering, and SAE-TS. Our results also highlight important trade-offs between steering scale and general model capabilities that are consistent across all tested steering methods.
Authors: Maxime De Bois, Flora Parmentier, Rapha\"el Puget, Matthew Tanti, Jordan Peltier
Abstract: To take the esports scene to the next level, we introduce PandaSkill, a framework for assessing player performance and skill rating. Traditional rating systems like Elo and TrueSkill often overlook individual contributions and face challenges in professional esports due to limited game data and fragmented competitive scenes. PandaSkill leverages machine learning to estimate in-game player performance from individual player statistics. Each in-game role is modeled independently, ensuring a fair comparison between them. Then, using these performance scores, PandaSkill updates the player skill ratings using the Bayesian framework OpenSkill in a free-for-all setting. In this setting, skill ratings are updated solely based on performance scores rather than game outcomes, hightlighting individual contributions. To address the challenge of isolated rating pools that hinder cross-regional comparisons, PandaSkill introduces a dual-rating system that combines players' regional ratings with a meta-rating representing each region's overall skill level. Applying PandaSkill to five years of professional League of Legends matches worldwide, we show that our method produces skill ratings that better predict game outcomes and align more closely with expert opinions compared to existing methods.
Authors: Zizhou Zhang, Xinshi Li, Yu Cheng, Zhenrui Chen, Qianying Liu
Abstract: Credit risk management within supply chains has emerged as a critical research area due to its significant implications for operational stability and financial sustainability. The intricate interdependencies among supply chain participants mean that credit risks can propagate across networks, with impacts varying by industry. This study explores the application of Generative Adversarial Networks (GANs) to enhance credit risk identification in supply chains. GANs enable the generation of synthetic credit risk scenarios, addressing challenges related to data scarcity and imbalanced datasets. By leveraging GAN-generated data, the model improves predictive accuracy while effectively capturing dynamic and temporal dependencies in supply chain data. The research focuses on three representative industries-manufacturing (steel), distribution (pharmaceuticals), and services (e-commerce) to assess industry-specific credit risk contagion. Experimental results demonstrate that the GAN-based model outperforms traditional methods, including logistic regression, decision trees, and neural networks, achieving superior accuracy, recall, and F1 scores. The findings underscore the potential of GANs in proactive risk management, offering robust tools for mitigating financial disruptions in supply chains. Future research could expand the model by incorporating external market factors and supplier relationships to further enhance predictive capabilities. Keywords- Generative Adversarial Networks (GANs); Supply Chain Risk; Credit Risk Identification; Machine Learning; Data Augmentation
Authors: Ilya Chevyrev, Andrey Kormilitzin
Abstract: We provide an introduction to the signature method, focusing on its theoretical properties and machine learning applications. Our presentation is divided into two parts. In the first part, we present the definition and fundamental properties of the signature of a path. The signature is a sequence of numbers associated with a path that captures many of its important analytic and geometric properties. As a sequence of numbers, the signature serves as a compact description (dimension reduction) of a path. In presenting its theoretical properties, we assume only familiarity with classical real analysis and integration, and supplement theory with straightforward examples. We also mention several advanced topics, including the role of the signature in rough path theory. In the second part, we present practical applications of the signature to the area of machine learning. The signature method is a non-parametric way of transforming data into a set of features that can be used in machine learning tasks. In this method, data are converted into multi-dimensional paths, by means of embedding algorithms, of which the signature is then computed. We describe this pipeline in detail, making a link with the properties of the signature presented in the first part. We furthermore review some of the developments of the signature method in machine learning and, as an illustrative example, present a detailed application of the method to handwritten digit classification.
Authors: Wu Lin, Mohammad Emtiyaz Khan, Mark Schmidt
Abstract: Stein's method (Stein, 1973; 1981) is a powerful tool for statistical applications and has significantly impacted machine learning. Stein's lemma plays an essential role in Stein's method. Previous applications of Stein's lemma either required strong technical assumptions or were limited to Gaussian distributions with restricted covariance structures. In this work, we extend Stein's lemma to exponential-family mixture distributions, including Gaussian distributions with full covariance structures. Our generalization enables us to establish a connection between Stein's lemma and the reparameterization trick to derive gradients of expectations of a large class of functions under weak assumptions. Using this connection, we can derive many new reparameterizable gradient identities that go beyond the reach of existing works. For example, we give gradient identities when the expectation is taken with respect to Student's t-distribution, skew Gaussian, exponentially modified Gaussian, and normal inverse Gaussian.
Authors: Yuke Zhu, Josiah Wong, Ajay Mandlekar, Roberto Mart\'in-Mart\'in, Abhishek Joshi, Kevin Lin, Abhiram Maddukuri, Soroush Nasiriany, Yifeng Zhu
Abstract: robosuite is a simulation framework for robot learning powered by the MuJoCo physics engine. It offers a modular design for creating robotic tasks as well as a suite of benchmark environments for reproducible research. This paper discusses the key system modules and the benchmark environments of our new release robosuite v1.5.
Authors: Ilia Kamyshev, Sahar Moghimian Hoosh, Dmitrii Kriukov, Elena Gryazina, Henni Ouerdane
Abstract: The global effort toward renewable energy and the electrification of energy-intensive sectors have significantly increased the demand for electricity, making energy efficiency a critical focus. Non-intrusive load monitoring (NILM) enables detailed analyses of household electricity usage by disaggregating the total power consumption into individual appliance-level data. In this paper, we propose COLD (Concurrent Loads Disaggregator), a transformer-based model specifically designed to address the challenges of disaggregating high-frequency data with multiple simultaneously working devices. COLD supports up to 42 devices and accurately handles scenarios with up to 11 concurrent loads, achieving 95% load identification accuracy and 82% disaggregation performance on the test data. In addition, we introduce a new fully labeled high-frequency NILM dataset for load disaggregation derived from the UK-DALE 16 kHz dataset. Finally, we analyze the decline in NILM model performance as the number of concurrent loads increases.
Authors: Sanket Kalwar, Animikh Aich, Tanay Dixit, Adit Chhabra
Abstract: In autoencoder, the encoder generally approximates the latent distribution over the dataset, and the decoder generates samples using this learned latent distribution. There is very little control over the latent vector as using the random latent vector for generation will lead to trivial outputs. This work tries to address this issue by using the LatentGAN generator to directly learn to approximate the latent distribution of the autoencoder and show meaningful results on MNIST, 3D Chair, and CelebA datasets, an additional information-theoretic constrain is used which successfully learns to control autoencoder latent distribution. With this, our model also achieves an error rate of 2.38 on MNIST unsupervised image classification, which is better as compared to InfoGAN and AAE.
Authors: Jaime Moraga
Abstract: This article describes Jigsaw, a convolutional neural network (CNN) used in geosciences and based on Inception but tailored for geoscientific analyses. Introduces JigsawHSI (based on Jigsaw) and uses it on the land-use land-cover (LULC) classification problem with the Indian Pines, Pavia University and Salinas hyperspectral image data sets. The network is compared against HybridSN, a spectral-spatial 3D-CNN followed by 2D-CNN that achieves state-of-the-art results on the datasets. This short article proves that JigsawHSI is able to meet or exceed HybridSN's performance in all three cases. It also introduces a generalized Jigsaw architecture in d-dimensional space for any number of multimodal inputs. Additionally, the use of jigsaw in geosciences is highlighted, while the code and toolkit are made available.
Authors: Hu\'e Sullivan, Hurlin Christophe, P\'erignon Christophe, Saurin S\'ebastien
Abstract: As they play an increasingly important role in determining access to credit, credit scoring models are under growing scrutiny from banking supervisors and internal model validators. These authorities need to monitor the model performance and identify its key drivers. To facilitate this, we introduce the XPER methodology to decompose a performance metric (e.g., AUC, $R^2$) into specific contributions associated with the various features of a forecasting model. XPER is theoretically grounded on Shapley values and is both model-agnostic and performance metric-agnostic. Furthermore, it can be implemented either at the model level or at the individual level. Using a novel dataset of car loans, we decompose the AUC of a machine-learning model trained to forecast the default probability of loan applicants. We show that a small number of features can explain a surprisingly large part of the model performance. Notably, the features that contribute the most to the predictive performance of the model may not be the ones that contribute the most to individual forecasts (SHAP). Finally, we show how XPER can be used to deal with heterogeneity issues and improve performance.
Authors: Lu Xia, Michiel E. Hochstenbach, Stefano Massei
Abstract: When training neural networks with low-precision computation, rounding errors often cause stagnation or are detrimental to the convergence of the optimizers; in this paper we study the influence of rounding errors on the convergence of the gradient descent method for problems satisfying the Polyak-\Lojasiewicz inequality. Within this context, we show that, in contrast, biased stochastic rounding errors may be beneficial since choosing a proper rounding strategy eliminates the vanishing gradient problem and forces the rounding bias in a descent direction. Furthermore, we obtain a bound on the convergence rate that is stricter than the one achieved by unbiased stochastic rounding. The theoretical analysis is validated by comparing the performances of various rounding strategies when optimizing several examples using low-precision fixed-point number formats.
Authors: Zheng Dong, Zekai Fan, Shixiang Zhu
Abstract: Point processes offer a versatile framework for sequential event modeling. However, the computational challenges and constrained representational power of the existing point process models have impeded their potential for wider applications. This limitation becomes especially pronounced when dealing with event data that is associated with multi-dimensional or high-dimensional marks such as texts or images. To address this challenge, this study proposes a novel event-generation framework for modeling point processes with high-dimensional marks. We aim to capture the distribution of events without explicitly specifying the conditional intensity or probability density function. Instead, we use a conditional generator that takes the history of events as input and generates the high-quality subsequent event that is likely to occur given the prior observations. The proposed framework offers a host of benefits, including considerable representational power to capture intricate dynamics in multi- or even high-dimensional event space, as well as exceptional efficiency in learning the model and generating samples. Our numerical results demonstrate superior performance compared to other state-of-the-art baselines.
Authors: Boyao Li, Alexander J. Thomson, Houssam Nassif, Matthew M. Engelhard, David Page
Abstract: Deep neural networks (DNNs) lack the precise semantics and definitive probabilistic interpretation of probabilistic graphical models (PGMs). In this paper, we propose an innovative solution by constructing infinite tree-structured PGMs that correspond exactly to neural networks. Our research reveals that DNNs, during forward propagation, indeed perform approximations of PGM inference that are precise in this alternative PGM structure. Not only does our research complement existing studies that describe neural networks as kernel machines or infinite-sized Gaussian processes, it also elucidates a more direct approximation that DNNs make to exact inference in PGMs. Potential benefits include improved pedagogy and interpretation of DNNs, and algorithms that can merge the strengths of PGMs and DNNs.
Authors: Kuangyu Ding, Jingyang Li, Kim-Chuan Toh
Abstract: Stochastic gradient methods for minimizing nonconvex composite objective functions typically rely on the Lipschitz smoothness of the differentiable part, but this assumption fails in many important problem classes like quadratic inverse problems and neural network training, leading to instability of the algorithms in both theory and practice. To address this, we propose a family of stochastic Bregman proximal gradient (SBPG) methods that only require smooth adaptivity. SBPG replaces the quadratic approximation in SGD with a Bregman proximity measure, offering a better approximation model that handles non-Lipschitz gradients in nonconvex objectives. We establish the convergence properties of vanilla SBPG and show it achieves optimal sample complexity in the nonconvex setting. Experimental results on quadratic inverse problems demonstrate SBPG's robustness in terms of stepsize selection and sensitivity to the initial point. Furthermore, we introduce a momentum-based variant, MSBPG, which enhances convergence by relaxing the mini-batch size requirement while preserving the optimal oracle complexity. We apply MSBPG to the training of deep neural networks, utilizing a polynomial kernel function to ensure smooth adaptivity of the loss function. Experimental results on benchmark datasets confirm the effectiveness and robustness of MSBPG in training neural networks. Given its negligible additional computational cost compared to SGD in large-scale optimization, MSBPG shows promise as a universal open-source optimizer for future applications.
Authors: Walter Hernandez Cruz, Kamil Tylinski, Alastair Moore, Niall Roche, Nikhil Vadgama, Horst Treiblmaier, Jiangbo Shangguan, Paolo Tasca, Jiahua Xu
Abstract: Emerging technologies, such as Distributed Ledger Technology (DLT), face growing scrutiny for their environmental impact, especially when it comes to the energy use of the Proof of Work (PoW) consensus mechanism and broader Environmental, Social, and Governance (ESG) considerations. Yet, much of the existing systematic literature reviews of DLT rely on the limited analyses of citations, abstracts, and keywords, failing to fully capture the field's complexity and ESG concerns. To address these challenges, we analyze the full text of 24,539 publications using Natural Language Processing (NLP) with our manually labeled Named Entity Recognition (NER) dataset of 39,427 entities for DLT. This method identifies 505 key publications connecting DLT and ESG domains, providing a more comprehensive and nuanced understanding of the field. Our combined NLP and temporal graph analysis reveals critical trends in DLT evolution and ESG impacts, including the pivotal role of research in cryptography and peer-to-peer networks, Bitcoin's persistent impact on research and environmental concerns (a "Lindy effect"), Ethereum's influence on Proof of Stake (PoS) and smart contracts adoption, and a shift towards energy-efficient consensus mechanisms. Our contributions include the first DLT-specific NER dataset, addressing the scarcity of high-quality labeled NLP data for blockchain research; a methodology integrating NLP and temporal graph analysis for interdisciplinary literature review at large scale; and the first NLP-driven DLT literature review emphasizing ESG aspects.
Authors: Sungyeon Kim, Donghyun Kim, Suha Kwak
Abstract: A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of data. In this regard, we explore a new metric learning paradigm, called Unified Metric Learning (UML), which learns a unified distance metric capable of capturing relations across multiple data distributions. UML presents new challenges, such as imbalanced data distribution and bias towards dominant distributions. These issues cause standard metric learning methods to fail in learning a unified metric. To address these challenges, we propose Parameter-efficient Unified Metric leArning (PUMA), which consists of a pre-trained frozen model and two additional modules, stochastic adapter and prompt pool. These modules enable to capture dataset-specific knowledge while avoiding bias towards dominant distributions. Additionally, we compile a new unified metric learning benchmark with a total of 8 different datasets. PUMA outperforms the state-of-the-art dataset-specific models while using about 69 times fewer trainable parameters.
Authors: Tim J. Adler, Jan-Hinrich N\"olke, Annika Reinke, Minu Dietlinde Tizabi, Sebastian Gruber, Dasha Trofimova, Lynton Ardizzone, Paul F. Jaeger, Florian Buettner, Ullrich K\"othe, Lena Maier-Hein
Abstract: Current deep learning-based solutions for image analysis tasks are commonly incapable of handling problems to which multiple different plausible solutions exist. In response, posterior-based methods such as conditional Diffusion Models and Invertible Neural Networks have emerged; however, their translation is hampered by a lack of research on adequate validation. In other words, the way progress is measured often does not reflect the needs of the driving practical application. Closing this gap in the literature, we present the first systematic framework for the application-driven validation of posterior-based methods in inverse problems. As a methodological novelty, it adopts key principles from the field of object detection validation, which has a long history of addressing the question of how to locate and match multiple object instances in an image. Treating modes as instances enables us to perform mode-centric validation, using well-interpretable metrics from the application perspective. We demonstrate the value of our framework through instantiations for a synthetic toy example and two medical vision use cases: pose estimation in surgery and imaging-based quantification of functional tissue parameters for diagnostics. Our framework offers key advantages over common approaches to posterior validation in all three examples and could thus revolutionize performance assessment in inverse problems.
Authors: Zhuoran Yu, Chenchen Zhu, Sean Culatana, Raghuraman Krishnamoorthi, Fanyi Xiao, Yong Jae Lee
Abstract: Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training images from the finetuned model can enhance an ImageNet classifier's performance. However, performance degrades as synthetic images outnumber real ones. In this paper, we explore whether generative fine-tuning is essential for this improvement and whether it is possible to further scale up training using more synthetic data. We present a new framework leveraging off-the-shelf generative models to generate synthetic training images, addressing multiple challenges: class name ambiguity, lack of diversity in naive prompts, and domain shifts. Specifically, we leverage large language models (LLMs) and CLIP to resolve class name ambiguity. To diversify images, we propose contextualized diversification (CD) and stylized diversification (SD) methods, also prompted by LLMs. Finally, to mitigate domain shifts, we leverage domain adaptation techniques with auxiliary batch normalization for synthetic images. Our framework consistently enhances recognition model performance with more synthetic data, up to 6x of original ImageNet size showcasing the potential of synthetic data for improved recognition models and strong out-of-domain generalization.
Authors: Ilana Sebag, Muni Sreenivas Pydi, Jean-Yves Franceschi, Alain Rakotomamonjy, Mike Gartrell, Jamal Atif, Alexandre Allauzen
Abstract: Safeguarding privacy in sensitive training data is paramount, particularly in the context of generative modeling. This can be achieved through either differentially private stochastic gradient descent or a differentially private metric for training models or generators. In this paper, we introduce a novel differentially private generative modeling approach based on a gradient flow in the space of probability measures. To this end, we define the gradient flow of the Gaussian-smoothed Sliced Wasserstein Distance, including the associated stochastic differential equation (SDE). By discretizing and defining a numerical scheme for solving this SDE, we demonstrate the link between smoothing and differential privacy based on a Gaussian mechanism, due to a specific form of the SDE's drift term. We then analyze the differential privacy guarantee of our gradient flow, which accounts for both the smoothing and the Wiener process introduced by the SDE itself. Experiments show that our proposed model can generate higher-fidelity data at a low privacy budget compared to a generator-based model, offering a promising alternative.
Authors: Abhishek Setty, Rasul Abdusalamov, Felix Motzoi
Abstract: Chebyshev polynomials have shown significant promise as an efficient tool for both classical and quantum neural networks to solve linear and nonlinear differential equations. In this work, we adapt and generalize this framework in a quantum machine learning setting for a variety of problems, including the 2D Poisson's equation, second-order linear differential equation, system of differential equations, nonlinear Duffing and Riccati equation. In particular, we propose in the quantum setting a modified Self-Adaptive Physics-Informed Neural Network (SAPINN) approach, where self-adaptive weights are applied to problems with multi-objective loss functions. We further explore capturing correlations in our loss function using a quantum-correlated measurement, resulting in improved accuracy for initial value problems. We analyse also the use of entangling layers and their impact on the solution accuracy for second-order differential equations. The results indicate a promising approach to the near-term evaluation of differential equations on quantum devices.
Authors: Souradip Chakraborty, Anukriti Singh, Amisha Bhaskar, Pratap Tokekar, Dinesh Manocha, Amrit Singh Bedi
Abstract: The effectiveness of reinforcement learning (RL) agents in continuous control robotics tasks is mainly dependent on the design of the underlying reward function, which is highly prone to reward hacking. A misalignment between the reward function and underlying human preferences (values, social norms) can lead to catastrophic outcomes in the real world especially in the context of robotics for critical decision making. Recent methods aim to mitigate misalignment by learning reward functions from human preferences and subsequently performing policy optimization. However, these methods inadvertently introduce a distribution shift during reward learning due to ignoring the dependence of agent-generated trajectories on the reward learning objective, ultimately resulting in sub-optimal alignment. Hence, in this work, we address this challenge by advocating for the adoption of regularized reward functions that more accurately mirror the intended behaviors of the agent. We propose a novel concept of reward regularization within the robotic RLHF (RL from Human Feedback) framework, which we refer to as \emph{agent preferences}. Our approach uniquely incorporates not just human feedback in the form of preferences but also considers the preferences of the RL agent itself during the reward function learning process. This dual consideration significantly mitigates the issue of distribution shift in RLHF with a computationally tractable algorithm. We provide a theoretical justification for the proposed algorithm by formulating the robotic RLHF problem as a bilevel optimization problem and developing a computationally tractable version of the same. We demonstrate the efficiency of our algorithm {\ours} in several continuous control benchmarks in DeepMind Control Suite \cite{tassa2018deepmind}.
Authors: Kundan Krishna, Sanjana Ramprasad, Prakhar Gupta, Byron C. Wallace, Zachary C. Lipton, Jeffrey P. Bigham
Abstract: LLMs can generate factually incorrect statements even when provided access to reference documents. Such errors can be dangerous in high-stakes applications (e.g., document-grounded QA for healthcare or finance). We present GenAudit -- a tool intended to assist fact-checking LLM responses for document-grounded tasks. GenAudit suggests edits to the LLM response by revising or removing claims that are not supported by the reference document, and also presents evidence from the reference for facts that do appear to have support. We train models to execute these tasks, and design an interactive interface to present suggested edits and evidence to users. Comprehensive evaluation by human raters shows that GenAudit can detect errors in 8 different LLM outputs when summarizing documents from diverse domains. User studies demonstrate that using GenAudit can substantially improve the performance of humans at finding errors in LLM-generated summaries. We release our tool (GenAudit) and fact-checking model for public use.
Authors: Maksim Kuprashevich, Grigorii Alekseenko, Irina Tolstykh
Abstract: Multimodal Large Language Models (MLLMs) have recently gained immense popularity. Powerful commercial models like ChatGPT-4V and Gemini, as well as open-source ones such as LLaVA, are essentially general-purpose models and are applied to solve a wide variety of tasks, including those in computer vision. These neural networks possess such strong general knowledge and reasoning abilities that they have proven capable of working even on tasks for which they were not specifically trained. We compared the capabilities of the most powerful MLLMs to date: ShareGPT4V, ChatGPT, LLaVA-Next in a specialized task of age and gender estimation with our state-of-the-art specialized model, MiVOLO. We also updated MiVOLO and provide details and new metrics in this article. This comparison has yielded some interesting results and insights about the strengths and weaknesses of the participating models. Furthermore, we attempted various ways to fine-tune the ShareGPT4V model for this specific task, aiming to achieve state-of-the-art results in this particular challenge. Although such a model would not be practical in production, as it is incredibly expensive compared to a specialized model like MiVOLO, it could be very useful in some tasks, like data annotation.
Authors: Manish Chandra, Debasis Ganguly, Iadh Ounis
Abstract: In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectively control the generative process seeking to improve the downstream task performance. Existing ICL approaches use an identical number of examples (a pre-configured hyper-parameter) for each data instance. Our work alleviates the limitations of this 'one fits all' approach by dynamically predicting the number of examples for each data instance to be used in few-shot inference with LLMs. In particular, we employ a multi-label classifier, the parameters of which are fitted using a training set, where the label for each instance in this training set indicates if using a specific value of k (number of most similar examples from 0 up to a maximum value) leads to correct k-shot downstream predictions. Our experiments on a number of text classification benchmarks show that AICL substantially outperforms standard ICL by up to 17%.
Authors: Johannes J. Brust
Abstract: For minimization problems without 2nd derivative information, methods that estimate Hessian matrices can be very effective. However, conventional techniques generate dense matrices that are prohibitive for large problems. Limited-memory compact representations express the dense arrays in terms of a low rank representation and have become the state-of-the-art for software implementations on large deterministic problems. We develop new compact representations that are parameterized by a choice of vectors and that reduce to existing well known formulas for special choices. We demonstrate effectiveness of the compact representations for large eigenvalue computations, tensor factorizations and nonlinear regressions.
Authors: Diego A. de Aguiar, Hugo L. Fran\c{c}a, Cassio M. Oishi
Abstract: Neural networks in fluid mechanics offer an efficient approach for exploring complex flows, including multiphase and free surface flows. The recurrent neural network, particularly the Long Short-Term Memory (LSTM) model, proves attractive for learning mappings from transient inputs to dynamic outputs. This study applies LSTM to predict transient and static outputs for fluid flows under surface tension effects. Specifically, we explore two distinct droplet dynamic scenarios: droplets with diverse initial shapes impacting with solid surfaces, as well as the coalescence of two droplets following collision. Using only dimensionless numbers and geometric time series data from numerical simulations, LSTM predicts the energy budget. The marker-and-cell front-tracking methodology combined with a marker-and-cell finite-difference strategy is adopted for simulating the droplet dynamics. Using a recurrent neural network (RNN) architecture fed with time series data derived from geometrical parameters, as for example droplet diameter variation, our study shows the accuracy of our approach in predicting energy budgets, as for instance the kinetic, dissipation, and surface energy trends, across a range of Reynolds and Weber numbers in droplet dynamic problems. Finally, a two-phase sequential neural network using only geometric data, which is readily available in experimental settings, is employed to predict the energies and then use them to estimate static parameters, such as the Reynolds and Weber numbers. While our methodology has been primarily validated with simulation data, its adaptability to experimental datasets is a promising avenue for future exploration. We hope that our strategy can be useful for diverse applications, spanning from inkjet printing to combustion engines, where the prediction of energy budgets or dissipation energies is crucial.
Authors: Francesco Di Feola, Lorenzo Tronchin, Valerio Guarrasi, Paolo Soda
Abstract: Generative Adversarial Networks (GANs) have proved as a powerful framework for denoising applications in medical imaging. However, GAN-based denoising algorithms still suffer from limitations in capturing complex relationships within the images. In this regard, the loss function plays a crucial role in guiding the image generation process, encompassing how much a synthetic image differs from a real image. To grasp highly complex and non-linear textural relationships in the training process, this work presents a novel approach to capture and embed multi-scale texture information into the loss function. Our method introduces a differentiable multi-scale texture representation of the images dynamically aggregated by a self-attention layer, thus exploiting end-to-end gradient-based optimization. We validate our approach by carrying out extensive experiments in the context of low-dose CT denoising, a challenging application that aims to enhance the quality of noisy CT scans. We utilize three publicly available datasets, including one simulated and two real datasets. The results are promising as compared to other well-established loss functions, being also consistent across three different GAN architectures. The code is available at: https://github.com/TrainLaboratory/MultiScaleTextureLoss-MSTLF
URLs: https://github.com/TrainLaboratory/MultiScaleTextureLoss-MSTLF
Authors: Xin Zhu, Ahmet Enis Cetin
Abstract: The lack of an efficient preamble detection algorithm remains a challenge for solving preamble collision problems in intelligent random access (RA) in the cellular Internet of Things (IoT). To address this problem, we present an early preamble detection scheme based on a maximum likelihood estimation (MLE) model at the first step of the grant-based RA procedure. A novel blind normalized Stein variational gradient descent (SVGD)-based detector is proposed to obtain an approximate solution to the MLE model. First, by exploring the relationship between the Hadamard transform and wavelet packet transform, a new modified Hadamard transform (MHT) is developed to separate high-frequency components from signals using the second-order derivative filter. Next, to eliminate noise and mitigate the vanishing gradients problem in the SVGD-based detectors, the block MHT layer is designed based on the MHT, scaling layer, soft-thresholding layer, inverse MHT and sparsity penalty. Then, the blind normalized SVGD algorithm is derived to perform preamble detection without prior knowledge of noise power and the number of active IoT devices. The experimental results show the proposed block MHT layer outperforms other transform-based methods in terms of computation costs and denoising performance. Furthermore, with the assistance of the block MHT layer, the proposed blind normalized SVGD algorithm achieves a higher preamble detection accuracy and throughput than other state-of-the-art detection methods.
Authors: Junyang Zhang, Cristian Emanuel Ocampo Rivera, Kyle Tyni, Steven Nguyen
Abstract: Navigation precision, speed and stability are crucial for safe Unmanned Aerial Vehicle (UAV) flight maneuvers and effective flight mission executions in dynamic environments. Different flight missions may have varying objectives, such as minimizing energy consumption, achieving precise positioning, or maximizing speed. A controller that can adapt to different objectives on the fly is highly valuable. Proportional Integral Derivative (PID) controllers are one of the most popular and widely used control algorithms for drones and other control systems, but their linear control algorithm fails to capture the nonlinear nature of the dynamic wind conditions and complex drone system. Manually tuning the PID gains for various missions can be time-consuming and requires significant expertise. This paper aims to revolutionize drone flight control by presenting the AirPilot, a nonlinear Deep Reinforcement Learning (DRL) - enhanced Proportional Integral Derivative (PID) drone controller using Proximal Policy Optimization (PPO). AirPilot controller combines the simplicity and effectiveness of traditional PID control with the adaptability, learning capability, and optimization potential of DRL. This makes it better suited for modern drone applications where the environment is dynamic, and mission-specific performance demands are high. We employed a COEX Clover autonomous drone for training the DRL agent within the simulator and implemented it in a real-world lab setting, which marks a significant milestone as one of the first attempts to apply a DRL-based flight controller on an actual drone. Airpilot is capable of reducing the navigation error of the default PX4 PID position controller by 90%, improving effective navigation speed of a fine-tuned PID controller by 21%, reducing settling time and overshoot by 17% and 16% respectively.
Authors: Ionut M. Motoi, Leonardo Saraceni, Daniele Nardi, Thomas A. Ciarfuglia
Abstract: Satellite imagery is crucial for tasks like environmental monitoring and urban planning. Typically, it relies on semantic segmentation or Land Use Land Cover (LULC) classification to categorize each pixel. Despite the advancements brought about by Deep Neural Networks (DNNs), their performance in segmentation tasks is hindered by challenges such as limited availability of labeled data, class imbalance and the inherent variability and complexity of satellite images. In order to mitigate those issues, our study explores the effectiveness of a Cut-and-Paste augmentation technique for semantic segmentation in satellite images. We adapt this augmentation, which usually requires labeled instances, to the case of semantic segmentation. By leveraging the connected components in the semantic segmentation labels, we extract instances that are then randomly pasted during training. Using the DynamicEarthNet dataset and a U-Net model for evaluation, we found that this augmentation significantly enhances the mIoU score on the test set from 37.9 to 44.1. This finding highlights the potential of the Cut-and-Paste augmentation to improve the generalization capabilities of semantic segmentation models in satellite imagery.
Authors: Xiangpeng Li, Ali Mostafavi
Abstract: There is a limitation in the literature of data-driven analyses for the ex-post evaluation of community risk and resilience, particularly using features related to the performance of coupled human-infrastructure systems. To address this gap, in this study we created a machine learning-based method for the ex-post assessment of community risk and resilience and their interplay based on features related to the coupled human-infrastructure systems performance. Utilizing feature groups related to population protective actions, infrastructure/building performance features, and recovery features, we examined the risk and resilience performance of communities in the context of the 2017 Hurricane Harvey in Harris County, Texas. These features related to the coupled human-infrastructure systems performance were processed using the K-means clustering method to classify census block groups into four distinct clusters then, based on feature analysis, these clusters were labeled and designated into four quadrants of risk-resilience archetypes. Finally, we analyzed the disparities in risk-resilience status of spatial areas across different clusters as well as different income groups. The findings unveil the risk-resilience status of spatial areas shaped by their coupled human-infrastructure systems performance and their interactions. The results also inform about features that contribute to high resilience in high-risk areas. For example, the results indicate that in high-risk areas, evacuation rates contributed to a greater resilience, while in low-risk areas, preparedness contributed to greater resilience.
Authors: Daniel Freedman, Eyal Rozenberg, Alex Bronstein
Abstract: A central problem in quantum mechanics involves solving the Electronic Schrodinger Equation for a molecule or material. The Variational Monte Carlo approach to this problem approximates a particular variational objective via sampling, and then optimizes this approximated objective over a chosen parameterized family of wavefunctions, known as the ansatz. Recently neural networks have been used as the ansatz, with accompanying success. However, sampling from such wavefunctions has required the use of a Markov Chain Monte Carlo approach, which is inherently inefficient. In this work, we propose a solution to this problem via an ansatz which is cheap to sample from, yet satisfies the requisite quantum mechanical properties. We prove that a normalizing flow using the following two essential ingredients satisfies our requirements: (a) a base distribution which is constructed from Determinantal Point Processes; (b) flow layers which are equivariant to a particular subgroup of the permutation group. We then show how to construct both continuous and discrete normalizing flows which satisfy the requisite equivariance. We further demonstrate the manner in which the non-smooth nature ("cusps") of the wavefunction may be captured, and how the framework may be generalized to provide induction across multiple molecules. The resulting theoretical framework entails an efficient approach to solving the Electronic Schrodinger Equation.
Authors: Alfreds Lapkovskis, Natalia Nefedova, Ali Beikmohammadi
Abstract: Plant classification is vital for ecological conservation and agricultural productivity, enhancing our understanding of plant growth dynamics and aiding species preservation. The advent of deep learning (DL) techniques has revolutionized this field by enabling autonomous feature extraction, significantly reducing the dependence on manual expertise. However, conventional DL models often rely solely on single data sources, failing to capture the full biological diversity of plant species comprehensively. Recent research has turned to multimodal learning to overcome this limitation by integrating multiple data types, which enriches the representation of plant characteristics. This shift introduces the challenge of determining the optimal point for modality fusion. In this paper, we introduce a pioneering multimodal DL-based approach for plant classification with automatic modality fusion. Utilizing the multimodal fusion architecture search, our method integrates images from multiple plant organs -- flowers, leaves, fruits, and stems -- into a cohesive model. To address the lack of multimodal datasets, we contributed Multimodal-PlantCLEF, a restructured version of the PlantCLEF2015 dataset tailored for multimodal tasks. Our method achieves 82.61% accuracy on 979 classes of Multimodal-PlantCLEF, surpassing state-of-the-art methods and outperforming late fusion by 10.33%. Through the incorporation of multimodal dropout, our approach demonstrates strong robustness to missing modalities. We validate our model against established benchmarks using standard performance metrics and McNemar's test, further underscoring its superiority.
Authors: Hussein Jawad (LaMME), Nicolas J. -B. BRUNEL (LaMME)
Abstract: Large Language Models (LLMs) have surged in popularity in recent months, yet they possess concerning capabilities for generating harmful content when manipulated. This study introduces the Query-Response Optimization Attack (QROA), an optimization-based strategy designed to exploit LLMs through a black-box, query-only interaction. QROA adds an optimized trigger to a malicious instruction to compel the LLM to generate harmful content. Unlike previous approaches, QROA does not require access to the model's logit information or any other internal data and operates solely through the standard query-response interface of LLMs. Inspired by deep Q-learning and Greedy coordinate descent, the method iteratively updates tokens to maximize a designed reward function. We tested our method on various LLMs such as Vicuna, Falcon, and Mistral, achieving an Attack Success Rate (ASR) over 80\%. We also tested the model against Llama2-chat, the fine-tuned version of Llama2 designed to resist Jailbreak attacks, achieving good ASR with a suboptimal initial trigger seed. This study demonstrates the feasibility of generating jailbreak attacks against deployed LLMs in the public domain using black-box optimization methods, enabling more comprehensive safety testing of LLMs.
Authors: Avital Shafran, Roei Schuster, Vitaly Shmatikov
Abstract: Retrieval-augmented generation (RAG) systems respond to queries by retrieving relevant documents from a knowledge database and applying an LLM to the retrieved documents. We demonstrate that RAG systems that operate on databases with untrusted content are vulnerable to denial-of-service attacks we call jamming. An adversary can add a single ``blocker'' document to the database that will be retrieved in response to a specific query and result in the RAG system not answering this query - ostensibly because it lacks the relevant information or because the answer is unsafe. We describe and measure the efficacy of several methods for generating blocker documents, including a new method based on black-box optimization. This method (1) does not rely on instruction injection, (2) does not require the adversary to know the embedding or LLM used by the target RAG system, and (3) does not rely on an auxiliary LLM. We evaluate jamming attacks on several LLMs and embeddings and demonstrate that the existing safety metrics for LLMs do not capture their vulnerability to jamming. We then discuss defenses against blocker documents.
Authors: Yang Cai, Gabriele Farina, Julien Grand-Cl\'ement, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Weiqiang Zheng
Abstract: Self-play via online learning is one of the premier ways to solve large-scale two-player zero-sum games, both in theory and practice. Particularly popular algorithms include optimistic multiplicative weights update (OMWU) and optimistic gradient-descent-ascent (OGDA). While both algorithms enjoy $O(1/T)$ ergodic convergence to Nash equilibrium in two-player zero-sum games, OMWU offers several advantages including logarithmic dependence on the size of the payoff matrix and $\widetilde{O}(1/T)$ convergence to coarse correlated equilibria even in general-sum games. However, in terms of last-iterate convergence in two-player zero-sum games, an increasingly popular topic in this area, OGDA guarantees that the duality gap shrinks at a rate of $O(1/\sqrt{T})$, while the best existing last-iterate convergence for OMWU depends on some game-dependent constant that could be arbitrarily large. This begs the question: is this potentially slow last-iterate convergence an inherent disadvantage of OMWU, or is the current analysis too loose? Somewhat surprisingly, we show that the former is true. More generally, we prove that a broad class of algorithms that do not forget the past quickly all suffer the same issue: for any arbitrarily small $\delta>0$, there exists a $2\times 2$ matrix game such that the algorithm admits a constant duality gap even after $1/\delta$ rounds. This class of algorithms includes OMWU and other standard optimistic follow-the-regularized-leader algorithms.
Authors: Gabriel Sarch, Lawrence Jang, Michael J. Tarr, William W. Cohen, Kenneth Marino, Katerina Fragkiadaki
Abstract: Large-scale LLMs and VLMs excel at few-shot learning but require high-quality examples. We introduce In-Context Abstraction Learning (ICAL), which iteratively refines suboptimal trajectories into high-quality data with optimized actions and detailed reasoning. Given an inefficient demonstration, a VLM corrects actions and annotates causal relationships, object states, subgoals, and task-relevant visuals, forming "programs of thought." With human feedback, these programs are improved as the agent executes them in a similar environment. The resulting examples, used as prompt context or fine-tuning data, significantly boost decision-making while reducing human feedback needs. ICAL surpasses state-of-the-art in TEACh (dialogue-based instruction following), VisualWebArena (multimodal web agents), and Ego4D (egocentric video action anticipation). In TEACh, combining fine-tuning and retrieval on ICAL examples outperforms raw human demonstrations and expert examples, achieving a 17.5% increase in goal-condition success. In VisualWebArena, retrieval-augmented GPT-4V with ICAL improves task success rate 1.6x over GPT-4V, while fine-tuning Qwen2-VL achieves a 2.8x improvement. In Ego4D, ICAL outperforms few-shot GPT-4V and remains competitive with supervised models. Overall, ICAL scales 2x better than raw human demonstrations and reduces manual prompt engineering.
Authors: Garima Chhikara, Anurag Sharma, V. Gurucharan, Kripabandhu Ghosh, Abhijnan Chakraborty
Abstract: Citizen reporting platforms like Safe City in India help the public and authorities stay informed about sexual harassment incidents. However, the high volume of data shared on these platforms makes reviewing each individual case challenging. Therefore, a summarization algorithm capable of processing and understanding various Indian code-mixed languages is essential. In recent years, Large Language Models (LLMs) have shown exceptional performance in NLP tasks, including summarization. LLMs inherently produce abstractive summaries by paraphrasing the original text, while the generation of extractive summaries - selecting specific subsets from the original text - through LLMs remains largely unexplored. Moreover, LLMs have a limited context window size, restricting the amount of data that can be processed at once. We tackle these challenge by introducing LaMSUM, a novel multi-level framework designed to generate extractive summaries for large collections of Safe City posts using LLMs. LaMSUM integrates summarization with different voting methods to achieve robust summaries. Extensive evaluation using three popular LLMs (Llama, Mistral and GPT-4o) demonstrates that LaMSUM outperforms state-of-the-art extractive summarization methods for Safe City posts. Overall, this work represents one of the first attempts to achieve extractive summarization through LLMs, and is likely to support stakeholders by offering a comprehensive overview and enabling them to develop effective policies to minimize incidents of unwarranted harassment.
Authors: Alex Lence, Federica Granese, Ahmad Fall, Blaise Hanczar, Joe-Elie Salem, Jean-Daniel Zucker, Edi Prifti
Abstract: In this work, we address the challenge of reconstructing the complete 12-lead ECG signal from its incomplete parts. We focus on two main scenarios: (i) reconstructing missing signal segments within an ECG lead and (ii) recovering entire leads from signal in another unique lead. Two emerging clinical applications emphasize the relevance of our work. The first is the increasing need to digitize paper-stored ECGs for utilization in AI-based applications, often limited to digital 12 lead 10s ECGs. The second is the widespread use of wearable devices that record ECGs but typically capture only one or a few leads. In both cases, a non-negligible amount of information is lost or not recorded. Our approach aims to recover this missing signal. We propose ECGrecover, a U-Net neural network model trained on a novel composite objective function to address the reconstruction problem. This function incorporates both spatial and temporal features of the ECG by combining the distance in amplitude and sycnhronization through time between the reconstructed and the real digital signals. We used real-life ECG datasets and through comprehensive assessments compared ECGrecover with three state-of-the-art methods based on generative adversarial networks (EKGAN, Pix2Pix) as well as the CopyPaste strategy. The results demonstrated that ECGrecover consistently outperformed state-of-the-art methods in standard distortion metrics as well as in preserving critical ECG characteristics, particularly the P, QRS, and T wave coordinates.
Authors: Hung Vinh Tran, Tong Chen, Quoc Viet Hung Nguyen, Zi Huang, Lizhen Cui, Hongzhi Yin
Abstract: Since the creation of the Web, recommender systems (RSs) have been an indispensable mechanism in information filtering. State-of-the-art RSs primarily depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables. To prevent over-parameterized embedding tables from harming scalability, both academia and industry have seen increasing efforts in compressing RS embeddings. However, despite the prosperity of lightweight embedding-based RSs (LERSs), a wide diversity is seen in evaluation protocols, resulting in obstacles when relating LERS performance to real-world usability. Moreover, despite the common goal of lightweight embeddings, LERSs are evaluated with a single choice between the two main recommendation tasks -- collaborative filtering and content-based recommendation. This lack of discussions on cross-task transferability hinders the development of unified, more scalable solutions. Motivated by these issues, this study investigates various LERSs' performance, efficiency, and cross-task transferability via a thorough benchmarking process. Additionally, we propose an efficient embedding compression method using magnitude pruning, which is an easy-to-deploy yet highly competitive baseline that outperforms various complex LERSs. Our study reveals the distinct performance of LERSs across the two tasks, shedding light on their effectiveness and generalizability. To support edge-based recommendations, we tested all LERSs on a Raspberry Pi 4, where the efficiency bottleneck is exposed. Finally, we conclude this paper with critical summaries of LERS performance, model selection suggestions, and underexplored challenges around LERSs for future research. To encourage future research, we publish source codes and artifacts at \href{this link}{https://github.com/chenxing1999/recsys-benchmark}.
Authors: Vaclav Voracek
Abstract: Randomized smoothing is a popular certified defense against adversarial attacks. In its essence, we need to solve a problem of statistical estimation which is usually very time-consuming since we need to perform numerous (usually $10^5$) forward passes of the classifier for every point to be certified. In this paper, we review the statistical estimation problems for randomized smoothing to find out if the computational burden is necessary. In particular, we consider the (standard) task of adversarial robustness where we need to decide if a point is robust at a certain radius or not using as few samples as possible while maintaining statistical guarantees. We present estimation procedures employing confidence sequences enjoying the same statistical guarantees as the standard methods, with the optimal sample complexities for the estimation task and empirically demonstrate their good performance. Additionally, we provide a randomized version of Clopper-Pearson confidence intervals resulting in strictly stronger certificates.
Authors: Ivan Villa-Renteria, Mason L. Wang, Zachary Shah, Zhe Li, Soohyun Kim, Neelesh Ramachandran, Mert Pilanci
Abstract: We present Subtractive Training, a simple and novel method for synthesizing individual musical instrument stems given other instruments as context. This method pairs a dataset of complete music mixes with 1) a variant of the dataset lacking a specific stem, and 2) LLM-generated instructions describing how the missing stem should be reintroduced. We then fine-tune a pretrained text-to-audio diffusion model to generate the missing instrument stem, guided by both the existing stems and the text instruction. Our results demonstrate Subtractive Training's efficacy in creating authentic drum stems that seamlessly blend with the existing tracks. We also show that we can use the text instruction to control the generation of the inserted stem in terms of rhythm, dynamics, and genre, allowing us to modify the style of a single instrument in a full song while keeping the remaining instruments the same. Lastly, we extend this technique to MIDI formats, successfully generating compatible bass, drum, and guitar parts for incomplete arrangements.
Authors: Rongzhe Wei, Eli Chien, Pan Li
Abstract: Graph diffusion, which iteratively propagates real-valued substances among the graph, is used in numerous graph/network-involved applications. However, releasing diffusion vectors may reveal sensitive linking information in the data such as transaction information in financial network data. However, protecting the privacy of graph data is challenging due to its interconnected nature. This work proposes a novel graph diffusion framework with edge-level differential privacy guarantees by using noisy diffusion iterates. The algorithm injects Laplace noise per diffusion iteration and adopts a degree-based thresholding function to mitigate the high sensitivity induced by low-degree nodes. Our privacy loss analysis is based on Privacy Amplification by Iteration (PABI), which to our best knowledge, is the first effort that analyzes PABI with Laplace noise and provides relevant applications. We also introduce a novel Infinity-Wasserstein distance tracking method, which tightens the analysis of privacy leakage and makes PABI more applicable in practice. We evaluate this framework by applying it to Personalized Pagerank computation for ranking tasks. Experiments on real-world network data demonstrate the superiority of our method under stringent privacy conditions.
Authors: Tom Beucler, Arthur Grundner, Sara Shamekh, Peter Ukkonen, Matthew Chantry, Ryan Lagerquist
Abstract: The added value of machine learning for weather and climate applications is measurable through performance metrics, but explaining it remains challenging, particularly for large deep learning models. Inspired by climate model hierarchies, we propose that a full hierarchy of Pareto-optimal models, defined within an appropriately determined error-complexity plane, can guide model development and help understand the models' added value. We demonstrate the use of Pareto fronts in atmospheric physics through three sample applications, with hierarchies ranging from semi-empirical models with minimal parameters to deep learning algorithms. First, in cloud cover parameterization, we find that neural networks identify nonlinear relationships between cloud cover and its thermodynamic environment, and assimilate previously neglected features such as vertical gradients in relative humidity that improve the representation of low cloud cover. This added value is condensed into a ten-parameter equation that rivals deep learning models. Second, we establish a machine learning model hierarchy for emulating shortwave radiative transfer, distilling the importance of bidirectional vertical connectivity for accurately representing absorption and scattering, especially for multiple cloud layers. Third, we emphasize the importance of convective organization information when modeling the relationship between tropical precipitation and its surrounding environment. We discuss the added value of temporal memory when high-resolution spatial information is unavailable, with implications for precipitation parameterization. Therefore, by comparing data-driven models directly with existing schemes using Pareto optimality, we promote process understanding by hierarchically unveiling system complexity, with the hope of improving the trustworthiness of machine learning models in atmospheric applications.
Authors: Lisa Hemforth, Baptiste Couvy-Duchesne, Kevin De Matos, Camille Brianceau, Matthieu Joulot, Tobias Banaschewski, Arun L. W. Bokde, Sylvane Desrivi\`eres, Herta Flor, Antoine Grigis, Hugh Garavan, Penny Gowland, Andreas Heinz, R\"udiger Br\"uhl, Jean-Luc Martinot, Marie-Laure Paill\`ere Martinot, Eric Artiges, Dimitri Papadopoulos, Herve Lemaitre, Tomas Paus, Luise Poustka, Sarah Hohmann, Nathalie Holz, Juliane H. Fr\"ohner, Michael N. Smolka, Nilakshi Vaidya, Henrik Walter, Robert Whelan, Gunter Schumann, Christian B\"uchel, JB Poline, Bernd Itterman, Vincent Frouin, Alexandre Martin, IMAGEN study group, Claire Cury, Olivier Colliot
Abstract: Incomplete Hippocampal Inversion (IHI), sometimes called hippocampal malrotation, is an atypical anatomical pattern of the hippocampus found in about 20% of the general population. IHI can be visually assessed on coronal slices of T1 weighted MR images, using a composite score that combines four anatomical criteria. IHI has been associated with several brain disorders (epilepsy, schizophrenia). However, these studies were based on small samples. Furthermore, the factors (genetic or environmental) that contribute to the genesis of IHI are largely unknown. Large-scale studies are thus needed to further understand IHI and their potential relationships to neurological and psychiatric disorders. However, visual evaluation is long and tedious, justifying the need for an automatic method. In this paper, we propose, for the first time, to automatically rate IHI. We proceed by predicting four anatomical criteria, which are then summed up to form the IHI score, providing the advantage of an interpretable score. We provided an extensive experimental investigation of different machine learning methods and training strategies. We performed automatic rating using a variety of deep learning models (conv5-FC3, ResNet and SECNN) as well as a ridge regression. We studied the generalization of our models using different cohorts and performed multi-cohort learning. We relied on a large population of 2,008 participants from the IMAGEN study, 993 and 403 participants from the QTIM/QTAB studies as well as 985 subjects from the UKBiobank. We showed that deep learning models outperformed a ridge regression. We demonstrated that the performances of the conv5-FC3 network were at least as good as more complex networks while maintaining a low complexity and computation time. We showed that training on a single cohort may lack in variability while training on several cohorts improves generalization.
Authors: Alexandros Kontogiannis, Richard Hodgkinson, Emily L. Manchester
Abstract: We solve a Bayesian inverse Navier-Stokes (N-S) problem that assimilates velocimetry data in order to jointly reconstruct the flow field and learn the unknown N-S parameters. By incorporating a Carreau shear-thinning viscosity model into the N-S problem, we devise an algorithm that learns the most likely Carreau parameters of a shear-thinning fluid, and estimates their uncertainties, from velocimetry data alone. We then conduct a flow-MRI experiment to obtain velocimetry data of an axisymmetric laminar jet through an idealised medical device (FDA nozzle) for a blood analogue fluid. We show that the algorithm can successfully reconstruct the flow field by learning the most likely Carreau parameters, and that the learned parameters are in very good agreement with rheometry measurements. The algorithm accepts any algebraic effective viscosity model, as long as the model is differentiable, and it can be extended to more complicated non-Newtonian fluids (e.g. Oldroyd-B fluid) if a viscoelastic model is incorporated into the N-S problem.
Authors: Xin Hao, Bahareh Nakisa, Mohmmad Naim Rastgoo, Richard Dazeley, Gaoyang Pang
Abstract: Deep reinforcement Learning (DRL) offers a powerful framework for training AI agents to coordinate with human partners. However, DRL faces two critical challenges in human-AI coordination (HAIC): sparse rewards and unpredictable human behaviors. These challenges significantly limit DRL to identify effective coordination policies, due to its impaired capability of optimizing exploration and exploitation. To address these limitations, we propose an innovative behavior- and context-aware reward (BCR) for DRL, which optimizes exploration and exploitation by leveraging human behaviors and contextual information in HAIC. Our BCR consists of two components: (i)~Novel dual intrinsic rewards to enhance exploration. This scheme composes an AI self-motivated intrinsic reward and a human-motivated intrinsic reward, which are designed to increase the capture of sparse rewards by a logarithmic-based strategy; and (ii)~New context-aware weights for the designed rewards to improve exploitation. This mechanism helps the AI agent prioritize actions that better coordinate with the human partner by utilizing contextual information that can reflect the evolution of learning in HAIC. Extensive simulations in the Overcooked environment demonstrate that our approach can increase the cumulative sparse rewards by approximately 20% and reduce the convergence time by about 67% compared to state-of-the-art baselines.
Authors: Felix J. Yu, Nicholas Kamp, Carlos A. Arg\"uelles
Abstract: Recent discoveries by neutrino telescopes, such as the IceCube Neutrino Observatory, relied extensively on machine learning (ML) tools to infer physical quantities from the raw photon hits detected. Neutrino telescope reconstruction algorithms are limited by the sparse sampling of photons by the optical modules due to the relatively large spacing ($10-100\,{\rm m})$ between them. In this letter, we propose a novel technique that learns photon transport through the detector medium through the use of deep learning-driven super-resolution of data events. These ``improved'' events can then be reconstructed using traditional or ML techniques, resulting in improved resolution. Our strategy arranges additional ``virtual'' optical modules within an existing detector geometry and trains a convolutional neural network to predict the hits on these virtual optical modules. We show that this technique improves the angular reconstruction of muons in a generic ice-based neutrino telescope. Our results readily extend to water-based neutrino telescopes and other event morphologies.
Authors: Deaglan J. Bartlett, Marco Chiarenza, Ludvig Doeser, Florent Leclercq
Abstract: $N$-body simulations are computationally expensive, so machine-learning (ML)-based emulation techniques have emerged as a way to increase their speed. Although fast, surrogate models have limited trustworthiness due to potentially substantial emulation errors that current approaches cannot correct for. To alleviate this problem, we introduce COmoving Computer Acceleration (COCA), a hybrid framework interfacing ML with an $N$-body simulator. The correct physical equations of motion are solved in an emulated frame of reference, so that any emulation error is corrected by design. This approach corresponds to solving for the perturbation of particle trajectories around the machine-learnt solution, which is computationally cheaper than obtaining the full solution, yet is guaranteed to converge to the truth as one increases the number of force evaluations. Although applicable to any ML algorithm and $N$-body simulator, this approach is assessed in the particular case of particle-mesh cosmological simulations in a frame of reference predicted by a convolutional neural network, where the time dependence is encoded as an additional input parameter to the network. COCA efficiently reduces emulation errors in particle trajectories, requiring far fewer force evaluations than running the corresponding simulation without ML. We obtain accurate final density and velocity fields for a reduced computational budget. We demonstrate that this method shows robustness when applied to examples outside the range of the training data. When compared to the direct emulation of the Lagrangian displacement field using the same training resources, COCA's ability to correct emulation errors results in more accurate predictions. COCA makes $N$-body simulations cheaper by skipping unnecessary force evaluations, while still solving the correct equations of motion and correcting for emulation errors made by ML.
Authors: Purvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou, George K. Thiravathukal, James C. Davis, Yung-Hsiang Lu
Abstract: We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understanding tasks. ViTTMs are designed for non-sequential computer vision tasks such as image classification and segmentation. Our model creates two sets of tokens: process tokens and memory tokens; process tokens pass through encoder blocks and read-write from memory tokens at each encoder block in the network, allowing them to store and retrieve information from memory. By ensuring that there are fewer process tokens than memory tokens, we are able to reduce the inference time of the network while maintaining its accuracy. On ImageNet-1K, the state-of-the-art ViT-B has median latency of 529.5ms and 81.0% accuracy, while our ViTTM-B is 56% faster (234.1ms), with 2.4 times fewer FLOPs, with an accuracy of 82.9%. On ADE20K semantic segmentation, ViT-B achieves 45.65mIoU at 13.8 frame-per-second (FPS) whereas our ViTTM-B model acheives a 45.17 mIoU with 26.8 FPS (+94%).
Authors: Quanting Xie, So Yeon Min, Pengliang Ji, Yue Yang, Tianyi Zhang, Kedi Xu, Aarav Bajaj, Ruslan Salakhutdinov, Matthew Johnson-Roberson, Yonatan Bisk
Abstract: There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhorse of large-scale non-parametric knowledge; however, existing techniques do not directly transfer to the embodied domain, which is multimodal, where data is highly correlated, and perception requires abstraction. To address these challenges, we introduce Embodied-RAG, a framework that enhances the foundational model of an embodied agent with a non-parametric memory system capable of autonomously constructing hierarchical knowledge for both navigation and language generation. Embodied-RAG handles a full range of spatial and semantic resolutions across diverse environments and query types, whether for a specific object or a holistic description of ambiance. At its core, Embodied-RAG's memory is structured as a semantic forest, storing language descriptions at varying levels of detail. This hierarchical organization allows the system to efficiently generate context-sensitive outputs across different robotic platforms. We demonstrate that Embodied-RAG effectively bridges RAG to the robotics domain, successfully handling over 250 explanation and navigation queries across kilometer-level environments, highlighting its promise as a general-purpose non-parametric system for embodied agents.
Authors: Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, Sanjeev Arora
Abstract: As large language models (LLMs) become increasingly advanced, their ability to exhibit compositional generalization -- the capacity to combine learned skills in novel ways not encountered during training -- has garnered significant attention. This type of generalization, particularly in scenarios beyond training data, is also of great interest in the study of AI safety and alignment. A recent study introduced the SKILL-MIX evaluation, where models are tasked with composing a short paragraph demonstrating the use of a specified $k$-tuple of language skills. While small models struggled with composing even with $k=3$, larger models like GPT-4 performed reasonably well with $k=5$ and $6$. In this paper, we employ a setup akin to SKILL-MIX to evaluate the capacity of smaller models to learn compositional generalization from examples. Utilizing a diverse set of language skills -- including rhetorical, literary, reasoning, theory of mind, and common sense -- GPT-4 was used to generate text samples that exhibit random subsets of $k$ skills. Subsequent fine-tuning of 7B and 13B parameter models on these combined skill texts, for increasing values of $k$, revealed the following findings: (1) Training on combinations of $k=2$ and $3$ skills results in noticeable improvements in the ability to compose texts with $k=4$ and $5$ skills, despite models never having seen such examples during training. (2) When skill categories are split into training and held-out groups, models significantly improve at composing texts with held-out skills during testing despite having only seen training skills during fine-tuning, illustrating the efficacy of the training approach even with previously unseen skills. This study also suggests that incorporating skill-rich (potentially synthetic) text into training can substantially enhance the compositional capabilities of models.
Authors: Yubo Li, Rema Padman
Abstract: Objective: To improve prediction of Chronic Kidney Disease (CKD) progression to End Stage Renal Disease (ESRD) using machine learning (ML) and deep learning (DL) models applied to an integrated clinical and claims dataset of varying observation windows, supported by explainable AI (XAI) to enhance interpretability and reduce bias. Materials and Methods: We utilized data about 10,326 CKD patients, combining their clinical and claims information from 2009 to 2018. Following data preprocessing, cohort identification, and feature engineering, we evaluated multiple statistical, ML and DL models using data extracted from five distinct observation windows. Feature importance and Shapley value analysis were employed to understand key predictors. Models were tested for robustness, clinical relevance, misclassification errors and bias issues. Results: Integrated data models outperformed those using single data sources, with the Long Short-Term Memory (LSTM) model achieving the highest AUC (0.93) and F1 score (0.65). A 24-month observation window was identified as optimal for balancing early detection and prediction accuracy. The 2021 eGFR equation improved prediction accuracy and reduced racial bias, notably for African American patients. Discussion: Improved ESRD prediction accuracy, results interpretability and bias mitigation strategies presented in this study have the potential to significantly enhance CKD and ESRD management, support targeted early interventions and reduce healthcare disparities. Conclusion: This study presents a robust framework for predicting ESRD outcomes in CKD patients, improving clinical decision-making and patient care through multi-sourced, integrated data and AI/ML methods. Future research will expand data integration and explore the application of this framework to other chronic diseases.
Authors: Soon Hoe Lim, Yijin Wang, Annan Yu, Emma Hart, Michael W. Mahoney, Xiaoye S. Li, N. Benjamin Erichson
Abstract: Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces. However, the impact of the specific choice of probability path model on forecasting performance remains under-explored. In this work, we demonstrate that forecasting spatio-temporal data with flow matching is highly sensitive to the selection of the probability path model. Motivated by this insight, we propose a novel probability path model designed to improve forecasting performance. Our empirical results across various dynamical system benchmarks show that our model achieves faster convergence during training and improved predictive performance compared to existing probability path models. Importantly, our approach is efficient during inference, requiring only a few sampling steps. This makes our proposed model practical for real-world applications and opens new avenues for probabilistic forecasting.
Authors: Manling Li, Shiyu Zhao, Qineng Wang, Kangrui Wang, Yu Zhou, Sanjana Srivastava, Cem Gokmen, Tony Lee, Li Erran Li, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei, Jiayuan Mao, Jiajun Wu
Abstract: We aim to evaluate Large Language Models (LLMs) for embodied decision making. While a significant body of work has been leveraging LLMs for decision making in embodied environments, we still lack a systematic understanding of their performance because they are usually applied in different domains, for different purposes, and built based on different inputs and outputs. Furthermore, existing evaluations tend to rely solely on a final success rate, making it difficult to pinpoint what ability is missing in LLMs and where the problem lies, which in turn blocks embodied agents from leveraging LLMs effectively and selectively. To address these limitations, we propose a generalized interface (Embodied Agent Interface) that supports the formalization of various types of tasks and input-output specifications of LLM-based modules. Specifically, it allows us to unify 1) a broad set of embodied decision-making tasks involving both state and temporally extended goals, 2) four commonly-used LLM-based modules for decision making: goal interpretation, subgoal decomposition, action sequencing, and transition modeling, and 3) a collection of fine-grained metrics which break down evaluation into various types of errors, such as hallucination errors, affordance errors, various types of planning errors, etc. Overall, our benchmark offers a comprehensive assessment of LLMs' performance for different subtasks, pinpointing the strengths and weaknesses in LLM-powered embodied AI systems, and providing insights for effective and selective use of LLMs in embodied decision making.
Authors: Erik Arakelyan, Pasquale Minervini, Pat Verga, Patrick Lewis, Isabelle Augenstein
Abstract: Modern Question Answering (QA) and Reasoning approaches based on Large Language Models (LLMs) commonly use prompting techniques, such as Chain-of-Thought (CoT), assuming the resulting generation will have a more granular exploration and reasoning over the question space and scope. However, such methods struggle with generating outputs that are faithful to the intermediate chain of reasoning produced by the model. On the other end of the spectrum, neuro-symbolic methods such as Faithful CoT (F-CoT) propose to combine LLMs with external symbolic solvers. While such approaches boast a high degree of faithfulness, they usually require a model trained for code generation and struggle with tasks that are ambiguous or hard to formalise strictly. We introduce $\textbf{F}$aithful $\textbf{L}$ogic-$\textbf{A}$ided $\textbf{R}$easoning and $\textbf{E}$xploration ($\textbf{FLARE}$), a novel interpretable approach for traversing the problem space using task decompositions. We use the LLM to plan a solution, soft-formalise the query into facts and predicates using a logic programming code and simulate that code execution using an exhaustive multi-hop search over the defined space. Our method allows us to compute the faithfulness of the reasoning process w.r.t. the generated code and analyse the steps of the multi-hop search without relying on external solvers. Our methods achieve SOTA results on $\mathbf{7}$ out of $\mathbf{9}$ diverse reasoning benchmarks. We also show that model faithfulness positively correlates with overall performance and further demonstrate that $\textbf{FLARE}$ allows pinpointing the decisive factors sufficient for and leading to the correct answer with optimal reasoning during the multi-hop search.
Authors: Naren Sengodan
Abstract: Breast cancer histopathology image classification is critical for early detection and improved patient outcomes. 1 This study introduces a novel approach leveraging EfficientNetV2 models, to improve feature extraction and focus on relevant tissue regions. The proposed models were evaluated on the BreakHis dataset across multiple magnification scales (40X, 100X, 200X, and 400X). 2 Among them, the EfficientNetV2-XL with CBAM achieved outstanding performance, reaching a peak accuracy of 99.01 percent and an F1-score of 98.31 percent at 400X magnification, outperforming state-of-the-art methods. 3 By integrating Contrast Limited Adaptive Histogram Equalization (CLAHE) for preprocessing and optimizing computational efficiency, this method demonstrates its suitability for real-time clinical deployment. 3 The results underscore the potential of attention-enhanced scalable architectures in advancing diagnostic precision for breast cancer detection.
Authors: Ameya Uppina, S Navaneetha Krishnan, Talluri Krishna Sai Teja, Nikhil N Iyer, Joe Dhanith P R
Abstract: Diabetic Retinopathy DR is a severe complication of diabetes. Damaged or abnormal blood vessels can cause loss of vision. The need for massive screening of a large population of diabetic patients has generated an interest in a computer-aided fully automatic diagnosis of DR. In the realm of Deep learning frameworks, particularly convolutional neural networks CNNs, have shown great interest and promise in detecting DR by analyzing retinal images. However, several challenges have been faced in the application of deep learning in this domain. High-quality, annotated datasets are scarce, and the variations in image quality and class imbalances pose significant hurdles in developing a dependable model. In this paper, we demonstrate the proficiency of two Convolutional Neural Networks CNNs based models, UNET and Stacked UNET utilizing the APTOS Asia Pacific Tele-Ophthalmology Society Dataset. This system achieves an accuracy of 92.81% for the UNET and 93.32% for the stacked UNET architecture. The architecture classifies the images into five categories ranging from 0 to 4, where 0 is no DR and 4 is proliferative DR.
Authors: Stephen P. Boyd, Tetiana Parshakova, Ernest K. Ryu, Jaewook J. Suh
Abstract: We present a novel methodology for convex optimization algorithm design using ideas from electric RLC circuits. Given an optimization problem, the first stage of the methodology is to design an appropriate electric circuit whose continuous-time dynamics converge to the solution of the optimization problem at hand. Then, the second stage is an automated, computer-assisted discretization of the continuous-time dynamics, yielding a provably convergent discrete-time algorithm. Our methodology recovers many classical (distributed) optimization algorithms and enables users to quickly design and explore a wide range of new algorithms with convergence guarantees.
Authors: Elisabeth Pfaehler, Daniel Pflugfelder, Hanno Scharr
Abstract: In the acquisition of Magnetic Resonance (MR) images shorter scan times lead to higher image noise. Therefore, automatic image denoising using deep learning methods is of high interest. MR images containing line-like structures such as roots or vessels yield special characteristics as they display connected structures and yield sparse information. For this kind of data, it is important to consider voxel neighborhoods when training a denoising network. In this paper, we translate the Perceptual Loss to 3D data by comparing feature maps of untrained networks in the loss function as done previously for 2D data. We tested the performance of untrained Perceptual Loss (uPL) on 3D image denoising of MR images displaying brain vessels (MR angiograms - MRA) and images of plant roots in soil. We investigate the impact of various uPL characteristics such as weight initialization, network depth, kernel size, and pooling operations on the results. We tested the performance of the uPL loss on four Rician noise levels using evaluation metrics such as the Structural Similarity Index Metric (SSIM). We observe, that our uPL outperforms conventional loss functions such as the L1 loss or a loss based on the Structural Similarity Index Metric (SSIM). The uPL network's initialization is not important, while network depth and pooling operations impact denoising performance. E.g. for both datasets a network with five convolutional layers led to the best performance while a network with more layers led to a performance drop. We also find that small uPL networks led to better or comparable results than using large networks such as VGG. We observe superior performance of our loss for both datasets, all noise levels, and three network architectures. In conclusion, for images containing line-like structures, uPL is an alternative to other loss functions for 3D image denoising.
Authors: Ryoma Yataka, Adriano Cardace, Pu Perry Wang, Petros Boufounos, Ryuhei Takahashi
Abstract: Indoor radar perception has seen rising interest due to affordable costs driven by emerging automotive imaging radar developments and the benefits of reduced privacy concerns and reliability under hazardous conditions (e.g., fire and smoke). However, existing radar perception pipelines fail to account for distinctive characteristics of the multi-view radar setting. In this paper, we propose Radar dEtection TRansformer (RETR), an extension of the popular DETR architecture, tailored for multi-view radar perception. RETR inherits the advantages of DETR, eliminating the need for hand-crafted components for object detection and segmentation in the image plane. More importantly, RETR incorporates carefully designed modifications such as 1) depth-prioritized feature similarity via a tunable positional encoding (TPE); 2) a tri-plane loss from both radar and camera coordinates; and 3) a learnable radar-to-camera transformation via reparameterization, to account for the unique multi-view radar setting. Evaluated on two indoor radar perception datasets, our approach outperforms existing state-of-the-art methods by a margin of 15.38+ AP for object detection and 11.91+ IoU for instance segmentation, respectively. Our implementation is available at https://github.com/merlresearch/radar-detection-transformer.
URLs: https://github.com/merlresearch/radar-detection-transformer.
Authors: Benjamin D. M. Jones, Lana Mineh, Ashley Montanaro
Abstract: We numerically benchmark 30 optimisers on 372 instances of the variational quantum eigensolver for solving the Fermi-Hubbard system with the Hamiltonian variational ansatz. We rank the optimisers with respect to metrics such as final energy achieved and function calls needed to get within a certain tolerance level, and find that the best performing optimisers are variants of gradient descent such as Momentum and ADAM (using finite difference), SPSA, CMAES, and BayesMGD. We also perform gradient analysis and observe that the step size for finite difference has a very significant impact. We also consider using simultaneous perturbation (inspired by SPSA) as a gradient subroutine: here finite difference can lead to a more precise estimate of the ground state but uses more calls, whereas simultaneous perturbation can converge quicker but may be less precise in the later stages. Finally, we also study the quantum natural gradient algorithm: we implement this method for 1-dimensional Fermi-Hubbard systems, and find that whilst it can reach a lower energy with fewer iterations, this improvement is typically lost when taking total function calls into account. Our method involves performing careful hyperparameter sweeping on 4 instances. We present a variety of analysis and figures, detailed optimiser notes, and discuss future directions.
Authors: Andrew T. McNutt, Abhinav K. Adduri, Caleb N. Ellington, Monica T. Dayao, Eric P. Xing, Hosein Mohimani, David R. Koes
Abstract: Virtual screening of small molecules against protein targets can accelerate drug discovery and development by predicting drug-target interactions (DTIs). However, structure-based methods like molecular docking are too slow to allow for broad proteome-scale screens, limiting their application in screening for off-target effects or new molecular mechanisms. Recently, vector-based methods using protein language models (PLMs) have emerged as a complementary approach that bypasses explicit 3D structure modeling. Here, we develop SPRINT, a vector-based approach for screening entire chemical libraries against whole proteomes for DTIs and novel mechanisms of action. SPRINT improves on prior work by using a self-attention based architecture and structure-aware PLMs to learn drug-target co-embeddings for binder prediction, search, and retrieval. SPRINT achieves SOTA enrichment factors in virtual screening on LIT-PCBA, DTI classification benchmarks, and binding affinity prediction benchmarks, while providing interpretability in the form of residue-level attention maps. In addition to being both accurate and interpretable, SPRINT is ultra-fast: querying the whole human proteome against the ENAMINE Real Database (6.7B drugs) for the 100 most likely binders per protein takes 16 minutes. SPRINT promises to enable virtual screening at an unprecedented scale, opening up new opportunities for in silico drug repurposing and development. SPRINT is available on the web as ColabScreen: https://bit.ly/colab-screen
Authors: Pengcheng Xu, Boyuan Jiang, Xiaobin Hu, Donghao Luo, Qingdong He, Jiangning Zhang, Chengjie Wang, Yunsheng Wu, Charles Ling, Boyu Wang
Abstract: Leveraging the large generative prior of the flow transformer for tuning-free image editing requires authentic inversion to project the image into the model's domain and a flexible invariance control mechanism to preserve non-target contents. However, the prevailing diffusion inversion performs deficiently in flow-based models, and the invariance control cannot reconcile diverse rigid and non-rigid editing tasks. To address these, we systematically analyze the \textbf{inversion and invariance} control based on the flow transformer. Specifically, we unveil that the Euler inversion shares a similar structure to DDIM yet is more susceptible to the approximation error. Thus, we propose a two-stage inversion to first refine the velocity estimation and then compensate for the leftover error, which pivots closely to the model prior and benefits editing. Meanwhile, we propose the invariance control that manipulates the text features within the adaptive layer normalization, connecting the changes in the text prompt to image semantics. This mechanism can simultaneously preserve the non-target contents while allowing rigid and non-rigid manipulation, enabling a wide range of editing types such as visual text, quantity, facial expression, etc. Experiments on versatile scenarios validate that our framework achieves flexible and accurate editing, unlocking the potential of the flow transformer for versatile image editing.
Authors: Andreas C. Schneider, Valentin Neuhaus, David A. Ehrlich, Abdullah Makkeh, Alexander S. Ecker, Viola Priesemann, Michael Wibral
Abstract: In modern deep neural networks, the learning dynamics of the individual neurons is often obscure, as the networks are trained via global optimization. Conversely, biological systems build on self-organized, local learning, achieving robustness and efficiency with limited global information. We here show how self-organization between individual artificial neurons can be achieved by designing abstract bio-inspired local learning goals. These goals are parameterized using a recent extension of information theory, Partial Information Decomposition (PID), which decomposes the information that a set of information sources holds about an outcome into unique, redundant and synergistic contributions. Our framework enables neurons to locally shape the integration of information from various input classes, i.e. feedforward, feedback, and lateral, by selecting which of the three inputs should contribute uniquely, redundantly or synergistically to the output. This selection is expressed as a weighted sum of PID terms, which, for a given problem, can be directly derived from intuitive reasoning or via numerical optimization, offering a window into understanding task-relevant local information processing. Achieving neuron-level interpretability while enabling strong performance using local learning, our work advances a principled information-theoretic foundation for local learning strategies.
Authors: Minh Le, Tien Ngoc Luu, An Nguyen The, Thanh-Thien Le, Trang Nguyen, Tung Thanh Nguyen, Linh Ngo Van, Thien Huu Nguyen
Abstract: To address catastrophic forgetting in Continual Relation Extraction (CRE), many current approaches rely on memory buffers to rehearse previously learned knowledge while acquiring new tasks. Recently, prompt-based methods have emerged as potent alternatives to rehearsal-based strategies, demonstrating strong empirical performance. However, upon analyzing existing prompt-based approaches for CRE, we identified several critical limitations, such as inaccurate prompt selection, inadequate mechanisms for mitigating forgetting in shared parameters, and suboptimal handling of cross-task and within-task variances. To overcome these challenges, we draw inspiration from the relationship between prefix-tuning and mixture of experts, proposing a novel approach that employs a prompt pool for each task, capturing variations within each task while enhancing cross-task variances. Furthermore, we incorporate a generative model to consolidate prior knowledge within shared parameters, eliminating the need for explicit data storage. Extensive experiments validate the efficacy of our approach, demonstrating superior performance over state-of-the-art prompt-based and rehearsal-free methods in continual relation extraction.
Authors: Wonsuk Jang, Thierry Tambe
Abstract: The rapidly increasing size of large language models (LLMs) presents significant challenges in memory usage and computational costs. Quantizing both weights and activations can address these issues, with hardware-supported fine-grained scaling emerging as a promising solution to mitigate outliers. However, existing methods struggle to capture nuanced block data distributions. We propose BlockDialect, a block-wise fine-grained mixed format technique that assigns a per-block optimal number format from a formatbook for better data representation. Additionally, we introduce DialectFP4, a formatbook of FP4 variants (akin to dialects) that adapt to diverse data distributions. To leverage this efficiently, we propose a two-stage approach for online DialectFP4 activation quantization. Importantly, DialectFP4 ensures energy efficiency by selecting representable values as scaled integers compatible with low-precision integer arithmetic. BlockDialect achieves 10.78% (7.48%) accuracy gain on the LLaMA3-8B (LLaMA2-7B) model compared to MXFP4 format with lower bit usage per data, while being only 5.45% (2.69%) below full precision even when quantizing full-path matrix multiplication. Focusing on how to represent over how to scale, our work presents a promising path for energy-efficient LLM inference.
Authors: Yoshitomo Matsubara, Matteo Mendula, Marco Levorato
Abstract: Split computing ($\neq$ split learning) is a promising approach to deep learning models for resource-constrained edge computing systems, where weak sensor (mobile) devices are wirelessly connected to stronger edge servers through channels with limited communication capacity. State-of-theart work on split computing presents methods for single tasks such as image classification, object detection, or semantic segmentation. The application of existing methods to multitask problems degrades model accuracy and/or significantly increase runtime latency. In this study, we propose Ladon, the first multi-task-head supervised compression model for multi-task split computing. Experimental results show that the multi-task supervised compression model either outperformed or rivaled strong lightweight baseline models in terms of predictive performance for ILSVRC 2012, COCO 2017, and PASCAL VOC 2012 datasets while learning compressed representations at its early layers. Furthermore, our models reduced end-to-end latency (by up to 95.4%) and energy consumption of mobile devices (by up to 88.2%) in multi-task split computing scenarios.
Authors: Umesh Yadav, Suman Niroula, Gaurav Kumar Gupta, Bicky Yadav
Abstract: This paper investigates the resilience of a ResNet-50 image classification model under two prominent security threats: Fast Gradient Sign Method (FGSM) adversarial attacks and malicious payload injection. Initially, the model attains a 53.33% accuracy on clean images. When subjected to FGSM perturbations, its overall accuracy remains unchanged; however, the model's confidence in incorrect predictions notably increases. Concurrently, a payload injection scheme is successfully executed in 93.33% of the tested samples, revealing how stealthy attacks can manipulate model predictions without degrading visual quality. These findings underscore the vulnerability of even high-performing neural networks and highlight the urgency of developing more robust defense mechanisms for security-critical applications.
Authors: Beichen Zhang, Yuhong Liu, Xiaoyi Dong, Yuhang Zang, Pan Zhang, Haodong Duan, Yuhang Cao, Dahua Lin, Jiaqi Wang
Abstract: Cutting-edge large language models (LLMs) demonstrate promising performance in solving complex math problems with a divide-and-conquer pipeline and the assistance of in-context learning (ICL) examples. However, their potential for improvement is limited by two critical problems within their ICL examples: granularity-mismatch and the ensuing negative-effect noise problem. Specifically, the LLMs are capable of the dividing process yet mostly failed by inaccurate reasoning within a few conquer steps, while the ICL examples retrieved in question-grained sometimes lack relevant steps for a specific challenging reasoning step. Further, this disconnect may hinder the correct reasoning due to its irrelevance. To this end, we focus on improving the reasoning quality within each step and present BoostStep. BoostStep aligns the granularity between the retrieving and reasoning on step grained, and provides highly related ICL examples for each reasoning step with a novel `first-try' strategy. BoostStep provides more relevant examples than the coarse question-grained strategy, enhancing the model reasoning quality within each step steadily. BoostStep is a general and robust reasoning-enhancing method that not only improves standalone reasoning performance but also integrates seamlessly with Monte Carlo Tree Search methods (MCTS) to refine both candidate generation and decision-making. Quantitatively, it improves GPT-4o and Qwen2.5-Math-72B by 3.6\% and 2.0\% respectively on various mathematical benchmarks, and 7.5\% gain combined with MCTS.
Authors: Johan Larsson, Jonas Wallin
Abstract: Regularized models are often sensitive to the scales of the features in the data and it has therefore become standard practice to normalize (center and scale) the features before fitting the model. But there are many different ways to normalize the features and the choice may have dramatic effects on the resulting model. In spite of this, there has so far been no research on this topic. In this paper, we begin to bridge this knowledge gap by studying normalization in the context of lasso, ridge, and elastic net regression. We focus on normal and binary features and show that the class balances of binary features directly influences the regression coefficients and that this effect depends on the combination of normalization and regularization methods used. We demonstrate that this effect can be mitigated by scaling binary features with their variance in the case of the lasso and standard deviation in the case of ridge regression, but that this comes at the cost of increased variance. For the elastic net, we show that scaling the penalty weights, rather than the features, can achieve the same effect. Finally, we also tackle mixes of binary and normal features as well as interactions and provide some initial results on how to normalize features in these cases.
Authors: Jonathan Keane, Sam Keyser, Jeremy Kedziora
Abstract: The use of reward functions to structure AI learning and decision making is core to the current reinforcement learning paradigm; however, without careful design of reward functions, agents can learn to solve problems in ways that may be considered "undesirable" or "unethical." Without thorough understanding of the incentives a reward function creates, it can be difficult to impose principled yet general control mechanisms over its behavior. In this paper, we study methods for constructing guardrails for AI agents that use reward functions to learn decision making. We introduce a novel approach, which we call strategy masking, to explicitly learn and then suppress undesirable AI agent behavior. We apply our method to study lying in AI agents and show that it can be used to effectively modify agent behavior by suppressing lying post-training without compromising agent ability to perform effectively.
Authors: Feiyi Chen, Leilei Zhang, Guansong Pang, Roger Zimmermann, Shuiguang Deng
Abstract: In anomaly detection, methods based on large language models (LLMs) can incorporate expert knowledge by reading professional document, while task-specific small models excel at extracting normal data patterns and detecting value fluctuations from training data of target applications. Inspired by the human nervous system, where the brain stores expert knowledge and the peripheral nervous system and spinal cord handle specific tasks like withdrawal and knee-jerk reflexes, we propose CoLLaTe, a framework designed to facilitate collaboration between LLMs and task-specific models, leveraging the strengths of both models for anomaly detection. In particular, we first formulate the collaboration process and identify two key challenges in the collaboration: (1) the misalignment between the expression domains of the LLMs and task-specific small models, and (2) error accumulation arising from the predictions of both models. To address these challenges, we then introduce two key components in CoLLaTe: a model alignment module and a collaborative loss function. Through theoretical analysis and experimental validation, we demonstrate that these components effectively mitigate the identified challenges and achieve better performance than both LLM-based and task-specific models.
Authors: Duy Khanh Lam
Abstract: This paper investigates the investment problem of constructing an optimal no-short sequential portfolio strategy in a market with a latent dependence structure between asset prices and partly unobservable side information, which is often high-dimensional. The results demonstrate that a dynamic strategy, which forms a portfolio based on perfect knowledge of the dependence structure and full market information over time, may not grow at a higher rate infinitely often than a constant strategy, which remains invariant over time. Specifically, if the market is stationary, implying that the dependence structure is statistically stable, the growth rate of an optimal dynamic strategy, utilizing the maximum capacity of the entire market information, almost surely decays over time into an equilibrium state, asymptotically converging to the growth rate of a constant strategy. Technically, this work reassesses the common belief that a constant strategy only attains the optimal limiting growth rate of dynamic strategies when the market process is identically and independently distributed. By analyzing the dynamic log-optimal portfolio strategy as the optimal benchmark in a stationary market with side information, we show that a random optimal constant strategy almost surely exists, even when a limiting growth rate for the dynamic strategy does not. Consequently, two approaches to learning algorithms for portfolio construction are discussed, demonstrating the safety of removing side information from the learning process while still guaranteeing an asymptotic growth rate comparable to that of the optimal dynamic strategy.
Authors: Krrish Chawla, Aryan Sahai, Mario DePavia, Sudharsan Sundar, Brando Miranda
Abstract: Contrary to the conventional emphasis on dataset size, we explore the role of data alignment -- an often overlooked aspect of data quality -- in training capable Large Language Models (LLMs). To do so, we use the Task2Vec-based alignment coefficient, a quantitative measure of the similarity between two datasets, to quantify the impact of alignment between training data and evaluation data on downstream performance. In particular, we conduct controlled \textit{interventional} experiments for two settings: 1. the impact of increased alignment coefficients between various pre-training (pt) against evaluation datasets, and 2. the impact of increased alignment coefficients between domain specific fine-tuning (ft) against domain specific evaluation. The domain specific task we explore is Autoformalization -- the machine translation task between natural language and code for formal verification. In both settings, we find a strong, predictable negative correlation between the alignment coefficient of a model's training and evaluation data and the model's loss/perplexity on the respective downstream task. These findings suggest a re-evaluation of LLM training approaches, demonstrating the relevance of data alignment compared to data quantity, especially in specialized downstream tasks such as Autoformalization.
Authors: Zhiwei Gao, George Em Karniadakis
Abstract: Uncertainty quantification (UQ) plays a pivotal role in scientific machine learning, especially when surrogate models are used to approximate complex systems. Although multilayer perceptions (MLPs) are commonly employed as surrogates, they often suffer from overfitting due to their large number of parameters. Kolmogorov-Arnold networks (KANs) offer an alternative solution with fewer parameters. However, gradient-based inference methods, such as Hamiltonian Monte Carlo (HMC), may result in computational inefficiency when applied to KANs, especially for large-scale datasets, due to the high cost of back-propagation. To address these challenges, we propose a novel approach, combining the dropout Tikhonov ensemble Kalman inversion (DTEKI) with Chebyshev KANs. This gradient-free method effectively mitigates overfitting and enhances numerical stability. Additionally, we incorporate the active subspace method to reduce the parameter-space dimensionality, allowing us to improve the accuracy of predictions and obtain more reliable uncertainty estimates. Extensive experiments demonstrate the efficacy of our approach in various test cases, including scenarios with large datasets and high noise levels. Our results show that the new method achieves comparable or better accuracy, much higher efficiency as well as stability compared to HMC, in addition to scalability. Moreover, by leveraging the low-dimensional parameter subspace, our method preserves prediction accuracy while substantially reducing further the computational cost.
Authors: Zhipeng Ye, Feng Jiang, Qiufeng Wang, Kaizhu Huang, Jiaqi Huang
Abstract: CLIP (Contrastive Language-Image Pre-training) has attained great success in pattern recognition and computer vision. Transferring CLIP to downstream tasks (e.g. zero- or few-shot classification) is a hot topic in multimodal learning. However, current studies primarily focus on either prompt learning for text or adapter tuning for vision, without fully exploiting the complementary information and correlations among image-text pairs. In this paper, we propose an Image Description Enhanced CLIP-Adapter (IDEA) method to adapt CLIP to few-shot image classification tasks. This method captures fine-grained features by leveraging both visual features and textual descriptions of images. IDEA is a training-free method for CLIP, and it can be comparable to or even exceeds state-of-the-art models on multiple tasks. Furthermore, we introduce Trainable-IDEA (T-IDEA), which extends IDEA by adding two lightweight learnable components (i.e., a projector and a learnable latent space), further enhancing the model's performance and achieving SOTA results on 11 datasets. As one important contribution, we employ the Llama model and design a comprehensive pipeline to generate textual descriptions for images of 11 datasets, resulting in a total of 1,637,795 image-text pairs, named "IMD-11". Our code and data are released at https://github.com/FourierAI/IDEA.
Authors: King-kui Sin, Xi Xuan, Chunyu Kit, Clara Ho-yan Chan, Honic Ho-kin Ip
Abstract: This paper addresses the challenges translating case law under Hong Kong's bilingual legal system. It highlights the initial success of translating all written statutes into Chinese before the 1997 handover, a task mandated by the Basic Law. The effort involved significant collaboration among legal, linguistic, and translation experts, resulting in a comprehensive and culturally appropriate bilingual legal system. However, translating case law remains a significant challenge due to the sheer volume and continuous growth of judicial decisions. The paper critiques the governments and judiciarys sporadic and uncoordinated efforts to translate case law, contrasting it with the thorough approach previously taken for statute translation. Although the government acknowledges the importance of legal bilingualism, it lacks a sustainable strategy for translating case law. The Judiciarys position that translating all judgments is unnecessary, unrealistic, and not cost-effectiveis analyzed and critiqued for its impact on legal transparency and public trust. A proposed solution involves leveraging machine translation technology through a human-machine interactive translation platform, which undergoes two major transitions. Initially based on a neural model, the platform transitions to using a large language model for improved translation accuracy. Furthermore, it evolves from a single-agent system to a multi-agent system, incorporating Translator, Annotator, and Proofreader agents. This multi-agent approach, supported by a grant, aims to facilitate efficient, high-quality translation of judicial judgments by integrating advanced artificial intelligence and continuous feedback mechanisms, thus better meeting the needs of a bilingual legal system.
Authors: Enes Yavuz Ugan, Ngoc-Quan Pham, Leonard B\"armann, Alex Waibel
Abstract: Code-switching, the alternation of languages within a single discourse, presents a significant challenge for Automatic Speech Recognition. Despite the unique nature of the task, performance is commonly measured with established metrics such as Word-Error-Rate (WER). However, in this paper, we question whether these general metrics accurately assess performance on code-switching. Specifically, using both Connectionist-Temporal-Classification and Encoder-Decoder models, we show fine-tuning on non-code-switched data from both matrix and embedded language improves classical metrics on code-switching test sets, although actual code-switched words worsen (as expected). Therefore, we propose Point-of-Interest Error Rate (PIER), a variant of WER that focuses only on specific words of interest. We instantiate PIER on code-switched utterances and show that this more accurately describes the code-switching performance, showing huge room for improvement in future work. This focused evaluation allows for a more precise assessment of model performance, particularly in challenging aspects such as inter-word and intra-word code-switching.
Authors: Masatoshi Uehara, Yulai Zhao, Chenyu Wang, Xiner Li, Aviv Regev, Sergey Levine, Tommaso Biancalani
Abstract: This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities, practical applications in fields such as biology often require sample generation that maximizes specific metrics (e.g., stability, affinity in proteins, closeness to target structures). In these scenarios, diffusion models can be adapted not only to generate realistic samples but also to explicitly maximize desired measures at inference time without fine-tuning. This tutorial explores the foundational aspects of such inference-time algorithms. We review these methods from a unified perspective, demonstrating that current techniques -- such as Sequential Monte Carlo (SMC)-based guidance, value-based sampling, and classifier guidance -- aim to approximate soft optimal denoising processes (a.k.a. policies in RL) that combine pre-trained denoising processes with value functions serving as look-ahead functions that predict from intermediate states to terminal rewards. Within this framework, we present several novel algorithms not yet covered in the literature. Furthermore, we discuss (1) fine-tuning methods combined with inference-time techniques, (2) inference-time algorithms based on search algorithms such as Monte Carlo tree search, which have received limited attention in current research, and (3) connections between inference-time algorithms in language models and diffusion models. The code of this tutorial on protein design is available at https://github.com/masa-ue/AlignInversePro
Authors: Bowen Wen, Matthew Trepte, Joseph Aribido, Jan Kautz, Orazio Gallo, Stan Birchfield
Abstract: Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching. We introduce FoundationStereo, a foundation model for stereo depth estimation designed to achieve strong zero-shot generalization. To this end, we first construct a large-scale (1M stereo pairs) synthetic training dataset featuring large diversity and high photorealism, followed by an automatic self-curation pipeline to remove ambiguous samples. We then design a number of network architecture components to enhance scalability, including a side-tuning feature backbone that adapts rich monocular priors from vision foundation models to mitigate the sim-to-real gap, and long-range context reasoning for effective cost volume filtering. Together, these components lead to strong robustness and accuracy across domains, establishing a new standard in zero-shot stereo depth estimation. Project page: https://nvlabs.github.io/FoundationStereo/
Authors: Pit Neitemeier, Bj\"orn Deiseroth, Constantin Eichenberg, Lukas Balles
Abstract: Tokenization is a fundamental step in natural language processing, breaking text into units that computational models can process. While learned subword tokenizers have become the de-facto standard, they present challenges such as large vocabularies, limited adaptability to new domains or languages, and sensitivity to spelling errors and variations. To overcome these limitations, we investigate a hierarchical architecture for autoregressive language modelling that combines character-level and word-level processing. It employs a lightweight character-level encoder to convert character sequences into word embeddings, which are then processed by a word-level backbone model and decoded back into characters via a compact character-level decoder. This method retains the sequence compression benefits of word-level tokenization without relying on a rigid, predefined vocabulary. We demonstrate, at scales up to 7 billion parameters, that hierarchical transformers match the downstream task performance of subword-tokenizer-based models while exhibiting significantly greater robustness to input perturbations. Additionally, during continued pretraining on an out-of-domain language, our model trains almost twice as fast, achieves superior performance on the target language, and retains more of its previously learned knowledge. Hierarchical transformers pave the way for NLP systems that are more robust, flexible, and generalizable across languages and domains.