Authors: Zhongkai Shangguan, Zanming Huang, Eshed Ohn-Bar, Ola Ozernov-Palchik, Derek Kosty, Michael Stoolmiller, Hank Fien
Abstract: Models for student reading performance can empower educators and institutions to proactively identify at-risk students, thereby enabling early and tailored instructional interventions. However, there are no suitable publicly available educational datasets for modeling and predicting future reading performance. In this work, we introduce the Enhanced Core Reading Instruction ECRI dataset, a novel large-scale longitudinal tabular dataset collected across 44 schools with 6,916 students and 172 teachers. We leverage the dataset to empirically evaluate the ability of state-of-the-art machine learning models to recognize early childhood educational patterns in multivariate and partial measurements. Specifically, we demonstrate a simple self-supervised strategy in which a Multi-Layer Perception (MLP) network is pre-trained over masked inputs to outperform several strong baselines while generalizing over diverse educational settings. To facilitate future developments in precise modeling and responsible use of models for individualized and early intervention strategies, our data and code are available at https://ecri-data.github.io/.
Authors: Hamed Fayyaz, Mehak Gupta, Alejandra Perez Ramirez, Claudine Jurkovitz, H. Timothy Bunnell, Thao-Ly T. Phan, Rahmatollah Beheshti
Abstract: Reliable prediction of pediatric obesity can offer a valuable resource to providers, helping them engage in timely preventive interventions before the disease is established. Many efforts have been made to develop ML-based predictive models of obesity, and some studies have reported high predictive performances. However, no commonly used clinical decision support tool based on existing ML models currently exists. This study presents a novel end-to-end pipeline specifically designed for pediatric obesity prediction, which supports the entire process of data extraction, inference, and communication via an API or a user interface. While focusing only on routinely recorded data in pediatric electronic health records (EHRs), our pipeline uses a diverse expert-curated list of medical concepts to predict the 1-3 years risk of developing obesity. Furthermore, by using the Fast Healthcare Interoperability Resources (FHIR) standard in our design procedure, we specifically target facilitating low-effort integration of our pipeline with different EHR systems. In our experiments, we report the effectiveness of the predictive model as well as its alignment with the feedback from various stakeholders, including ML scientists, providers, health IT personnel, health administration representatives, and patient group representatives.
Authors: Hui Dou, Xinyu Mu, Mengjun Yi, Feng Han, Jian Zhao, Furao Shen
Abstract: Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challenges for practical applications. In this study, we provide quantitative metrics for assessing CNN filters by clustering the feature maps corresponding to individual filters in the model via Gaussian Mixture Model (GMM). By analyzing the clustering results, we screen out some anomaly filters associated with outlier samples. We further analyze the relationship between the anomaly filters and model overfitting, proposing three hypotheses. This method is universally applicable across diverse CNN architectures without modifications, as evidenced by its successful application to models like AlexNet and LeNet-5. We present three meticulously designed experiments demonstrating our hypotheses from the perspectives of model behavior, dataset characteristics, and filter impacts. Through this work, we offer a novel perspective for evaluating the CNN performance and gain new insights into the operational behavior of model overfitting.
Authors: Aoming Liang, Qi Liu, Lei Xu, Fahad Sohrab, Weicheng Cui, Changhui Song, Moncef Gaubbouj
Abstract: Numerous studies have focused on learning and understanding the dynamics of physical systems from video data, such as spatial intelligence. Artificial intelligence requires quantitative assessments of the uncertainty of the model to ensure reliability. However, there is still a relative lack of systematic assessment of the uncertainties, particularly the uncertainties of the physical data. Our motivation is to introduce conformal prediction into the uncertainty assessment of dynamical systems, providing a method supported by theoretical guarantees. This paper uses the conformal prediction method to assess uncertainties with benchmark operator learning methods. We have also compared the Monte Carlo Dropout and Ensemble methods in the partial differential equations dataset, effectively evaluating uncertainty through straight roll-outs, making it ideal for time-series tasks.
Authors: Wenbin Pei, Ruohao Dai, Bing Xue, Mengjie Zhang, Qiang Zhang, Yiu-Ming Cheung, Shuyin Xia
Abstract: Class imbalance would lead to biased classifiers that favor the majority class and disadvantage the minority class. Unfortunately, from a practical perspective, the minority class is of importance in many real-life applications. Hybrid sampling methods address this by oversampling the minority class to increase the number of its instances, followed by undersampling to remove low-quality instances. However, most existing sampling methods face difficulties in generating diverse high-quality instances and often fail to remove noise or low-quality instances on a larger scale effectively. This paper therefore proposes an evolutionary multi-granularity hybrid sampling method, called EvoSampling. During the oversampling process, genetic programming (GP) is used with multi-task learning to effectively and efficiently generate diverse high-quality instances. During the undersampling process, we develop a granular ball-based undersampling method that removes noise in a multi-granular fashion, thereby enhancing data quality. Experiments on 20 imbalanced datasets demonstrate that EvoSampling effectively enhances the performance of various classification algorithms by providing better datasets than existing sampling methods. Besides, ablation studies further indicate that allowing knowledge transfer accelerates the GP's evolutionary learning process.
Authors: Muhammad Arslan Manzoor, Ruihong Zeng, Dilshod Azizov, Preslav Nakov, Shangsong Liang
Abstract: In the current era of rapidly growing digital data, evaluating the political bias and factuality of news outlets has become more important for seeking reliable information online. In this work, we study the classification problem of profiling news media from the lens of political bias and factuality. Traditional profiling methods, such as Pre-trained Language Models (PLMs) and Graph Neural Networks (GNNs) have shown promising results, but they face notable challenges. PLMs focus solely on textual features, causing them to overlook the complex relationships between entities, while GNNs often struggle with media graphs containing disconnected components and insufficient labels. To address these limitations, we propose MediaGraphMind (MGM), an effective solution within a variational Expectation-Maximization (EM) framework. Instead of relying on limited neighboring nodes, MGM leverages features, structural patterns, and label information from globally similar nodes. Such a framework not only enables GNNs to capture long-range dependencies for learning expressive node representations but also enhances PLMs by integrating structural information and therefore improving the performance of both models. The extensive experiments demonstrate the effectiveness of the proposed framework and achieve new state-of-the-art results. Further, we share our repository1 which contains the dataset, code, and documentation
Authors: Amanda Rios, Ibrahima Ndiour, Parual Datta, Omesh Tickoo, Nilesh Ahuja
Abstract: In the field of continual learning, relying on so-called oracles for novelty detection is commonplace albeit unrealistic. This paper introduces CONCLAD ("COntinuous Novel CLAss Detector"), a comprehensive solution to the under-explored problem of continual novel class detection in post-deployment data. At each new task, our approach employs an iterative uncertainty estimation algorithm to differentiate between known and novel class(es) samples, and to further discriminate between the different novel classes themselves. Samples predicted to be from a novel class with high-confidence are automatically pseudo-labeled and used to update our model. Simultaneously, a tiny supervision budget is used to iteratively query ambiguous novel class predictions, which are also used during update. Evaluation across multiple datasets, ablations and experimental settings demonstrate our method's effectiveness at separating novel and old class samples continuously. We will release our code upon acceptance.
Authors: Angel Yanguas-Gil, Matthew T. Dearing, Jeffrey W. Elam, Jessica C. Jones, Sungjoon Kim, Adnan Mohammad, Chi Thang Nguyen, Bratin Sengupta
Abstract: In this work we introduce an open-ended question benchmark, ALDbench, to evaluate the performance of large language models (LLMs) in materials synthesis, and in particular in the field of atomic layer deposition, a thin film growth technique used in energy applications and microelectronics. Our benchmark comprises questions with a level of difficulty ranging from graduate level to domain expert current with the state of the art in the field. Human experts reviewed the questions along the criteria of difficulty and specificity, and the model responses along four different criteria: overall quality, specificity, relevance, and accuracy. We ran this benchmark on an instance of OpenAI's GPT-4o. The responses from the model received a composite quality score of 3.7 on a 1 to 5 scale, consistent with a passing grade. However, 36% of the questions received at least one below average score. An in-depth analysis of the responses identified at least five instances of suspected hallucination. Finally, we observed statistically significant correlations between the difficulty of the question and the quality of the response, the difficulty of the question and the relevance of the response, and the specificity of the question and the accuracy of the response as graded by the human experts. This emphasizes the need to evaluate LLMs across multiple criteria beyond difficulty or accuracy.
Authors: Xingyu Xiao, Peng Chen
Abstract: The Fussell-Vesely Importance (FV) reflects the potential impact of a basic event on system failure, and is crucial for ensuring system reliability. However, traditional methods for calculating FV importance are complex and time-consuming, requiring the construction of fault trees and the calculation of minimal cut set. To address these limitations, this study proposes a hybrid real-time framework to evaluate the FV importance of basic events. Our framework combines expert knowledge with a data-driven model. First, we use Interpretive Structural Modeling (ISM) to build a virtual fault tree that captures the relationships between basic events. Unlike traditional fault trees, which include intermediate events, our virtual fault tree consists solely of basic events, reducing its complexity and space requirements. Additionally, our virtual fault tree considers the dependencies between basic events rather than assuming their independence, as is typically done in traditional fault trees. We then feed both the event relationships and relevant data into a graph neural network (GNN). This approach enables a rapid, data-driven calculation of FV importance, significantly reducing processing time and quickly identifying critical events, thus providing robust decision support for risk control. Results demonstrate that our model performs well in terms of MSE, RMSE, MAE, and R2, reducing computational energy consumption and offering real-time, risk-informed decision support for complex systems.
Authors: Shambhavi Krishna, Aishwarya Sahoo
Abstract: Collecting high-quality preference datasets for reinforcement learning from human feedback (RLHF) is resource-intensive and challenging. As a result, researchers often train reward models on extensive offline datasets which aggregate diverse generation sources and scoring/alignment policies. We hypothesize that this aggregation has an averaging effect on reward model scores, which limits signal and impairs the alignment process. Inspired by the field of inverse RL, we define the 'inverse alignment problem' in language model training, where our objective is to optimize the critic's reward for a fixed actor and a fixed offline preference dataset. We hypothesize that solving the inverse alignment problem will improve reward model quality by providing clearer feedback on the policy's current behavior. To that end, we investigate whether repeatedly fine-tuning a reward model on subsets of the offline preference dataset aligned with a periodically frozen policy during RLHF improves upon vanilla RLHF. Our empirical results demonstrate that this approach facilitates superior alignment and faster convergence compared to using an unaligned or out-of-distribution reward model relative to the LLM policy.
Authors: Marek Miltner, Jakub Z\'ika, Daniel Va\v{s}ata, Artem Bryksa, Magda Friedjungov\'a, Ond\v{r}ej \v{S}togl, Ram Rajagopal, Old\v{r}ich Star\'y
Abstract: This study addresses the challenge of predicting electric vehicle (EV) charging profiles in urban locations with limited data. Utilizing a neural network architecture, we aim to uncover latent charging profiles influenced by spatio-temporal factors. Our model focuses on peak power demand and daily load shapes, providing insights into charging behavior. Our results indicate significant impacts from the type of Basic Administrative Units on predicted load curves, which contributes to the understanding and optimization of EV charging infrastructure in urban settings and allows Distribution System Operators (DSO) to more efficiently plan EV charging infrastructure expansion.
Authors: Soroush Omranpour, Guillaume Rabusseau, Reihaneh Rabbany
Abstract: In this paper, we tackle the challenge of predicting stock movements in financial markets by introducing Higher Order Transformers, a novel architecture designed for processing multivariate time-series data. We extend the self-attention mechanism and the transformer architecture to a higher order, effectively capturing complex market dynamics across time and variables. To manage computational complexity, we propose a low-rank approximation of the potentially large attention tensor using tensor decomposition and employ kernel attention, reducing complexity to linear with respect to the data size. Additionally, we present an encoder-decoder model that integrates technical and fundamental analysis, utilizing multimodal signals from historical prices and related tweets. Our experiments on the Stocknet dataset demonstrate the effectiveness of our method, highlighting its potential for enhancing stock movement prediction in financial markets.
Authors: Siddhant Ray, Rui Pan, Zhuohan Gu, Kuntai Du, Ganesh Ananthanarayanan, Ravi Netravali, Junchen Jiang
Abstract: RAG (Retrieval Augmented Generation) allows LLMs (large language models) to generate better responses with external knowledge, but using more external knowledge often improves generation quality at the expense of response delay. Prior work either reduces the response delay (through better scheduling of RAG queries) or strives to maximize quality (which involves tuning the RAG workflow), but they fall short in optimizing the tradeoff between the delay and quality of RAG responses. This paper presents RAGServe, the first RAG system that jointly schedules queries and adapts the key RAG configurations of each query, such as the number of retrieved text chunks and synthesis methods, in order to balance quality optimization and response delay reduction. Using 4 popular RAG-QA datasets, we show that compared with the state-of-the-art RAG optimization schemes, RAGServe reduces the generation latency by $1.64-2.54\times$ without sacrificing generation quality.
Authors: Brandon Gower-Winter, Georg Krempl, Sergey Dragomiretskiy, Tineke Jelsma, Arno Siebes
Abstract: Concept Drift has been extensively studied within the context of Stream Learning. However, it is often assumed that the deployed model's predictions play no role in the concept drift the system experiences. Closer inspection reveals that this is not always the case. Automated trading might be prone to self-fulfilling feedback loops. Likewise, malicious entities might adapt to evade detectors in the adversarial setting resulting in a self-negating feedback loop that requires the deployed models to constantly retrain. Such settings where a model may induce concept drift are called performative. In this work, we investigate this phenomenon. Our contributions are as follows: First, we define performative drift within a stream learning setting and distinguish it from other causes of drift. We introduce a novel type of drift detection task, aimed at identifying potential performative concept drift in data streams. We propose a first such performative drift detection approach, called CheckerBoard Performative Drift Detection (CB-PDD). We apply CB-PDD to both synthetic and semi-synthetic datasets that exhibit varying degrees of self-fulfilling feedback loops. Results are positive with CB-PDD showing high efficacy, low false detection rates, resilience to intrinsic drift, comparability to other drift detection techniques, and an ability to effectively detect performative drift in semi-synthetic datasets. Secondly, we highlight the role intrinsic (traditional) drift plays in obfuscating performative drift and discuss the implications of these findings as well as the limitations of CB-PDD.
Authors: Ahmed Mohamed Hussain, Nada Abughanam, Panos Papadimitratos
Abstract: The deployment of the Internet of Things (IoT) in smart cities and critical infrastructure has enhanced connectivity and real-time data exchange but introduced significant security challenges. While effective, cryptography can often be resource-intensive for small-footprint resource-constrained (i.e., IoT) devices. Radio Frequency Fingerprinting (RFF) offers a promising authentication alternative by using unique RF signal characteristics for device identification at the Physical (PHY)-layer, without resorting to cryptographic solutions. The challenge is two-fold: how to deploy such RFF in a large scale and for resource-constrained environments. Edge computing, processing data closer to its source, i.e., the wireless device, enables faster decision-making, reducing reliance on centralized cloud servers. Considering a modest edge device, we introduce two truly lightweight Edge AI-based RFF schemes tailored for resource-constrained devices. We implement two Deep Learning models, namely a Convolution Neural Network and a Transformer-Encoder, to extract complex features from the IQ samples, forming device-specific RF fingerprints. We convert the models to TensorFlow Lite and evaluate them on a Raspberry Pi, demonstrating the practicality of Edge deployment. Evaluations demonstrate the Transformer-Encoder outperforms the CNN in identifying unique transmitter features, achieving high accuracy (> 0.95) and ROC-AUC scores (> 0.90) while maintaining a compact model size of 73KB, appropriate for resource-constrained devices.
Authors: Giorgio Morales, John Sheppard
Abstract: Obtaining high certainty in predictive models is crucial for making informed and trustworthy decisions in many scientific and engineering domains. However, extensive experimentation required for model accuracy can be both costly and time-consuming. This paper presents an adaptive sampling approach designed to reduce epistemic uncertainty in predictive models. Our primary contribution is the development of a metric that estimates potential epistemic uncertainty leveraging prediction interval-generation neural networks. This estimation relies on the distance between the predicted upper and lower bounds and the observed data at the tested positions and their neighboring points. Our second contribution is the proposal of a batch sampling strategy based on Gaussian processes (GPs). A GP is used as a surrogate model of the networks trained at each iteration of the adaptive sampling process. Using this GP, we design an acquisition function that selects a combination of sampling locations to maximize the reduction of epistemic uncertainty across the domain. We test our approach on three unidimensional synthetic problems and a multi-dimensional dataset based on an agricultural field for selecting experimental fertilizer rates. The results demonstrate that our method consistently converges faster to minimum epistemic uncertainty levels compared to Normalizing Flows Ensembles, MC-Dropout, and simple GPs.
Authors: Karina Halevy, Karly Hou, Charumathi Badrinath
Abstract: Data augmentation methods, especially SoTA interpolation-based methods such as Fair Mixup, have been widely shown to increase model fairness. However, this fairness is evaluated on metrics that do not capture model uncertainty and on datasets with only one, relatively large, minority group. As a remedy, multicalibration has been introduced to measure fairness while accommodating uncertainty and accounting for multiple minority groups. However, existing methods of improving multicalibration involve reducing initial training data to create a holdout set for post-processing, which is not ideal when minority training data is already sparse. This paper uses multicalibration to more rigorously examine data augmentation for classification fairness. We stress-test four versions of Fair Mixup on two structured data classification problems with up to 81 marginalized groups, evaluating multicalibration violations and balanced accuracy. We find that on nearly every experiment, Fair Mixup \textit{worsens} baseline performance and fairness, but the simple vanilla Mixup \textit{outperforms} both Fair Mixup and the baseline, especially when calibrating on small groups. \textit{Combining} vanilla Mixup with multicalibration post-processing, which enforces multicalibration through post-processing on a holdout set, further increases fairness.
Authors: Avinandan Bose, Zhihan Xiong, Aadirupa Saha, Simon Shaolei Du, Maryam Fazel
Abstract: Reinforcement Learning from Human Feedback (RLHF) is currently the leading approach for aligning large language models with human preferences. Typically, these models rely on extensive offline preference datasets for training. However, offline algorithms impose strict concentrability requirements, which are often difficult to satisfy. On the other hand, while online algorithms can avoid the concentrability issue, pure online exploration could be expensive due to the active preference query cost and real-time implementation overhead. In this paper, we propose a novel approach: Hybrid Preference Optimization (HPO) which combines online exploration with existing offline preferences by relaxing the stringent concentrability conditions for offline exploration, as well as significantly improving the sample efficiency for its online counterpart. We give the first provably optimal theoretical bound for Hybrid RLHF with preference feedback, providing sample complexity bounds for policy optimization with matching lower bounds. Our results yield improved sample efficiency of hybrid RLHF over pure offline and online exploration.
Authors: Arash Hajisafi, Maria Despoina Siampou, Bita Azarijoo, Cyrus Shahabi
Abstract: Accurately modeling and analyzing time series data is crucial for downstream applications across various fields, including healthcare, finance, astronomy, and epidemiology. However, real-world time series often exhibit irregularities such as misaligned timestamps, missing entries, and variable sampling rates, complicating their analysis. Existing approaches often rely on imputation, which can introduce biases. A few approaches that directly model irregularity tend to focus exclusively on either capturing intra-series patterns or inter-series relationships, missing the benefits of integrating both. To this end, we present WaveGNN, a novel framework designed to directly (i.e., no imputation) embed irregularly sampled multivariate time series data for accurate predictions. WaveGNN utilizes a Transformer-based encoder to capture intra-series patterns by directly encoding the temporal dynamics of each time series. To capture inter-series relationships, WaveGNN uses a dynamic graph neural network model, where each node represents a sensor, and the edges capture the long- and short-term relationships between them. Our experimental results on real-world healthcare datasets demonstrate that WaveGNN consistently outperforms existing state-of-the-art methods, with an average relative improvement of 14.7% in F1-score when compared to the second-best baseline in cases with extreme sparsity. Our ablation studies reveal that both intra-series and inter-series modeling significantly contribute to this notable improvement.
Authors: Dongfang Zhao
Abstract: The increasing prevalence of high-dimensional data demands efficient and scalable compression methods to support modern applications. However, existing techniques like PCA and Autoencoders often rely on auxiliary metadata or intricate architectures, limiting their practicality for streaming or infinite datasets. In this paper, we introduce a stateless compression framework that leverages polynomial representations to achieve compact, interpretable, and scalable data reduction. By eliminating the need for auxiliary data, our method supports direct algebraic operations in the compressed domain while minimizing error growth during computations. Through extensive experiments on synthetic and real-world datasets, we show that our approach achieves high compression ratios without compromising reconstruction accuracy, all while maintaining simplicity and scalability.
Authors: Jinglong Luo, Guanzhong Chen, Yehong Zhang, Shiyu Liu, Hui Wang, Yue Yu, Xun Zhou, Yuan Qi, Zenglin Xu
Abstract: As pre-trained models, like Transformers, are increasingly deployed on cloud platforms for inference services, the privacy concerns surrounding model parameters and inference data are becoming more acute. Current Privacy-Preserving Transformer Inference (PPTI) frameworks struggle with the "impossible trinity" of privacy, efficiency, and performance. For instance, Secure Multi-Party Computation (SMPC)-based solutions offer strong privacy guarantees but come with significant inference overhead and performance trade-offs. On the other hand, PPTI frameworks that use random permutations achieve inference efficiency close to that of plaintext and maintain accurate results but require exposing some model parameters and intermediate results, thereby risking substantial privacy breaches. Addressing this "impossible trinity" with a single technique proves challenging. To overcome this challenge, we propose Centaur, a novel hybrid PPTI framework. Unlike existing methods, Centaur protects model parameters with random permutations and inference data with SMPC, leveraging the structure of Transformer models. By designing a series of efficient privacy-preserving algorithms, Centaur leverages the strengths of both techniques to achieve a better balance between privacy, efficiency, and performance in PPTI. We comprehensively evaluate the effectiveness of Centaur on various types of Transformer models and datasets. Experimental results demonstrate that the privacy protection capabilities offered by Centaur can withstand various existing model inversion attack methods. In terms of performance and efficiency, Centaur not only maintains the same performance as plaintext inference but also improves inference speed by $5.0-30.4$ times.
Authors: Jingyang Li, Kuangyu Ding, Kim-Chuan Toh, Pan Zhou
Abstract: Preconditioned stochastic optimization algorithms, exemplified by Shampoo, have demonstrated superior performance over first-order optimizers, providing both theoretical advantages in convergence rates and practical improvements in large-scale neural network training. However, they incur substantial memory overhead due to the storage demands of non-diagonal preconditioning matrices. To address this, we introduce 4-bit quantization for Shampoo's preconditioners. We introduced two key methods: First, we apply Cholesky decomposition followed by quantization of the Cholesky factors, reducing memory usage by leveraging their lower triangular structure while preserving symmetry and positive definiteness to minimize information loss. To our knowledge, this is the first quantization approach applied to Cholesky factors of preconditioners. Second, we incorporate error feedback in the quantization process, efficiently storing Cholesky factors and error states in the lower and upper triangular parts of the same matrix. Through extensive experiments, we demonstrate that combining Cholesky quantization with error feedback enhances memory efficiency and algorithm performance in large-scale deep-learning tasks. Theoretically, we also provide convergence proofs for quantized Shampoo under both smooth and non-smooth stochastic optimization settings.
Authors: Chandra Kundu, Abiy Tasissa, HanQin Cai
Abstract: This paper addresses the problem of estimating the positions of points from distance measurements corrupted by sparse outliers. Specifically, we consider a setting with two types of nodes: anchor nodes, for which exact distances to each other are known, and target nodes, for which complete but corrupted distance measurements to the anchors are available. To tackle this problem, we propose a novel algorithm powered by Nystr\"om method and robust principal component analysis. Our method is computationally efficient as it processes only a localized subset of the distance matrix and does not require distance measurements between target nodes. Empirical evaluations on synthetic datasets, designed to mimic sensor localization, and on molecular experiments, demonstrate that our algorithm achieves accurate recovery with a modest number of anchors, even in the presence of high levels of sparse outliers.
Authors: Renqiang Luo, Huafei Huang, Ivan Lee, Chengpei Xu, Jianzhong Qi, Feng Xia
Abstract: Recent studies have highlighted significant fairness issues in Graph Transformer (GT) models, particularly against subgroups defined by sensitive features. Additionally, GTs are computationally intensive and memory-demanding, limiting their application to large-scale graphs. Our experiments demonstrate that graph partitioning can enhance the fairness of GT models while reducing computational complexity. To understand this improvement, we conducted a theoretical investigation into the root causes of fairness issues in GT models. We found that the sensitive features of higher-order nodes disproportionately influence lower-order nodes, resulting in sensitive feature bias. We propose Fairness-aware scalable GT based on Graph Partitioning (FairGP), which partitions the graph to minimize the negative impact of higher-order nodes. By optimizing attention mechanisms, FairGP mitigates the bias introduced by global attention, thereby enhancing fairness. Extensive empirical evaluations on six real-world datasets validate the superior performance of FairGP in achieving fairness compared to state-of-the-art methods. The codes are available at https://github.com/LuoRenqiang/FairGP.
Authors: Guanyu Nie, Vaneet Aggarwal, Christopher John Quinn
Abstract: In this paper, we present the first sublinear $\alpha$-regret bounds for online $k$-submodular optimization problems with full-bandit feedback, where $\alpha$ is a corresponding offline approximation ratio. Specifically, we propose online algorithms for multiple $k$-submodular stochastic combinatorial multi-armed bandit problems, including (i) monotone functions and individual size constraints, (ii) monotone functions with matroid constraints, (iii) non-monotone functions with matroid constraints, (iv) non-monotone functions without constraints, and (v) monotone functions without constraints. We transform approximation algorithms for offline $k$-submodular maximization problems into online algorithms through the offline-to-online framework proposed by Nie et al. (2023a). A key contribution of our work is analyzing the robustness of the offline algorithms.
Authors: Dupati Srikar Chandra, P. K. Srijith, Dana Rezazadegan, Chris McCarthy
Abstract: Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while learning a new task. Moreover, retraining large models like transformers from scratch for every new task is costly. An effective approach to address continual learning is to use a large pre-trained model with task-specific adapters to adapt to the new tasks. Though this approach can mitigate catastrophic forgetting, they fail to transfer knowledge across tasks as each task is learning adapters separately. To address this, we propose a novel approach Linked Adapters that allows knowledge transfer through a weighted attention mechanism to other task-specific adapters. Linked adapters use a multi-layer perceptron (MLP) to model the attention weights, which overcomes the challenge of backward knowledge transfer in continual learning in addition to modeling the forward knowledge transfer. During inference, our proposed approach effectively leverages knowledge transfer through MLP-based attention weights across all the lateral task adapters. Through numerous experiments conducted on diverse image classification datasets, we effectively demonstrated the improvement in performance on the continual learning tasks using Linked Adapters.
Authors: Juncheng Wang, Bingjie Yan, Yituo Liu
Abstract: We consider online convex optimization with time-varying constraints and conduct performance analysis using two stringent metrics: dynamic regret with respect to the online solution benchmark, and hard constraint violation that does not allow any compensated violation over time. We propose an efficient algorithm called Constrained Online Learning with Doubly-bounded Queue (COLDQ), which introduces a novel virtual queue that is both lower and upper bounded, allowing tight control of the constraint violation without the need for the Slater condition. We prove via a new Lyapunov drift analysis that COLDQ achieves $O(T^\frac{1+V_x}{2})$ dynamic regret and $O(T^{V_g})$ hard constraint violation, where $V_x$ and $V_g$ capture the dynamics of the loss and constraint functions. For the first time, the two bounds smoothly approach to the best-known $O(T^\frac{1}{2})$ regret and $O(1)$ violation, as the dynamics of the losses and constraints diminish. For strongly convex loss functions, COLDQ matches the best-known $O(\log{T})$ static regret while maintaining the $O(T^{V_g})$ hard constraint violation. We further introduce an expert-tracking variation of COLDQ, which achieves the same performance bounds without any prior knowledge of the system dynamics. Simulation results demonstrate that COLDQ outperforms the state-of-the-art approaches.
Authors: Fengshuo Bai, Runze Liu, Yali Du, Ying Wen, Yaodong Yang
Abstract: Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives, often bypassing traditional reward-based defenses. Prior methods have primarily focused on reducing cumulative rewards; however, rewards are typically too generic to capture complex safety requirements effectively. As a result, focusing solely on reward reduction can lead to suboptimal attack strategies, particularly in safety-critical scenarios where more precise behavior manipulation is needed. To address these challenges, we propose RAT, a method designed for universal, targeted behavior attacks. RAT trains an intention policy that is explicitly aligned with human preferences, serving as a precise behavioral target for the adversary. Concurrently, an adversary manipulates the victim's policy to follow this target behavior. To enhance the effectiveness of these attacks, RAT dynamically adjusts the state occupancy measure within the replay buffer, allowing for more controlled and effective behavior manipulation. Our empirical results on robotic simulation tasks demonstrate that RAT outperforms existing adversarial attack algorithms in inducing specific behaviors. Additionally, RAT shows promise in improving agent robustness, leading to more resilient policies. We further validate RAT by guiding Decision Transformer agents to adopt behaviors aligned with human preferences in various MuJoCo tasks, demonstrating its effectiveness across diverse tasks.
Authors: Sergei V. Kozyrev, Ilya A Lopatin, Alexander N Pechen
Abstract: While there are many works on the applications of machine learning, not so many of them are trying to understand the theoretical justifications to explain their efficiency. In this work, overfitting control (or generalization property) in machine learning is explained using analogies from physics and biology. For stochastic gradient Langevin dynamics, we show that the Eyring formula of kinetic theory allows to control overfitting in the algorithmic stability approach - when wide minima of the risk function with low free energy correspond to low overfitting. For the generative adversarial network (GAN) model, we establish an analogy between GAN and the predator-prey model in biology. An application of this analogy allows us to explain the selection of wide likelihood maxima and overfitting reduction for GANs.
Authors: Jianfeng Li, Jiawen Zhang, Feng Wang, Lianbo Ma
Abstract: One-shot methods have significantly advanced the field of neural architecture search (NAS) by adopting weight-sharing strategy to reduce search costs. However, the accuracy of performance estimation can be compromised by co-adaptation. Few-shot methods divide the entire supernet into individual sub-supernets by splitting edge by edge to alleviate this issue, yet neglect relationships among edges and result in performance degradation on huge search space. In this paper, we introduce HEP-NAS, a hierarchy-wise partition algorithm designed to further enhance accuracy. To begin with, HEP-NAS treats edges sharing the same end node as a hierarchy, permuting and splitting edges within the same hierarchy to directly search for the optimal operation combination for each intermediate node. This approach aligns more closely with the ultimate goal of NAS. Furthermore, HEP-NAS selects the most promising sub-supernet after each segmentation, progressively narrowing the search space in which the optimal architecture may exist. To improve performance evaluation of sub-supernets, HEP-NAS employs search space mutual distillation, stabilizing the training process and accelerating the convergence of each individual sub-supernet. Within a given budget, HEP-NAS enables the splitting of all edges and gradually searches for architectures with higher accuracy. Experimental results across various datasets and search spaces demonstrate the superiority of HEP-NAS compared to state-of-the-art methods.
Authors: Haorong Han, Jidong Yuan, Chixuan Wei, Zhongyang Yu
Abstract: Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup for consistency regularization may degrade SSL performance by compromising the purity of artificial labels. Moreover, most pseudo-labeling based methods utilize thresholding strategy to exclude low-confidence data, aiming to mitigate confirmation bias; however, this approach limits the utility of unlabeled samples. To address these challenges, we propose RegMixMatch, a novel framework that optimizes the use of Mixup with both high- and low-confidence samples in SSL. First, we introduce semi-supervised RegMixup, which effectively addresses reduced artificial labels purity by using both mixed samples and clean samples for training. Second, we develop a class-aware Mixup technique that integrates information from the top-2 predicted classes into low-confidence samples and their artificial labels, reducing the confirmation bias associated with these samples and enhancing their effective utilization. Experimental results demonstrate that RegMixMatch achieves state-of-the-art performance across various SSL benchmarks.
Authors: Zhuoran Qiao, Feizhi Ding, Thomas Dresselhaus, Mia A. Rosenfeld, Xiaotian Han, Owen Howell, Aniketh Iyengar, Stephen Opalenski, Anders S. Christensen, Sai Krishna Sirumalla, Frederick R. Manby, Thomas F. Miller III, Matthew Welborn
Abstract: Structure determination is essential to a mechanistic understanding of diseases and the development of novel therapeutics. Machine-learning-based structure prediction methods have made significant advancements by computationally predicting protein and bioassembly structures from sequences and molecular topology alone. Despite substantial progress in the field, challenges remain to deliver structure prediction models to real-world drug discovery. Here, we present NeuralPLexer3 -- a physics-inspired flow-based generative model that achieves state-of-the-art prediction accuracy on key biomolecular interaction types and improves training and sampling efficiency compared to its predecessors and alternative methodologies. Examined through newly developed benchmarking strategies, NeuralPLexer3 excels in vital areas that are crucial to structure-based drug design, such as physical validity and ligand-induced conformational changes.
Authors: Anand Krishna, Philips George John, Adarsh Barik, Vincent Y. F. Tan
Abstract: In this work, we extend the concept of the $p$-mean welfare objective from social choice theory (Moulin 2004) to study $p$-mean regret in stochastic multi-armed bandit problems. The $p$-mean regret, defined as the difference between the optimal mean among the arms and the $p$-mean of the expected rewards, offers a flexible framework for evaluating bandit algorithms, enabling algorithm designers to balance fairness and efficiency by adjusting the parameter $p$. Our framework encompasses both average cumulative regret and Nash regret as special cases.
We introduce a simple, unified UCB-based algorithm (Explore-Then-UCB) that achieves novel $p$-mean regret bounds. Our algorithm consists of two phases: a carefully calibrated uniform exploration phase to initialize sample means, followed by the UCB1 algorithm of Auer, Cesa-Bianchi, and Fischer (2002). Under mild assumptions, we prove that our algorithm achieves a $p$-mean regret bound of $\tilde{O}\left(\sqrt{\frac{k}{T^{\frac{1}{2|p|}}}}\right)$ for all $p \leq -1$, where $k$ represents the number of arms and $T$ the time horizon. When $-1
Authors: Hanwei Fan, Ya Wang, Sicheng Li, Tingyuan Liang, Wei Zhang
Abstract: With the continuous advancement of processors, modern micro-architecture designs have become increasingly complex. The vast design space presents significant challenges for human designers, making design space exploration (DSE) algorithms a significant tool for $\mu$-arch design. In recent years, efforts have been made in the development of DSE algorithms, and promising results have been achieved. However, the existing DSE algorithms, e.g., Bayesian Optimization and ensemble learning, suffer from poor interpretability, hindering designers' understanding of the decision-making process. To address this limitation, we propose utilizing Fuzzy Neural Networks to induce and summarize knowledge and insights from the DSE process, enhancing interpretability and controllability. Furthermore, to improve efficiency, we introduce a multi-fidelity reinforcement learning approach, which primarily conducts exploration using cheap but less precise data, thereby substantially diminishing the reliance on costly data. Experimental results show that our method achieves excellent results with a very limited sample budget and successfully surpasses the current state-of-the-art. Our DSE framework is open-sourced and available at https://github.com/fanhanwei/FNN\_MFRL\_ArchDSE/\ .
Authors: Mattia Fanan, Davide Dalle Pezze, Emad Efatinasab, Ruggero Carli, Mirco Rampazzo, Gian Antonio Susto
Abstract: Behavior-based Driver Identification is an emerging technology that recognizes drivers based on their unique driving behaviors, offering important applications such as vehicle theft prevention and personalized driving experiences. However, most studies fail to account for the real-world challenges of deploying Deep Learning models within vehicles. These challenges include operating under limited computational resources, adapting to new drivers, and changes in driving behavior over time. The objective of this study is to evaluate if Continual Learning (CL) is well-suited to address these challenges, as it enables models to retain previously learned knowledge while continually adapting with minimal computational overhead and resource requirements. We tested several CL techniques across three scenarios of increasing complexity based on the well-known OCSLab dataset. This work provides an important step forward in scalable driver identification solutions, demonstrating that CL approaches, such as DER, can obtain strong performance, with only an 11% reduction in accuracy compared to the static scenario. Furthermore, to enhance the performance, we propose two new methods, SmooER and SmooDER, that leverage the temporal continuity of driver identity over time to enhance classification accuracy. Our novel method, SmooDER, achieves optimal results with only a 2% reduction compared to the 11\% of the DER approach. In conclusion, this study proves the feasibility of CL approaches to address the challenges of Driver Identification in dynamic environments, making them suitable for deployment on cloud infrastructure or directly within vehicles.
Authors: Nilo Schwencke, Cyril Furtlehner
Abstract: In the recent years, Physics Informed Neural Networks (PINNs) have received strong interest as a method to solve PDE driven systems, in particular for data assimilation purpose. This method is still in its infancy, with many shortcomings and failures that remain not properly understood. In this paper we propose a natural gradient approach to PINNs which contributes to speed-up and improve the accuracy of the training. Based on an in depth analysis of the differential geometric structures of the problem, we come up with two distinct contributions: (i) a new natural gradient algorithm that scales as $\min(P^2S, S^2P)$, where $P$ is the number of parameters, and $S$ the batch size; (ii) a mathematically principled reformulation of the PINNs problem that allows the extension of natural gradient to it, with proved connections to Green's function theory.
Authors: Yichun Yang, Rong-Hua Li, Meihao Liao, Longlong Lin, Guoren Wang
Abstract: Graph propagation (GP) computation plays a crucial role in graph data analysis, supporting various applications such as graph node similarity queries, graph node ranking, graph clustering, and graph neural networks. Existing methods, mainly relying on power iteration or push computation frameworks, often face challenges with slow convergence rates when applied to large-scale graphs. To address this issue, we propose a novel and powerful approach that accelerates power iteration and push methods using Chebyshev polynomials. Specifically, we first present a novel Chebyshev expansion formula for general GP functions, offering a new perspective on GP computation and achieving accelerated convergence. Building on these theoretical insights, we develop a novel Chebyshev power iteration method (\ltwocheb) and a novel Chebyshev push method (\chebpush). Our \ltwocheb method demonstrates an approximate acceleration of $O(\sqrt{N})$ compared to existing power iteration techniques for both personalized PageRank and heat kernel PageRank computations, which are well-studied GP problems. For \chebpush, we propose an innovative subset Chebyshev recurrence technique, enabling the design of a push-style local algorithm with provable error guarantee and reduced time complexity compared to existing push methods. We conduct extensive experiments using 5 large real-world datasets to evaluate our proposed algorithms, demonstrating their superior efficiency compared to state-of-the-art approaches.
Authors: Yongchao Ye, Xinting Zhu, Xuejin Shen, Xiaoyu Chen, Lishuai Li, S. Joe Qin
Abstract: Satellite pattern-of-life (PoL) identification is crucial for space safety and satellite monitoring, involving the analysis of typical satellite behaviors such as station-keeping, drift, etc. However, existing PoL identification methods remain underdeveloped due to the complexity of aerospace systems, variability in satellite behaviors, and fluctuating observation sampling rates. In a first attempt, we developed a domain expertise-informed machine learning method (Expert-ML) to combine satellite orbital movement knowledge and machine learning models. The Expert-ML method achieved high accuracy results in simulation data and real-world data with normal sampling rate. However, this approach lacks of generality as it requires domain expertise and its performance degraded significantly when data sampling rate varied. To achieve generality, we propose a novel diffusion-based PoL identification method. Distinct from prior approaches, the proposed method leverages a diffusion model to achieve end-to-end identification without manual refinement or domain-specific knowledge. Specifically, we employ a multivariate time-series encoder to capture hidden representations of satellite positional data. The encoded features are subsequently incorporated as conditional information in the denoising process to generate PoL labels. Through experimentation across real-world satellite settings, our proposed diffusion-based method demonstrates its high identification quality and provides a robust solution even with reduced data sampling rates, indicating its great potential in practical satellite behavior pattern identification, tracking and related mission deployment.
Authors: Edward Pearce-Crump, William J. Knottenbelt
Abstract: Group equivariant neural networks are growing in importance owing to their ability to generalise well in applications where the data has known underlying symmetries. Recent characterisations of a class of these networks that use high-order tensor power spaces as their layers suggest that they have significant potential; however, their implementation remains challenging owing to the prohibitively expensive nature of the computations that are involved. In this work, we present a fast matrix multiplication algorithm for any equivariant weight matrix that maps between tensor power layer spaces in these networks for four groups: the symmetric, orthogonal, special orthogonal, and symplectic groups. We obtain this algorithm by developing a diagrammatic framework based on category theory that enables us to not only express each weight matrix as a linear combination of diagrams but also makes it possible for us to use these diagrams to factor the original computation into a series of steps that are optimal. We show that this algorithm improves the Big-$O$ time complexity exponentially in comparison to a na\"{i}ve matrix multiplication.
Authors: Yongyu Wang
Abstract: Graph Neural Networks (GNNs) are currently one of the most powerful types of neural network architectures. Their advantage lies in the ability to leverage both the graph topology, which represents the relationships between samples, and the features of the samples themselves. However, the given graph topology often contains noisy edges, and GNNs are vulnerable to noise in the graph structure. This issue remains unresolved. In this paper, we propose using adversarial robustness evaluation to select a small subset of robust nodes that are less affected by noise. We then only feed the features of these robust nodes, along with the KNN graph constructed from these nodes, into the GNN for classification. Additionally, we compute the centroids for each class. For the remaining non-robust nodes, we assign them to the class whose centroid is closest to them. Experimental results show that this method significantly improves the accuracy of GNNs.
Authors: Wonkyo Choe, Yangfeng Ji, Felix Lin
Abstract: To deploy LLMs on resource-contained platforms such as mobile robotics and wearables, non-transformers LLMs have achieved major breakthroughs. Recently, a novel RNN-based LLM family, Repentance Weighted Key Value (RWKV) models have shown promising results in text generation on resource-constrained devices thanks to their computational efficiency. However, these models remain too large to be deployed on embedded devices due to their high parameter count. In this paper, we propose an efficient suite of compression techniques, tailored to the RWKV architecture. These techniques include low-rank approximation, sparsity predictors, and clustering head, designed to align with the model size. Our methods compress the RWKV models by 4.95--3.8x with only 2.95pp loss in accuracy.
Authors: Xiangfei Qiu, Xingjian Wu, Yan Lin, Chenjuan Guo, Jilin Hu, Bin Yang
Abstract: Multivariate time series forecasting is crucial for various applications, such as financial investment, energy management, weather forecasting, and traffic optimization. However, accurate forecasting is challenging due to two main factors. First, real-world time series often show heterogeneous temporal patterns caused by distribution shifts over time. Second, correlations among channels are complex and intertwined, making it hard to model the interactions among channels precisely and flexibly. In this study, we address these challenges by proposing a general framework called \textbf{DUET}, which introduces \underline{DU}al clustering on the temporal and channel dimensions to \underline{E}nhance multivariate \underline{T}ime series forecasting. First, we design a Temporal Clustering Module (TCM) that clusters time series into fine-grained distributions to handle heterogeneous temporal patterns. For different distribution clusters, we design various pattern extractors to capture their intrinsic temporal patterns, thus modeling the heterogeneity. Second, we introduce a novel Channel-Soft-Clustering strategy and design a Channel Clustering Module (CCM), which captures the relationships among channels in the frequency domain through metric learning and applies sparsification to mitigate the adverse effects of noisy channels. Finally, DUET combines TCM and CCM to incorporate both the temporal and channel dimensions. Extensive experiments on 25 real-world datasets from 10 application domains, demonstrate the state-of-the-art performance of DUET.
Authors: Marcin Pietro\'n, Kamil Faber, Dominik \.Zurek, Roberto Corizzo
Abstract: Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effective due to their potential to adapt the model architecture as new tasks are presented. However, many existing solutions do not efficiently exploit model sparsity, and are prone to capacity saturation due to their inefficient use of available weights, which limits the number of learnable tasks. In this paper, we propose TinySubNets (TSN), a novel architectural CL strategy that addresses the issues through the unique combination of pruning with different sparsity levels, adaptive quantization, and weight sharing. Pruning identifies a subset of weights that preserve model performance, making less relevant weights available for future tasks. Adaptive quantization allows a single weight to be separated into multiple parts which can be assigned to different tasks. Weight sharing between tasks boosts the exploitation of capacity and task similarity, allowing for the identification of a better trade-off between model accuracy and capacity. These features allow TSN to efficiently leverage the available capacity, enhance knowledge transfer, and reduce computational resource consumption. Experimental results involving common benchmark CL datasets and scenarios show that our proposed strategy achieves better results in terms of accuracy than existing state-of-the-art CL strategies. Moreover, our strategy is shown to provide a significantly improved model capacity exploitation. Code released at: https://github.com/lifelonglab/tinysubnets.
Authors: Zhi Zhou, Kun-Yang Yu, Lan-Zhe Guo, Yu-Feng Li
Abstract: Tabular data plays a vital role in various real-world scenarios and finds extensive applications. Although recent deep tabular models have shown remarkable success, they still struggle to handle data distribution shifts, leading to performance degradation when testing distributions change. To remedy this, a robust tabular model must adapt to generalize to unknown distributions during testing. In this paper, we investigate the problem of fully test-time adaptation (FTTA) for tabular data, where the model is adapted using only the testing data. We identify three key challenges: the existence of label and covariate distribution shifts, the lack of effective data augmentation, and the sensitivity of adaptation, which render existing FTTA methods ineffective for tabular data. To this end, we propose the Fully Test-time Adaptation for Tabular data, namely FTAT, which enables FTTA methods to robustly optimize the label distribution of predictions, adapt to shifted covariate distributions, and suit a variety of tasks and models effectively. We conduct comprehensive experiments on six benchmark datasets, which are evaluated using three metrics. The experimental results demonstrate that FTAT outperforms state-of-the-art methods by a margin.
Authors: Afsaneh Mahmoudi, Emil Bj\"ornson
Abstract: Federated learning (FL) is a distributed learning framework where users train a global model by exchanging local model updates with a server instead of raw datasets, preserving data privacy and reducing communication overhead. However, the latency grows with the number of users and the model size, impeding the successful FL over traditional wireless networks with orthogonal access. Cell-free massive multiple-input multipleoutput (CFmMIMO) is a promising solution to serve numerous users on the same time/frequency resource with similar rates. This architecture greatly reduces uplink latency through spatial multiplexing but does not take application characteristics into account. In this paper, we co-optimize the physical layer with the FL application to mitigate the straggler effect. We introduce a novel adaptive mixed-resolution quantization scheme of the local gradient vector updates, where only the most essential entries are given high resolution. Thereafter, we propose a dynamic uplink power control scheme to manage the varying user rates and mitigate the straggler effect. The numerical results demonstrate that the proposed method achieves test accuracy comparable to classic FL while reducing communication overhead by at least 93% on the CIFAR-10, CIFAR-100, and Fashion-MNIST datasets. We compare our methods against AQUILA, Top-q, and LAQ, using the max-sum rate and Dinkelbach power control schemes. Our approach reduces the communication overhead by 75% and achieves 10% higher test accuracy than these benchmarks within a constrained total latency budget.
Authors: Haocheng Duan, Hao Wu, Sean Qian
Abstract: Conventional automatic incident detection (AID) has relied heavily on all incident reports exclusively for training and evaluation. However, these reports suffer from a number of issues, such as delayed reports, inaccurate descriptions, false alarms, missing reports, and incidents that do not necessarily influence traffic. Relying on these reports to train or calibrate AID models hinders their ability to detect traffic anomalies effectively and timely, even leading to convergence issues in the model training process. Moreover, conventional AID models are not inherently designed to capture the early indicators of any generic incidents. It remains unclear how far ahead an AID model can report incidents. The AID applications in the literature are also spatially limited because the data used by most models is often limited to specific test road segments. To solve these problems, we propose a deep learning framework utilizing prior domain knowledge and model-designing strategies. This allows the model to detect a broader range of anomalies, not only incidents that significantly influence traffic flow but also early characteristics of incidents along with historically unreported anomalies. We specially design the model to target the early-stage detection/prediction of an incident. Additionally, unlike most conventional AID studies, we use widely available data, enhancing our method's scalability. The experimental results across numerous road segments on different maps demonstrate that our model leads to more effective and early anomaly detection. Our framework does not focus on stacking or tweaking various deep learning models; instead, it focuses on model design and training strategies to improve early detection performance.
Authors: Claudio Moroni, Claudio Borile, Carolina Mattsson, Michele Starnini, Andr\'e Panisson
Abstract: Link Prediction is a foundational task in Graph Representation Learning, supporting applications like link recommendation, knowledge graph completion and graph generation. Graph Neural Networks have shown the most promising results in this domain and are currently the de facto standard approach to learning from graph data. However, a key distinction exists between Undirected and Directed Link Prediction: the former just predicts the existence of an edge, while the latter must also account for edge directionality and bidirectionality. This translates to Directed Link Prediction (DLP) having three sub-tasks, each defined by how training, validation and test sets are structured. Most research on DLP overlooks this trichotomy, focusing solely on the "existence" sub-task, where training and test sets are random, uncorrelated samples of positive and negative directed edges. Even in the works that recognize the aforementioned trichotomy, models fail to perform well across all three sub-tasks. In this study, we experimentally demonstrate that training Neural DLP (NDLP) models only on the existence sub-task, using methods adapted from Neural Undirected Link Prediction, results in parameter configurations that fail to capture directionality and bidirectionality, even after rebalancing edge classes. To address this, we propose three strategies that handle the three tasks simultaneously. Our first strategy, the Multi-Class Framework for Neural Directed Link Prediction (MC-NDLP) maps NDLP to a Multi-Class training objective. The second and third approaches adopt a Multi-Task perspective, either with a Multi-Objective (MO-DLP) or a Scalarized (S-DLP) strategy. Our results show that these methods outperform traditional approaches across multiple datasets and models, achieving equivalent or superior performance in addressing the three DLP sub-tasks.
Authors: Junliang Lyu, Yixuan Zhang, Xiaoling Lu, Feng Zhou
Abstract: This work addresses a key limitation in current federated learning approaches, which predominantly focus on homogeneous tasks, neglecting the task diversity on local devices. We propose a principled integration of multi-task learning using multi-output Gaussian processes (MOGP) at the local level and federated learning at the global level. MOGP handles correlated classification and regression tasks, offering a Bayesian non-parametric approach that naturally quantifies uncertainty. The central server aggregates the posteriors from local devices, updating a global MOGP prior redistributed for training local models until convergence. Challenges in performing posterior inference on local devices are addressed through the P\'{o}lya-Gamma augmentation technique and mean-field variational inference, enhancing computational efficiency and convergence rate. Experimental results on both synthetic and real data demonstrate superior predictive performance, OOD detection, uncertainty calibration and convergence rate, highlighting the method's potential in diverse applications. Our code is publicly available at https://github.com/JunliangLv/task_diversity_BFL.
Authors: Hu Qiye, Zhou Hao, Yu RuoXi
Abstract: The phenomenon of grokking in over-parameterized neural networks has garnered significant interest. It involves the neural network initially memorizing the training set with zero training error and near-random test error. Subsequent prolonged training leads to a sharp transition from no generalization to perfect generalization. Our study comprises extensive experiments and an exploration of the research behind the mechanism of grokking. Through experiments, we gained insights into its behavior concerning the training data fraction, the model, and the optimization. The mechanism of grokking has been a subject of various viewpoints proposed by researchers, and we introduce some of these perspectives.
Authors: Yongchun Qin, Pengfei Fang, Hui Xue
Abstract: Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on leveraging the rich semantic information of pre-trained models (PTMs) in CIL tasks. Prompt learning has been adopted in CIL for its ability to adjust data distribution to better align with pre-trained knowledge. This paper critically examines the limitations of existing methods from the perspective of prompt learning, which heavily rely on input information. To address this issue, we propose a novel PTM-based CIL method called Input-Agnostic Prompt Enhancement with Negative Feedback Regulation (PEARL). In PEARL, we implement an input-agnostic global prompt coupled with an adaptive momentum update strategy to reduce the model's dependency on data distribution, thereby effectively mitigating catastrophic forgetting. Guided by negative feedback regulation, this adaptive momentum update addresses the parameter sensitivity inherent in fixed-weight momentum updates. Furthermore, it fosters the continuous enhancement of the prompt for new tasks by harnessing correlations between different tasks in CIL. Experiments on six benchmarks demonstrate that our method achieves state-of-the-art performance. The code is available at: https://github.com/qinyongchun/PEARL.
Authors: Zhenyu Lei, Yushun Dong, Jundong Li, Chen Chen
Abstract: Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.
Authors: Chenxi Yang, Divyanshu Saxena, Rohit Dwivedula, Kshiteej Mahajan, Swarat Chaudhuri, Aditya Akella
Abstract: Learning-based congestion controllers offer better adaptability compared to traditional heuristic algorithms. However, the inherent unreliability of learning techniques can cause learning-based controllers to behave poorly, creating a need for formal guarantees. While methods for formally verifying learned congestion controllers exist, these methods offer binary feedback that cannot optimize the controller toward better behavior. We improve this state-of-the-art via C3, a new learning framework for congestion control that integrates the concept of formal certification in the learning loop. C3 uses an abstract interpreter that can produce robustness and performance certificates to guide the training process, rewarding models that are robust and performant even on worst-case inputs. Our evaluation demonstrates that unlike state-of-the-art learned controllers, C3-trained controllers provide both adaptability and worst-case reliability across a range of network conditions.
Authors: Abhiram Raju, Praneeth Vepakomma
Abstract: Hemodialysis patients who are on donor lists for kidney transplant may get misidentified, delaying their wait time. Thus, predicting their survival time is crucial for optimizing waiting lists and personalizing treatment plans. Predicting survival times for patients often requires large quantities of high quality but sensitive data. This data is siloed and since individual datasets are smaller and less diverse, locally trained survival models do not perform as well as centralized ones. Hence, we propose the use of Federated Learning in the context of predicting survival for hemodialysis patients. Federated Learning or FL can have comparatively better performances than local models while not sharing data between centers. However, despite the increased use of such technologies, the application of FL in survival and even more, dialysis patients remains sparse. This paper studies the performance of FL for data of hemodialysis patients from NephroPlus, the largest private network of dialysis centers in India.
Authors: Binita Maity, Shrutimoy Das, Anirban Dasgupta
Abstract: Individual fairness guarantees are often desirable properties to have, but they become hard to formalize when the dataset contains outliers. Here, we investigate the problem of developing an individually fair $k$-means clustering algorithm for datasets that contain outliers. That is, given $n$ points and $k$ centers, we want that for each point which is not an outlier, there must be a center within the $\frac{n}{k}$ nearest neighbours of the given point. While a few of the recent works have looked into individually fair clustering, this is the first work that explores this problem in the presence of outliers for $k$-means clustering. For this purpose, we define and solve a linear program (LP) that helps us identify the outliers. We exclude these outliers from the dataset and apply a rounding algorithm that computes the $k$ centers, such that the fairness constraint of the remaining points is satisfied. We also provide theoretical guarantees that our method leads to a guaranteed approximation of the fair radius as well as the clustering cost. We also demonstrate our techniques empirically on real-world datasets.
Authors: Yibo Yang, Justus C. Will, Stephan Mandt
Abstract: Diffusion probabilistic models have achieved mainstream success in many generative modeling tasks, from image generation to inverse problem solving. A distinct feature of these models is that they correspond to deep hierarchical latent variable models optimizing a variational evidence lower bound (ELBO) on the data likelihood. Drawing on a basic connection between likelihood modeling and compression, we explore the potential of diffusion models for progressive coding, resulting in a sequence of bits that can be incrementally transmitted and decoded with progressively improving reconstruction quality. Unlike prior work based on Gaussian diffusion or conditional diffusion models, we propose a new form of diffusion model with uniform noise in the forward process, whose negative ELBO corresponds to the end-to-end compression cost using universal quantization. We obtain promising first results on image compression, achieving competitive rate-distortion and rate-realism results on a wide range of bit-rates with a single model, bringing neural codecs a step closer to practical deployment.
Authors: Hong-Wei Wu, Wei-Yao Wang, Kuang-Da Wang, Wen-Chih Peng
Abstract: Tabular data are fundamental in common machine learning applications, ranging from finance to genomics and healthcare. This paper focuses on tabular regression tasks, a field where deep learning (DL) methods are not consistently superior to machine learning (ML) models due to the challenges posed by irregular target functions inherent in tabular data, causing sensitive label changes with minor variations from features. To address these issues, we propose a novel Arithmetic-Aware Pre-training and Adaptive-Regularized Fine-tuning framework (APAR), which enables the model to fit irregular target function in tabular data while reducing the negative impact of overfitting. In the pre-training phase, APAR introduces an arithmetic-aware pretext objective to capture intricate sample-wise relationships from the perspective of continuous labels. In the fine-tuning phase, a consistency-based adaptive regularization technique is proposed to self-learn appropriate data augmentation. Extensive experiments across 10 datasets demonstrated that APAR outperforms existing GBDT-, supervised NN-, and pretrain-finetune NN-based methods in RMSE (+9.43% $\sim$ 20.37%), and empirically validated the effects of pre-training tasks, including the study of arithmetic operations. Our code and data are publicly available at https://github.com/johnnyhwu/APAR.
Authors: M. Giselle Fern\'andez-Godino, Wai Tong Chung, Akshay A. Gowardhan, Matthias Ihme, Qingkai Kong, Donald D. Lucas, Stephen C. Myers
Abstract: High-resolution spatiotemporal simulations effectively capture the complexities of atmospheric plume dispersion in complex terrain. However, their high computational cost makes them impractical for applications requiring rapid responses or iterative processes, such as optimization, uncertainty quantification, or inverse modeling. To address this challenge, this work introduces the Dual-Stage Temporal Three-dimensional UNet Super-resolution (DST3D-UNet-SR) model, a highly efficient deep learning model for plume dispersion prediction. DST3D-UNet-SR is composed of two sequential modules: the temporal module (TM), which predicts the transient evolution of a plume in complex terrain from low-resolution temporal data, and the spatial refinement module (SRM), which subsequently enhances the spatial resolution of the TM predictions. We train DST3DUNet- SR using a comprehensive dataset derived from high-resolution large eddy simulations (LES) of plume transport. We propose the DST3D-UNet-SR model to significantly accelerate LES simulations of three-dimensional plume dispersion by three orders of magnitude. Additionally, the model demonstrates the ability to dynamically adapt to evolving conditions through the incorporation of new observational data, substantially improving prediction accuracy in high-concentration regions near the source. Keywords: Atmospheric sciences, Geosciences, Plume transport,3D temporal sequences, Artificial intelligence, CNN, LSTM, Autoencoder, Autoregressive model, U-Net, Super-resolution, Spatial Refinement.
Authors: Sanjana Gundapaneni, Zhuo Zhi, Miguel Rodrigues
Abstract: The imperative for early detection of type 2 diabetes mellitus (T2DM) is challenged by its asymptomatic onset and dependence on suboptimal clinical diagnostic tests, contributing to its widespread global prevalence. While research into noninvasive T2DM screening tools has advanced, conventional machine learning approaches remain limited to unimodal inputs due to extensive feature engineering requirements. In contrast, deep learning models can leverage multimodal data for a more holistic understanding of patients' health conditions. However, the potential of chest X-ray (CXR) imaging, one of the most commonly performed medical procedures, remains underexplored. This study evaluates the integration of CXR images with other noninvasive data sources, including electronic health records (EHRs) and electrocardiography signals, for T2DM detection. Utilising datasets meticulously compiled from the MIMIC-IV databases, we investigated two deep fusion paradigms: an early fusion-based multimodal transformer and a modular joint fusion ResNet-LSTM architecture. The end-to-end trained ResNet-LSTM model achieved an AUROC of 0.86, surpassing the CXR-only baseline by 2.3% with just 9863 training samples. These findings demonstrate the diagnostic value of CXRs within multimodal frameworks for identifying at-risk individuals early. Additionally, the dataset preprocessing pipeline has also been released to support further research in this domain.
Authors: Mingjing Xu, Peizhong Ju, Jia Liu, Haibo Yang
Abstract: Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives (e.g., multi-task learning, multi-objective reinforcement learning, among many others). Despite the long history of MOO, recent years have witnessed a surge in interest within the ML community in the development of gradient manipulation algorithms for MOO, thanks to the availability of gradient information in many ML problems. However, existing gradient manipulation methods for MOO often suffer from long training times, primarily due to the need for computing dynamic weights by solving an additional optimization problem to determine a common descent direction that can decrease all objectives simultaneously. To address this challenge, we propose a new and efficient algorithm called Periodic Stochastic Multi-Gradient Descent (PSMGD) to accelerate MOO. PSMGD is motivated by the key observation that dynamic weights across objectives exhibit small changes under minor updates over short intervals during the optimization process. Consequently, our PSMGD algorithm is designed to periodically compute these dynamic weights and utilizes them repeatedly, thereby effectively reducing the computational overload. Theoretically, we prove that PSMGD can achieve state-of-the-art convergence rates for strongly-convex, general convex, and non-convex functions. Additionally, we introduce a new computational complexity measure, termed backpropagation complexity, and demonstrate that PSMGD could achieve an objective-independent backpropagation complexity. Through extensive experiments, we verify that PSMGD can provide comparable or superior performance to state-of-the-art MOO algorithms while significantly reducing training time.
Authors: Alex Morehead, Jianlin Cheng
Abstract: Powerful generative models of protein-ligand structure have recently been proposed, but few of these methods support both flexible protein-ligand docking and affinity estimation. Of those that do, none can directly model multiple binding ligands concurrently or have been rigorously benchmarked on pharmacologically relevant drug targets, hindering their widespread adoption in drug discovery efforts. In this work, we propose FlowDock, a deep geometric generative model based on conditional flow matching that learns to directly map unbound (apo) structures to their bound (holo) counterparts for an arbitrary number of binding ligands. Furthermore, FlowDock provides predicted structural confidence scores and binding affinity values with each of its generated protein-ligand complex structures, enabling fast virtual screening of new (multi-ligand) drug targets. For the commonly-used PoseBusters Benchmark dataset, FlowDock achieves a 51% blind docking success rate using unbound (apo) protein input structures and without any information derived from multiple sequence alignments, and for the challenging new DockGen-E dataset, FlowDock matches the performance of single-sequence Chai-1 for binding pocket generalization. Additionally, in the ligand category of the 16th community-wide Critical Assessment of Techniques for Structure Prediction (CASP16), FlowDock ranked among the top-5 methods for pharmacological binding affinity estimation across 140 protein-ligand complexes, demonstrating the efficacy of its learned representations in virtual screening. Source code, data, and pre-trained models are available at https://github.com/BioinfoMachineLearning/FlowDock.
Authors: Changyu Gao, Andrew Lowy, Xingyu Zhou, Stephen J. Wright
Abstract: The sensitivity of machine learning algorithms to outliers, particularly in high-dimensional spaces, necessitates the development of robust methods. Within the framework of $\epsilon$-contamination model, where the adversary can inspect and replace up to $\epsilon$ fraction of the samples, a fundamental open question is determining the optimal rates for robust stochastic convex optimization (robust SCO), provided the samples under $\epsilon$-contamination. We develop novel algorithms that achieve minimax-optimal excess risk (up to logarithmic factors) under the $\epsilon$-contamination model. Our approach advances beyonds existing algorithms, which are not only suboptimal but also constrained by stringent requirements, including Lipschitzness and smoothness conditions on sample functions.Our algorithms achieve optimal rates while removing these restrictive assumptions, and notably, remain effective for nonsmooth but Lipschitz population risks.
Authors: Hanning Zhang, Pengcheng Wang, Shizhe Diao, Yong Lin, Rui Pan, Hanze Dong, Dylan Zhang, Pavlo Molchanov, Tong Zhang
Abstract: Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL) guided by reward models, particularly those focusing on process rewards, which score each intermediate step rather than solely evaluating the final outcome. This approach is more effective at guiding policy models towards correct reasoning trajectories. In this work, we propose an entropy-regularized process reward model (ER-PRM) that integrates KL-regularized Markov Decision Processes (MDP) to balance policy optimization with the need to prevent the policy from shifting too far from its initial distribution. We derive a novel reward construction method based on the theoretical results. Our theoretical analysis shows that we could derive the optimal reward model from the initial policy sampling. Our empirical experiments on the MATH and GSM8K benchmarks demonstrate that ER-PRM consistently outperforms existing process reward models, achieving 1% improvement on GSM8K and 2-3% improvement on MATH under best-of-N evaluation, and more than 1% improvement under RLHF. These results highlight the efficacy of entropy-regularization in enhancing LLMs' reasoning capabilities.
Authors: Zhendong Mi, Renming Zheng, Haowen Zhong, Yue Sun, Shaoyi Huang
Abstract: Recent advances in agentic LLMs have demonstrated remarkable automated Verilog code generation capabilities. However, existing approaches either demand substantial computational resources or rely on LLM-assisted single-agent prompt learning techniques, which we observe for the first time has a degeneration issue - characterized by deteriorating generative performance and diminished error detection and correction capabilities. This paper proposes a novel multi-agent prompt learning framework to address these limitations and enhance code generation quality. We show for the first time that multi-agent architectures can effectively mitigate the degeneration risk while improving code error correction capabilities, resulting in higher-quality Verilog code generation. Experimental results show that the proposed method could achieve 96.4% and 96.5% pass@10 scores on VerilogEval Machine and Human benchmarks, respectively while attaining 100% Syntax and 99.9% Functionality pass@5 metrics on the RTLLM benchmark.
Authors: Pengfei Fang, Yongchun Qin, Hui Xue
Abstract: Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically encountered in FSCIL, knowledge distillation is employed as a way to maintain the knowledge from learned data distribution. Recognizing the limitations of generating discriminative feature representations in a few-shot context, our approach incorporates structural information between samples into knowledge distillation. This structural information serves as a remedy for the low quality of features. Diverging from traditional structured distillation methods that compute sample similarity, we introduce the Displacement Knowledge Distillation (DKD) method. DKD utilizes displacement rather than similarity between samples, incorporating both distance and angular information to significantly enhance the information density retained through knowledge distillation. Observing performance disparities in feature distribution between base and novel classes, we propose the Dual Distillation Network (DDNet). This network applies traditional knowledge distillation to base classes and DKD to novel classes, challenging the conventional integration of novel classes with base classes. Additionally, we implement an instance-aware sample selector during inference to dynamically adjust dual branch weights, thereby leveraging the complementary strengths of each approach. Extensive testing on three benchmarks demonstrates that DDNet achieves state-of-the-art results. Moreover, through rigorous experimentation and comparison, we establish the robustness and general applicability of our proposed DKD method.
Authors: Zeeshan Patel, James DeLoye, Lance Mathias
Abstract: In this paper, we present a comprehensive theoretical comparison of diffusion and flow matching under the Generator Matching framework. Despite their apparent differences, both diffusion and flow matching can be viewed under the unified framework of Generator Matching. By recasting both diffusion and flow matching under the same generative Markov framework, we provide theoretical insights into why flow matching models can be more robust empirically and how novel model classes can be constructed by mixing deterministic and stochastic components. Our analysis offers a fresh perspective on the relationships between state-of-the-art generative modeling paradigms.
Authors: Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen, Xiao Li, Jing Li
Abstract: Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, while memorization, where models inadvertently replicate exact or near-identical training data, has been thoroughly investigated in image and text generation, its effects on tabular data remain largely unexplored. In this paper, we conduct the first comprehensive investigation of memorization phenomena in diffusion models for tabular data. Our empirical analysis reveals that memorization appears in tabular diffusion models and increases with larger training epochs. We further examine the influence of factors such as dataset sizes, feature dimensions, and different diffusion models on memorization. Additionally, we provide a theoretical explanation for why memorization occurs in tabular diffusion models. To address this issue, we propose TabCutMix, a simple yet effective data augmentation technique that exchanges randomly selected feature segments between random same-class training sample pairs. Building upon this, we introduce TabCutMixPlus, an enhanced method that clusters features based on feature correlations and ensures that features within the same cluster are exchanged together during augmentation. This clustering mechanism mitigates out-of-distribution (OOD) generation issues by maintaining feature coherence. Experimental results across various datasets and diffusion models demonstrate that TabCutMix effectively mitigates memorization while maintaining high-quality data generation.
Authors: Jacob F. Pettit, Chak Shing Lee, Jiachen Yang, Alex Ho, Daniel Faissol, Brenden Petersen, Mikel Landajuela
Abstract: We consider the challenge of black-box optimization within hybrid discrete-continuous and variable-length spaces, a problem that arises in various applications, such as decision tree learning and symbolic regression. We propose DisCo-DSO (Discrete-Continuous Deep Symbolic Optimization), a novel approach that uses a generative model to learn a joint distribution over discrete and continuous design variables to sample new hybrid designs. In contrast to standard decoupled approaches, in which the discrete and continuous variables are optimized separately, our joint optimization approach uses fewer objective function evaluations, is robust against non-differentiable objectives, and learns from prior samples to guide the search, leading to significant improvement in performance and sample efficiency. Our experiments on a diverse set of optimization tasks demonstrate that the advantages of DisCo-DSO become increasingly evident as the complexity of the problem increases. In particular, we illustrate DisCo-DSO's superiority over the state-of-the-art methods for interpretable reinforcement learning with decision trees.
Authors: Xin Wang (Jeff), Feiling wang (Jeff), Xuegang Ban (Jeff)
Abstract: This paper proposes a sensitivity analysis framework based on set valued mapping for deep neural networks (DNN) to understand and compute how the solutions (model weights) of DNN respond to perturbations in the training data. As a DNN may not exhibit a unique solution (minima) and the algorithm of solving a DNN may lead to different solutions with minor perturbations to input data, we focus on the sensitivity of the solution set of DNN, instead of studying a single solution. In particular, we are interested in the expansion and contraction of the set in response to data perturbations. If the change of solution set can be bounded by the extent of the data perturbation, the model is said to exhibit the Lipschitz like property. This "set-to-set" analysis approach provides a deeper understanding of the robustness and reliability of DNNs during training. Our framework incorporates both isolated and non-isolated minima, and critically, does not require the assumption that the Hessian of loss function is non-singular. By developing set-level metrics such as distance between sets, convergence of sets, derivatives of set-valued mapping, and stability across the solution set, we prove that the solution set of the Fully Connected Neural Network holds Lipschitz-like properties. For general neural networks (e.g., Resnet), we introduce a graphical-derivative-based method to estimate the new solution set following data perturbation without retraining.
Authors: Binghui Zhang, Sayedeh Leila Noorbakhsh, Yun Dong, Yuan Hong, Binghui Wang
Abstract: Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain task utility as well. Particularly, we propose an information-theoretic framework to achieve the goals through the lens of representation learning, i.e., learning representations that are robust to both adversarial examples and attribute inference adversaries. We also derive novel theoretical results under our framework, e.g., the inherent trade-off between adversarial robustness/utility and attribute privacy, and guaranteed attribute privacy leakage against attribute inference adversaries.
Authors: Yixuan Zhang, Zhidong Li, Yang Wang, Fang Chen, Xuhui Fan, Feng Zhou
Abstract: Machine learning algorithms often struggle to eliminate inherent data biases, particularly those arising from unreliable labels, which poses a significant challenge in ensuring fairness. Existing fairness techniques that address label bias typically involve modifying models and intervening in the training process, but these lack flexibility for large-scale datasets. To address this limitation, we introduce a data selection method designed to efficiently and flexibly mitigate label bias, tailored to more practical needs. Our approach utilizes a zero-shot predictor as a proxy model that simulates training on a clean holdout set. This strategy, supported by peer predictions, ensures the fairness of the proxy model and eliminates the need for an additional holdout set, which is a common requirement in previous methods. Without altering the classifier's architecture, our modality-agnostic method effectively selects appropriate training data and has proven efficient and effective in handling label bias and improving fairness across diverse datasets in experimental evaluations.
Authors: Yujun Li, Hongyuan Zhang, Yuan Yuan
Abstract: Graph contrastive learning (GCL) aims to learn representations from unlabeled graph data in a self-supervised manner and has developed rapidly in recent years. However, edgelevel contrasts are not well explored by most existing GCL methods. Most studies in GCL only regard edges as auxiliary information while updating node features. One of the primary obstacles of edge-based GCL is the heavy computation burden. To tackle this issue, we propose a model that can efficiently learn edge features for GCL, namely AugmentationFree Edge Contrastive Learning (AFECL) to achieve edgeedge contrast. AFECL depends on no augmentation consisting of two parts. Firstly, we design a novel edge feature generation method, where edge features are computed by embedding concatenation of their connected nodes. Secondly, an edge contrastive learning scheme is developed, where edges connecting the same nodes are defined as positive pairs, and other edges are defined as negative pairs. Experimental results show that compared with recent state-of-the-art GCL methods or even some supervised GNNs, AFECL achieves SOTA performance on link prediction and semi-supervised node classification of extremely scarce labels. The source code is available at https://github.com/YujunLi361/AFECL.
Authors: Wengang Guo, Wei Ye
Abstract: Spectral clustering is a popular clustering method. It first maps data into the spectral embedding space and then uses Kmeans to find clusters. However, the two decoupled steps prohibit joint optimization for the optimal solution. In addition, it needs to construct the similarity graph for samples, which suffers from the curse of dimensionality when the data are high-dimensional. To address these two challenges, we introduce \textbf{D}eep \textbf{S}pectral \textbf{C}lustering (\textbf{DSC}), which consists of two main modules: the spectral embedding module and the greedy Kmeans module. The former module learns to efficiently embed raw samples into the spectral embedding space using deep neural networks and power iteration. The latter module improves the cluster structures of Kmeans on the learned spectral embeddings by a greedy optimization strategy, which iteratively reveals the direction of the worst cluster structures and optimizes embeddings in this direction. To jointly optimize spectral embeddings and clustering, we seamlessly integrate the two modules and optimize them in an end-to-end manner. Experimental results on seven real-world datasets demonstrate that DSC achieves state-of-the-art clustering performance.
Authors: Qingwen Tian, Yuxin Xu, Yixuan Yang, Zhen Wang, Ziqi Liu, Pengju Yan, Xiaolin Li
Abstract: Molecular 3D conformations play a key role in determining how molecules interact with other molecules or protein surfaces. Recent deep learning advancements have improved conformation prediction, but slow training speeds and difficulties in utilizing high-degree features limit performance. We propose EquiFlow, an equivariant conditional flow matching model with optimal transport. EquiFlow uniquely applies conditional flow matching in molecular 3D conformation prediction, leveraging simulation-free training to address slow training speeds. It uses a modified Equiformer model to encode Cartesian molecular conformations along with their atomic and bond properties into higher-degree embeddings. Additionally, EquiFlow employs an ODE solver, providing faster inference speeds compared to diffusion models with SDEs. Experiments on the QM9 dataset show that EquiFlow predicts small molecule conformations more accurately than current state-of-the-art models.
Authors: Tiancheng Gao, Graham W. Taylor
Abstract: DNA barcodes are crucial in biodiversity analysis for building automatic identification systems that recognize known species and discover unseen species. Unlike human genome modeling, barcode-based invertebrate identification poses challenges in the vast diversity of species and taxonomic complexity. Among Transformer-based foundation models, BarcodeBERT excelled in species-level identification of invertebrates, highlighting the effectiveness of self-supervised pretraining on barcode-specific datasets. Recently, structured state space models (SSMs) have emerged, with a time complexity that scales sub-quadratically with the context length. SSMs provide an efficient parameterization of sequence modeling relative to attention-based architectures. Given the success of Mamba and Mamba-2 in natural language, we designed BarcodeMamba, a performant and efficient foundation model for DNA barcodes in biodiversity analysis. We conducted a comprehensive ablation study on the impacts of self-supervised training and tokenization methods, and compared both versions of Mamba layers in terms of expressiveness and their capacity to identify "unseen" species held back from training. Our study shows that BarcodeMamba has better performance than BarcodeBERT even when using only 8.3% as many parameters, and improves accuracy to 99.2% on species-level accuracy in linear probing without fine-tuning for "seen" species. In our scaling study, BarcodeMamba with 63.6% of BarcodeBERT's parameters achieved 70.2% genus-level accuracy in 1-nearest neighbor (1-NN) probing for unseen species. The code repository to reproduce our experiments is available at https://github.com/bioscan-ml/BarcodeMamba.
Authors: Zihao Guo, Qingyun Sun, Haonan Yuan, Xingcheng Fu, Min Zhou, Yisen Gao, Jianxin Li
Abstract: Real-world graphs have inherently complex and diverse topological patterns, known as topological heterogeneity. Most existing works learn graph representation in a single constant curvature space that is insufficient to match the complex geometric shapes, resulting in low-quality embeddings with high distortion. This also constitutes a critical challenge for graph foundation models, which are expected to uniformly handle a wide variety of diverse graph data. Recent studies have indicated that product manifold gains the possibility to address topological heterogeneity. However, the product manifold is still homogeneous, which is inadequate and inflexible for representing the mixed heterogeneous topology. In this paper, we propose a novel Graph Mixture of Riemannian Experts (GraphMoRE) framework to effectively tackle topological heterogeneity by personalized fine-grained topology geometry pattern preservation. Specifically, to minimize the embedding distortion, we propose a topology-aware gating mechanism to select the optimal embedding space for each node. By fusing the outputs of diverse Riemannian experts with learned gating weights, we construct personalized mixed curvature spaces for nodes, effectively embedding the graph into a heterogeneous manifold with varying curvatures at different points. Furthermore, to fairly measure pairwise distances between different embedding spaces, we present a concise and effective alignment strategy. Extensive experiments on real-world and synthetic datasets demonstrate that our method achieves superior performance with lower distortion, highlighting its potential for modeling complex graphs with topological heterogeneity, and providing a novel architectural perspective for graph foundation models.
Authors: Nooshin Yousefzadeh, Rahul Sengupta, Sanjay Ranka
Abstract: Effective congestion management along signalized corridors is essential for improving productivity and reducing costs, with arterial travel time serving as a key performance metric. Traditional approaches, such as Coordinated Signal Timing and Adaptive Traffic Control Systems, often lack scalability and generalizability across diverse urban layouts. We propose Fusion-based Dynamic Graph Neural Networks (FDGNN), a structured framework for simultaneous modeling of travel time distributions in both directions along arterial corridors. FDGNN utilizes attentional graph convolution on dynamic, bidirectional graphs and integrates fusion techniques to capture evolving spatiotemporal traffic dynamics. The framework is trained on extensive hours of simulation data and utilizes GPU computation to ensure scalability. The results demonstrate that our framework can efficiently and accurately model travel time as a normal distribution on arterial roads leveraging a unique dynamic graph representation of corridor traffic states. This representation integrates sequential traffic signal timing plans, local driving behaviors, temporal turning movement counts, and ingress traffic volumes, even when aggregated over intervals as short as a single cycle length. The results demonstrate resilience to effective traffic variations, including cycle lengths, green time percentages, traffic density, and counterfactual routes. Results further confirm its stability under varying conditions at different intersections. This framework supports dynamic signal timing, enhances congestion management, and improves travel time reliability in real-world applications.
Authors: Taehun Cha, Donghun Lee
Abstract: In causal inference, randomized experiment is a de facto method to overcome various theoretical issues in observational study. However, the experimental design requires expensive costs, so an efficient experimental design is necessary. We propose ABC3, a Bayesian active learning policy for causal inference. We show a policy minimizing an estimation error on conditional average treatment effect is equivalent to minimizing an integrated posterior variance, similar to Cohn criteria \citep{cohn1994active}. We theoretically prove ABC3 also minimizes an imbalance between the treatment and control groups and the type 1 error probability. Imbalance-minimizing characteristic is especially notable as several works have emphasized the importance of achieving balance. Through extensive experiments on real-world data sets, ABC3 achieves the highest efficiency, while empirically showing the theoretical results hold.
Authors: Gazi Nazia Nur, Mohammad Ahnaf Sadat
Abstract: In this paper, we investigate the impact of adversarial attacks on the explainability of deep learning models, which are commonly criticized for their black-box nature despite their capacity for autonomous feature extraction. This black-box nature can affect the perceived trustworthiness of these models. To address this, explainability techniques such as GradCAM, SmoothGrad, and LIME have been developed to clarify model decision-making processes. Our research focuses on the robustness of these explanations when models are subjected to adversarial attacks, specifically those involving subtle image perturbations that are imperceptible to humans but can significantly mislead models. For this, we utilize attack methods like the Fast Gradient Sign Method (FGSM) and the Basic Iterative Method (BIM) and observe their effects on model accuracy and explanations. The results reveal a substantial decline in model accuracy, with accuracies dropping from 89.94% to 58.73% and 45.50% under FGSM and BIM attacks, respectively. Despite these declines in accuracy, the explanation of the models measured by metrics such as Intersection over Union (IoU) and Root Mean Square Error (RMSE) shows negligible changes, suggesting that these metrics may not be sensitive enough to detect the presence of adversarial perturbations.
Authors: Yun Qu, Yuhang Jiang, Boyuan Wang, Yixiu Mao, Cheems Wang, Chang Liu, Xiangyang Ji
Abstract: Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face challenges, including training difficulties due to redundancy and ambiguous attributions stemming from overlooking the multifaceted nature of mission performance evaluation. Hopefully, Large Language Model (LLM) encompasses fruitful decision-making knowledge and provides a plausible tool for reward redistribution. Even so, deploying LLM in this case is non-trivial due to the misalignment between linguistic knowledge and the symbolic form requirement, together with inherent randomness and hallucinations in inference. To tackle these issues, we introduce LaRe, a novel LLM-empowered symbolic-based decision-making framework, to improve credit assignment. Key to LaRe is the concept of the Latent Reward, which works as a multi-dimensional performance evaluation, enabling more interpretable goal attainment from various perspectives and facilitating more effective reward redistribution. We examine that semantically generated code from LLM can bridge linguistic knowledge and symbolic latent rewards, as it is executable for symbolic objects. Meanwhile, we design latent reward self-verification to increase the stability and reliability of LLM inference. Theoretically, reward-irrelevant redundancy elimination in the latent reward benefits RL performance from more accurate reward estimation. Extensive experimental results witness that LaRe (i) achieves superior temporal credit assignment to SOTA methods, (ii) excels in allocating contributions among multiple agents, and (iii) outperforms policies trained with ground truth rewards for certain tasks.
Authors: Bingchen Wang, Zhaoxuan Wu, Fusheng Liu, Bryan Kian Hsiang Low
Abstract: Collaborative machine learning (CML) provides a promising paradigm for democratizing advanced technologies by enabling cost-sharing among participants. However, the potential for rent-seeking behaviors among parties can undermine such collaborations. Contract theory presents a viable solution by rewarding participants with models of varying accuracy based on their contributions. However, unlike monetary compensation, using models as rewards introduces unique challenges, particularly due to the stochastic nature of these rewards when contribution costs are privately held information. This paper formalizes the optimal contracting problem within CML and proposes a transformation that simplifies the non-convex optimization problem into one that can be solved through convex optimization algorithms. We conduct a detailed analysis of the properties that an optimal contract must satisfy when models serve as the rewards, and we explore the potential benefits and welfare implications of these contract-driven CML schemes through numerical experiments.
Authors: Juntao Dai, Yaodong Yang, Qian Zheng, Gang Pan
Abstract: A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation (ABE) method relies on the infinite-horizon discounted advantage function. This dependence leads to catastrophic errors in finite-horizon scenarios with non-discounted constraints, resulting in safety-violation updates. In response, we propose the first estimation method for finite-horizon non-discounted constraints in deep Safe RL, termed Gradient-based Estimation (GBE), which relies on the analytic gradient derived along trajectories. Our theoretical and empirical analyses demonstrate that GBE can effectively estimate constraint changes over a finite horizon. Constructing a surrogate optimization problem with GBE, we developed a novel Safe RL algorithm called Constrained Gradient-based Policy Optimization (CGPO). CGPO identifies feasible optimal policies by iteratively resolving sub-problems within trust regions. Our empirical results reveal that CGPO, unlike baseline algorithms, successfully estimates the constraint functions of subsequent policies, thereby ensuring the efficiency and feasibility of each update.
Authors: Da Li, Junping Yin, Jin Xu, Xinxin Li, Juan Zhang
Abstract: Symbolic regression automatically searches for mathematical equations to reveal underlying mechanisms within datasets, offering enhanced interpretability compared to black box models. Traditionally, symbolic regression has been considered to be purely numeric-driven, with insufficient attention given to the potential contributions of visual information in augmenting this process. When dealing with high-dimensional and complex datasets, existing symbolic regression models are often inefficient and tend to generate overly complex equations, making subsequent mechanism analysis complicated. In this paper, we propose the vision-guided multimodal symbolic regression model, called ViSymRe, that systematically explores how visual information can improve various metrics of symbolic regression. Compared to traditional models, our proposed model has the following innovations: (1) It integrates three modalities: vision, symbol and numeric to enhance symbolic regression, enabling the model to benefit from the strengths of each modality; (2) It establishes a meta-learning framework that can learn from historical experiences to efficiently solve new symbolic regression problems; (3) It emphasizes the simplicity and structural rationality of the equations rather than merely numerical fitting. Extensive experiments show that our proposed model exhibits strong generalization capability and noise resistance. The equations it generates outperform state-of-the-art numeric-only baselines in terms of fitting effect, simplicity and structural accuracy, thus being able to facilitate accurate mechanism analysis and the development of theoretical models.
Authors: Joar Skalse, Alessandro Abate
Abstract: The aim of inverse reinforcement learning (IRL) is to infer an agent's preferences from observing their behaviour. Usually, preferences are modelled as a reward function, $R$, and behaviour is modelled as a policy, $\pi$. One of the central difficulties in IRL is that multiple preferences may lead to the same observed behaviour. That is, $R$ is typically underdetermined by $\pi$, which means that $R$ is only partially identifiable. Recent work has characterised the extent of this partial identifiability for different types of agents, including optimal and Boltzmann-rational agents. However, work so far has only considered agents that discount future reward exponentially: this is a serious limitation, especially given that extensive work in the behavioural sciences suggests that humans are better modelled as discounting hyperbolically. In this work, we newly characterise partial identifiability in IRL for agents with non-exponential discounting: our results are in particular relevant for hyperbolical discounting, but they also more generally apply to agents that use other types of (non-exponential) discounting. We significantly show that generally IRL is unable to infer enough information about $R$ to identify the correct optimal policy, which entails that IRL alone can be insufficient to adequately characterise the preferences of such agents.
Authors: Pengqian Lu, Jie Lu, Anjin Liu, Guangquan Zhang
Abstract: Concept drift, characterized by unpredictable changes in data distribution over time, poses significant challenges to machine learning models in streaming data scenarios. Although error rate-based concept drift detectors are widely used, they often fail to identify drift in the early stages when the data distribution changes but error rates remain constant. This paper introduces the Prediction Uncertainty Index (PU-index), derived from the prediction uncertainty of the classifier, as a superior alternative to the error rate for drift detection. Our theoretical analysis demonstrates that: (1) The PU-index can detect drift even when error rates remain stable. (2) Any change in the error rate will lead to a corresponding change in the PU-index. These properties make the PU-index a more sensitive and robust indicator for drift detection compared to existing methods. We also propose a PU-index-based Drift Detector (PUDD) that employs a novel Adaptive PU-index Bucketing algorithm for detecting drift. Empirical evaluations on both synthetic and real-world datasets demonstrate PUDD's efficacy in detecting drift in structured and image data.
Authors: Lien P. Le, Xuan-Hien Nguyen Thi, Thu Nguyen, Michael A. Riegler, P{\aa}l Halvorsen, Binh T. Nguyen
Abstract: Healthcare time series data is vital for monitoring patient activity but often contains noise and missing values due to various reasons such as sensor errors or data interruptions. Imputation, i.e., filling in the missing values, is a common way to deal with this issue. In this study, we compare imputation methods, including Multiple Imputation with Random Forest (MICE-RF) and advanced deep learning approaches (SAITS, BRITS, Transformer) for noisy, missing time series data in terms of MAE, F1-score, AUC, and MCC, across missing data rates (10 % - 80 %). Our results show that MICE-RF can effectively impute missing data compared to deep learning methods and the improvement in classification of data imputed indicates that imputation can have denoising effects. Therefore, using an imputation algorithm on time series with missing data can, at the same time, offer denoising effects.
Authors: Jin Li, Zitong Yu, Ziqiang He, Z. Jane Wang, Xiangui Kang
Abstract: Imperceptible adversarial attacks have recently attracted increasing research interests. Existing methods typically incorporate external modules or loss terms other than a simple $l_p$-norm into the attack process to achieve imperceptibility, while we argue that such additional designs may not be necessary. In this paper, we rethink the essence of imperceptible attacks and propose two simple yet effective strategies to unleash the potential of PGD, the common and classical attack, for imperceptibility from an optimization perspective. Specifically, the Dynamic Step Size is introduced to find the optimal solution with minimal attack cost towards the decision boundary of the attacked model, and the Adaptive Early Stop strategy is adopted to reduce the redundant strength of adversarial perturbations to the minimum level. The proposed PGD-Imperceptible (PGD-Imp) attack achieves state-of-the-art results in imperceptible adversarial attacks for both untargeted and targeted scenarios. When performing untargeted attacks against ResNet-50, PGD-Imp attains 100$\%$ (+0.3$\%$) ASR, 0.89 (-1.76) $l_2$ distance, and 52.93 (+9.2) PSNR with 57s (-371s) running time, significantly outperforming existing methods.
Authors: Songgaojun Deng, Maarten de Rijke
Abstract: Time series forecasting is vital in many real-world applications, yet developing models that generalize well on unseen relevant domains -- such as forecasting web traffic data on new platforms/websites or estimating e-commerce demand in new regions -- remains underexplored. Existing forecasting models often struggle with domain shifts in time series data, as the temporal patterns involve complex components like trends, seasonality, etc. While some prior work addresses this by matching feature distributions across domains or disentangling domain-shared features using label information, they fail to reveal insights into the latent temporal dependencies, which are critical for identifying common patterns across domains and achieving generalization. We propose a framework for domain generalization in time series forecasting by mining the latent factors that govern temporal dependencies across domains. Our approach uses a decomposition-based architecture with a new Conditional $\beta$-Variational Autoencoder (VAE), wherein time series data is first decomposed into trend-cyclical and seasonal components, each modeled independently through separate $\beta$-VAE modules. The $\beta$-VAE aims to capture disentangled latent factors that control temporal dependencies across domains. We enhance the learning of domain-specific information with a decoder-conditional design and introduce domain regularization to improve the separation of domain-shared and domain-specific latent factors. Our proposed method is flexible and can be applied to various time series forecasting models, enabling effective domain generalization with simplicity and efficiency. We validate its effectiveness on five real-world time series datasets, covering web traffic, e-commerce, finance and power consumption, demonstrating improved generalization performance over state-of-the-art methods.
Authors: Bat-Sheva Einbinder, Liran Ringel, Yaniv Romano
Abstract: The risk-controlling prediction sets (RCPS) framework is a general tool for transforming the output of any machine learning model to design a predictive rule with rigorous error rate control. The key idea behind this framework is to use labeled hold-out calibration data to tune a hyper-parameter that affects the error rate of the resulting prediction rule. However, the limitation of such a calibration scheme is that with limited hold-out data, the tuned hyper-parameter becomes noisy and leads to a prediction rule with an error rate that is often unnecessarily conservative. To overcome this sample-size barrier, we introduce a semi-supervised calibration procedure that leverages unlabeled data to rigorously tune the hyper-parameter without compromising statistical validity. Our procedure builds upon the prediction-powered inference framework, carefully tailoring it to risk-controlling tasks. We demonstrate the benefits and validity of our proposal through two real-data experiments: few-shot image classification and early time series classification.
Authors: Ziang Zhou, Zhihao Ding, Jieming Shi, Qing Li, Shiqi Shen
Abstract: Graph Neural Networks (GNNs) are fundamental to graph-based learning and excel in node classification tasks. However, GNNs suffer from scalability issues due to the need for multi-hop data during inference, limiting their use in latency-sensitive applications. Recent studies attempt to distill GNNs into multi-layer perceptrons (MLPs) for faster inference. They typically treat GNN and MLP models as single units for distillation, insufficiently utilizing the fine-grained knowledge within GNN layers. In this paper, we propose TINED, a novel method that distills GNNs to MLPs layer-wise through Teacher Injection with fine-tuning and Dirichlet Energy Distillation techniques. We analyze key operations in GNN layers, feature transformation (FT) and graph propagation (GP), and identify that an FT performs the same computation as a fully-connected (FC) layer in MLPs. Thus, we propose directly injecting valuable teacher parameters of an FT in a GNN into an FC layer of the student MLP, assisted by fine-tuning. In TINED, FC layers in an MLP mirror the order of the corresponding FTs and GPs in GNN. We provide a theoretical bound on the approximation of GPs. Moreover, we observe that in a GNN layer, FT and GP operations often have opposing smoothing effects: GP is aggressive, while FT is conservative, in smoothing. Using Dirichlet energy, we design a DE ratio to quantify these smoothing effects and propose Dirichlet Energy Distillation to distill these characteristics from GNN layers to MLP layers. Extensive experiments demonstrate that TINED achieves superior performance over GNNs and state-of-the-art distillation methods under various settings across seven datasets. The code is in supplementary material.
Authors: Elad Shohama, Hadar Cohena, Khalil Wattada, Havana Rikab, Dan Vilenchik
Abstract: Explainable AI (XAI) methods typically focus on identifying essential input features or more abstract concepts for tasks like image or text classification. However, for algorithmic tasks like combinatorial optimization, these concepts may depend not only on the input but also on the current state of the network, like in the graph neural networks (GNN) case. This work studies concept learning for an existing GNN model trained to solve Boolean satisfiability (SAT). \textcolor{black}{Our analysis reveals that the model learns key concepts matching those guiding human-designed SAT heuristics, particularly the notion of 'support.' We demonstrate that these concepts are encoded in the top principal components (PCs) of the embedding's covariance matrix, allowing for unsupervised discovery. Using sparse PCA, we establish the minimality of these concepts and show their teachability through a simplified GNN. Two direct applications of our framework are (a) We improve the convergence time of the classical WalkSAT algorithm and (b) We use the discovered concepts to "reverse-engineer" the black-box GNN and rewrite it as a white-box textbook algorithm. Our results highlight the potential of concept learning in understanding and enhancing algorithmic neural networks for combinatorial optimization tasks.
Authors: Pedro Miguel S\'anchez S\'anchez, Enrique Tom\'as Mart\'inez Beltr\'an, Miguel Fern\'andez Llamas, G\'er\^ome Bovet, Gregorio Mart\'inez P\'erez, Alberto Huertas Celdr\'an
Abstract: Decentralized Federated Learning (DFL) trains models in a collaborative and privacy-preserving manner while removing model centralization risks and improving communication bottlenecks. However, DFL faces challenges in efficient communication management and model aggregation within decentralized environments, especially with heterogeneous data distributions. Thus, this paper introduces ProFe, a novel communication optimization algorithm for DFL that combines knowledge distillation, prototype learning, and quantization techniques. ProFe utilizes knowledge from large local models to train smaller ones for aggregation, incorporates prototypes to better learn unseen classes, and applies quantization to reduce data transmitted during communication rounds. The performance of ProFe has been validated and compared to the literature by using benchmark datasets like MNIST, CIFAR10, and CIFAR100. Results showed that the proposed algorithm reduces communication costs by up to ~40-50% while maintaining or improving model performance. In addition, it adds ~20% training time due to increased complexity, generating a trade-off.
Authors: Cyrus Neary, Nathan Tsao, Ufuk Topcu
Abstract: We develop compositional learning algorithms for coupled dynamical systems. While deep learning has proven effective at modeling complex relationships from data, compositional couplings between system components typically introduce algebraic constraints on state variables, posing challenges to many existing data-driven approaches to modeling dynamical systems. Towards developing deep learning models for constrained dynamical systems, we introduce neural port-Hamiltonian differential algebraic equations (N-PHDAEs), which use neural networks to parametrize unknown terms in both the differential and algebraic components of a port-Hamiltonian DAE. To train these models, we propose an algorithm that uses automatic differentiation to perform index reduction, automatically transforming the neural DAE into an equivalent system of neural ordinary differential equations (N-ODEs), for which established model inference and backpropagation methods exist. The proposed compositional modeling framework and learning algorithms may be applied broadly to learn control-oriented models of dynamical systems in a variety of application areas, however, in this work, we focus on their application to the modeling of electrical networks. Experiments simulating the dynamics of nonlinear circuits exemplify the benefits of our approach: the proposed N-PHDAE model achieves an order of magnitude improvement in prediction accuracy and constraint satisfaction when compared to a baseline N-ODE over long prediction time horizons. We also validate the compositional capabilities of our approach through experiments on a simulated D.C. microgrid: we train individual N-PHDAE models for separate grid components, before coupling them to accurately predict the behavior of larger-scale networks.
Authors: G\"ozde \"Ozcan, Chengzhi Shi, Stratis Ioannidis
Abstract: Ou et al. (2022) introduce the problem of learning set functions from data generated by a so-called optimal subset oracle. Their approach approximates the underlying utility function with an energy-based model, whose parameters are estimated via mean-field variational inference. Ou et al. (2022) show this reduces to fixed point iterations; however, as the number of iterations increases, automatic differentiation quickly becomes computationally prohibitive due to the size of the Jacobians that are stacked during backpropagation. We address this challenge with implicit differentiation and examine the convergence conditions for the fixed-point iterations. We empirically demonstrate the efficiency of our method on synthetic and real-world subset selection applications including product recommendation, set anomaly detection and compound selection tasks.
Authors: Lanxiang Hu, Tajana Rosing, Hao Zhang
Abstract: Specializing large language models (LLMs) for local deployment in domain-specific use cases is necessary for strong performance while meeting latency and privacy constraints. However, conventional task-specific adaptation approaches do not show simultaneous memory saving and inference speedup at deployment time. Practical compression techniques like quantization and pruning require dedicated hardware or kernel support to achieve measured inference speedup. We develop TrimLLM based on the layer-wise specialization phenomenon we empirically observed and verified on contemporary LLMs. TrimLLM reduces the depth of LLMs via progressive layer dropping. We show it retains LLMs' capacity in specific domains and achieves inference speedup irrespective of hardware and deep learning frameworks. We evaluated TrimLLM on LLMs of various sizes for inference; models adapted on medical, legal, and financial datasets all demonstrate $2.1-5.7\times$ inference speedup on consumer GPUs and up to $3.1\times$ speedup on A100 when compared to state-of-the-art model compression algorithms, with no loss in accuracy at 50$\sim$60\% model compression ratio.
Authors: Marzieh Mirzaeibonehkhater, Mohammad Ali Labbaf-Khaniki, Mohammad Manthouri
Abstract: Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often struggle to capture the complex temporal patterns in bearing vibration data, leading to suboptimal performance. To address this limitation, we propose a novel attention mechanism, Temporal Decomposition Attention (TDA), which combines temporal bias encoding with seasonal-trend decomposition to capture both long-term dependencies and periodic fluctuations in time series data. Additionally, we incorporate the Hull Exponential Moving Average (HEMA) for feature extraction, enabling the model to effectively capture meaningful characteristics from the data while reducing noise. Our approach integrates TDA into the Transformer architecture, allowing the model to focus separately on the trend and seasonal components of the data. Experimental results on the Case Western Reserve University (CWRU) bearing fault detection dataset demonstrate that our approach outperforms traditional attention mechanisms and achieves state-of-the-art performance in terms of accuracy and interpretability. The HEMA-Transformer-TDA model achieves an accuracy of 98.1%, with exceptional precision, recall, and F1-scores, demonstrating its effectiveness in bearing fault detection and its potential for application in other time series tasks with seasonal patterns or trends.
Authors: Xixian Wang, Zhongjian Wang
Abstract: We present an estimate of the Wasserstein distance between the data distribution and the generation of score-based generative models, assuming an $\epsilon$-accurate approximation of the score and a Gaussian-type tail behavior of the data distribution. The complexity bound in dimension is $O(\sqrt{d})$, with a logarithmic constant. Such Gaussian tail assumption applies to the distribution of a compact support target with early stopping technique and the Bayesian posterior with a bounded observation operator. Corresponding convergence and complexity bounds are derived. The crux of the analysis lies in the Lipchitz bound of the score, which is related to the Hessian estimate of a viscous Hamilton-Jacobi equation (vHJ). This latter is demonstrated by employing a dimension independent kernel estimate. Consequently, our complexity bound scales linearly (up to a logarithmic constant) with the square root of the trace of the covariance operator, which relates to the invariant distribution of forward process. Our analysis also extends to the probabilistic flow ODE, as the sampling process.
Authors: Guan Wang, Haoyi Niu, Jianxiong Li, Li Jiang, Jianming Hu, Xianyuan Zhan
Abstract: Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing the notoriously difficult credit assignment challenge of value learning in conventional RL paradigm. Sequential modeling, however, requires capturing accurate dynamics across long horizons in trajectory data to ensure reasonable policy performance. To meet this requirement, leveraging large, expressive models has become a popular choice in recent literature, which, however, comes at the cost of significantly increased computation and inference latency. Contradictory yet promising, we reveal that lightweight models as simple as shallow 2-layer MLPs, can also enjoy accurate dynamics consistency and significantly reduced sequential modeling errors against large expressive models by adopting a simple recursive planning scheme: recursively planning coarse-grained future sub-goals based on current and target information, and then executes the action with a goal-conditioned policy learned from data rela-beled with these sub-goal ground truths. We term our method Recursive Skip-Step Planning (RSP). Simple yet effective, RSP enjoys great efficiency improvements thanks to its lightweight structure, and substantially outperforms existing methods, reaching new SOTA performances on the D4RL benchmark, especially in multi-stage long-horizon tasks.
Authors: Salar Abbaspourazad, Anshuman Mishra, Joseph Futoma, Andrew C. Miller, Ian Shapiro
Abstract: Modern wearable devices can conveniently and continuously record various biosignals in the many different environments of daily living, ultimately enabling a rich view of individual health. However, not all biosignals are the same: high-fidelity measurements, such as photoplethysmography (PPG), contain more physiological information, but require optical sensors with a high power footprint. In a resource-constrained setting, such biosignals may be unavailable. Alternatively, a lower-fidelity biosignal, such as accelerometry that captures minute cardiovascular information during low-motion periods, has a significantly smaller power footprint and is available in almost any wearable device. Here, we demonstrate that we can distill representational knowledge across biosignals, i.e., from PPG to accelerometry, using 20 million minutes of unlabeled data, collected from ~172K participants in the Apple Heart and Movement Study under informed consent. We first pre-train PPG encoders via self-supervised learning, and then distill their representational knowledge to accelerometry encoders. We demonstrate strong cross-modal alignment on unseen data, e.g., 99.2% top-1 accuracy for retrieving PPG embeddings from accelerometry embeddings. We show that distilled accelerometry encoders have significantly more informative representations compared to self-supervised or supervised encoders trained directly on accelerometry data, observed by at least 23%-49% improved performance for predicting heart rate and heart rate variability. We also show that distilled accelerometry encoders are readily predictive of a wide array of downstream health targets, i.e., they are generalist foundation models. We believe accelerometry foundation models for health may unlock new opportunities for developing digital biomarkers from any wearable device, and help individuals track their health more frequently and conveniently.
Authors: Amime Mohamed Aboussalah, Yassine Abbahaddou
Abstract: Generative models like Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) often fail to capture the full diversity of their training data, leading to mode collapse. While this issue is well-explored in image generation, it remains underinvestigated for time series data. We introduce a new definition of mode collapse specific to time series and propose a novel metric, DMD-GEN, to quantify its severity. Our metric utilizes Dynamic Mode Decomposition (DMD), a data-driven technique for identifying coherent spatiotemporal patterns, and employs Optimal Transport between DMD eigenvectors to assess discrepancies between the underlying dynamics of the original and generated data. This approach not only quantifies the preservation of essential dynamic characteristics but also provides interpretability by pinpointing which modes have collapsed. We validate DMD-GEN on both synthetic and real-world datasets using various generative models, including TimeGAN, TimeVAE, and DiffusionTS. The results demonstrate that DMD-GEN correlates well with traditional evaluation metrics for static data while offering the advantage of applicability to dynamic data. This work offers for the first time a definition of mode collapse for time series, improving understanding, and forming the basis of our tool for assessing and improving generative models in the time series domain.
Authors: Ashish Parmanand Pandey, Alan John Varghese, Sarang Patil, Mengjia Xu
Abstract: Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in temporal graph data, they face scalability challenges due to quadratic computational complexity. This study presents a comparative analysis of dynamic graph embedding approaches using transformers and the recently proposed Mamba architecture, a state-space model with linear complexity. We introduce three novel models: TransformerG2G augment with graph convolutional networks, DG-Mamba, and GDG-Mamba with graph isomorphism network edge convolutions. Our experiments on multiple benchmark datasets demonstrate that Mamba-based models achieve comparable or superior performance to transformer-based approaches in link prediction tasks while offering significant computational efficiency gains on longer sequences. Notably, DG-Mamba variants consistently outperform transformer-based models on datasets with high temporal variability, such as UCI, Bitcoin, and Reality Mining, while maintaining competitive performance on more stable graphs like SBM. We provide insights into the learned temporal dependencies through analysis of attention weights and state matrices, revealing the models' ability to capture complex temporal patterns. By effectively combining state-space models with graph neural networks, our work addresses key limitations of previous approaches and contributes to the growing body of research on efficient temporal graph representation learning. These findings offer promising directions for scaling dynamic graph embedding to larger, more complex real-world networks, potentially enabling new applications in areas such as social network analysis, financial modeling, and biological system dynamics.
Authors: Andr\'as Balogh, M\'ark Jelasity
Abstract: Measuring the similarity of the internal representations of deep neural networks is an important and challenging problem. Model stitching has been proposed as a possible approach, where two half-networks are connected by mapping the output of the first half-network to the input of the second one. The representations are considered functionally similar if the resulting stitched network achieves good task-specific performance. The mapping is normally created by training an affine stitching layer on the task at hand while freezing the two half-networks, a method called task loss matching. Here, we argue that task loss matching may be very misleading as a similarity index. For example, it can indicate very high similarity between very distant layers, whose representations are known to have different functional properties. Moreover, it can indicate very distant layers to be more similar than architecturally corresponding layers. Even more surprisingly, when comparing layers within the same network, task loss matching often indicates that some layers are more similar to a layer than itself. We argue that the main reason behind these problems is that task loss matching tends to create out-of-distribution representations to improve task-specific performance. We demonstrate that direct matching (when the mapping minimizes the distance between the stitched representations) does not suffer from these problems. We compare task loss matching, direct matching, and well-known similarity indices such as CCA and CKA. We conclude that direct matching strikes a good balance between the structural and functional requirements for a good similarity index.
Authors: Hong Zhang, Ying Liu, Romit Maulik
Abstract: Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present a semi-implicit neural ODE approach that exploits the partitionable structure of the underlying dynamics. Our technique leads to an implicit neural network with significant computational advantages over existing approaches because of enhanced stability and efficient linear solves during time integration. We show that our approach outperforms existing approaches on a variety of applications including graph classification and learning complex dynamical systems. We also demonstrate that our approach can train challenging neural ODEs where both explicit methods and fully implicit methods are intractable.
Authors: Xiang Li, Qiaomin Xie
Abstract: The convergence behavior of Stochastic Gradient Descent (SGD) crucially depends on the stepsize configuration. When using a constant stepsize, the SGD iterates form a Markov chain, enjoying fast convergence during the initial transient phase. However, when reaching stationarity, the iterates oscillate around the optimum without making further progress. In this paper, we study the convergence diagnostics for SGD with constant stepsize, aiming to develop an effective dynamic stepsize scheme. We propose a novel coupling-based convergence diagnostic procedure, which monitors the distance of two coupled SGD iterates for stationarity detection. Our diagnostic statistic is simple and is shown to track the transition from transience stationarity theoretically. We conduct extensive numerical experiments and compare our method against various existing approaches. Our proposed coupling-based stepsize scheme is observed to achieve superior performance across a diverse set of convex and non-convex problems. Moreover, our results demonstrate the robustness of our approach to a wide range of hyperparameters.
Authors: Weibin Chen, Azhir Mahmood, Michel Tsamados, So Takao
Abstract: The rapid growth of earth observation systems calls for a scalable approach to interpolate remote-sensing observations. These methods in principle, should acquire more information about the observed field as data grows. Gaussian processes (GPs) are candidate model choices for interpolation. However, due to their poor scalability, they usually rely on inducing points for inference, which restricts their expressivity. Moreover, commonly imposed assumptions such as stationarity prevents them from capturing complex patterns in the data. While deep GPs can overcome this issue, training and making inference with them are difficult, again requiring crude approximations via inducing points. In this work, we instead approach the problem through Bayesian deep learning, where spatiotemporal fields are represented by deep neural networks, whose layers share the inductive bias of stationary GPs on the plane/sphere via random feature expansions. This allows one to (1) capture high frequency patterns in the data, and (2) use mini-batched gradient descent for large scale training. We experiment on various remote sensing data at local/global scales, showing that our approach produce competitive or superior results to existing methods, with well-calibrated uncertainties.
Authors: Xiannan Huang, Yixin Chen, Quan Yuan, Chao Yang
Abstract: Predicting future bus trip chains for an existing user is of great significance for operators of public transit systems. Existing methods always treat this task as a time-series prediction problem, but the 1-dimensional time series structure cannot express the complex relationship between trips. To better capture the inherent patterns in bus travel behavior, this paper proposes a novel approach that synthesizes future bus trip chains based on those from similar days. Key similarity patterns are defined and tested using real-world data, and a similarity function is then developed to capture these patterns. Afterwards, a graph is constructed where each day is represented as a node and edge weight reflects the similarity between days. Besides, the trips on a given day can be regarded as labels for each node, transferring the bus trip chain prediction problem to a semi-supervised classification problem on a graph. To address this, we propose several methods and validate them on a real-world dataset of 10000 bus users, achieving state-of-the-art prediction results. Analyzing the parameters of similarity function reveals some interesting bus usage patterns, allowing us can to cluster bus users into three types: repeat-dominated, evolve-dominate and repeat-evolve balanced. In summary, our work demonstrates the effectiveness of similarity-based prediction for bus trip chains and provides a new perspective for analyzing individual bus travel patterns. The code for our prediction model is publicly available.
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: Xiaochong Dong, Xuemin Zhang, Ming Yang, Shengwei Mei
Abstract: Leveraging spatio-temporal correlations among wind farms can significantly enhance the accuracy of ultra-short-term wind power forecasting. However, the complex and dynamic nature of these correlations presents significant modeling challenges. To address this, we propose a spatio-temporal dynamic hypergraph learning (STDHL) model. This model uses a hypergraph structure to represent spatial features among wind farms. Unlike traditional graph structures, which only capture pair-wise node features, hypergraphs create hyperedges connecting multiple nodes, enabling the representation and transmission of higher-order spatial features. The STDHL model incorporates a novel dynamic hypergraph convolutional layer to model dynamic spatial correlations and a grouped temporal convolutional layer for channel-independent temporal modeling. The model uses spatio-temporal encoders to extract features from multi-source covariates, which are mapped to quantile results through a forecast decoder. Experimental results using the GEFCom dataset show that the STDHL model outperforms existing state-of-the-art methods. Furthermore, an in-depth analysis highlights the critical role of spatio-temporal covariates in improving ultra-short-term forecasting accuracy.
Authors: Xiaochong Dong, Jun Dan, Yingyun Sun, Yang Liu, Xuemin Zhang, Shengwei Mei
Abstract: Driven by global climate change and the ongoing energy transition, the coupling between power supply capabilities and meteorological factors has become increasingly significant. Over the long term, accurately quantifying the power generation capacity of renewable energy under the influence of climate change is essential for the development of sustainable power systems. However, due to interdisciplinary differences in data requirements, climate data often lacks the necessary hourly resolution to capture the short-term variability and uncertainties of renewable energy resources. To address this limitation, a super-resolution recurrent diffusion model (SRDM) has been developed to enhance the temporal resolution of climate data and model the short-term uncertainty. The SRDM incorporates a pre-trained decoder and a denoising network, that generates long-term, high-resolution climate data through a recurrent coupling mechanism. The high-resolution climate data is then converted into power value using the mechanism model, enabling the simulation of wind and photovoltaic (PV) power generation capacity on future long-term scales. Case studies were conducted in the Ejina region of Inner Mongolia, China, using fifth-generation reanalysis (ERA5) and coupled model intercomparison project (CMIP6) data under two climate pathways: SSP126 and SSP585. The results demonstrate that the SRDM outperforms existing generative models in generating super-resolution climate data. For the Ejina region, under a high-emission pathway, the annual utilization hours of wind power are projected to decrease by 2.82 hours/year, while those for PV power are projected to decrease by 0.26 hours/year. Furthermore, the research highlights the estimation biases introduced when low-resolution climate data is used for power conversion.
Authors: Naoki Sato, Koshiro Izumi, Hideaki Iiduka
Abstract: A scaled conjugate gradient method that accelerates existing adaptive methods utilizing stochastic gradients is proposed for solving nonconvex optimization problems with deep neural networks. It is shown theoretically that, whether with constant or diminishing learning rates, the proposed method can obtain a stationary point of the problem. Additionally, its rate of convergence with diminishing learning rates is verified to be superior to that of the conjugate gradient method. The proposed method is shown to minimize training loss functions faster than the existing adaptive methods in practical applications of image and text classification. Furthermore, in the training of generative adversarial networks, one version of the proposed method achieved the lowest Frechet inception distance score among those of the adaptive methods.
Authors: Wentao Yu, Shuo Chen, Yongxin Tong, Tianlong Gu, Chen Gong
Abstract: Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets.
Authors: Robert B. Parker, Oscar Dowson, Nicole LoGiudice, Manuel Garcia, Russell Bent
Abstract: We compare full-space, reduced-space, and gray-box formulations for representing trained neural networks in nonlinear constrained optimization problems. We test these formulations on a transient stability-constrained, security-constrained alternating current optimal power flow (SCOPF) problem where the transient stability criteria are represented by a trained neural network surrogate. Optimization problems are implemented in JuMP and trained neural networks are embedded using a new Julia package: MathOptAI.jl. To study the bottlenecks of the three formulations, we use neural networks with up to 590 million trained parameters. The full-space formulation is bottlenecked by the linear solver used by the optimization algorithm, while the reduced-space formulation is bottlenecked by the algebraic modeling environment and derivative computations. The gray-box formulation is the most scalable and is capable of solving with the largest neural networks tested. It is bottlenecked by evaluation of the neural network's outputs and their derivatives, which may be accelerated with a graphics processing unit (GPU). Leveraging the gray-box formulation and GPU acceleration, we solve our test problem with our largest neural network surrogate in 2.5$\times$ the time required for a simpler SCOPF problem without the stability constraint.
Authors: Milad Soltany, Farhad Pourpanah, Mahdiyar Molahasani, Michael Greenspan, Ali Etemad
Abstract: In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data heterogeneity within a federated learning framework. FedSB utilizes label smoothing at the client level to prevent overfitting to domain-specific features, thereby enhancing generalization capabilities across diverse domains when aggregating local models into a global model. Additionally, FedSB incorporates a decentralized budgeting mechanism which balances training among clients, which is shown to improve the performance of the aggregated global model. Extensive experiments on four commonly used multi-domain datasets, PACS, VLCS, OfficeHome, and TerraInc, demonstrate that FedSB outperforms competing methods, achieving state-of-the-art results on three out of four datasets, indicating the effectiveness of FedSB in addressing data heterogeneity.
Authors: Xing Lei, Xuetao Zhang, Donglin Wang
Abstract: Recently, a state-of-the-art family of algorithms, known as Goal-Conditioned Weighted Supervised Learning (GCWSL) methods, has been introduced to tackle challenges in offline goal-conditioned reinforcement learning (RL). GCWSL optimizes a lower bound of the goal-conditioned RL objective and has demonstrated outstanding performance across diverse goal-reaching tasks, providing a simple, effective, and stable solution. However, prior research has identified a critical limitation of GCWSL: the lack of trajectory stitching capabilities. To address this, goal data augmentation strategies have been proposed to enhance these methods. Nevertheless, existing techniques often struggle to sample suitable augmented goals for GCWSL effectively. In this paper, we establish unified principles for goal data augmentation, focusing on goal diversity, action optimality, and goal reachability. Based on these principles, we propose a Model-based Goal Data Augmentation (MGDA) approach, which leverages a learned dynamics model to sample more suitable augmented goals. MGDA uniquely incorporates the local Lipschitz continuity assumption within the learned model to mitigate the impact of compounding errors. Empirical results show that MGDA significantly enhances the performance of GCWSL methods on both state-based and vision-based maze datasets, surpassing previous goal data augmentation techniques in improving stitching capabilities.
Authors: Chandan K Reddy, Parshin Shojaee
Abstract: Scientific discovery is a complex cognitive process that has driven human knowledge and technological progress for centuries. While artificial intelligence (AI) has made significant advances in automating aspects of scientific reasoning, simulation, and experimentation, we still lack integrated AI systems capable of performing autonomous long-term scientific research and discovery. This paper examines the current state of AI for scientific discovery, highlighting recent progress in large language models and other AI techniques applied to scientific tasks. We then outline key challenges and promising research directions toward developing more comprehensive AI systems for scientific discovery, including the need for science-focused AI agents, improved benchmarks and evaluation metrics, multimodal scientific representations, and unified frameworks combining reasoning, theorem proving, and data-driven modeling. Addressing these challenges could lead to transformative AI tools to accelerate progress across disciplines towards scientific discovery.
Authors: Alberto Chiappa, Briti Gangopadhyay, Zhao Wang, Shingo Takamatsu
Abstract: Online advertising has become one of the most successful business models of the internet era. Impression opportunities are typically allocated through real-time auctions, where advertisers bid to secure advertisement slots. Deciding the best bid for an impression opportunity is challenging, due to the stochastic nature of user behavior and the variability of advertisement traffic over time. In this work, we propose a framework for training auto-bidding agents in multi-slot second-price auctions to maximize acquisitions (e.g., clicks, conversions) while adhering to budget and cost-per-acquisition (CPA) constraints. We exploit the insight that, after an advertisement campaign concludes, determining the optimal bids for each impression opportunity can be framed as a multiple-choice knapsack problem (MCKP) with a nonlinear objective. We propose an "oracle" algorithm that identifies a near-optimal combination of impression opportunities and advertisement slots, considering both past and future advertisement traffic data. This oracle solution serves as a training target for a student network which bids having access only to real-time information, a method we term Oracle Imitation Learning (OIL). Through numerical experiments, we demonstrate that OIL achieves superior performance compared to both online and offline reinforcement learning algorithms, offering improved sample efficiency. Notably, OIL shifts the complexity of training auto-bidding agents from crafting sophisticated learning algorithms to solving a nonlinear constrained optimization problem efficiently.
Authors: Nianze Tao
Abstract: Generating novel molecules with higher properties than the training space, namely the out-of-distribution generation, is important for ${de~novo}$ drug design. However, it is not easy for distribution learning-based models, for example diffusion models, to solve this challenge as these methods are designed to fit the distribution of training data as close as possible. In this paper, we show that Bayesian flow network is capable of effortlessly generating high quality out-of-distribution samples that meet several scenarios. We introduce a semi-autoregressive training/sampling method that helps to enhance the model performance and surpass the state-of-the-art models.
Authors: Gangqiang Hu, Jianfeng Lu, Jianmin Han, Shuqin Cao, Jing Liu, Hao Fu
Abstract: Due to the sensitivity of data, federated learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized federated learning (SD-FL), clients' communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges present in real-world scenarios. To tackle this issue, we propose a trust-aware client scheduling mechanism (TRAIL) that assesses client states and contributions, enhancing model training efficiency through selective client participation. Our focus is on a semi-decentralized federated learning framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we develop an adaptive hidden semi-Markov model (AHSMM) to estimate clients' communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7\% in test accuracy and a reduction of 15.3\% in training loss.
Authors: Bikram Khanal, Pablo Rivas
Abstract: Quantum machine learning offers a transformative approach to solving complex problems, but the inherent noise hinders its practical implementation in near-term quantum devices. This obstacle makes it challenging to understand the generalization capabilities of quantum circuit models. Designing robust quantum machine learning models under noise requires a principled understanding of complexity and generalization, extending beyond classical capacity measures. This study investigates the generalization properties of parameterized quantum machine learning models under the influence of noise. We present a data-dependent generalization bound grounded in the quantum Fisher information matrix. We leverage statistical learning theory to relate the parameter space volumes and training sizes to estimate the generalization capability of the trained model. By integrating local parameter neighborhoods and effective dimensions defined through quantum Fisher information matrix eigenvalues, we provide a structured characterization of complexity in quantum models. We analyze the tightness of the bound and discuss the trade-off between model expressiveness and generalization performance.
Authors: Nobuo Namura, Sho Takemori
Abstract: Real-world optimization problems often involve complex objective functions with costly evaluations. While Bayesian optimization (BO) with Gaussian processes is effective for these challenges, it suffers in high-dimensional spaces due to performance degradation from limited function evaluations. To overcome this, simplification techniques like dimensionality reduction have been employed, yet they often rely on assumptions about the problem characteristics, potentially underperforming when these assumptions do not hold. Trust-region-based methods, which avoid such assumptions, focus on local search but risk stagnation in local optima. In this study, we propose a novel acquisition function, regional expected improvement (REI), designed to enhance trust-region-based BO in medium to high-dimensional settings. REI identifies regions likely to contain the global optimum, improving performance without relying on specific problem characteristics. We provide a theoretical proof that REI effectively identifies optimal trust regions and empirically demonstrate that incorporating REI into trust-region-based BO outperforms conventional BO and other high-dimensional BO methods in medium to high-dimensional real-world problems.
Authors: Wei Dai, Kai Hwang, Jicong Fan
Abstract: Unsupervised anomaly detection (UAD) plays an important role in modern data analytics and it is crucial to provide simple yet effective and guaranteed UAD algorithms for real applications. In this paper, we present a novel UAD method for tabular data by evaluating how much noise is in the data. Specifically, we propose to learn a deep neural network from the clean (normal) training dataset and a noisy dataset, where the latter is generated by adding highly diverse noises to the clean data. The neural network can learn a reliable decision boundary between normal data and anomalous data when the diversity of the generated noisy data is sufficiently high so that the hard abnormal samples lie in the noisy region. Importantly, we provide theoretical guarantees, proving that the proposed method can detect anomalous data successfully, although the method does not utilize any real anomalous data in the training stage. Extensive experiments through more than 60 benchmark datasets demonstrate the effectiveness of the proposed method in comparison to 12 baselines of UAD. Our method obtains a 92.27\% AUC score and a 1.68 ranking score on average. Moreover, compared to the state-of-the-art UAD methods, our method is easier to implement.
Authors: Yutian Lei, Luping Ji, Pei Liu
Abstract: Out-of-distribution (OOD) detection is indispensable for deploying reliable machine learning systems in real-world scenarios. Recent works, using auxiliary outliers in training, have shown good potential. However, they seldom concern the intrinsic correlations between in-distribution (ID) and OOD data. In this work, we discover an obvious correlation that OOD data usually possesses significant ID attributes. These attributes should be factored into the training process, rather than blindly suppressed as in previous approaches. Based on this insight, we propose a structured multi-view-based out-of-distribution detection learning (MVOL) framework, which facilitates rational handling of the intrinsic in-distribution attributes in outliers. We provide theoretical insights on the effectiveness of MVOL for OOD detection. Extensive experiments demonstrate the superiority of our framework to others. MVOL effectively utilizes both auxiliary OOD datasets and even wild datasets with noisy in-distribution data. Code is available at https://github.com/UESTC-nnLab/MVOL.
Authors: Purity Mugambi, Alexandra Meliou, Madalina Fiterau
Abstract: A crucial step in cohort studies is to extract the required cohort from one or more study datasets. This step is time-consuming, especially when a researcher is presented with a dataset that they have not previously worked with. When the cohort has to be extracted from multiple datasets, cohort extraction can be extremely laborious. In this study, we present an approach for partially automating cohort extraction from multiple electronic health record (EHR) databases. We formulate the guided multi-dataset cohort extraction problem in which selection criteria are first converted into queries, translating them from natural language text to language that maps to database entities. Then, using FLMs, columns of interest identified from the queries are automatically matched between the study databases. Finally, the generated queries are run across all databases to extract the study cohort. We propose and evaluate an algorithm for automating column matching on two large, popular and publicly-accessible EHR databases -- MIMIC-III and eICU. Our approach achieves a high top-three accuracy of $92\%$, correctly matching $12$ out of the $13$ columns of interest, when using a small, pre-trained general purpose language model. Furthermore, this accuracy is maintained even as the search space (i.e., size of the database) increases.
Authors: Mengde Han, Tianqing Zhu, Lefeng Zhang, Huan Huo, Wanlei Zhou
Abstract: Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method is particularly pertinent when entities possess datasets with identical sample identifiers but diverse attributes. Recent privacy regulations emphasize an individual's \emph{right to be forgotten}, which necessitates the ability for models to unlearn specific training data. The primary challenge is to develop a mechanism to eliminate the influence of a specific client from a model without erasing all relevant data from other clients. Our research investigates the removal of a single client's contribution within the VFL framework. We introduce an innovative modification to traditional VFL by employing a mechanism that inverts the typical learning trajectory with the objective of extracting specific data contributions. This approach seeks to optimize model performance using gradient ascent, guided by a pre-defined constrained model. We also introduce a backdoor mechanism to verify the effectiveness of the unlearning procedure. Our method avoids fully accessing the initial training data and avoids storing parameter updates. Empirical evidence shows that the results align closely with those achieved by retraining from scratch. Utilizing gradient ascent, our unlearning approach addresses key challenges in VFL, laying the groundwork for future advancements in this domain. All the code and implementations related to this paper are publicly available at https://github.com/mengde-han/VFL-unlearn.
Authors: Prajwal Kailas, Max Homilius, Rahul C. Deo, Calum A. MacRae
Abstract: Accurate diagnostic coding of medical notes is crucial for enhancing patient care, medical research, and error-free billing in healthcare organizations. Manual coding is a time-consuming task for providers, and diagnostic codes often exhibit low sensitivity and specificity, whereas the free text in medical notes can be a more precise description of a patients status. Thus, accurate automated diagnostic coding of medical notes has become critical for a learning healthcare system. Recent developments in long-document transformer architectures have enabled attention-based deep-learning models to adjudicate medical notes. In addition, contrastive loss functions have been used to jointly pre-train large language and image models with noisy labels. To further improve the automated adjudication of medical notes, we developed an approach based on i) models for ICD-10 diagnostic code sequences using a large real-world data set, ii) large language models for medical notes, and iii) contrastive pre-training to build an integrated model of both ICD-10 diagnostic codes and corresponding medical text. We demonstrate that a contrastive approach for pre-training improves performance over prior state-of-the-art models for the MIMIC-III-50, MIMIC-III-rare50, and MIMIC-III-full diagnostic coding tasks.
Authors: Naoki Sato, Hideaki Iiduka
Abstract: Graduated optimization is a global optimization technique that is used to minimize a multimodal nonconvex function by smoothing the objective function with noise and gradually refining the solution. This paper experimentally evaluates the performance of the explicit graduated optimization algorithm with an optimal noise scheduling derived from a previous study and discusses its limitations. It uses traditional benchmark functions and empirical loss functions for modern neural network architectures for evaluating. In addition, this paper extends the implicit graduated optimization algorithm, which is based on the fact that stochastic noise in the optimization process of SGD implicitly smooths the objective function, to SGD with momentum, analyzes its convergence, and demonstrates its effectiveness through experiments on image classification tasks with ResNet architectures.
Authors: Yuxin Wang, Maresa Schr\"oder, Dennis Frauen, Jonas Schweisthal, Konstantin Hess, Stefan Feuerriegel
Abstract: Constructing confidence intervals (CIs) for the average treatment effect (ATE) from patient records is crucial to assess the effectiveness and safety of drugs. However, patient records typically come from different hospitals, thus raising the question of how multiple observational datasets can be effectively combined for this purpose. In our paper, we propose a new method that estimates the ATE from multiple observational datasets and provides valid CIs. Our method makes little assumptions about the observational datasets and is thus widely applicable in medical practice. The key idea of our method is that we leverage prediction-powered inferences and thereby essentially `shrink' the CIs so that we offer more precise uncertainty quantification as compared to na\"ive approaches. We further prove the unbiasedness of our method and the validity of our CIs. We confirm our theoretical results through various numerical experiments. Finally, we provide an extension of our method for constructing CIs from combinations of experimental and observational datasets.
Authors: Andrea Perin, Stephane Deny
Abstract: Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds significant promise for improving predictions in machine learning. In this work, we aim to understand when and how deep networks can learn symmetries from data. We focus on a supervised classification paradigm where data symmetries are only partially observed during training: some classes include all transformations of a cyclic group, while others include only a subset. We ask: can deep networks generalize symmetry invariance to the partially sampled classes? In the infinite-width limit, where kernel analogies apply, we derive a neural kernel theory of symmetry learning to address this question. The group-cyclic nature of the dataset allows us to analyze the spectrum of neural kernels in the Fourier domain; here we find a simple characterization of the generalization error as a function of the interaction between class separation (signal) and class-orbit density (noise). We observe that generalization can only be successful when the local structure of the data prevails over its non-local, symmetric, structure, in the kernel space defined by the architecture. This occurs when (1) classes are sufficiently distinct and (2) class orbits are sufficiently dense. Our framework also applies to equivariant architectures (e.g., CNNs), and recovers their success in the special case where the architecture matches the inherent symmetry of the data. Empirically, our theory reproduces the generalization failure of finite-width networks (MLP, CNN, ViT) trained on partially observed versions of rotated-MNIST. We conclude that conventional networks trained with supervision lack a mechanism to learn symmetries that have not been explicitly embedded in their architecture a priori. Our framework could be extended to guide the design of architectures and training procedures able to learn symmetries from data.
Authors: Mohsen Rashki
Abstract: Machine learning (ML) has emerged as a powerful tool for tackling complex regression and classification tasks, yet its success often hinges on the quality of training data. This study introduces a novel ML paradigm inspired by domain knowledge of the structure of output function, akin to physics-informed ML, but rooted in probabilistic principles rather than physical laws. The proposed approach integrates the probabilistic structure of the target variable (such as its cumulative distribution function) into the training process. This probabilistic information is obtained from historical data or estimated using structural reliability methods during experimental design. By embedding domain-specific probabilistic insights into the learning process, the method enhances model accuracy and mitigates risks of overfitting and underfitting. Applications in regression, image denoising, and classification demonstrate the effectiveness of the approach in addressing real-world problems.
Authors: Bowen Deng, Tong Wang, Lele Fu, Sheng Huang, Chuan Chen, Tao Zhang
Abstract: Graph node clustering is a fundamental unsupervised task. Existing methods typically train an encoder through selfsupervised learning and then apply K-means to the encoder output. Some methods use this clustering result directly as the final assignment, while others initialize centroids based on this initial clustering and then finetune both the encoder and these learnable centroids. However, due to their reliance on K-means, these methods inherit its drawbacks when the cluster separability of encoder output is low, facing challenges from the Uniform Effect and Cluster Assimilation. We summarize three reasons for the low cluster separability in existing methods: (1) lack of contextual information prevents discrimination between similar nodes from different clusters; (2) training tasks are not sufficiently aligned with the downstream clustering task; (3) the cluster information in the graph structure is not appropriately exploited. To address these issues, we propose conTrastive grapH clustEring by SwApping fUsed gRomov-wasserstein coUplingS (THESAURUS). Our method introduces semantic prototypes to provide contextual information, and employs a cross-view assignment prediction pretext task that aligns well with the downstream clustering task. Additionally, it utilizes Gromov-Wasserstein Optimal Transport (GW-OT) along with the proposed prototype graph to thoroughly exploit cluster information in the graph structure. To adapt to diverse real-world data, THESAURUS updates the prototype graph and the prototype marginal distribution in OT by using momentum. Extensive experiments demonstrate that THESAURUS achieves higher cluster separability than the prior art, effectively mitigating the Uniform Effect and Cluster Assimilation issues
Authors: Nuowei Liu, Changzhi Sun, Tao Ji, Junfeng Tian, Jianxin Tang, Yuanbin Wu, Man Lan
Abstract: Current Large Language Models (LLMs) for understanding proteins primarily treats amino acid sequences as a text modality. Meanwhile, Protein Language Models (PLMs), such as ESM-2, have learned massive sequential evolutionary knowledge from the universe of natural protein sequences. Furthermore, structure-based encoders like ProteinMPNN learn the structural information of proteins through Graph Neural Networks. However, whether the incorporation of protein encoders can enhance the protein understanding of LLMs has not been explored. To bridge this gap, we propose EvoLlama, a multimodal framework that connects a structure-based encoder, a sequence-based protein encoder and an LLM for protein understanding. EvoLlama consists of a ProteinMPNN structure encoder, an ESM-2 protein sequence encoder, a multimodal projector to align protein and text representations and a Llama-3 text decoder. To train EvoLlama, we fine-tune it on protein-oriented instructions and protein property prediction datasets verbalized via natural language instruction templates. Our experiments show that EvoLlama's protein understanding capabilities have been significantly enhanced, outperforming other fine-tuned protein-oriented LLMs in zero-shot settings by an average of 1%-8% and surpassing the state-of-the-art baseline with supervised fine-tuning by an average of 6%. On protein property prediction datasets, our approach achieves promising results that are competitive with state-of-the-art task-specific baselines. We will release our code in a future version.
Authors: Changhai Zhou, Yuhua Zhou, Shijie Han, Qian Qiao, Hongguang Li
Abstract: The rise of large language models (LLMs) has significantly advanced various natural language processing (NLP) tasks. However, the resource demands of these models pose substantial challenges. Structured pruning is an effective approach to reducing model size, but it often results in significant accuracy degradation, necessitating parameter updates to adapt. Unfortunately, such fine-tuning requires substantial memory, which limits its applicability. To address these challenges, we introduce quantization into the structured pruning framework to reduce memory consumption during both fine-tuning and inference. However, the combined errors from pruning and quantization increase the difficulty of fine-tuning, requiring a more refined quantization scheme. To this end, we propose QPruner, a novel framework that employs structured pruning to reduce model size, followed by a layer-wise mixed-precision quantization scheme. Quantization precisions are assigned to each layer based on their importance to the target task, and Bayesian optimization is employed to refine precision allocation strategies, ensuring a balance between model accuracy and memory efficiency. Extensive experiments on benchmark datasets demonstrate that QPruner significantly outperforms existing methods in memory savings while maintaining or improving model performance.
Authors: Yuyang Tao, Shufei Ge
Abstract: The Mapper algorithm is an essential tool for visualizing complex, high dimensional data in topology data analysis (TDA) and has been widely used in biomedical research. It outputs a combinatorial graph whose structure implies the shape of the data. However,the need for manual parameter tuning and fixed intervals, along with fixed overlapping ratios may impede the performance of the standard Mapper algorithm. Variants of the standard Mapper algorithms have been developed to address these limitations, yet most of them still require manual tuning of parameters. Additionally, many of these variants, including the standard version found in the literature, were built within a deterministic framework and overlooked the uncertainty inherent in the data. To relax these limitations, in this work, we introduce a novel framework that implicitly represents intervals through a hidden assignment matrix, enabling automatic parameter optimization via stochastic gradient descent. In this work, we develop a soft Mapper framework based on a Gaussian mixture model(GMM) for flexible and implicit interval construction. We further illustrate the robustness of the soft Mapper algorithm by introducing the Mapper graph mode as a point estimation for the output graph. Moreover, a stochastic gradient descent algorithm with a specific topological loss function is proposed for optimizing parameters in the model. Both simulation and application studies demonstrate its effectiveness in capturing the underlying topological structures. In addition, the application to an RNA expression dataset obtained from the Mount Sinai/JJ Peters VA Medical Center Brain Bank (MSBB) successfully identifies a distinct subgroup of Alzheimer's Disease.
Authors: Nour Jamoussi, Giuseppe Serra, Photios A. Stavrou, Marios Kountouris
Abstract: In this work, we study the problem of aggregation in the context of Bayesian Federated Learning (BFL). Using an information geometric perspective, we interpret the BFL aggregation step as finding the barycenter of the trained posteriors for a pre-specified divergence metric. We study the barycenter problem for the parametric family of $\alpha$-divergences and, focusing on the standard case of independent and Gaussian distributed parameters, we recover the closed-form solution of the reverse Kullback-Leibler barycenter and develop the analytical form of the squared Wasserstein-2 barycenter. Considering a non-IID setup, where clients possess heterogeneous data, we analyze the performance of the developed algorithms against state-of-the-art (SOTA) Bayesian aggregation methods in terms of accuracy, uncertainty quantification (UQ), model calibration (MC), and fairness. Finally, we extend our analysis to the framework of Hybrid Bayesian Deep Learning (HBDL), where we study how the number of Bayesian layers in the architecture impacts the considered performance metrics. Our experimental results show that the proposed methodology presents comparable performance with the SOTA while offering a geometric interpretation of the aggregation phase.
Authors: Wei Chen, Guo Ye, Yakun Wang, Zhao Zhang, Libang Zhang, Daxin Wang, Zhiqiang Zhang, Fuzhen Zhuang
Abstract: Unsupervised Graph Domain Adaptation (UGDA) seeks to bridge distribution shifts between domains by transferring knowledge from labeled source graphs to given unlabeled target graphs. Existing UGDA methods primarily focus on aligning features in the latent space learned by graph neural networks (GNNs) across domains, often overlooking structural shifts, resulting in limited effectiveness when addressing structurally complex transfer scenarios. Given the sensitivity of GNNs to local structural features, even slight discrepancies between source and target graphs could lead to significant shifts in node embeddings, thereby reducing the effectiveness of knowledge transfer. To address this issue, we introduce a novel approach for UGDA called Target-Domain Structural Smoothing (TDSS). TDSS is a simple and effective method designed to perform structural smoothing directly on the target graph, thereby mitigating structural distribution shifts and ensuring the consistency of node representations. Specifically, by integrating smoothing techniques with neighborhood sampling, TDSS maintains the structural coherence of the target graph while mitigating the risk of over-smoothing. Our theoretical analysis shows that TDSS effectively reduces target risk by improving model smoothness. Empirical results on three real-world datasets demonstrate that TDSS outperforms recent state-of-the-art baselines, achieving significant improvements across six transfer scenarios. The code is available in https://github.com/cwei01/TDSS.
Authors: Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino, Sajal K. Das
Abstract: This paper proposes a novel federated algorithm that leverages momentum-based variance reduction with adaptive learning to address non-convex settings across heterogeneous data. We intend to minimize communication and computation overhead, thereby fostering a sustainable federated learning system. We aim to overcome challenges related to gradient variance, which hinders the model's efficiency, and the slow convergence resulting from learning rate adjustments with heterogeneous data. The experimental results on the image classification tasks with heterogeneous data reveal the effectiveness of our suggested algorithms in non-convex settings with an improved communication complexity of $\mathcal{O}(\epsilon^{-1})$ to converge to an $\epsilon$-stationary point - compared to the existing communication complexity $\mathcal{O}(\epsilon^{-2})$ of most prior works. The proposed federated version maintains the trade-off between the convergence rate, number of communication rounds, and test accuracy while mitigating the client drift in heterogeneous settings. The experimental results demonstrate the efficiency of our algorithms in image classification tasks (MNIST, CIFAR-10) with heterogeneous data.
Authors: Hangyu Zhu, Yuxiang Fan, Zhenping Xie
Abstract: Federated learning (FL) is a privacy preserving machine learning paradigm designed to collaboratively learn a global model without data leakage. Specifically, in a typical FL system, the central server solely functions as an coordinator to iteratively aggregate the collected local models trained by each client, potentially introducing single-point transmission bottleneck and security threats. To mitigate this issue, decentralized federated learning (DFL) has been proposed, where all participating clients engage in peer-to-peer communication without a central server. Nonetheless, DFL still suffers from training degradation as FL does due to the non-independent and identically distributed (non-IID) nature of client data. And incorporating personalization layers into DFL may be the most effective solutions to alleviate the side effects caused by non-IID data. Therefore, in this paper, we propose a novel unit representation aided personalized decentralized federated learning framework, named UA-PDFL, to deal with the non-IID challenge in DFL. By adaptively adjusting the level of personalization layers through the guidance of the unit representation, UA-PDFL is able to address the varying degrees of data skew. Based on this scheme, client-wise dropout and layer-wise personalization are proposed to further enhance the learning performance of DFL. Extensive experiments empirically prove the effectiveness of our proposed method.
Authors: Dexter Le, Aybars Yunusoglu, Karn Tiwari, Murat Isik, I. Can Dikmen
Abstract: In the evolving landscape of transportation systems, integrating Large Language Models (LLMs) offers a promising frontier for advancing intelligent decision-making across various applications. This paper introduces a novel 3-dimensional framework that encapsulates the intersection of applications, machine learning methodologies, and hardware devices, particularly emphasizing the role of LLMs. Instead of using multiple machine learning algorithms, our framework uses a single, data-centric LLM architecture that can analyze time series, images, and videos. We explore how LLMs can enhance data interpretation and decision-making in transportation. We apply this LLM framework to different sensor datasets, including time-series data and visual data from sources like Oxford Radar RobotCar, D-Behavior (D-Set), nuScenes by Motional, and Comma2k19. The goal is to streamline data processing workflows, reduce the complexity of deploying multiple models, and make intelligent transportation systems more efficient and accurate. The study was conducted using state-of-the-art hardware, leveraging the computational power of AMD RTX 3060 GPUs and Intel i9-12900 processors. The experimental results demonstrate that our framework achieves an average accuracy of 91.33\% across these datasets, with the highest accuracy observed in time-series data (92.7\%), showcasing the model's proficiency in handling sequential information essential for tasks such as motion planning and predictive maintenance. Through our exploration, we demonstrate the versatility and efficacy of LLMs in handling multimodal data within the transportation sector, ultimately providing insights into their application in real-world scenarios. Our findings align with the broader conference themes, highlighting the transformative potential of LLMs in advancing transportation technologies.
Authors: Andrei Semenov, Philip Zmushko, Alexander Pichugin, Aleksandr Beznosikov
Abstract: Vertical Federated Learning (VFL) aims to enable collaborative training of deep learning models while maintaining privacy protection. However, the VFL procedure still has components that are vulnerable to attacks by malicious parties. In our work, we consider feature reconstruction attacks, a common risk targeting input data compromise. We theoretically claim that feature reconstruction attacks cannot succeed without knowledge of the prior distribution on data. Consequently, we demonstrate that even simple model architecture transformations can significantly impact the protection of input data during VFL. Confirming these findings with experimental results, we show that MLP-based models are resistant to state-of-the-art feature reconstruction attacks.
Authors: Eloy Geenjaar, Lie Lu
Abstract: Transfer learning for bio-signals has recently become an important technique to improve prediction performance on downstream tasks with small bio-signal datasets. Recent works have shown that pre-training a neural network model on a large dataset (e.g. EEG) with a self-supervised task, replacing the self-supervised head with a linear classification head, and fine-tuning the model on different downstream bio-signal datasets (e.g., EMG or ECG) can dramatically improve the performance on those datasets. In this paper, we propose a new convolution-transformer hybrid model architecture with masked auto-encoding for low-data bio-signal transfer learning, introduce a frequency-based masked auto-encoding task, employ a more comprehensive evaluation framework, and evaluate how much and when (multimodal) pre-training improves fine-tuning performance. We also introduce a dramatically more performant method of aligning a downstream dataset with a different temporal length and sampling rate to the original pre-training dataset. Our findings indicate that the convolution-only part of our hybrid model can achieve state-of-the-art performance on some low-data downstream tasks. The performance is often improved even further with our full model. In the case of transformer-based models we find that pre-training especially improves performance on downstream datasets, multimodal pre-training often increases those gains further, and our frequency-based pre-training performs the best on average for the lowest and highest data regimes.
Authors: Xue Yang, Depan Peng, Yan Feng, Xiaohu Tang, Weijun Fang, Jun Shao
Abstract: Bidirectional privacy-preservation federated learning is crucial as both local gradients and the global model may leak privacy. However, only a few works attempt to achieve it, and they often face challenges such as excessive communication and computational overheads, or significant degradation of model accuracy, which hinders their practical applications. In this paper, we design an efficient and high-accuracy bidirectional privacy-preserving scheme for federated learning to complete secure model training and secure aggregation. To efficiently achieve bidirectional privacy, we design an efficient and accuracy-lossless model perturbation method on the server side (called $\mathbf{MP\_Server}$) that can be combined with local differential privacy (LDP) to prevent clients from accessing the model, while ensuring that the local gradients obtained on the server side satisfy LDP. Furthermore, to ensure model accuracy, we customize a distributed differential privacy mechanism on the client side (called $\mathbf{DDP\_Client}$). When combined with $\mathbf{MP\_Server}$, it ensures LDP of the local gradients, while ensuring that the aggregated result matches the accuracy of central differential privacy (CDP). Extensive experiments demonstrate that our scheme significantly outperforms state-of-the-art bidirectional privacy-preservation baselines (SOTAs) in terms of computational cost, model accuracy, and defense ability against privacy attacks. Particularly, given target accuracy, the training time of SOTAs is approximately $200$ times, or even over $1000$ times, longer than that of our scheme. When the privacy budget is set relatively small, our scheme incurs less than $6\%$ accuracy loss compared to the privacy-ignoring method, while SOTAs suffer up to $20\%$ accuracy loss. Experimental results also show that the defense capability of our scheme outperforms than SOTAs.
Authors: Fangbing Liu, Qing Wang
Abstract: Optimizing spectral graph neural networks (GNNs) remains a critical challenge in the field, yet the underlying processes are not well understood. In this paper, we investigate the inherent differences between graph convolution parameters and feature transformation parameters in spectral GNNs and their impact on the optimization landscape. Our analysis reveals that these differences contribute to a poorly conditioned problem, resulting in suboptimal performance. To address this issue, we introduce the concept of the block condition number of the Hessian matrix, which characterizes the difficulty of poorly conditioned problems in spectral GNN optimization. We then propose an asymmetric learning approach, dynamically preconditioning gradients during training to alleviate poorly conditioned problems. Theoretically, we demonstrate that asymmetric learning can reduce block condition numbers, facilitating easier optimization. Extensive experiments on eighteen benchmark datasets show that asymmetric learning consistently improves the performance of spectral GNNs for both heterophilic and homophilic graphs. This improvement is especially notable for heterophilic graphs, where the optimization process is generally more complex than for homophilic graphs. Code is available at https://github.com/Mia-321/asym-opt.git.
Authors: Minghao Xu, Lichuan Xiang, Xu Cai, Hongkai Wen
Abstract: In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum (SGDM). SGD-SaI performs learning rate Scaling at Initialization (SaI) to distinct parameter groups, guided by their respective gradient signal-to-noise ratios (g-SNR). By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first iteration and cuts the optimizer's memory usage by half compared to AdamW. Despite its simplicity and efficiency, SGD-SaI consistently matches or outperforms AdamW in training a variety of Transformer-based tasks, effectively overcoming a long-standing challenge of using SGD for training Transformers. SGD-SaI excels in ImageNet-1K classification with Vision Transformers(ViT) and GPT-2 pretraining for large language models (LLMs, transformer decoder-only), demonstrating robustness to hyperparameter variations and practicality for diverse applications. We further tested its robustness on tasks like LoRA fine-tuning for LLMs and diffusion models, where it consistently outperforms state-of-the-art optimizers. From a memory efficiency perspective, SGD-SaI achieves substantial memory savings for optimizer states, reducing memory usage by 5.93 GB for GPT-2 (1.5B parameters) and 25.15 GB for Llama2-7B compared to AdamW in full-precision training settings.
Authors: Xinquan Chen, Junqi Gao, Biqing Qi, Dong Li, Yiang Luo, Fangyuan Li, Pengfei Li
Abstract: Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs, as its derivative cannot be backpropagated. To address this issue, hypernetwork based methods, which utilize neural networks to learn the gradients of non-differentiable quantization functions, have emerged as a promising approach due to their adaptive learning capabilities to reduce estimation errors. However, existing hypernetwork based methods typically rely solely on current gradient information, neglecting the influence of historical gradients. This oversight can lead to accumulated gradient errors when calculating gradient momentum during optimization. To incorporate historical gradient information, we design a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization. To further enhance gradient generation in hypernetworks, we propose a Fast and Slow Gradient Generation (FSG) method. Additionally, to produce more precise gradients, we introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients. Extensive comparative experiments on the CIFAR-10 and CIFAR-100 datasets demonstrate that our method achieves faster convergence and lower loss values, outperforming existing baselines.Code is available at http://github.com/two-tiger/FSG .
Authors: Mulugeta Weldezgina Asres, Christian Walter Omlin, The CMS-HCAL Collaboration
Abstract: Extracting anomaly causality facilitates diagnostics once monitoring systems detect system faults. Identifying anomaly causes in large systems involves investigating a more extensive set of monitoring variables across multiple subsystems. However, learning causal graphs comes with a significant computational burden that restrains the applicability of most existing methods in real-time and large-scale deployments. In addition, modern monitoring applications for large systems often generate large amounts of binary alarm flags, and the distinct characteristics of binary anomaly data -- the meaning of state transition and data sparsity -- challenge existing causality learning mechanisms. This study proposes an anomaly causal discovery approach (AnomalyCD), addressing the accuracy and computational challenges of generating causal graphs from binary flag data sets. The AnomalyCD framework presents several strategies, such as anomaly flag characteristics incorporating causality testing, sparse data and link compression, and edge pruning adjustment approaches. We validate the performance of this framework on two datasets: monitoring sensor data of the readout-box system of the Compact Muon Solenoid experiment at CERN, and a public data set for information technology monitoring. The results demonstrate the considerable reduction of the computation overhead and moderate enhancement of the accuracy of temporal causal discovery on binary anomaly data sets.
Authors: Jingze Shi, Bingheng Wu
Abstract: In order to make the foundation model more efficient and effective, our idea is combining sequence transformation and state transformation. First, we prove the availability of rotary position embedding in the state space duality algorithm, which reduces the perplexity of the hybrid quadratic causal self-attention and state space duality by more than 4%, to ensure that the combining sequence transformation unifies position encoding. Second, we propose dynamic mask attention, which maintains 100% accuracy in the more challenging multi-query associative recall task, improving by more than 150% compared to quadratic causal self-attention and state space duality, to ensure that the combining sequence transformation selectively filters relevant information. Third, we design cross domain mixture of experts, which makes the computational speed of expert retrieval with more than 1024 experts 8 to 10 times faster than the mixture of experts, to ensure that the combining state transformation quickly retrieval mixture. Finally, we summarize these matrix algorithms that can form the foundation model: Wonderful Matrices, which can be a competitor to popular model architectures.
Authors: Alex F. Spies, William Edwards, Michael I. Ivanitskiy, Adrians Skapars, Tilman R\"auker, Katsumi Inoue, Alessandra Russo, Murray Shanahan
Abstract: Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop surprisingly structured representations. When such representations comprehensively reflect the task domain's structure, they are commonly referred to as ``World Models'' (WMs). In this work, we discover such WMs in transformers trained on maze tasks. In particular, by employing Sparse Autoencoders (SAEs) and analysing attention patterns, we examine the construction of WMs and demonstrate consistency between the circuit analysis and the SAE feature-based analysis. We intervene upon the isolated features to confirm their causal role and, in doing so, find asymmetries between certain types of interventions. Surprisingly, we find that models are able to reason with respect to a greater number of active features than they see during training, even if attempting to specify these in the input token sequence would lead the model to fail. Futhermore, we observe that varying positional encodings can alter how WMs are encoded in a model's residual stream. By analyzing the causal role of these WMs in a toy domain we hope to make progress toward an understanding of emergent structure in the representations acquired by Transformers, leading to the development of more interpretable and controllable AI systems.
Authors: Minjae Cho, Chuangchuang Sun
Abstract: Meta-Reinforcement Learning (Meta-RL) enables fast adaptation to new testing tasks. Despite recent advancements, it is still challenging to learn performant policies across multiple complex and high-dimensional tasks. To address this, we propose a novel architecture with three hierarchical levels for 1) learning task representations, 2) discovering task-agnostic macro-actions in an automated manner, and 3) learning primitive actions. The macro-action can guide the low-level primitive policy learning to more efficiently transition to goal states. This can address the issue that the policy may forget previously learned behavior while learning new, conflicting tasks. Moreover, the task-agnostic nature of the macro-actions is enabled by removing task-specific components from the state space. Hence, this makes them amenable to re-composition across different tasks and leads to promising fast adaptation to new tasks. Also, the prospective instability from the tri-level hierarchies is effectively mitigated by our innovative, independently tailored training schemes. Experiments in the MetaWorld framework demonstrate the improved sample efficiency and success rate of our approach compared to previous state-of-the-art methods.
Authors: Zewen Yang, Xiaobing Dai, Sandra Hirche
Abstract: This is a complementary document for the paper titled "Asynchronous Distributed Gaussian Process Regression for Online Learning and Dynamical Systems".
Authors: Ahmad Hassanpour, Amir Zarei, Khawla Mallat, Anderson Santana de Oliveira, Bian Yang
Abstract: This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between privacy and utility. One focus of this work is sharpness-aware training (SAT) and its integration with differential privacy (DP-SAT) to further improve this balance. Additionally, we examine fairness in both private and non-private learning models trained on datasets with synthetic and real-world biases. We also measure the privacy risks involved in these scenarios by performing membership inference attacks (MIAs) and explore the consequences of eliminating high-privacy risk samples, termed outliers. Moreover, we introduce a new metric, named \emph{harmonic score}, which combines accuracy, privacy, and fairness into a single measure. Through empirical analysis using generalization techniques, we achieve an accuracy of 81.11\% under $(8, 10^{-5})$-DP on CIFAR-10, surpassing the 79.5\% reported by De et al. (2022). Moreover, our experiments show that memorization of training samples can begin before the overfitting point, and generalization techniques do not guarantee the prevention of this memorization. Our analysis of synthetic biases shows that generalization techniques can amplify model bias in both private and non-private models. Additionally, our results indicate that increased bias in training data leads to reduced accuracy, greater vulnerability to privacy attacks, and higher model bias. We validate these findings with the CelebA dataset, demonstrating that similar trends persist with real-world attribute imbalances. Finally, our experiments show that removing outlier data decreases accuracy and further amplifies model bias.
Authors: Kamaljyoti Nath, Varun Kumar, Daniel J. Smith, George Em Karniadakis
Abstract: Improving diesel engine efficiency and emission reduction have been critical research topics. Recent government regulations have shifted this focus to another important area related to engine health and performance monitoring. Although the advancements in the use of deep learning methods for system monitoring have shown promising results in this direction, designing efficient methods suitable for field systems remains an open research challenge. The objective of this study is to develop a computationally efficient neural network-based approach for identifying unknown parameters of a mean value diesel engine model to facilitate physics-based health monitoring and maintenance forecasting. We propose a hybrid method combining physics informed neural networks, PINNs, and a deep neural operator, DeepONet to predict unknown parameters and gas flow dynamics in a diesel engine. The operator network predicts independent actuator dynamics learnt through offline training, thereby reducing the PINNs online computational cost. To address PINNs need for retraining with changing input scenarios, we propose two transfer learning (TL) strategies. The first strategy involves multi-stage transfer learning for parameter identification. While this method is computationally efficient as compared to online PINN training, improvements are required to meet field requirements. The second TL strategy focuses solely on training the output weights and biases of a subset of multi-head networks pretrained on a larger dataset, substantially reducing computation time during online prediction. We also evaluate our model for epistemic and aleatoric uncertainty by incorporating dropout in pretrained networks and Gaussian noise in the training dataset. This strategy offers a tailored, computationally inexpensive, and physics-based approach for parameter identification in diesel engine sub systems.
Authors: Oren Neumann, Claudius Gros
Abstract: Neural scaling laws are observed in a range of domains, to date with no clear understanding of why they occur. Recent theories suggest that loss power laws arise from Zipf's law, a power law observed in domains like natural language. One theory suggests that language scaling laws emerge when Zipf-distributed task quanta are learned in descending order of frequency. In this paper we examine power-law scaling in AlphaZero, a reinforcement learning algorithm, using a theory of language-model scaling. We find that game states in training and inference data scale with Zipf's law, which is known to arise from the tree structure of the environment, and examine the correlation between scaling-law and Zipf's-law exponents. In agreement with quanta scaling theory, we find that agents optimize state loss in descending order of frequency, even though this order scales inversely with modelling complexity. We also find that inverse scaling, the failure of models to improve with size, is correlated with unusual Zipf curves where end-game states are among the most frequent states. We show evidence that larger models shift their focus to these less-important states, sacrificing their understanding of important early-game states.
Authors: Sheikh Junaid Fayaz, Nestor Montiel-Bohorquez, Shashank Bishnoi, Matteo Romano, Manuele Gatti, N. M. Anoop Krishnan
Abstract: Cement production, exceeding 4.1 billion tonnes and contributing 2.4 tonnes of CO2 annually, faces critical challenges in quality control and process optimization. While traditional process models for cement manufacturing are confined to steady-state conditions with limited predictive capability for mineralogical phases, modern plants operate under dynamic conditions that demand real-time quality assessment. Here, exploiting a comprehensive two-year operational dataset from an industrial cement plant, we present a machine learning framework that accurately predicts clinker mineralogy from process data. Our model achieves unprecedented prediction accuracy for major clinker phases while requiring minimal input parameters, demonstrating robust performance under varying operating conditions. Through post-hoc explainable algorithms, we interpret the hierarchical relationships between clinker oxides and phase formation, providing insights into the functioning of an otherwise black-box model. This digital twin framework can potentially enable real-time optimization of cement production, thereby providing a route toward reducing material waste and ensuring quality while reducing the associated emissions under real plant conditions. Our approach represents a significant advancement in industrial process control, offering a scalable solution for sustainable cement manufacturing.
Authors: Taiyan Zhang, Renchi Yang, Mingyu Yan, Xiaochun Ye, Dongrui Fan, Yurui Lai
Abstract: Graph neural networks (GNNs) have emerged as go-to models for node classification in graph data due to their powerful abilities in fusing graph structures and attributes. However, such models strongly rely on adequate high-quality labeled data for training, which are expensive to acquire in practice. With the advent of large language models (LLMs), a promising way is to leverage their superb zero-shot capabilities and massive knowledge for node labeling. Despite promising results reported, this methodology either demands considerable queries to LLMs, or suffers from compromised performance caused by noisy labels produced by LLMs. To remedy these issues, this work presents Cella, an active self-training framework that integrates LLMs into GNNs in a cost-effective manner. The design recipe of Cella is to iteratively identify small sets of "critical" samples using GNNs and extract informative pseudo-labels for them with both LLMs and GNNs as additional supervision signals to enhance model training. Particularly, Cella includes three major components: (i) an effective active node selection strategy for initial annotations; (ii) a judicious sample selection scheme to sift out the "critical" nodes based on label disharmonicity and entropy; and (iii) a label refinement module combining LLMs and GNNs with rewired topology. Our extensive experiments over five benchmark text-attributed graph datasets demonstrate that Cella significantly outperforms the state of the arts under the same query budget to LLMs in terms of label-free node classification. In particular, on the DBLP dataset with 14.3k nodes, Cella is able to achieve an 8.08% conspicuous improvement in accuracy over the state-of-the-art at a cost of less than one cent.
Authors: Linfeng Zhao, Lawson L. S. Wong
Abstract: Learning navigation capabilities in different environments has long been one of the major challenges in decision-making. In this work, we focus on zero-shot navigation ability using given abstract $2$-D top-down maps. Like human navigation by reading a paper map, the agent reads the map as an image when navigating in a novel layout, after learning to navigate on a set of training maps. We propose a model-based reinforcement learning approach for this multi-task learning problem, where it jointly learns a hypermodel that takes top-down maps as input and predicts the weights of the transition network. We use the DeepMind Lab environment and customize layouts using generated maps. Our method can adapt better to novel environments in zero-shot and is more robust to noise.
Authors: Honglin Yang, Ji Ma, Xiao Yu
Abstract: The optimization-based meta-learning approach is gaining increased traction because of its unique ability to quickly adapt to a new task using only small amounts of data. However, existing optimization-based meta-learning approaches, such as MAML, ANIL and their variants, generally employ backpropagation for upper-level gradient estimation, which requires using historical lower-level parameters/gradients and thus increases computational and memory overhead in each iteration. In this paper, we propose a meta-learning algorithm that can avoid using historical parameters/gradients and significantly reduce memory costs in each iteration compared to existing optimization-based meta-learning approaches. In addition to memory reduction, we prove that our proposed algorithm converges sublinearly with the iteration number of upper-level optimization, and the convergence error decays sublinearly with the batch size of sampled tasks. In the specific case in terms of deterministic meta-learning, we also prove that our proposed algorithm converges to an exact solution. Moreover, we quantify that the computational complexity of the algorithm is on the order of $\mathcal{O}(\epsilon^{-1})$, which matches existing convergence results on meta-learning even without using any historical parameters/gradients. Experimental results on meta-learning benchmarks confirm the efficacy of our proposed algorithm.
Authors: Lucas Tes\'an, David Gonz\'alez, Pedro Martins, El\'ias Cueto
Abstract: The growing importance of real-time simulation in the medical field has exposed the limitations and bottlenecks inherent in the digital representation of complex biological systems. This paper presents a novel methodology aimed at advancing current lines of research in soft tissue simulation. The proposed approach introduces a hybrid model that integrates the geometric bias of graph neural networks with the physical bias derived from the imposition of a metriplectic structure as soft and hard constrains in the architecture, being able to simulate hepatic tissue with dissipative properties. This approach provides an efficient solution capable of generating predictions at high feedback rate while maintaining a remarkable generalization ability for previously unseen anatomies. This makes these features particularly relevant in the context of precision medicine and haptic rendering. Based on the adopted methodologies, we propose a model that predicts human liver responses to traction and compression loads in as little as 7.3 milliseconds for optimized configurations and as fast as 1.65 milliseconds in the most efficient cases, all in the forward pass. The model achieves relative position errors below 0.15\%, with stress tensor and velocity estimations maintaining relative errors under 7\%. This demonstrates the robustness of the approach developed, which is capable of handling diverse load states and anatomies effectively. This work highlights the feasibility of integrating real-time simulation with patient-specific geometries through deep learning, paving the way for more robust digital human twins in medical applications.
Authors: Arunabh Singh, Joyjit Mukherjee
Abstract: System identification, the process of deriving mathematical models of dynamical systems from observed input-output data, has undergone a paradigm shift with the advent of learning-based methods. Addressing the intricate challenges of data-driven discovery in nonlinear dynamical systems, these methods have garnered significant attention. Among them, Sparse Identification of Nonlinear Dynamics (SINDy) has emerged as a transformative approach, distilling complex dynamical behaviors into interpretable linear combinations of basis functions. However, SINDy relies on domain-specific expertise to construct its foundational "library" of basis functions, which limits its adaptability and universality. In this work, we introduce a nonlinear system identification framework called LeARN that transcends the need for prior domain knowledge by learning the library of basis functions directly from data. To enhance adaptability to evolving system dynamics under varying noise conditions, we employ a novel meta-learning-based system identification approach that uses a lightweight deep neural network (DNN) to dynamically refine these basis functions. This not only captures intricate system behaviors but also adapts seamlessly to new dynamical regimes. We validate our framework on the Neural Fly dataset, showcasing its robust adaptation and generalization capabilities. Despite its simplicity, our LeARN achieves competitive dynamical error performance compared to SINDy. This work presents a step toward the autonomous discovery of dynamical systems, paving the way for a future where machine learning uncovers the governing principles of complex systems without requiring extensive domain-specific interventions.
Authors: Connor Lawless, Yingxi Li, Anders Wikum, Madeleine Udell, Ellen Vitercik
Abstract: Mixed integer linear programming (MILP) solvers ship with a staggering number of parameters that are challenging to select a priori for all but expert optimization users, but can have an outsized impact on the performance of the MILP solver. Existing machine learning (ML) approaches to configure solvers require training ML models by solving thousands of related MILP instances, generalize poorly to new problem sizes, and often require implementing complex ML pipelines and custom solver interfaces that can be difficult to integrate into existing optimization workflows. In this paper, we introduce a new LLM-based framework to configure which cutting plane separators to use for a given MILP problem with little to no training data based on characteristics of the instance, such as a natural language description of the problem and the associated LaTeX formulation. We augment these LLMs with descriptions of cutting plane separators available in a given solver, grounded by summarizing the existing research literature on separators. While individual solver configurations have a large variance in performance, we present a novel ensembling strategy that clusters and aggregates configurations to create a small portfolio of high-performing configurations. Our LLM-based methodology requires no custom solver interface, can find a high-performing configuration by solving only a small number of MILPs, and can generate the configuration with simple API calls that run in under a second. Numerical results show our approach is competitive with existing configuration approaches on a suite of classic combinatorial optimization problems and real-world datasets with only a fraction of the training data and computation time.
Authors: Eliot Xing, Vernon Luk, Jean Oh
Abstract: Recent advances in GPU-based parallel simulation have enabled practitioners to collect large amounts of data and train complex control policies using deep reinforcement learning (RL), on commodity GPUs. However, such successes for RL in robotics have been limited to tasks sufficiently simulated by fast rigid-body dynamics. Simulation techniques for soft bodies are comparatively several orders of magnitude slower, thereby limiting the use of RL due to sample complexity requirements. To address this challenge, this paper presents both a novel RL algorithm and a simulation platform to enable scaling RL on tasks involving rigid bodies and deformables. We introduce Soft Analytic Policy Optimization (SAPO), a maximum entropy first-order model-based actor-critic RL algorithm, which uses first-order analytic gradients from differentiable simulation to train a stochastic actor to maximize expected return and entropy. Alongside our approach, we develop Rewarped, a parallel differentiable multiphysics simulation platform that supports simulating various materials beyond rigid bodies. We re-implement challenging manipulation and locomotion tasks in Rewarped, and show that SAPO outperforms baselines over a range of tasks that involve interaction between rigid bodies, articulations, and deformables.
Authors: Zhengxing Cheng, Yuheng Huang, Zhixuan Zhang, Dan Ou, Qingwen Liu
Abstract: Given the ubiquity of multi-task in practical systems, Multi-Task Learning (MTL) has found widespread application across diverse domains. In real-world scenarios, these tasks often have different priorities. For instance, In web search, relevance is often prioritized over other metrics, such as click-through rates or user engagement. Existing frameworks pay insufficient attention to the prioritization among different tasks, which typically adjust task-specific loss function weights to differentiate task priorities. However, this approach encounters challenges as the number of tasks grows, leading to exponential increases in hyper-parameter tuning complexity. Furthermore, the simultaneous optimization of multiple objectives can negatively impact the performance of high-priority tasks due to interference from lower-priority tasks. In this paper, we introduce a novel multi-task learning framework employing Lagrangian Differential Multiplier Methods for step-wise multi-task optimization. It is designed to boost the performance of high-priority tasks without interference from other tasks. Its primary advantage lies in its ability to automatically optimize multiple objectives without requiring balancing hyper-parameters for different tasks, thereby eliminating the need for manual tuning. Additionally, we provide theoretical analysis demonstrating that our method ensures optimization guarantees, enhancing the reliability of the process. We demonstrate its effectiveness through experiments on multiple public datasets and its application in Taobao search, a large-scale industrial search ranking system, resulting in significant improvements across various business metrics.
Authors: Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza
Abstract: Reinforcement learning (RL) algorithms aim to balance exploiting the current best strategy with exploring new options that could lead to higher rewards. Most common RL algorithms use undirected exploration, i.e., select random sequences of actions. Exploration can also be directed using intrinsic rewards, such as curiosity or model epistemic uncertainty. However, effectively balancing task and intrinsic rewards is challenging and often task-dependent. In this work, we introduce a framework, MaxInfoRL, for balancing intrinsic and extrinsic exploration. MaxInfoRL steers exploration towards informative transitions, by maximizing intrinsic rewards such as the information gain about the underlying task. When combined with Boltzmann exploration, this approach naturally trades off maximization of the value function with that of the entropy over states, rewards, and actions. We show that our approach achieves sublinear regret in the simplified setting of multi-armed bandits. We then apply this general formulation to a variety of off-policy model-free RL methods for continuous state-action spaces, yielding novel algorithms that achieve superior performance across hard exploration problems and complex scenarios such as visual control tasks.
Authors: Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen, Sung-En Chang, Timothy Rupprecht, Lei Lu, Enfu Nan, Changdi Yang, Yumei He, Xingchen Xu, Yu Huang, Wei Wang, Yue Chen, Yong He, Yanzhi Wang
Abstract: Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are proprietary LLMs like GPT-4 and GPT-o1, which have captured widespread attention in the AI community due to their remarkable performance and versatility. Simultaneously, open-source LLMs, such as LLaMA and Mistral, have made great contributions to the ever-increasing popularity of LLMs due to the ease to customize and deploy the models across diverse applications. Although open-source LLMs present unprecedented opportunities for innovation and research, the commercialization of LLMs has raised concerns about transparency, reproducibility, and safety. Many open-source LLMs fail to meet fundamental transparency requirements by withholding essential components like training code and data, and some use restrictive licenses whilst claiming to be "open-source," which may hinder further innovations on LLMs. To mitigate this issue, we introduce Moxin 7B, a fully open-source LLM developed in accordance with the Model Openness Framework (MOF), a ranked classification system that evaluates AI models based on model completeness and openness, adhering to principles of open science, open source, open data, and open access. Our model achieves the highest MOF classification level of "open science" through the comprehensive release of pre-training code and configurations, training and fine-tuning datasets, and intermediate and final checkpoints. Experiments show that our model achieves superior performance in zero-shot evaluation compared with popular 7B models and performs competitively in few-shot evaluation.
Authors: Suchithra Kunhoth, Somaya Al- Maadeed, Younes Akbari, Rafif Al Saady
Abstract: Precision medicine has become a central focus in breast cancer management, advancing beyond conventional methods to deliver more precise and individualized therapies. Traditionally, histopathology images have been used primarily for diagnostic purposes; however, they are now recognized for their potential in molecular profiling, which provides deeper insights into cancer prognosis and treatment response. Recent advancements in artificial intelligence (AI) have enabled digital pathology to analyze histopathologic images for both targeted molecular and broader omic biomarkers, marking a pivotal step in personalized cancer care. These technologies offer the capability to extract various biomarkers such as genomic, transcriptomic, proteomic, and metabolomic markers directly from the routine hematoxylin and eosin (H&E) stained images, which can support treatment decisions without the need for costly molecular assays. In this work, we provide a comprehensive review of AI-driven techniques for biomarker detection, with a focus on diverse omic biomarkers that allow novel biomarker discovery. Additionally, we analyze the major challenges faced in this field for robust algorithm development. These challenges highlight areas where further research is essential to bridge the gap between AI research and clinical application.
Authors: Shuhe Wang, Shengyu Zhang, Jie Zhang, Runyi Hu, Xiaoya Li, Tianwei Zhang, Jiwei Li, Fei Wu, Guoyin Wang, Eduard Hovy
Abstract: This paper surveys research in the rapidly growing field of enhancing large language models (LLMs) with reinforcement learning (RL), a technique that enables LLMs to improve their performance by receiving feedback in the form of rewards based on the quality of their outputs, allowing them to generate more accurate, coherent, and contextually appropriate responses. In this work, we make a systematic review of the most up-to-date state of knowledge on RL-enhanced LLMs, attempting to consolidate and analyze the rapidly growing research in this field, helping researchers understand the current challenges and advancements. Specifically, we (1) detail the basics of RL; (2) introduce popular RL-enhanced LLMs; (3) review researches on two widely-used reward model-based RL techniques: Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF); and (4) explore Direct Preference Optimization (DPO), a set of methods that bypass the reward model to directly use human preference data for aligning LLM outputs with human expectations. We will also point out current challenges and deficiencies of existing methods and suggest some avenues for further improvements.
Authors: Ajay Kushwaha, Eralp Demir, Amrita Basak
Abstract: Crystal plasticity (CP) modeling is a vital tool for predicting the mechanical behavior of materials, but its calibration involves numerous (>8) constitutive parameters, often requiring time-consuming trial-and-error methods. This paper proposes a robust calibration approach using Bayesian optimization (BO) to identify optimal CP model parameters under fatigue loading conditions. Utilizing cyclic data from additively manufactured Hastelloy X specimens at 500 degree-F, the BO framework, integrated with a Gaussian process surrogate model, significantly reduces the number of required simulations. A novel objective function is developed to match experimental stress-strain data across different strain amplitudes. Results demonstrate that effective CP model calibration is achieved within 75 iterations, with as few as 50 initial simulations. Sensitivity analysis reveals the influence of CP parameters at various loading points on the stress-strain curve. The results show that the stress-strain response is predominantly controlled by parameters related to yield, with increased influence from backstress parameters during compressive loading. In addition, the effect of introducing twins into the synthetic microstructure on fatigue behavior is studied, and a relationship between microstructural features and the fatigue indicator parameter is established. Results show that larger diameter grains, which exhibit a higher Schmid factor and an average misorientation of approximately 42 degrees +/- 1.67 degree, are identified as probable sites for failure. The proposed optimization framework can be applied to any material system or CP model, streamlining the calibration process and improving the predictive accuracy of such models.
Authors: Shaofei Cai, Bowei Zhang, Zihao Wang, Haowei Lin, Xiaojian Ma, Anji Liu, Yitao Liang
Abstract: Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language instruction) has enabled agents to learn diverse behaviors, these agents often struggle with following instructions. While augmenting the dataset with instruction labels can mitigate this issue, acquiring such high-quality annotations at scale is impractical. To address this issue, we frame the problem as a semi-supervised learning task and introduce GROOT-2, a multimodal instructable agent trained using a novel approach that combines weak supervision with latent variable models. Our method consists of two key components: constrained self-imitating, which utilizes large amounts of unlabeled demonstrations to enable the policy to learn diverse behaviors, and human intention alignment, which uses a smaller set of labeled demonstrations to ensure the latent space reflects human intentions. GROOT-2's effectiveness is validated across four diverse environments, ranging from video games to robotic manipulation, demonstrating its robust multimodal instruction-following capabilities.
Authors: Ofir Nabati, Guy Tennenholtz, ChihWei Hsu, Moonkyung Ryu, Deepak Ramachandran, Yinlam Chow, Xiang Li, Craig Boutilier
Abstract: We address the problem of personalized, interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human raters, we create a novel dataset of sequential preferences, which we leverage, together with large-scale open-source (non-sequential) datasets. We construct user-preference and user-choice models using an EM strategy and identify varying user preference types. We then leverage a large multimodal language model (LMM) and a value-based RL approach to suggest a personalized and diverse slate of prompt expansions to the user. Our Personalized And Sequential Text-to-image Agent (PASTA) extends T2I models with personalized multi-turn capabilities, fostering collaborative co-creation and addressing uncertainty or underspecification in a user's intent. We evaluate PASTA using human raters, showing significant improvement compared to baseline methods. We also release our sequential rater dataset and simulated user-rater interactions to support future research in personalized, multi-turn T2I generation.
Authors: Hongning Ruan, Yulin Shao, Qianqian Yang, Liang Zhao, Zhaoyang Zhang, Dusit Niyato
Abstract: Point clouds have gained prominence in numerous applications due to their ability to accurately depict 3D objects and scenes. However, compressing unstructured, high-precision point cloud data effectively remains a significant challenge. In this paper, we propose NeRC$^{\textbf{3}}$, a novel point cloud compression framework leveraging implicit neural representations to handle both geometry and attributes. Our approach employs two coordinate-based neural networks to implicitly represent a voxelized point cloud: the first determines the occupancy status of a voxel, while the second predicts the attributes of occupied voxels. By feeding voxel coordinates into these networks, the receiver can efficiently reconstructs the original point cloud's geometry and attributes. The neural network parameters are quantized and compressed alongside auxiliary information required for reconstruction. Additionally, we extend our method to dynamic point cloud compression with techniques to reduce temporal redundancy, including a 4D spatial-temporal representation termed 4D-NeRC$^{\textbf{3}}$. Experimental results validate the effectiveness of our approach: for static point clouds, NeRC$^{\textbf{3}}$ outperforms octree-based methods in the latest G-PCC standard. For dynamic point clouds, 4D-NeRC$^{\textbf{3}}$ demonstrates superior geometry compression compared to state-of-the-art G-PCC and V-PCC standards and achieves competitive results for joint geometry and attribute compression.
Authors: SeungBum Ha, Taehwan Lee, Jiyoun Lim, Sung Whan Yoon
Abstract: Federated learning (FL) has recently garnered attention as a data-decentralized training framework that enables the learning of deep models from locally distributed samples while keeping data privacy. Built upon the framework, immense efforts have been made to establish FL benchmarks, which provide rigorous evaluation settings that control data heterogeneity across clients. Prior efforts have mainly focused on handling relatively simple classification tasks, where each sample is annotated with a one-hot label, such as MNIST, CIFAR, LEAF benchmark, etc. However, little attention has been paid to demonstrating an FL benchmark that handles complicated semantics, where each sample encompasses diverse semantic information from multiple labels, such as Panoptic Scene Graph Generation (PSG) with objects, subjects, and relations between them. Because the existing benchmark is designed to distribute data in a narrow view of a single semantic, e.g., a one-hot label, managing the complicated semantic heterogeneity across clients when formalizing FL benchmarks is non-trivial. In this paper, we propose a benchmark process to establish an FL benchmark with controllable semantic heterogeneity across clients: two key steps are i) data clustering with semantics and ii) data distributing via controllable semantic heterogeneity across clients. As a proof of concept, we first construct a federated PSG benchmark, demonstrating the efficacy of the existing PSG methods in an FL setting with controllable semantic heterogeneity of scene graphs. We also present the effectiveness of our benchmark by applying robust federated learning algorithms to data heterogeneity to show increased performance. Our code is available at https://github.com/Seung-B/FL-PSG.
Authors: Ximing Xing, Juncheng Hu, Jing Zhang, Dong Xu, Qian Yu
Abstract: The generation of Scalable Vector Graphics (SVG) assets from textual data remains a significant challenge, largely due to the scarcity of high-quality vector datasets and the limitations in scalable vector representations required for modeling intricate graphic distributions. This work introduces SVGFusion, a Text-to-SVG model capable of scaling to real-world SVG data without reliance on a text-based discrete language model or prolonged SDS optimization. The essence of SVGFusion is to learn a continuous latent space for vector graphics with a popular Text-to-Image framework. Specifically, SVGFusion consists of two modules: a Vector-Pixel Fusion Variational Autoencoder (VP-VAE) and a Vector Space Diffusion Transformer (VS-DiT). VP-VAE takes both the SVGs and corresponding rasterizations as inputs and learns a continuous latent space, whereas VS-DiT learns to generate a latent code within this space based on the text prompt. Based on VP-VAE, a novel rendering sequence modeling strategy is proposed to enable the latent space to embed the knowledge of construction logics in SVGs. This empowers the model to achieve human-like design capabilities in vector graphics, while systematically preventing occlusion in complex graphic compositions. Moreover, our SVGFusion's ability can be continuously improved by leveraging the scalability of the VS-DiT by adding more VS-DiT blocks. A large-scale SVG dataset is collected to evaluate the effectiveness of our proposed method. Extensive experimentation has confirmed the superiority of our SVGFusion over existing SVG generation methods, achieving enhanced quality and generalizability, thereby establishing a novel framework for SVG content creation. Code, model, and data will be released at: \href{https://ximinng.github.io/SVGFusionProject/}{https://ximinng.github.io/SVGFusionProject/}
URLs: https://ximinng.github.io/SVGFusionProject/, https://ximinng.github.io/SVGFusionProject/
Authors: Maxime Noizet (UTC, Heudiasyc), Philippe Xu (ENSTA Paris), Philippe Bonnifait (UTC, Heudiasyc)
Abstract: Detecting road features is a key enabler for autonomous driving and localization. For instance, a reliable detection of poles which are widespread in road environments can improve localization. Modern deep learning-based perception systems need a significant amount of annotated data. Automatic annotation avoids time-consuming and costly manual annotation. Because automatic methods are prone to errors, managing annotation uncertainty is crucial to ensure a proper learning process. Fusing multiple annotation sources on the same dataset can be an efficient way to reduce the errors. This not only improves the quality of annotations, but also improves the learning of perception models. In this paper, we consider the fusion of three automatic annotation methods in images: feature projection from a high accuracy vector map combined with a lidar, image segmentation and lidar segmentation. Our experimental results demonstrate the significant benefits of multi-modal automatic annotation for pole detection through a comparative evaluation on manually annotated images. Finally, the resulting multi-modal fusion is used to fine-tune an object detection model for pole base detection using unlabeled data, showing overall improvements achieved by enhancing network specialization. The dataset is publicly available.
Authors: Jimmy Wu, William Chong, Robert Holmberg, Aaditya Prasad, Yihuai Gao, Oussama Khatib, Shuran Song, Szymon Rusinkiewicz, Jeannette Bohg
Abstract: Exploiting the promise of recent advances in imitation learning for mobile manipulation will require the collection of large numbers of human-guided demonstrations. This paper proposes an open-source design for an inexpensive, robust, and flexible mobile manipulator that can support arbitrary arms, enabling a wide range of real-world household mobile manipulation tasks. Crucially, our design uses powered casters to enable the mobile base to be fully holonomic, able to control all planar degrees of freedom independently and simultaneously. This feature makes the base more maneuverable and simplifies many mobile manipulation tasks, eliminating the kinematic constraints that create complex and time-consuming motions in nonholonomic bases. We equip our robot with an intuitive mobile phone teleoperation interface to enable easy data acquisition for imitation learning. In our experiments, we use this interface to collect data and show that the resulting learned policies can successfully perform a variety of common household mobile manipulation tasks.
Authors: Yihe Zhang, Bryce Turney, Purushottam Sigdel, Xu Yuan, Eric Rappin, Adrian Lago, Sytske Kimball, Li Chen, Paul Darby, Lu Peng, Sercan Aygun, Yazhou Tu, M. Hassan Najafi, Nian-Feng Tzeng
Abstract: Accurate and timely regional weather prediction is vital for sectors dependent on weather-related decisions. Traditional prediction methods, based on atmospheric equations, often struggle with coarse temporal resolutions and inaccuracies. This paper presents a novel machine learning (ML) model, called MiMa (short for Micro-Macro), that integrates both near-surface observational data from Kentucky Mesonet stations (collected every five minutes, known as Micro data) and hourly atmospheric numerical outputs (termed as Macro data) for fine-resolution weather forecasting. The MiMa model employs an encoder-decoder transformer structure, with two encoders for processing multivariate data from both datasets and a decoder for forecasting weather variables over short time horizons. Each instance of the MiMa model, called a modelet, predicts the values of a specific weather parameter at an individual Mesonet station. The approach is extended with Re-MiMa modelets, which are designed to predict weather variables at ungauged locations by training on multivariate data from a few representative stations in a region, tagged with their elevations. Re-MiMa (short for Regional-MiMa) can provide highly accurate predictions across an entire region, even in areas without observational stations. Experimental results show that MiMa significantly outperforms current models, with Re-MiMa offering precise short-term forecasts for ungauged locations, marking a significant advancement in weather forecasting accuracy and applicability.
Authors: Idoko Agbo, Dr Hoda El-Sayed, M. D Kamruzzan Sarker
Abstract: The intersection of technology and mental health has spurred innovative approaches to assessing emotional well-being, particularly through computational techniques applied to audio data analysis. This study explores the application of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models on wavelet extracted features and Mel-frequency Cepstral Coefficients (MFCCs) for emotion detection from spoken speech. Data augmentation techniques, feature extraction, normalization, and model training were conducted to evaluate the models' performance in classifying emotional states. Results indicate that the CNN model achieved a higher accuracy of 61% compared to the LSTM model's accuracy of 56%. Both models demonstrated better performance in predicting specific emotions such as surprise and anger, leveraging distinct audio features like pitch and speed variations. Recommendations include further exploration of advanced data augmentation techniques, combined feature extraction methods, and the integration of linguistic analysis with speech characteristics for improved accuracy in mental health diagnostics. Collaboration for standardized dataset collection and sharing is recommended to foster advancements in affective computing and mental health care interventions.
Authors: Runtao Liu, Chen I Chieh, Jindong Gu, Jipeng Zhang, Renjie Pi, Qifeng Chen, Philip Torr, Ashkan Khakzar, Fabio Pizzati
Abstract: Text-to-image (T2I) models have become widespread, but their limited safety guardrails expose end users to harmful content and potentially allow for model misuse. Current safety measures are typically limited to text-based filtering or concept removal strategies, able to remove just a few concepts from the model's generative capabilities. In this work, we introduce SafetyDPO, a method for safety alignment of T2I models through Direct Preference Optimization (DPO). We enable the application of DPO for safety purposes in T2I models by synthetically generating a dataset of harmful and safe image-text pairs, which we call CoProV2. Using a custom DPO strategy and this dataset, we train safety experts, in the form of low-rank adaptation (LoRA) matrices, able to guide the generation process away from specific safety-related concepts. Then, we merge the experts into a single LoRA using a novel merging strategy for optimal scaling performance. This expert-based approach enables scalability, allowing us to remove 7 times more harmful concepts from T2I models compared to baselines. SafetyDPO consistently outperforms the state-of-the-art on many benchmarks and establishes new practices for safety alignment in T2I networks. Code and data will be shared at https://safetydpo.github.io/.
Authors: Yushu Wu, Zhixing Zhang, Yanyu Li, Yanwu Xu, Anil Kag, Yang Sui, Huseyin Coskun, Ke Ma, Aleksei Lebedev, Ju Hu, Dimitris Metaxas, Yanzhi Wang, Sergey Tulyakov, Jian Ren
Abstract: We have witnessed the unprecedented success of diffusion-based video generation over the past year. Recently proposed models from the community have wielded the power to generate cinematic and high-resolution videos with smooth motions from arbitrary input prompts. However, as a supertask of image generation, video generation models require more computation and are thus hosted mostly on cloud servers, limiting broader adoption among content creators. In this work, we propose a comprehensive acceleration framework to bring the power of the large-scale video diffusion model to the hands of edge users. From the network architecture scope, we initialize from a compact image backbone and search out the design and arrangement of temporal layers to maximize hardware efficiency. In addition, we propose a dedicated adversarial fine-tuning algorithm for our efficient model and reduce the denoising steps to 4. Our model, with only 0.6B parameters, can generate a 5-second video on an iPhone 16 PM within 5 seconds. Compared to server-side models that take minutes on powerful GPUs to generate a single video, we accelerate the generation by magnitudes while delivering on-par quality.
Authors: Oz Amram, Luca Anzalone, Joschka Birk, Darius A. Faroughy, Anna Hallin, Gregor Kasieczka, Michael Kr\"amer, Ian Pang, Humberto Reyes-Gonzalez, David Shih
Abstract: Foundation models are deep learning models pre-trained on large amounts of data which are capable of generalizing to multiple datasets and/or downstream tasks. This work demonstrates how data collected by the CMS experiment at the Large Hadron Collider can be useful in pre-training foundation models for HEP. Specifically, we introduce the AspenOpenJets dataset, consisting of approximately 180M high $p_T$ jets derived from CMS 2016 Open Data. We show how pre-training the OmniJet-$\alpha$ foundation model on AspenOpenJets improves performance on generative tasks with significant domain shift: generating boosted top and QCD jets from the simulated JetClass dataset. In addition to demonstrating the power of pre-training of a jet-based foundation model on actual proton-proton collision data, we provide the ML-ready derived AspenOpenJets dataset for further public use.
Authors: Maria Victoria Carro, Francisca Gauna Selasco, Denise Alejandra Mester, Margarita Gonzales, Mario A. Leiva, Maria Vanina Martinez, Gerardo I. Simari
Abstract: Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of causality, in which people perceive a causal relationship between two variables despite lacking supporting evidence. This cognitive bias has been proposed to underlie many societal problems, including social prejudice, stereotype formation, misinformation, and superstitious thinking. In this research, we investigate whether large language models (LLMs) develop causal illusions, both in real-world and controlled laboratory contexts of causal learning and inference. To this end, we built a dataset of over 2K samples including purely correlational cases, situations with null contingency, and cases where temporal information excludes the possibility of causality by placing the potential effect before the cause. We then prompted the models to make statements or answer causal questions to evaluate their tendencies to infer causation erroneously in these structured settings. Our findings show a strong presence of causal illusion bias in LLMs. Specifically, in open-ended generation tasks involving spurious correlations, the models displayed bias at levels comparable to, or even lower than, those observed in similar studies on human subjects. However, when faced with null-contingency scenarios or temporal cues that negate causal relationships, where it was required to respond on a 0-100 scale, the models exhibited significantly higher bias. These findings suggest that the models have not uniformly, consistently, or reliably internalized the normative principles essential for accurate causal learning.
Authors: Albert Cheu, Debanuj Nayak
Abstract: Many algorithms have been developed to estimate probability distributions subject to differential privacy (DP): such an algorithm takes as input independent samples from a distribution and estimates the density function in a way that is insensitive to any one sample. A recent line of work, initiated by Raskhodnikova et al. (Neurips '21), explores a weaker objective: a differentially private algorithm that approximates a single sample from the distribution. Raskhodnikova et al. studied the sample complexity of DP \emph{single-sampling} i.e., the minimum number of samples needed to perform this task. They showed that the sample complexity of DP single-sampling is less than the sample complexity of DP learning for certain distribution classes. We define two variants of \emph{multi-sampling}, where the goal is to privately approximate $m>1$ samples. This better models the realistic scenario where synthetic data is needed for exploratory data analysis. A baseline solution to \emph{multi-sampling} is to invoke a single-sampling algorithm $m$ times on independently drawn datasets of samples. When the data comes from a finite domain, we improve over the baseline by a factor of $m$ in the sample complexity. When the data comes from a Gaussian, Ghazi et al. (Neurips '23) show that \emph{single-sampling} can be performed under approximate differential privacy; we show it is possible to \emph{single- and multi-sample Gaussians with known covariance subject to pure DP}. Our solution uses a variant of the Laplace mechanism that is of independent interest. We also give sample complexity lower bounds, one for strong multi-sampling of finite distributions and another for weak multi-sampling of bounded-covariance Gaussians.
Authors: Ana Ozaki, Roberto Confalonieri, Ricardo Guimar\~aes, Anders Imenes
Abstract: Decision trees are a popular machine learning method, known for their inherent explainability. In Explainable AI, decision trees can be used as surrogate models for complex black box AI models or as approximations of parts of such models. A key challenge of this approach is determining how accurately the extracted decision tree represents the original model and to what extent it can be trusted as an approximation of their behavior. In this work, we investigate the use of the Probably Approximately Correct (PAC) framework to provide a theoretical guarantee of fidelity for decision trees extracted from AI models. Based on theoretical results from the PAC framework, we adapt a decision tree algorithm to ensure a PAC guarantee under certain conditions. We focus on binary classification and conduct experiments where we extract decision trees from BERT-based language models with PAC guarantees. Our results indicate occupational gender bias in these models.
Authors: Jinnan Guo, Kapil Vaswani, Andrew Paverd, Peter Pietzuch
Abstract: In federated learning (FL), data providers jointly train a model without disclosing their training data. Despite its privacy benefits, a malicious data provider can simply deviate from the correct training protocol without being detected, thus attacking the trained model. While current solutions have explored the use of trusted execution environment (TEEs) to combat such attacks, there is a mismatch with the security needs of FL: TEEs offer confidentiality guarantees, which are unnecessary for FL and make them vulnerable to side-channel attacks, and focus on coarse-grained attestation, which does not capture the execution of FL training. We describe ExclaveFL, an FL platform that achieves end-to-end transparency and integrity for detecting attacks. ExclaveFL achieves this by employing a new hardware security abstraction, exclaves, which focus on integrity-only guarantees. ExclaveFL uses exclaves to protect the execution of FL tasks, while generating signed statements containing fine-grained, hardware-based attestation reports of task execution at runtime. ExclaveFL then enables auditing using these statements to construct an attested dataflow graph and then check that the FL training jobs satisfies claims, such as the absence of attacks. Our experiments show that ExclaveFL introduces a less than 9% overhead while detecting a wide-range of attacks.
Authors: Mohammad Reza Samsami, Mats Leon Richter, Juan Rodriguez, Megh Thakkar, Sarath Chandar, Maxime Gasse
Abstract: Large language models must balance their weight-encoded knowledge with in-context information from prompts to generate accurate responses. This paper investigates this interplay by analyzing how models of varying capacities within the same family handle intentionally misleading in-context information. Our experiments demonstrate that larger models exhibit higher resilience to deceptive prompts, showcasing an advanced ability to interpret and integrate prompt information with their internal knowledge. Furthermore, we find that larger models outperform smaller ones in following legitimate instructions, indicating that their resilience is not due to disregarding in-context information. We also show that this phenomenon is likely not a result of memorization but stems from the models' ability to better leverage implicit task-relevant information from the prompt alongside their internally stored knowledge.
Authors: Shaohan Chen, Zheyan Liu, Huili Zheng, Qimin Zhang, Yiru Gong
Abstract: Cardiovascular disease (CVD) persists as a primary cause of death on a global scale, which requires more effective and timely detection methods. Traditional supervised learning approaches for CVD detection rely heavily on large-labeled datasets, which are often difficult to obtain. This paper employs semi-supervised learning models to boost efficiency and accuracy of CVD detection when there are few labeled samples. By leveraging both labeled and vast amounts of unlabeled data, our approach demonstrates improvements in prediction performance, while reducing the dependency on labeled data. Experimental results in a publicly available dataset show that semi-supervised models outperform traditional supervised learning techniques, providing an intriguing approach for the initial identification of cardiovascular disease within clinical environments.
Authors: Yiwen Gu, Mahir Patel, Margrit Betke
Abstract: In this paper, we present a contrastive learning based framework, ExeChecker, for the interpretation of rehabilitation exercises. Our work builds upon state-of-the-art advances in the area of human pose estimation, graph-attention neural networks, and transformer interpretablity. The downstream task is to assist rehabilitation by providing informative feedback to users while they are performing prescribed exercises. We utilize a contrastive learning strategy during training. Given a tuple of correctly and incorrectly executed exercises, our model is able to identify and highlight those joints that are involved in an incorrect movement and thus require the user's attention. We collected an in-house dataset, ExeCheck, with paired recordings of both correct and incorrect execution of exercises. In our experiments, we tested our method on this dataset as well as the UI-PRMD dataset and found ExeCheck outperformed the baseline method using pairwise sequence alignment in identifying joints of physical relevance in rehabilitation exercises.
Authors: Sara Ghazanfari, Siddharth Garg, Nicolas Flammarion, Prashanth Krishnamurthy, Farshad Khorrami, Francesco Croce
Abstract: Human perception of similarity across uni- and multimodal inputs is highly complex, making it challenging to develop automated metrics that accurately mimic it. General purpose vision-language models, such as CLIP and large multi-modal models (LMMs), can be applied as zero-shot perceptual metrics, and several recent works have developed models specialized in narrow perceptual tasks. However, the extent to which existing perceptual metrics align with human perception remains unclear. To investigate this question, we introduce UniSim-Bench, a benchmark encompassing 7 multi-modal perceptual similarity tasks, with a total of 25 datasets. Our evaluation reveals that while general-purpose models perform reasonably well on average, they often lag behind specialized models on individual tasks. Conversely, metrics fine-tuned for specific tasks fail to generalize well to unseen, though related, tasks. As a first step towards a unified multi-task perceptual similarity metric, we fine-tune both encoder-based and generative vision-language models on a subset of the UniSim-Bench tasks. This approach yields the highest average performance, and in some cases, even surpasses taskspecific models. Nevertheless, these models still struggle with generalization to unseen tasks, highlighting the ongoing challenge of learning a robust, unified perceptual similarity metric capable of capturing the human notion of similarity. The code and models are available at https://github.com/SaraGhazanfari/UniSim.
Authors: Borja Molina Coronado
Abstract: Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many defenses have been proposed, they often fail short when facing heterogeneous data distributions among participating clients. In this paper, we propose a novel defense mechanism for federated learning systems designed to mitigate backdoor attacks on the clients-side. Our approach leverages adversarial learning techniques and model patching to neutralize the impact of backdoor attacks. Through extensive experiments on the MNIST and Fashion-MNIST datasets, we demonstrate that our defense effectively reduces backdoor accuracy, outperforming existing state-of-the-art defenses, such as LFighter, FLAME, and RoseAgg, in i.i.d. and non-i.i.d. scenarios, while maintaining competitive or superior accuracy on clean data.
Authors: Julian D. Santamaria, Claudia Isaza, Jhony H. Giraldo
Abstract: Foundation Models (FMs) have been successful in various computer vision tasks like image classification, object detection and image segmentation. However, these tasks remain challenging when these models are tested on datasets with different distributions from the training dataset, a problem known as domain shift. This is especially problematic for recognizing animal species in camera-trap images where we have variability in factors like lighting, camouflage and occlusions. In this paper, we propose the Camera Trap Language-guided Contrastive Learning (CATALOG) model to address these issues. Our approach combines multiple FMs to extract visual and textual features from camera-trap data and uses a contrastive loss function to train the model. We evaluate CATALOG on two benchmark datasets and show that it outperforms previous state-of-the-art methods in camera-trap image recognition, especially when the training and testing data have different animal species or come from different geographical areas. Our approach demonstrates the potential of using FMs in combination with multi-modal fusion and contrastive learning for addressing domain shifts in camera-trap image recognition. The code of CATALOG is publicly available at https://github.com/Julian075/CATALOG.
Authors: Mukesh Karunanethy, Raghunathan Rengaswamy, Mahesh V Panchagnula
Abstract: We test the hypothesis that the microscopic temporal structure of near-field turbulence downstream of a sudden contraction contains geometry-identifiable information pertaining to the shape of the upstream obstruction. We measure a set of spatially sparse velocity time-series data downstream of differently-shaped orifices. We then train random forest multiclass classifier models on a vector of invariants derived from this time-series. We test the above hypothesis with 25 somewhat similar orifice shapes to push the model to its extreme limits. Remarkably, the algorithm was able to identify the orifice shape with 100% accuracy and 100% precision. This outcome is enabled by the uniqueness in the downstream temporal evolution of turbulence structures in the flow past orifices, combined with the random forests' ability to learn subtle yet discerning features in the turbulence microstructure. We are also able to explain the underlying flow physics that enables such classification by listing the invariant measures in the order of increasing information entropy. We show that the temporal autocorrelation coefficients of the time-series are most sensitive to orifice shape and are therefore informative. The ability to identify changes in system geometry without the need for physical disassembly offers tremendous potential for flow control and system identification. Furthermore, the proposed approach could potentially have significant applications in other unrelated fields as well, by deploying the core methodology of training random forest classifiers on vectors of invariant measures obtained from time-series data.
Authors: Hanti Lin
Abstract: The debate between scientific realism and anti-realism remains at a stalemate, with reconciliation seeming hopeless. Yet, important work remains: to seek a common ground, even if only to uncover deeper points of disagreement. I develop the idea that everyone values some truths, and use it to benefit both sides of the debate. More specifically, many anti-realists, such as instrumentalists, have yet to seriously engage with Sober's call to justify their preferred version of Ockham's razor through a positive epistemology. Meanwhile, realists face a similar challenge: providing a non-circular explanation of how their version of Ockham's razor connects to truth. Drawing insights from fields that study scientific inference -- statistics and machine learning -- I propose a common ground that addresses these challenges for both sides. This common ground also isolates a distinctively epistemic root of the irreconcilability in the realism debate.
Authors: Xue Wu, Kostas Tsioutsiouliklis
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, they often struggle with complex reasoning tasks and are prone to hallucination. Recent research has shown promising results in leveraging knowledge graphs (KGs) to enhance LLM performance. KGs provide a structured representation of entities and their relationships, offering a rich source of information that can enhance the reasoning capabilities of LLMs. For this work, we have developed different techniques that tightly integrate KG structures and semantics into LLM representations. Our results show that we are able to significantly improve the performance of LLMs in complex reasoning scenarios, and ground the reasoning process with KGs. We are the first to represent KGs with programming language and fine-tune pretrained LLMs with KGs. This integration facilitates more accurate and interpretable reasoning processes, paving the way for more advanced reasoning capabilities of LLMs.
Authors: Chenyue Xie, An-Kang Gao, Xiyun Lu
Abstract: Oceanic eddy kinetic energy (EKE) is a key quantity for measuring the intensity of mesoscale eddies and for parameterizing eddy effects in ocean climate models. Three decades of satellite altimetry observations allow a global assessment of sea surface information. However, the subsurface EKE with spatial filter has not been systematically studied due to the sparseness of subsurface observational data. The subsurface EKE can be inferred both theoretically and numerically from sea surface observations but is limited by the issue of decreasing correlation with sea surface variables as depth increases. In this work, inspired by the Taylor-series expansion of subsurface EKE, a multiple-input neural network approach is proposed to reconstruct the subsurface monthly mean EKE from sea surface variables and subsurface climatological variables (e.g., horizontal filtered velocity gradients). Four neural networks are trained on a high-resolution global ocean reanalysis dataset, namely, surface-input fully connected neural network model (FCNN), surface-input Residual neural network model (ResNet), multiple-input fully connected neural network model (MI-FCNN), and multiple-input residual neural network model (MI-ResNet). The proposed MI-FCNN and MI-ResNet models integrate the surface input variables and the vertical profiles of subsurface variables. The MI-ResNet model outperforms the FCNN, ResNet, and MI-FCNN models, and traditional physics-based models in both regional and global reconstruction of subsurface EKE in the upper 2000 m. In addition, the MI-ResNet model performs well for both regional and global observational data based on transfer learning. These findings reveal the potential of the MI-ResNet model for efficient and accurate reconstruction of subsurface oceanic variables.
Authors: Jinzong Dong, Zhaohui Jiang, Dong Pan, Haoyang Yu
Abstract: Confidence calibration of classification models is a technique to estimate the true posterior probability of the predicted class, which is critical for ensuring reliable decision-making in practical applications. Existing confidence calibration methods mostly use statistical techniques to estimate the calibration curve from data or fit a user-defined calibration function, but often overlook fully mining and utilizing the prior distribution behind the calibration curve. However, a well-informed prior distribution can provide valuable insights beyond the empirical data under the limited data or low-density regions of confidence scores. To fill this gap, this paper proposes a new method that integrates the prior distribution behind the calibration curve with empirical data to estimate a continuous calibration curve, which is realized by modeling the sampling process of calibration data as a binomial process and maximizing the likelihood function of the binomial process. We prove that the calibration curve estimating method is Lipschitz continuous with respect to data distribution and requires a sample size of $3/B$ of that required for histogram binning, where $B$ represents the number of bins. Also, a new calibration metric ($TCE_{bpm}$), which leverages the estimated calibration curve to estimate the true calibration error (TCE), is designed. $TCE_{bpm}$ is proven to be a consistent calibration measure. Furthermore, realistic calibration datasets can be generated by the binomial process modeling from a preset true calibration curve and confidence score distribution, which can serve as a benchmark to measure and compare the discrepancy between existing calibration metrics and the true calibration error. The effectiveness of our calibration method and metric are verified in real-world and simulated data.
Authors: Kaichen Xu, Qilong Wu, Yan Lu, Yinan Zheng, Wenlin Li, Xingjie Tang, Jun Wang, Xiaobo Sun
Abstract: The detection of anomalous tissue regions (ATRs) within affected tissues is crucial in clinical diagnosis and pathological studies. Conventional automated ATR detection methods, primarily based on histology images alone, falter in cases where ATRs and normal tissues have subtle visual differences. The recent spatial transcriptomics (ST) technology profiles gene expressions across tissue regions, offering a molecular perspective for detecting ATRs. However, there is a dearth of ATR detection methods that effectively harness complementary information from both histology images and ST. To address this gap, we propose MEATRD, a novel ATR detection method that integrates histology image and ST data. MEATRD is trained to reconstruct image patches and gene expression profiles of normal tissue spots (inliers) from their multimodal embeddings, followed by learning a one-class classification AD model based on latent multimodal reconstruction errors. This strategy harmonizes the strengths of reconstruction-based and one-class classification approaches. At the heart of MEATRD is an innovative masked graph dual-attention transformer (MGDAT) network, which not only facilitates cross-modality and cross-node information sharing but also addresses the model over-generalization issue commonly seen in reconstruction-based AD methods. Additionally, we demonstrate that modality-specific, task-relevant information is collated and condensed in multimodal bottleneck encoding generated in MGDAT, marking the first theoretical analysis of the informational properties of multimodal bottleneck encoding. Extensive evaluations across eight real ST datasets reveal MEATRD's superior performance in ATR detection, surpassing various state-of-the-art AD methods. Remarkably, MEATRD also proves adept at discerning ATRs that only show slight visual deviations from normal tissues.
Authors: Joshua Ho, Benjamin Ryan Roberts, Shuo Han, Haichen Wang
Abstract: We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes. The model is pretrained to learn a general and robust representation of collision data using challenging multiclass and multilabel classification tasks. Its performance is evaluated across five event classification tasks, which include both physics processes used during pretraining and new processes not encountered during pretraining. Fine-tuning the pretrained model significantly improves classification performance, particularly in scenarios with limited training data, demonstrating gains in both accuracy and computational efficiency. To investigate the underlying mechanisms behind these performance improvements, we employ a representational similarity evaluation framework based on Centered Kernel Alignment. This analysis reveals notable differences in the learned representations of fine-tuned pretrained models compared to baseline models trained from scratch.
Authors: Chi Zhang, Jiajun Song, Siyu Li, Yitao Liang, Yuxi Ma, Wei Wang, Yixin Zhu, Song-Chun Zhu
Abstract: Mathematics olympiads are prestigious competitions, with problem proposing and solving highly honored. Building artificial intelligence that proposes and solves olympiads presents an unresolved challenge in automated theorem discovery and proving, especially in geometry for its combination of numerical and spatial elements. We introduce TongGeometry, a Euclidean geometry system supporting tree-search-based guided problem proposing and solving. The efficient geometry system establishes the most extensive repository of geometry theorems to date: within the same computational budget as the existing state-of-the-art, TongGeometry discovers 6.7 billion geometry theorems requiring auxiliary constructions, including 4.1 billion exhibiting geometric symmetry. Among them, 10 theorems were proposed to regional mathematical olympiads with 3 of TongGeometry's proposals selected in real competitions, earning spots in a national team qualifying exam or a top civil olympiad in China and the US. Guided by fine-tuned large language models, TongGeometry solved all International Mathematical Olympiad geometry in IMO-AG-30, outperforming gold medalists for the first time. It also surpasses the existing state-of-the-art across a broader spectrum of olympiad-level problems. The full capabilities of the system can be utilized on a consumer-grade machine, making the model more accessible and fostering widespread democratization of its use. By analogy, unlike existing systems that merely solve problems like students, TongGeometry acts like a geometry coach, discovering, presenting, and proving theorems.
Authors: Zhiying Wang, Gang Sun, Yuhui Wang, Hongfang Yu, Dusit Niyato
Abstract: The Space-Air-Ground Integrated Network (SAGIN) framework is a crucial foundation for future networks, where satellites and aerial nodes assist in computational task offloading. The low-altitude economy, leveraging the flexibility and multifunctionality of Unmanned Aerial Vehicles (UAVs) in SAGIN, holds significant potential for development in areas such as communication and sensing. However, effective coordination is needed to streamline information exchange and enable efficient system resource allocation. In this paper, we propose a Clustering-based Multi-agent Deep Deterministic Policy Gradient (CMADDPG) algorithm to address the multi-UAV cooperative task scheduling challenges in SAGIN. The CMADDPG algorithm leverages dynamic UAV clustering to partition UAVs into clusters, each managed by a Cluster Head (CH) UAV, facilitating a distributed-centralized control approach. Within each cluster, UAVs delegate offloading decisions to the CH UAV, reducing intra-cluster communication costs and decision conflicts, thereby enhancing task scheduling efficiency. Additionally, by employing a multi-agent reinforcement learning framework, the algorithm leverages the extensive coverage of satellites to achieve centralized training and distributed execution of multi-agent tasks, while maximizing overall system profit through optimized task offloading decision-making. Simulation results reveal that the CMADDPG algorithm effectively optimizes resource allocation, minimizes queue delays, maintains balanced load distribution, and surpasses existing methods by achieving at least a 25\% improvement in system profit, showcasing its robustness and adaptability across diverse scenarios.
Authors: Tao Wu, Chuhao Zhou, Yen Heng Wong, Lin Gu, Jianfei Yang
Abstract: The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development of Embodied Question Answering (EQA), enhancing agents' abilities in language understanding and reasoning within complex and realistic scenarios. However, EQA in real-world scenarios remains challenging, as human-posed questions often contain noise that can interfere with an agent's exploration and response, bringing challenges especially for language beginners and non-expert users. To address this, we introduce a NoisyEQA benchmark designed to evaluate an agent's ability to recognize and correct noisy questions. This benchmark introduces four common types of noise found in real-world applications: Latent Hallucination Noise, Memory Noise, Perception Noise, and Semantic Noise generated through an automated dataset creation framework. Additionally, we also propose a 'Self-Correction' prompting mechanism and a new evaluation metric to enhance and measure both noise detection capability and answer quality. Our comprehensive evaluation reveals that current EQA agents often struggle to detect noise in questions, leading to responses that frequently contain erroneous information. Through our Self-Correct Prompting mechanism, we can effectively improve the accuracy of agent answers.
Authors: Yu Chen, Shuai Zheng, Nianyi Wang, Menglong Jin, Yan Chang
Abstract: Simulating fuel sloshing within aircraft tanks during flight is crucial for aircraft safety research. Traditional methods based on Navier-Stokes equations are computationally expensive. In this paper, we treat fluid motion as point cloud transformation and propose the first neural network method specifically designed for simulating fuel sloshing in aircraft. This model is also the deep learning model that is the first to be capable of stably modeling fluid particle dynamics in such complex scenarios. Our triangle feature fusion design achieves an optimal balance among fluid dynamics modeling, momentum conservation constraints, and global stability control. Additionally, we constructed the Fueltank dataset, the first dataset for aircraft fuel surface sloshing. It comprises 320,000 frames across four typical tank types and covers a wide range of flight maneuvers, including multi-directional rotations. We conducted comprehensive experiments on both our dataset and the take-off scenario of the aircraft. Compared to existing neural network-based fluid simulation algorithms, we significantly enhanced accuracy while maintaining high computational speed. Compared to traditional SPH methods, our speed improved approximately 10 times. Furthermore, compared to traditional fluid simulation software such as Flow3D, our computation speed increased by more than 300 times.
Authors: Nethmi S. Hewawiththi, M. Mahesha Viduranga, Vanodhya G. Warnasooriya, Tharindu Fernando, Himal A. Suraweera, Sridha Sridharan, Clinton Fookes
Abstract: Unmanned aerial vehicle-assisted disaster recovery missions have been promoted recently due to their reliability and flexibility. Machine learning algorithms running onboard significantly enhance the utility of UAVs by enabling real-time data processing and efficient decision-making, despite being in a resource-constrained environment. However, the limited bandwidth and intermittent connectivity make transmitting the outputs to ground stations challenging. This paper proposes a novel semantic extractor that can be adopted into any machine learning downstream task for identifying the critical data required for decision-making. The semantic extractor can be executed onboard which results in a reduction of data that needs to be transmitted to ground stations. We test the proposed architecture together with the semantic extractor on two publicly available datasets, FloodNet and RescueNet, for two downstream tasks: visual question answering and disaster damage level classification. Our experimental results demonstrate the proposed method maintains high accuracy across different downstream tasks while significantly reducing the volume of transmitted data, highlighting the effectiveness of our semantic extractor in capturing task-specific salient information.
Authors: Sertac Kilickaya, Mete Ahishali, Cansu Celebioglu, Fahad Sohrab, Levent Eren, Turker Ince, Murat Askar, Moncef Gabbouj
Abstract: The frequent breakdowns and malfunctions of industrial equipment have driven increasing interest in utilizing cost-effective and easy-to-deploy sensors, such as microphones, for effective condition monitoring of machinery. Microphones offer a low-cost alternative to widely used condition monitoring sensors with their high bandwidth and capability to detect subtle anomalies that other sensors might have less sensitivity. In this study, we investigate malfunctioning industrial machines to evaluate and compare anomaly detection performance across different machine types and fault conditions. Log-Mel spectrograms of machinery sound are used as input, and the performance is evaluated using the area under the curve (AUC) score for two different methods: baseline dense autoencoder (AE) and one-class deep Support Vector Data Description (deep SVDD) with different subspace dimensions. Our results over the MIMII sound dataset demonstrate that the deep SVDD method with a subspace dimension of 2 provides superior anomaly detection performance, achieving average AUC scores of 0.84, 0.80, and 0.69 for 6 dB, 0 dB, and -6 dB signal-to-noise ratios (SNRs), respectively, compared to 0.82, 0.72, and 0.64 for the baseline model. Moreover, deep SVDD requires 7.4 times fewer trainable parameters than the baseline dense AE, emphasizing its advantage in both effectiveness and computational efficiency.
Authors: Kefan Su, Yusen Huo, Zhilin Zhang, Shuai Dou, Chuan Yu, Jian Xu, Zongqing Lu, Bo Zheng
Abstract: Decision-making in large-scale games is an essential research area in artificial intelligence (AI) with significant real-world impact. However, the limited access to realistic large-scale game environments has hindered research progress in this area. In this paper, we present \textbf{AuctionNet}, a benchmark for bid decision-making in large-scale ad auctions derived from a real-world online advertising platform. AuctionNet is composed of three parts: an ad auction environment, a pre-generated dataset based on the environment, and performance evaluations of several baseline bid decision-making algorithms. More specifically, the environment effectively replicates the integrity and complexity of real-world ad auctions through the interaction of several modules: the ad opportunity generation module employs deep generative models to bridge the gap between simulated and real-world data while mitigating the risk of sensitive data exposure; the bidding module implements diverse auto-bidding agents trained with different decision-making algorithms; and the auction module is anchored in the classic Generalized Second Price (GSP) auction but also allows for customization of auction mechanisms as needed. To facilitate research and provide insights into the game environment, we have also pre-generated a substantial dataset based on the environment. The dataset contains trajectories involving 48 diverse agents competing with each other, totaling over 500 million records and occupying 80GB of storage. Performance evaluations of baseline algorithms such as linear programming, reinforcement learning, and generative models for bid decision-making are also presented as part of AuctionNet. We note that AuctionNet is applicable not only to research on bid decision-making algorithms in ad auctions but also to the general area of decision-making in large-scale games.
Authors: Ru Geng, Yixian Gao, Jian Zu, Hong-Kun Zhang
Abstract: A deep understanding of the intricate interactions between particles within a system is a key approach to revealing the essential characteristics of the system, whether it is an in-depth analysis of molecular properties in the field of chemistry or the design of new materials for specific performance requirements in materials science. To this end, we propose Graph Attention Hamiltonian Neural Network (GAHN), a neural network method that can understand the underlying structure of lattice Hamiltonian systems solely through the dynamic trajectories of particles. We can determine which particles in the system interact with each other, the proportion of interactions between different particles, and whether the potential energy of interactions between particles exhibits even symmetry or not. The obtained structure helps the neural network model to continue predicting the trajectory of the system and further understand the dynamic properties of the system. In addition to understanding the underlying structure of the system, it can be used for detecting lattice structural abnormalities, such as link defects, abnormal interactions, etc. These insights benefit system optimization, design, and detection of aging or damage. Moreover, this approach can integrate other components to deduce the link structure needed for specific parts, showcasing its scalability and potential. We tested it on a challenging molecular dynamics dataset, and the results proved its ability to accurately infer molecular bond connectivity, highlighting its scientific research potential.
Authors: Yixuan Liang, Yuncong Liu, Boyu Zhang, Christina Dan Wang, Hongyang Yang
Abstract: Financial sentiment analysis is crucial for understanding the influence of news on stock prices. Recently, large language models (LLMs) have been widely adopted for this purpose due to their advanced text analysis capabilities. However, these models often only consider the news content itself, ignoring its dissemination, which hampers accurate prediction of short-term stock movements. Additionally, current methods often lack sufficient contextual data and explicit instructions in their prompts, limiting LLMs' ability to interpret news. In this paper, we propose a data-driven approach that enhances LLM-powered sentiment-based stock movement predictions by incorporating news dissemination breadth, contextual data, and explicit instructions. We cluster recent company-related news to assess its reach and influence, enriching prompts with more specific data and precise instructions. This data is used to construct an instruction tuning dataset to fine-tune an LLM for predicting short-term stock price movements. Our experimental results show that our approach improves prediction accuracy by 8\% compared to existing methods.
Authors: Wang Zhen, Dong Yunyun
Abstract: Diffusion generative models are currently the most popular generative models. However, their underlying modeling process is quite complex, and starting directly with the seminal paper Denoising Diffusion Probability Model (DDPM) can be challenging. This paper aims to assist readers in building a foundational understanding of generative models by tracing the evolution from VAEs to DDPM through detailed mathematical derivations and a problem-oriented analytical approach. It also explores the core ideas and improvement strategies of current mainstream methodologies, providing guidance for undergraduate and graduate students interested in learning about diffusion models.
Authors: Zeljko Kraljevic, Joshua Au Yeung, Daniel Bean, James Teo, Richard J. Dobson
Abstract: Foresight 2 (FS2) is a large language model fine-tuned on hospital data for modelling patient timelines (GitHub 'removed for anon'). It can understand patients' clinical notes and predict SNOMED codes for a wide range of biomedical use cases, including diagnosis suggestions, risk forecasting, and procedure and medication recommendations. FS2 is trained on the free text portion of the MIMIC-III dataset, firstly through extracting biomedical concepts and then creating contextualised patient timelines, upon which the model is then fine-tuned. The results show significant improvement over the previous state-of-the-art for the next new biomedical concept prediction (P/R - 0.73/0.66 vs 0.52/0.32) and a similar improvement specifically for the next new disorder prediction (P/R - 0.69/0.62 vs 0.46/0.25). Finally, on the task of risk forecast, we compare our model to GPT-4-turbo (and a range of open-source biomedical LLMs) and show that FS2 performs significantly better on such tasks (P@5 - 0.90 vs 0.65). This highlights the need to incorporate hospital data into LLMs and shows that small models outperform much larger ones when fine-tuned on high-quality, specialised data.
Authors: Haoran Ding, No\'emie Jaquier, Jan Peters, Leonel Rozo
Abstract: Diffusion-based visuomotor policies excel at learning complex robotic tasks by effectively combining visual data with high-dimensional, multi-modal action distributions. However, diffusion models often suffer from slow inference due to costly denoising processes or require complex sequential training arising from recent distilling approaches. This paper introduces Riemannian Flow Matching Policy (RFMP), a model that inherits the easy training and fast inference capabilities of flow matching (FM). Moreover, RFMP inherently incorporates geometric constraints commonly found in realistic robotic applications, as the robot state resides on a Riemannian manifold. To enhance the robustness of RFMP, we propose Stable RFMP (SRFMP), which leverages LaSalle's invariance principle to equip the dynamics of FM with stability to the support of a target Riemannian distribution. Rigorous evaluation on eight simulated and real-world tasks show that RFMP successfully learns and synthesizes complex sensorimotor policies on Euclidean and Riemannian spaces with efficient training and inference phases, outperforming Diffusion Policies while remaining competitive with Consistency Policies.
Authors: Seemanta Bhattacharjee, MD. Muhtasim Fuad, A. K. M. Fakhrul Hossain
Abstract: Quantum Support Vector Machine is a kernel-based approach to classification problems. We study the applicability of quantum kernels to financial data, specifically our self-curated Dhaka Stock Exchange (DSEx) Broad Index dataset. To the best of our knowledge, this is the very first systematic research work on this dataset on the application of quantum kernel. We report empirical quantum advantage in our work, using several quantum kernels and proposing the best one for this dataset while verifying the Phase Space Terrain Ruggedness Index metric. We estimate the resources needed to carry out these investigations on a larger scale for future practitioners.
Authors: Canberk Ekmekci, Tekin Bicer, Zichao Wendy Di, Junjing Deng, Mujdat Cetin
Abstract: Ptychography is a scanning coherent diffractive imaging technique that enables imaging nanometer-scale features in extended samples. One main challenge is that widely used iterative image reconstruction methods often require significant amount of overlap between adjacent scan locations, leading to large data volumes and prolonged acquisition times. To address this key limitation, this paper proposes a Bayesian inversion method for ptychography that performs effectively even with less overlap between neighboring scan locations. Furthermore, the proposed method can quantify the inherent uncertainty on the ptychographic object, which is created by the ill-posed nature of the ptychographic inverse problem. At a high level, the proposed method first utilizes a deep generative model to learn the prior distribution of the object and then generates samples from the posterior distribution of the object by using a Markov Chain Monte Carlo algorithm. Our results from simulated ptychography experiments show that the proposed framework can consistently outperform a widely used iterative reconstruction algorithm in cases of reduced overlap. Moreover, the proposed framework can provide uncertainty estimates that closely correlate with the true error, which is not available in practice. The project website is available here.
Authors: Lichen Bai, Shitong Shao, Zikai Zhou, Zipeng Qi, Zhiqiang Xu, Haoyi Xiong, Zeke Xie
Abstract: Diffusion models, the most popular generative paradigm so far, can inject conditional information into the generation path to guide the latent towards desired directions. However, existing text-to-image diffusion models often fail to maintain high image quality and high prompt-image alignment for those challenging prompts. To mitigate this issue and enhance existing pretrained diffusion models, we mainly made three contributions in this paper. First, we theoretically and empirically demonstrate that the conditional guidance gap between the denoising and inversion processes captures prompt-related semantic information. Second, motivated by theoretical analysis, we derive Zigzag Diffusion Sampling (Z-Sampling), a novel sampling method that leverages the guidance gap to accumulate semantic information step-by-step throughout the entire generation process, leading to improved sampling results. Moreover, as a plug-and-play method, Z-Sampling can be generally applied to various diffusion models (e.g., accelerated ones and Transformer-based ones) with very limited coding and computational costs. Third, our extensive experiments demonstrate that Z-Sampling can generally and significantly enhance generation quality across various benchmark datasets, diffusion models, and performance evaluation metrics. For example, Z-Sampling can even make DreamShaper achieve the HPSv2 winning rate higher than 94% over the original results. Moreover, Z-Sampling can further enhance existing diffusion models combined with other orthogonal methods, including Diffusion-DPO.
Authors: Anton Alexandrov, Veselin Raychev, Dimitar I. Dimitrov, Ce Zhang, Martin Vechev, Kristina Toutanova
Abstract: We present BgGPT-Gemma-2-27B-Instruct and BgGPT-Gemma-2-9B-Instruct: continually pretrained and fine-tuned versions of Google's Gemma-2 models, specifically optimized for Bulgarian language understanding and generation. Leveraging Gemma-2's multilingual capabilities and over 100 billion tokens of Bulgarian and English text data, our models demonstrate strong performance in Bulgarian language tasks, setting a new standard for language-specific AI models. Our approach maintains the robust capabilities of the original Gemma-2 models, ensuring that the English language performance remains intact. To preserve the base model capabilities, we incorporate continual learning strategies based on recent Branch-and-Merge techniques as well as thorough curation and selection of training data. We provide detailed insights into our methodology, including the release of model weights with a commercial-friendly license, enabling broader adoption by researchers, companies, and hobbyists. Further, we establish a comprehensive set of benchmarks based on non-public educational data sources to evaluate models on Bulgarian language tasks as well as safety and chat capabilities. Our findings demonstrate the effectiveness of fine-tuning state-of-the-art models like Gemma 2 to enhance language-specific AI applications while maintaining cross-lingual capabilities.
Authors: Qilong Wu, Xiaoneng Xiang, Hejia Huang, Xuan Wang, Yeo Wei Jie, Ranjan Satapathy, Ricardo Shirota Filho, Bharadwaj Veeravalli
Abstract: The rapid growth of the financial sector and the rising focus on Environmental, Social, and Governance (ESG) considerations highlight the need for advanced NLP tools. However, open-source LLMs proficient in both finance and ESG domains remain scarce. To address this gap, we introduce SusGen-30K, a category-balanced dataset comprising seven financial NLP tasks and ESG report generation, and propose TCFD-Bench, a benchmark for evaluating sustainability report generation. Leveraging this dataset, we developed SusGen-GPT, a suite of models achieving state-of-the-art performance across six adapted and two off-the-shelf tasks, trailing GPT-4 by only 2% despite using 7-8B parameters compared to GPT-4's 1,700B. Based on this, we propose the SusGen system, integrated with Retrieval-Augmented Generation (RAG), to assist in sustainability report generation. This work demonstrates the efficiency of our approach, advancing research in finance and ESG.
Authors: Minjae Kwon, Ingy ElSayed-Aly, Lu Feng
Abstract: There is a surge of interest in using formal languages such as Linear Temporal Logic (LTL) and finite automata to precisely and succinctly specify complex tasks and derive reward functions for reinforcement learning (RL) in robotic applications. However, existing methods often assign sparse rewards (e.g., giving a reward of 1 only if a task is completed and 0 otherwise), necessitating extensive exploration to converge to a high-quality policy. To address this limitation, we propose a suite of reward functions that incentivize an RL agent to make measurable progress on tasks specified by LTL formulas and develop an adaptive reward shaping approach that dynamically updates these reward functions during the learning process. Experimental results on a range of RL-based robotic tasks demonstrate that the proposed approach is compatible with various RL algorithms and consistently outperforms baselines, achieving earlier convergence to better policies with higher task success rates and returns.
Authors: Berke Doga Basaran, Paul M. Matthews, Wenjia Bai
Abstract: Assessing lesions and tracking their progression over time in brain magnetic resonance (MR) images is essential for diagnosing and monitoring multiple sclerosis (MS). Machine learning models have shown promise in automating the segmentation of MS lesions. However, training these models typically requires large, well-annotated datasets. Unfortunately, MS imaging datasets are often limited in size, spread across multiple hospital sites, and exhibit different formats (such as cross-sectional or longitudinal) and annotation styles. This data diversity presents a significant obstacle to developing a unified model for MS lesion segmentation. To address this issue, we introduce SegHeD+, a novel segmentation model that can handle multiple datasets and tasks, accommodating heterogeneous input data and performing segmentation for all lesions, new lesions, and vanishing lesions. We integrate domain knowledge about MS lesions by incorporating longitudinal, anatomical, and volumetric constraints into the segmentation model. Additionally, we perform lesion-level data augmentation to enlarge the training set and further improve segmentation performance. SegHeD+ is evaluated on five MS datasets and demonstrates superior performance in segmenting all, new, and vanishing lesions, surpassing several state-of-the-art methods in the field.
Authors: Justin Le
Abstract: We introduce the diffusion model as a method to generate new samples. Generative models have been recently adopted for tasks such as art generation (Stable Diffusion, Dall-E) and text generation (ChatGPT). Diffusion models in particular apply noise to sample data and then "reverse" this noising process to generate new samples. We will formally define the noising and denoising processes, then introduce algorithms to train and generate with a diffusion model. Finally, we will explore a potential application of diffusion models in improving classifier performance on imbalanced data.
Authors: Simon Torka, Sahin Albayrak
Abstract: The advancement of AI technologies has greatly increased the complexity of AI pipelines as they include many stages such as data collection, pre-processing, training, evaluation and visualisation. To provide effective and accessible AI solutions, it is important to design pipelines for different user groups such as experts, professionals from different fields and laypeople. Ease of use and trust play a central role in the acceptance of AI systems. The presented system, ALPACA (Adaptive Learning Pipeline for Advanced Comprehensive AI Analysis), offers a comprehensive AI pipeline that addresses the needs of diverse user groups. ALPACA integrates visual and code-based development and facilitates all key phases of the AI pipeline. Its architecture is based on Celery (with Redis backend) for efficient task management, MongoDB for seamless data storage and Kubernetes for cloud-based scalability and resource utilisation. Future versions of ALPACA will support modern techniques such as federated and continuous learning as well as explainable AI methods to further improve security, usability and trustworthiness. The application is demonstrated by an Android app for similarity recognition, which emphasises ALPACA's potential for use in everyday life.
Authors: Simon Torka, Sahin Albayrak
Abstract: In recent years, the rise of AI-assisted code-generation tools has significantly transformed software development. While code generators have mainly been used to support conventional software development, their use will be extended to powerful and secure AI systems. Systems capable of generating code, such as ChatGPT, OpenAI Codex, GitHub Copilot, and AlphaCode, take advantage of advances in machine learning (ML) and natural language processing (NLP) enabled by large language models (LLMs). However, it must be borne in mind that these models work probabilistically, which means that although they can generate complex code from natural language input, there is no guarantee for the functionality and security of the generated code. However, to fully exploit the considerable potential of this technology, the security, reliability, functionality, and quality of the generated code must be guaranteed. This paper examines the implementation of these goals to date and explores strategies to optimize them. In addition, we explore how these systems can be optimized to create safe, high-performance, and executable artificial intelligence (AI) models, and consider how to improve their accessibility to make AI development more inclusive and equitable.
Authors: Hao Chen, Ze Wang, Xiang Li, Ximeng Sun, Fangyi Chen, Jiang Liu, Jindong Wang, Bhiksha Raj, Zicheng Liu, Emad Barsoum
Abstract: Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple codewords into each latent token, substantially increasing the representation capacity of the latent space. When applied to Transformer-based architectures, our approach compresses 256x256 and 512x512 images using as few as 32 or 64 1-dimensional tokens. Not only does SoftVQ-VAE show consistent and high-quality reconstruction, more importantly, it also achieves state-of-the-art and significantly faster image generation results across different denoising-based generative models. Remarkably, SoftVQ-VAE improves inference throughput by up to 18x for generating 256x256 images and 55x for 512x512 images while achieving competitive FID scores of 1.78 and 2.21 for SiT-XL. It also improves the training efficiency of the generative models by reducing the number of training iterations by 2.3x while maintaining comparable performance. With its fully-differentiable design and semantic-rich latent space, our experiment demonstrates that SoftVQ-VQE achieves efficient tokenization without compromising generation quality, paving the way for more efficient generative models. Code and model are released.
Authors: Eleanor Row, Gy\"orgy Fazekas
Abstract: We present a study that explores the role of user-centred design in developing Generative AI (GenAI) tools for music composition. Through semi-structured interviews with professional composers, we gathered insights on a novel generative model for creating variations, highlighting concerns around trust, transparency, and ethical design. The findings helped form a feedback loop, guiding improvements to the model that emphasised traceability, transparency and explainability. They also revealed new areas for innovation, including novel features for controllability and research questions on the ethical and practical implementation of GenAI models.
Authors: Daniel M. Benjamin, Fred Morstatter, Ali E. Abbas, Andres Abeliuk, Pavel Atanasov, Stephen Bennett, Andreas Beger, Saurabh Birari, David V. Budescu, Michele Catasta, Emilio Ferrara, Lucas Haravitch, Mark Himmelstein, KSM Tozammel Hossain, Yuzhong Huang, Woojeong Jin, Regina Joseph, Jure Leskovec, Akira Matsui, Mehrnoosh Mirtaheri, Xiang Ren, Gleb Satyukov, Rajiv Sethi, Amandeep Singh, Rok Sosic, Mark Steyvers, Pedro A Szekely, Michael D. Ward, Aram Galstyan
Abstract: Sound decision-making relies on accurate prediction for tangible outcomes ranging from military conflict to disease outbreaks. To improve crowdsourced forecasting accuracy, we developed SAGE, a hybrid forecasting system that combines human and machine generated forecasts. The system provides a platform where users can interact with machine models and thus anchor their judgments on an objective benchmark. The system also aggregates human and machine forecasts weighting both for propinquity and based on assessed skill while adjusting for overconfidence. We present results from the Hybrid Forecasting Competition (HFC) - larger than comparable forecasting tournaments - including 1085 users forecasting 398 real-world forecasting problems over eight months. Our main result is that the hybrid system generated more accurate forecasts compared to a human-only baseline which had no machine generated predictions. We found that skilled forecasters who had access to machine-generated forecasts outperformed those who only viewed historical data. We also demonstrated the inclusion of machine-generated forecasts in our aggregation algorithms improved performance, both in terms of accuracy and scalability. This suggests that hybrid forecasting systems, which potentially require fewer human resources, can be a viable approach for maintaining a competitive level of accuracy over a larger number of forecasting questions.
Authors: Lichun Zhang, Steve Ran Zhou, Moon Hyung Choi, Jeong Hoon Lee, Shengtian Sang, Adam Kinnaird, Wayne G. Brisbane, Giovanni Lughezzani, Davide Maffei, Vittorio Fasulo, Patrick Albers, Sulaiman Vesal, Wei Shao, Ahmed N. El Kaffas, Richard E. Fan, Geoffrey A. Sonn, Mirabela Rusu
Abstract: Prostate cancer is a leading cause of cancer-related deaths among men. The recent development of high frequency, micro-ultrasound imaging offers improved resolution compared to conventional ultrasound and potentially a better ability to differentiate clinically significant cancer from normal tissue. However, the features of prostate cancer remain subtle, with ambiguous borders with normal tissue and large variations in appearance, making it challenging for both machine learning and humans to localize it on micro-ultrasound images. We propose a novel Mask Enhanced Deeply-supervised Micro-US network, termed MedMusNet, to automatically and more accurately segment prostate cancer to be used as potential targets for biopsy procedures. MedMusNet leverages predicted masks of prostate cancer to enforce the learned features layer-wisely within the network, reducing the influence of noise and improving overall consistency across frames. MedMusNet successfully detected 76% of clinically significant cancer with a Dice Similarity Coefficient of 0.365, significantly outperforming the baseline Swin-M2F in specificity and accuracy (Wilcoxon test, Bonferroni correction, p-value<0.05). While the lesion-level and patient-level analyses showed improved performance compared to human experts and different baseline, the improvements did not reach statistical significance, likely on account of the small cohort. We have presented a novel approach to automatically detect and segment clinically significant prostate cancer on B-mode micro-ultrasound images. Our MedMusNet model outperformed other models, surpassing even human experts. These preliminary results suggest the potential for aiding urologists in prostate cancer diagnosis via biopsy and treatment decision-making.
Authors: Jinliang Shi, Shigang Li, Youxuan Xu, Rongtian Fu, Xueying Wang, Tong Wu
Abstract: Sparse Matrix-matrix Multiplication (SpMM) and Sampled Dense-dense Matrix Multiplication (SDDMM) are important sparse operators in scientific computing and deep learning. Tensor Core Units (TCUs) enhance modern accelerators with superior computing power, which is promising to boost the performance of matrix operators to a higher level. However, due to the irregularity of unstructured sparse data, it is difficult to deliver practical speedups on TCUs. To this end, we propose FlashSparse, a novel approach to bridge the gap between sparse workloads and the TCU architecture. Specifically, FlashSparse minimizes the sparse granularity for SpMM and SDDMM on TCUs through a novel swap-and-transpose matrix multiplication strategy. Benefiting from the minimum sparse granularity, the computation redundancy is remarkably reduced while the computing power of TCUs is fully utilized. Besides, FlashSparse is equipped with a memory-efficient thread mapping strategy for coalesced data access and a sparse matrix storage format to save memory footprint. Extensive experimental results on H100 and RTX 4090 GPUs show that FlashSparse sets a new state-of-the-art for sparse matrix multiplications (geometric mean 5.5x speedup over DTC-SpMM and 3.22x speedup over RoDe).
Authors: Haji Gul, Abdul Ghani Naim, Ajaz A. Bhat
Abstract: Knowledge graphs (KGs) are valuable for representing structured, interconnected information across domains, enabling tasks like semantic search, recommendation systems and inference. A pertinent challenge with KGs, however, is that many entities (i.e., heads, tails) or relationships are unknown. Knowledge Graph Completion (KGC) addresses this by predicting these missing nodes or links, enhancing the graph's informational depth and utility. Traditional methods like TransE and ComplEx predict tail entities but struggle with unseen entities. Textual-based models leverage additional semantics but come with high computational costs, semantic inconsistencies, and data imbalance issues. Recent LLM-based models show improvement but overlook contextual information and rely heavily on entity descriptions. In this study, we introduce a contextualized BERT model for KGC that overcomes these limitations by utilizing the contextual information from neighbouring entities and relationships to predict tail entities. Our model eliminates the need for entity descriptions and negative triplet sampling, reducing computational demands while improving performance. Our model outperforms state-of-the-art methods on standard datasets, improving Hit@1 by 5.3% and 4.88% on FB15k-237 and WN18RR respectively, setting a new benchmark in KGC.
Authors: Bhanu Tokas, Rahul Nair, Hannah Kerner
Abstract: Most of the ML datasets we use today are biased. When we train models on these biased datasets, they often not only learn dataset biases but can also amplify them -- a phenomenon known as bias amplification. Several co-occurrence-based metrics have been proposed to measure bias amplification between a protected attribute A (e.g., gender) and a task T (e.g., cooking). However, these metrics fail to measure biases when A is balanced with T. To measure bias amplification in balanced datasets, recent work proposed a predictability-based metric called leakage amplification. However, leakage amplification cannot identify the direction in which biases are amplified. In this work, we propose a new predictability-based metric called directional predictability amplification (DPA). DPA measures directional bias amplification, even for balanced datasets. Unlike leakage amplification, DPA is easier to interpret and less sensitive to attacker models (a hyperparameter in predictability-based metrics). Our experiments on tabular and image datasets show that DPA is an effective metric for measuring directional bias amplification. The code will be available soon.
Authors: Rahul Nair, Gabriel Tseng, Esther Rolf, Bhanu Tokas, Hannah Kerner
Abstract: Previous studies showed that image datasets lacking geographic diversity can lead to biased performance in models trained on them. While earlier work studied general-purpose image datasets (e.g., ImageNet) and simple tasks like image recognition, we investigated geo-biases in real-world driving datasets on a more complex task: instance segmentation. We examined if instance segmentation models trained on European driving scenes (Eurocentric models) are geo-biased. Consistent with previous work, we found that Eurocentric models were geo-biased. Interestingly, we found that geo-biases came from classification errors rather than localization errors, with classification errors alone contributing 10-90% of the geo-biases in segmentation and 19-88% of the geo-biases in detection. This showed that while classification is geo-biased, localization (including detection and segmentation) is geographically robust. Our findings show that in region-specific models (e.g., Eurocentric models), geo-biases from classification errors can be significantly mitigated by using coarser classes (e.g., grouping car, bus, and truck as 4-wheeler).
Authors: Haixu Wang, Jiguo Cao, Jian Pei
Abstract: This study presents a novel representation learning model tailored for dynamic networks, which describes the continuously evolving relationships among individuals within a population. The problem is encapsulated in the dimension reduction topic of functional data analysis. With dynamic networks represented as matrix-valued functions, our objective is to map this functional data into a set of vector-valued functions in a lower-dimensional learning space. This space, defined as a metric functional space, allows for the calculation of norms and inner products. By constructing this learning space, we address (i) attribute learning, (ii) community detection, and (iii) link prediction and recovery of individual nodes in the dynamic network. Our model also accommodates asymmetric low-dimensional representations, enabling the separate study of nodes' regulatory and receiving roles. Crucially, the learning method accounts for the time-dependency of networks, ensuring that representations are continuous over time. The functional learning space we define naturally spans the time frame of the dynamic networks, facilitating both the inference of network links at specific time points and the reconstruction of the entire network structure without direct observation. We validated our approach through simulation studies and real-world applications. In simulations, we compared our methods link prediction performance to existing approaches under various data corruption scenarios. For real-world applications, we examined a dynamic social network replicated across six ant populations, demonstrating that our low-dimensional learning space effectively captures interactions, roles of individual ants, and the social evolution of the network. Our findings align with existing knowledge of ant colony behavior.
Authors: Baocai Yin, Ji Zhao, Huajie Jiang, Ningning Hou, Yongli Hu, Amin Beheshti, Ming-Hsuan Yang, Yuankai Qi
Abstract: Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data for replay or add additional branches in the model to learn new knowledge, which has high memory requirements. In this paper, we propose a novel lightweight CL framework, Adapter-Enhanced Semantic Prompting (AESP), which integrates prompt tuning and adapter techniques. Specifically, we design semantic-guided prompts to enhance the generalization ability of visual features and utilize adapters to efficiently fuse the semantic information, aiming to learn more adaptive features for the continual learning task. Furthermore, to choose the right task prompt for feature adaptation, we have developed a novel matching mechanism for prompt selection. Extensive experiments on three CL datasets demonstrate that our approach achieves favorable performance across multiple metrics, showing its potential for advancing CL.
Authors: Zhe Yang, Tiantian Liang
Abstract: Session-based recommendation focuses on predicting the next item a user will interact with based on sequences of anonymous user sessions. A significant challenge in this field is data sparsity due to the typically short-term interactions. Most existing methods rely heavily on users' current interactions, overlooking the wealth of auxiliary information available. To address this, we propose a novel model, the Multi-Graph Co-Training model (MGCOT), which leverages not only the current session graph but also similar session graphs and a global item relation graph. This approach allows for a more comprehensive exploration of intrinsic relationships and better captures user intent from multiple views, enabling session representations to complement each other. Additionally, MGCOT employs multi-head attention mechanisms to effectively capture relevant session intent and uses contrastive learning to form accurate and robust session representations. Extensive experiments on three datasets demonstrate that MGCOT significantly enhances the performance of session-based recommendations, particularly on the Diginetica dataset, achieving improvements up to 2.00% in P@20 and 10.70% in MRR@20. Resources have been made publicly available in our GitHub repository https://github.com/liang-tian-tian/MGCOT.
Authors: Runze Jiang, Pengjian Shang
Abstract: Lempel-Ziv complexity (LZC) is a key measure for detecting the irregularity and complexity of nonlinear time series and has seen various improvements in recent decades. However, existing LZC-based metrics, such as Permutation Lempel-Ziv complexity (PLZC) and Dispersion-Entropy based Lempel-Ziv complexity (DELZC), focus mainly on patterns of independent embedding vectors, often overlooking the transition patterns within the time series. To address this gap, this paper introduces a novel LZC-based method called Bidirectional Transition Dispersion Entropy-based Lempel-Ziv complexity (BT-DELZC). Leveraging Markov chain theory, this method integrates a bidirectional transition network framework with DELZC to better capture dynamic signal information. Additionally, an improved hierarchical decomposition algorithm is used to extract features from various frequency components of the time series. The proposed BT-DELZC method is first evaluated through four simulated experiments, demonstrating its robustness and effectiveness in characterizing nonlinear time series. Additionally, two fault-bearing diagnosis experiments are conducted by combining the hierarchical BT-DELZC method with various classifiers from the machine learning domain. The results indicate that BT-DELZC achieves the highest accuracy across both datasets, significantly outperforming existing methods such as LZC, PLZC, and DELZC in extracting features related to fault bearings.
Authors: Sijia Zhou, Xin Li
Abstract: Section identification is an important task for library science, especially knowledge management. Identifying the sections of a paper would help filter noise in entity and relation extraction. In this research, we studied the paper section identification problem in the context of Chinese medical literature analysis, where the subjects, methods, and results are more valuable from a physician's perspective. Based on previous studies on English literature section identification, we experiment with the effective features to use with classic machine learning algorithms to tackle the problem. It is found that Conditional Random Fields, which consider sentence interdependency, is more effective in combining different feature sets, such as bag-of-words, part-of-speech, and headings, for Chinese literature section identification. Moreover, we find that classic machine learning algorithms are more effective than generic deep learning models for this problem. Based on these observations, we design a novel deep learning model, the Structural Bidirectional Long Short-Term Memory (SLSTM) model, which models word and sentence interdependency together with the contextual information. Experiments on a human-curated asthma literature dataset show that our approach outperforms the traditional machine learning methods and other deep learning methods and achieves close to 90% precision and recall in the task. The model shows good potential for use in other text mining tasks. The research has significant methodological and practical implications.
Authors: Haidong Zhang, Wancheng Ni, Xin Li, Yiping Yang
Abstract: Recommender systems are widely used for suggesting books, education materials, and products to users by exploring their behaviors. In reality, users' preferences often change over time, leading to studies on time-dependent recommender systems. However, most existing approaches that deal with time information remain primitive. In this paper, we extend existing methods and propose a hidden semi-Markov model to track the change of users' interests. Particularly, this model allows for capturing the different durations of user stays in a (latent) interest state, which can better model the heterogeneity of user interests and focuses. We derive an expectation maximization algorithm to estimate the parameters of the framework and predict users' actions. Experiments on three real-world datasets show that our model significantly outperforms the state-of-the-art time-dependent and static benchmark methods. Further analyses of the experiment results indicate that the performance improvement is related to the heterogeneity of state durations and the drift of user interests in the dataset.
Authors: Xiangming Wang, Haijin Zeng, Jiaoyang Chen, Sheng Liu, Yongyong Chen, Guoqing Chao
Abstract: In real-world scenarios, complex data such as multispectral images and multi-frame videos inherently exhibit robust low-rank property. This property is vital for multi-dimensional inverse problems, such as tensor completion, spectral imaging reconstruction, and multispectral image denoising. Existing tensor singular value decomposition (t-SVD) definitions rely on hand-designed or pre-given transforms, which lack flexibility for defining tensor nuclear norm (TNN). The TNN-regularized optimization problem is solved by the singular value thresholding (SVT) operator, which leverages the t-SVD framework to obtain the low-rank tensor. However, it is quite complicated to introduce SVT into deep neural networks due to the numerical instability problem in solving the derivatives of the eigenvectors. In this paper, we introduce a novel data-driven generative low-rank t-SVD model based on the learnable orthogonal transform, which can be naturally solved under its representation. Prompted by the linear algebra theorem of the Householder transformation, our learnable orthogonal transform is achieved by constructing an endogenously orthogonal matrix adaptable to neural networks, optimizing it as arbitrary orthogonal matrices. Additionally, we propose a low-rank solver as a generalization of SVT, which utilizes an efficient representation of generative networks to obtain low-rank structures. Extensive experiments highlight its significant restoration enhancements.
Authors: Luqi Wang, Wenbao Jiang
Abstract: As a cornerstone of blockchain technology in the 3.0 era, smart contracts play a pivotal role in the evolution of blockchain systems. In order to address the limitations of existing smart contract vulnerability detection models with regard to their generalisation capability, an AF-STip smart contract vulnerability detection framework incorporating efficient knowledge migration is proposed. AF-STip employs the teacher network as the main model and migrates the knowledge processed by the smart contract to the student model using a data-free knowledge distillation method. The student model utilises this knowledge to enhance its vulnerability detection capabilities. The approach markedly enhances the model's capacity for feature extraction and cross-class adaptation, while concurrently reducing computational overhead.In order to further enhance the extraction of vulnerability features, an adaptive fusion module is proposed in this paper, which aims to strengthen the interaction and fusion of feature information.The experimental results demonstrate that the STip model attains an average F1 value detection score of 91.16% for the four vulnerabilities without disclosing the original smart contract data. To validate the viability of the proposed lightweight migration approach, the student model is deployed in a migration learning task targeting a novel vulnerability type, resulting in an accuracy of 91.02% and an F1 score of 90.46%. To the best of our knowledge, AF-STip is the inaugural model to apply data-free knowledge migration to smart contract vulnerability detection. While markedly reducing the computational overhead, the method still demonstrates exceptional performance in detecting novel vulnerabilities.
Authors: Hanxiao Lu, Hongyu Cai, Yiming Liang, Antonio Bianchi, Z. Berkay Celik
Abstract: Language model approaches have recently been integrated into binary analysis tasks, such as function similarity detection and function signature recovery. These models typically employ a two-stage training process: pre-training via Masked Language Modeling (MLM) on machine code and fine-tuning for specific tasks. While MLM helps to understand binary code structures, it ignores essential code characteristics, including control and data flow, which negatively affect model generalization. Recent work leverages domain-specific features (e.g., control flow graphs and dynamic execution traces) in transformer-based approaches to improve binary code semantic understanding. However, this approach involves complex feature engineering, a cumbersome and time-consuming process that can introduce predictive uncertainty when dealing with stripped or obfuscated code, leading to a performance drop. In this paper, we introduce ProTST, a novel transformer-based methodology for binary code embedding. ProTST employs a hierarchical training process based on a unique tree-like structure, where knowledge progressively flows from fundamental tasks at the root to more specialized tasks at the leaves. This progressive teacher-student paradigm allows the model to build upon previously learned knowledge, resulting in high-quality embeddings that can be effectively leveraged for diverse downstream binary analysis tasks. The effectiveness of ProTST is evaluated in seven binary analysis tasks, and the results show that ProTST yields an average validation score (F1, MRR, and Recall@1) improvement of 14.8% compared to traditional two-stage training and an average validation score of 10.7% compared to multimodal two-stage frameworks.
Authors: Pawe{\l} M\k{a}ka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
Abstract: In this paper, we investigate the role of attention heads in Context-aware Machine Translation models for pronoun disambiguation in the English-to-German and English-to-French language directions. We analyze their influence by both observing and modifying the attention scores corresponding to the plausible relations that could impact a pronoun prediction. Our findings reveal that while some heads do attend the relations of interest, not all of them influence the models' ability to disambiguate pronouns. We show that certain heads are underutilized by the models, suggesting that model performance could be improved if only the heads would attend one of the relations more strongly. Furthermore, we fine-tune the most promising heads and observe the increase in pronoun disambiguation accuracy of up to 5 percentage points which demonstrates that the improvements in performance can be solidified into the models' parameters.
Authors: Jiahe Lin, George Michailidis
Abstract: State-space models (SSMs) offer a powerful framework for dynamical system analysis, wherein the temporal dynamics of the system are assumed to be captured through the evolution of the latent states, which govern the values of the observations. This paper provides a selective review of recent advancements in deep neural network-based approaches for SSMs, and presents a unified perspective for discrete time deep state space models and continuous time ones such as latent neural Ordinary Differential and Stochastic Differential Equations. It starts with an overview of the classical maximum likelihood based approach for learning SSMs, reviews variational autoencoder as a general learning pipeline for neural network-based approaches in the presence of latent variables, and discusses in detail representative deep learning models that fall under the SSM framework. Very recent developments, where SSMs are used as standalone architectural modules for improving efficiency in sequence modeling, are also examined. Finally, examples involving mixed frequency and irregularly-spaced time series data are presented to demonstrate the advantage of SSMs in these settings.
Authors: Yulin Wang, Haoji Zhang, Yang Yue, Shiji Song, Chao Deng, Junlan Feng, Gao Huang
Abstract: This paper presents a comprehensive exploration of the phenomenon of data redundancy in video understanding, with the aim to improve computational efficiency. Our investigation commences with an examination of spatial redundancy, which refers to the observation that the most informative region in each video frame usually corresponds to a small image patch, whose shape, size and location shift smoothly across frames. Motivated by this phenomenon, we formulate the patch localization problem as a dynamic decision task, and introduce a spatially adaptive video recognition approach, termed AdaFocus. In specific, a lightweight encoder is first employed to quickly process the full video sequence, whose features are then utilized by a policy network to identify the most task-relevant regions. Subsequently, the selected patches are inferred by a high-capacity deep network for the final prediction. The full model can be trained in end-to-end conveniently. Furthermore, AdaFocus can be extended by further considering temporal and sample-wise redundancies, i.e., allocating the majority of computation to the most task-relevant frames, and minimizing the computation spent on relatively "easier" videos. Our resulting approach, Uni-AdaFocus, establishes a comprehensive framework that seamlessly integrates spatial, temporal, and sample-wise dynamic computation, while it preserves the merits of AdaFocus in terms of efficient end-to-end training and hardware friendliness. In addition, Uni-AdaFocus is general and flexible as it is compatible with off-the-shelf efficient backbones (e.g., TSM and X3D), which can be readily deployed as our feature extractor, yielding a significantly improved computational efficiency. Empirically, extensive experiments based on seven benchmark datasets and three application scenarios substantiate that Uni-AdaFocus is considerably more efficient than the competitive baselines.
Authors: Fengpei Li, Haoxian Chen, Jiahe Lin, Arkin Gupta, Xiaowei Tan, Gang Xu, Yuriy Nevmyvaka, Agostino Capponi, Henry Lam
Abstract: Despite being an essential tool across engineering and finance, Monte Carlo simulation can be computationally intensive, especially in large-scale, path-dependent problems that hinder straightforward parallelization. A natural alternative is to replace simulation with machine learning or surrogate prediction, though this introduces challenges in understanding the resulting errors.We introduce a Prediction-Enhanced Monte Carlo (PEMC) framework where we leverage machine learning prediction as control variates, thus maintaining unbiased evaluations instead of the direct use of ML predictors. Traditional control variate methods require knowledge of means and focus on per-sample variance reduction. In contrast, PEMC aims at overall cost-aware variance reduction, eliminating the need for mean knowledge. PEMC leverages pre-trained neural architectures to construct effective control variates and replaces computationally expensive sample-path generation with efficient neural network evaluations. This allows PEMC to address scenarios where no good control variates are known. We showcase the efficacy of PEMC through two production-grade exotic option-pricing problems: swaption pricing in HJM model and the variance swap pricing in a stochastic local volatility model.
Authors: A. Kontogiannis, P. Nair, M. Loecher, D. B. Ennis, A. Marsden, M. P. Juniper
Abstract: We solve a Bayesian inverse Reynolds-averaged Navier-Stokes (RANS) problem that assimilates mean flow data by jointly reconstructing the mean flow field and learning its unknown RANS parameters. We devise an algorithm that learns the most likely parameters of an algebraic effective viscosity model, and estimates their uncertainties, from mean flow data of a turbulent flow. We conduct a flow MRI experiment to obtain mean flow data of a confined turbulent jet in an idealized medical device known as the FDA (Food and Drug Administration) nozzle. The algorithm successfully reconstructs the mean flow field and learns the most likely turbulence model parameters without overfitting. The methodology accepts any turbulence model, be it algebraic (explicit) or multi-equation (implicit), as long as the model is differentiable, and naturally extends to unsteady turbulent flows.
Authors: Trishita Tiwari, G. Edward Suh
Abstract: This work advocates for the use of sequence level probabilities for quantifying the risk of extraction training data from Large Language Models (LLMs) as they provide much finer-grained information than has been previously obtained. We re-analyze the effects of decoding schemes, model-size, prefix length, partial sequence leakages, and token positions to uncover new insights that have were not possible in prior work due to their choice of metrics. We perform this study on two pre-trained models, LLaMa and OPT, trained on the Common Crawl and Pile respectively. We discover that 1) Extraction rate, the predominant metric used in prior quantification work, underestimates the threat of leakage of training data in randomized LLMs by as much as 2.14x. 2) Though, on average, larger models and longer prefixes can extract more data, this is not true with a substantial portion of individual sequences. 30.4-41.5% of our sequences are easier to extract with either shorter prefixes or smaller models. 3) Contrary to prior belief, partial leakage in the commonly used decoding schemes like top-k and top-p are not easier than leaking verbatim training data. 4) Extracting later tokens in a sequence is as much as 912% easier than extracting earlier tokens. The insights gained from our analysis show that it is important to look at leakage of training data on a per-sequence basis.
Authors: Minhui Jiang, Yuansi Chen
Abstract: We study the problem of drawing samples from a logconcave distribution truncated on a polytope, motivated by computational challenges in Bayesian statistical models with indicator variables, such as probit regression. Building on interior point methods and the Dikin walk for sampling from uniform distributions, we analyze the mixing time of regularized Dikin walks. Our contributions are threefold. First, for a logconcave and log-smooth distribution with condition number $\kappa$, truncated on a polytope in $\mathbb{R}^n$ defined with $m$ linear constraints, we prove that the soft-threshold Dikin walk mixes in $\widetilde{O}((m+\kappa)n)$ iterations from a warm initialization. It improves upon prior work which required the polytope to be bounded and involved a bound dependent on the radius of the bounded region. Moreover, we introduce the regularized Dikin walk using Lewis weights for approximating the John ellipsoid. We show that it mixes in $\widetilde{O}((n^{2.5}+\kappa n)$. Second, we extend the mixing time guarantees mentioned above to weakly log-concave distributions truncated on polytopes, provided that they have a finite covariance matrix. Third, going beyond worst-case mixing time analysis, we demonstrate that soft-threshold Dikin walk can mix significantly faster when only a limited number of constraints intersect the high-probability mass of the distribution, improving the $\widetilde{O}((m+\kappa)n)$ upper bound to $\widetilde{O}(m + \kappa n)$. Additionally, per-iteration complexity of regularized Dikin walk and ways to generate a warm initialization are discussed to facilitate practical implementation.
Authors: Nargiz Humbatova, Jinhan Kim, Gunel Jahangirova, Shin Yoo, Paolo Tonella
Abstract: With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Several approaches have been proposed that automatically analyse and localise potential faults in DNNs under test. In this work, we evaluate and compare existing state-of-the-art fault localisation techniques, which operate based on both dynamic and static analysis of the DNN. The evaluation is performed on a benchmark consisting of both real faults obtained from bug reporting platforms and faulty models produced by a mutation tool. Our findings indicate that the usage of a single, specific ground truth (e.g., the human defined one) for the evaluation of DNN fault localisation tools results in pretty low performance (maximum average recall of 0.31 and precision of 0.23). However, such figures increase when considering alternative, equivalent patches that exist for a given faulty DNN. Results indicate that \dfd is the most effective tool, achieving an average recall of 0.61 and precision of 0.41 on our benchmark.
Authors: Ugur Dar, Mustafa Cavus
Abstract: Predictive models often face performance degradation due to evolving data distributions, a phenomenon known as data drift. Among its forms, concept drift, where the relationship between explanatory variables and the response variable changes, is particularly challenging to detect and adapt to. Traditional drift detection methods often rely on metrics such as accuracy or variable distributions, which may fail to capture subtle but significant conceptual changes. This paper introduces drifter, an R package designed to detect concept drift, and proposes a novel method called Profile Drift Detection (PDD) that enables both drift detection and an enhanced understanding of the cause behind the drift by leveraging an explainable AI tool - Partial Dependence Profiles (PDPs). The PDD method, central to the package, quantifies changes in PDPs through novel metrics, ensuring sensitivity to shifts in the data stream without excessive computational costs. This approach aligns with MLOps practices, emphasizing model monitoring and adaptive retraining in dynamic environments. The experiments across synthetic and real-world datasets demonstrate that PDD outperforms existing methods by maintaining high accuracy while effectively balancing sensitivity and stability. The results highlight its capability to adaptively retrain models in dynamic environments, making it a robust tool for real-time applications. The paper concludes by discussing the advantages, limitations, and future extensions of the package for broader use cases.
Authors: Yuqing Li, Jinglei Cheng, Xulong Tang, Youtao Zhang, Frederic T. Chong, Junyu Liu
Abstract: Quantum machine learning is considered one of the flagship applications of quantum computers, where variational quantum circuits could be the leading paradigm both in the near-term quantum devices and the early fault-tolerant quantum computers. However, it is not clear how to identify the regime of quantum advantages from these circuits, and there is no explicit theory to guide the practical design of variational ansatze to achieve better performance. We address these challenges with the stabilizer bootstrap, a method that uses stabilizer-based techniques to optimize quantum neural networks before their quantum execution, together with theoretical proofs and high-performance computing with 10000 qubits or random datasets up to 1000 data. We find that, in a general setup of variational ansatze, the possibility of improvements from the stabilizer bootstrap depends on the structure of the observables and the size of the datasets. The results reveal that configurations exhibit two distinct behaviors: some maintain a constant probability of circuit improvement, while others show an exponential decay in improvement probability as qubit numbers increase. These patterns are termed strong stabilizer enhancement and weak stabilizer enhancement, respectively, with most situations falling in between. Our work seamlessly bridges techniques from fault-tolerant quantum computing with applications of variational quantum algorithms. Not only does it offer practical insights for designing variational circuits tailored to large-scale machine learning challenges, but it also maps out a clear trajectory for defining the boundaries of feasible and practical quantum advantages.
Authors: Chengsen Wang, Qi Qi, Jingyu Wang, Haifeng Sun, Zirui Zhuang, Jinming Wu, Lei Zhang, Jianxin Liao
Abstract: Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal numerical data, using a fixed-length window for training and prediction on a single dataset, and cannot adapt to different scenarios. The powered pre-trained large language model has introduced new opportunities for time series analysis. Yet, existing methods are either inefficient in training, incapable of handling textual information, or lack zero-shot forecasting capability. In this paper, we innovatively model time series as a foreign language and construct ChatTime, a unified framework for time series and text processing. As an out-of-the-box multimodal time series foundation model, ChatTime provides zero-shot forecasting capability and supports bimodal input/output for both time series and text. We design a series of experiments to verify the superior performance of ChatTime across multiple tasks and scenarios, and create four multimodal datasets to address data gaps. The experimental results demonstrate the potential and utility of ChatTime.
Authors: Tom S. Juzek, Zina B. Ward
Abstract: Scientific English is currently undergoing rapid change, with words like "delve," "intricate," and "underscore" appearing far more frequently than just a few years ago. It is widely assumed that scientists' use of large language models (LLMs) is responsible for such trends. We develop a formal, transferable method to characterize these linguistic changes. Application of our method yields 21 focal words whose increased occurrence in scientific abstracts is likely the result of LLM usage. We then pose "the puzzle of lexical overrepresentation": WHY are such words overused by LLMs? We fail to find evidence that lexical overrepresentation is caused by model architecture, algorithm choices, or training data. To assess whether reinforcement learning from human feedback (RLHF) contributes to the overuse of focal words, we undertake comparative model testing and conduct an exploratory online study. While the model testing is consistent with RLHF playing a role, our experimental results suggest that participants may be reacting differently to "delve" than to other focal words. With LLMs quickly becoming a driver of global language change, investigating these potential sources of lexical overrepresentation is important. We note that while insights into the workings of LLMs are within reach, a lack of transparency surrounding model development remains an obstacle to such research.
Authors: Xiaoqing Chen, Tianwang Jia, Dongrui Wu
Abstract: An electroencephalogram (EEG) based brain-computer interface (BCI) enables direct communication between the brain and external devices. However, EEG-based BCIs face at least three major challenges in real-world applications: data scarcity and individual differences, adversarial vulnerability, and data privacy. While previous studies have addressed one or two of these issues, simultaneous accommodation of all three challenges remains challenging and unexplored. This paper fills this gap, by proposing an Augmented Robustness Ensemble (ARE) algorithm and integrating it into three privacy protection scenarios (centralized source-free transfer, federated source-free transfer, and source data perturbation), achieving simultaneously accurate decoding, adversarial robustness, and privacy protection of EEG-based BCIs. Experiments on three public EEG datasets demonstrated that our proposed approach outperformed over 10 classic and state-of-the-art approaches in both accuracy and robustness in all three privacy-preserving scenarios, even outperforming state-of-the-art transfer learning approaches that do not consider privacy protection at all. This is the first time that three major challenges in EEG-based BCIs can be addressed simultaneously, significantly improving the practicalness of EEG decoding in real-world BCIs.
Authors: Akshita Jha, Sanchit Kabra, Chandan K. Reddy
Abstract: Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension failure. For example, when a model misinterprets a text and produces a response that reinforces a stereotype, it becomes difficult to determine whether the issue arises from inherent bias or from a misunderstanding of the given content. In this paper, we conduct a multi-faceted evaluation that distinctly disentangles bias from flaws within the reading comprehension task. We propose a targeted stereotype mitigation framework that implicitly mitigates observed stereotypes in generative models through instruction-tuning on general-purpose datasets. We reduce stereotypical outputs by over 60% across multiple dimensions -- including nationality, age, gender, disability, and physical appearance -- by addressing comprehension-based failures, and without relying on explicit debiasing techniques. We evaluate several state-of-the-art generative models to demonstrate the effectiveness of our approach while maintaining the overall utility. Our findings highlight the need to critically disentangle the concept of `bias' from other types of errors to build more targeted and effective mitigation strategies. CONTENT WARNING: Some examples contain offensive stereotypes.
Authors: Junjie Lin, Jian Zhao, Yue Deng, Youpeng Zhao, Wengang Zhou, Houqiang Li
Abstract: Traditionally, AI development for two-player zero-sum games has relied on two primary techniques: decision trees and reinforcement learning (RL). A common approach involves using a fixed decision tree as one player's strategy while training an RL agent as the opponent to identify vulnerabilities in the decision tree, thereby improving its strategic strength iteratively. However, this process often requires significant human intervention to refine the decision tree after identifying its weaknesses, resulting in inefficiencies and hindering full automation of the strategy enhancement process. Fortunately, the advent of Large Language Models (LLMs) offers a transformative opportunity to automate the process. We propose RL-LLM-DT, an automatic decision tree generation method based on RL Evaluation and LLM Enhancement. Given an initial decision tree, the method involves two important iterative steps. Response Policy Search: RL is used to discover counter-strategies targeting the decision tree. Policy Improvement: LLMs analyze failure scenarios and generate improved decision tree code. In our method, RL focuses on finding the decision tree's flaws while LLM is prompted to generate an improved version of the decision tree. The iterative refinement process terminates when RL can't find any flaw of the tree or LLM fails to improve the tree. To evaluate the effectiveness of this integrated approach, we conducted experiments in a curling game. After iterative refinements, our curling AI based on the decision tree ranks first on the Jidi platform among 34 curling AIs in total, which demonstrates that LLMs can significantly enhance the robustness and adaptability of decision trees, representing a substantial advancement in the field of Game AI. Our code is available at https://github.com/Linjunjie99/RL-LLM-DT.
Authors: Yuning Han, Bingyin Zhao, Rui Chu, Feng Luo, Biplab Sikdar, Yingjie Lao
Abstract: Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that contain evident patterns, rendering remarkable attack effects yet easy detection upon human inspection and defensive algorithms. While it is possible to improve stealthiness by reducing the strength of the backdoor, doing so can significantly compromise its generality and effectiveness. In this paper, we propose UIBDiffusion, the universal imperceptible backdoor attack for diffusion models, which allows us to achieve superior attack and generation performance while evading state-of-the-art defenses. We propose a novel trigger generation approach based on universal adversarial perturbations (UAPs) and reveal that such perturbations, which are initially devised for fooling pre-trained discriminative models, can be adapted as potent imperceptible backdoor triggers for DMs. We evaluate UIBDiffusion on multiple types of DMs with different kinds of samplers across various datasets and targets. Experimental results demonstrate that UIBDiffusion brings three advantages: 1) Universality, the imperceptible trigger is universal (i.e., image and model agnostic) where a single trigger is effective to any images and all diffusion models with different samplers; 2) Utility, it achieves comparable generation quality (e.g., FID) and even better attack success rate (i.e., ASR) at low poison rates compared to the prior works; and 3) Undetectability, UIBDiffusion is plausible to human perception and can bypass Elijah and TERD, the SOTA defenses against backdoors for DMs. We will release our backdoor triggers and code.
Authors: Yuanfan Zheng, Jinlin Wu, Wuyang Li, Zhen Chen
Abstract: Domain Adaptive Object Detection (DAOD) transfers knowledge from a labeled source domain to an unannotated target domain under closed-set assumption. Universal DAOD (UniDAOD) extends DAOD to handle open-set, partial-set, and closed-set domain adaptation. In this paper, we first unveil two issues: domain-private category alignment is crucial for global-level features, and the domain probability heterogeneity of features across different levels. To address these issues, we propose a novel Dual Probabilistic Alignment (DPA) framework to model domain probability as Gaussian distribution, enabling the heterogeneity domain distribution sampling and measurement. The DPA consists of three tailored modules: the Global-level Domain Private Alignment (GDPA), the Instance-level Domain Shared Alignment (IDSA), and the Private Class Constraint (PCC). GDPA utilizes the global-level sampling to mine domain-private category samples and calculate alignment weight through a cumulative distribution function to address the global-level private category alignment. IDSA utilizes instance-level sampling to mine domain-shared category samples and calculates alignment weight through Gaussian distribution to conduct the domain-shared category domain alignment to address the feature heterogeneity. The PCC aggregates domain-private category centroids between feature and probability spaces to mitigate negative transfer. Extensive experiments demonstrate that our DPA outperforms state-of-the-art UniDAOD and DAOD methods across various datasets and scenarios, including open, partial, and closed sets. Codes are available at \url{https://github.com/zyfone/DPA}.
Authors: Prateek Verma
Abstract: We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge surge in generative audio, speech, and music models that utilize discrete audio tokens derived from neural compression algorithms, e.g. ENCODEC. However, one of the major drawbacks of this approach is handling the context length. It blows up for high-fidelity generative architecture if one has to account for all the audio contents at various frequencies for the next token prediction. By combining continuous audio representation like the spectrogram and discrete acoustic tokens, we retain the best of both worlds: Have all the information needed from the audio at a specific time instance in a single token, yet allow LLM to predict the future token to allow for sampling and other benefits discrete space provides. We show how our architecture improves the perplexity and negative log-likelihood scores for the next token prediction compared to a token-based LLM for speech and music.
Authors: Maria Efimovich, Jayden Lim, Vedant Mehta, Ethan Poon
Abstract: Classifying chest radiographs is a time-consuming and challenging task, even for experienced radiologists. This provides an area for improvement due to the difficulty in precisely distinguishing between conditions such as pleural effusion, pneumothorax, and pneumonia. We propose a novel transfer learning model for multi-label lung disease classification, utilizing the CheXpert dataset with over 12,617 images of frontal radiographs being analyzed. By integrating RadGraph parsing for efficient annotation extraction, we enhance the model's ability to accurately classify multiple lung diseases from complex medical images. The proposed model achieved an F1 score of 0.69 and an AUROC of 0.86, demonstrating its potential for clinical applications. Also explored was the use of Natural Language Processing (NLP) to parse report metadata and address uncertainties in disease classification. By comparing uncertain reports with more certain cases, the NLP-enhanced model improves its ability to conclusively classify conditions. This research highlights the connection between deep learning and NLP, underscoring their potential to enhance radiological diagnostics and aid in the efficient analysis of chest radiographs.
Authors: Shuo Wang, Issei Sato
Abstract: In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks without fine-tuning by leveraging contextual information provided within a prompt. However, ICL relies not only on contextual clues but also on the global knowledge acquired during pretraining for the next token prediction. Analyzing this process has been challenging due to the complex computational circuitry of LLMs. This paper investigates the balance between in-context information and pretrained bigram knowledge in token prediction, focusing on the induction head mechanism, a key component in ICL. Leveraging the fact that a two-layer transformer can implement the induction head mechanism with associative memories, we theoretically analyze the logits when a two-layer transformer is given prompts generated by a bigram model. In the experiments, we design specific prompts to evaluate whether the outputs of a two-layer transformer align with the theoretical results.
Authors: Minjun Kim, Minjee Kim, Jinhoon Jeong
Abstract: Generative models trained on multi-institutional datasets can provide an enriched understanding through diverse data distributions. However, training the models on medical images is often challenging due to hospitals' reluctance to share data for privacy reasons. Federated learning(FL) has emerged as a privacy-preserving solution for training distributed datasets across data centers by aggregating model weights from multiple clients instead of sharing raw data. Previous research has explored the adaptation of FL to generative models, yet effective aggregation algorithms specifically tailored for generative models remain unexplored. We hereby propose a novel algorithm aimed at improving the performance of generative models within FL. Our approach adaptively re-weights the contribution of each client, resulting in well-trained shared parameters. In each round, the server side measures the distribution distance between fake images generated by clients instead of directly comparing the Fr\'echet Inception Distance per client, thereby enhancing efficiency of the learning. Experimental results on three public chest X-ray datasets show superior performance in medical image generation, outperforming both centralized learning and conventional FL algorithms. Our code is available at https://github.com/danny0628/FedCAR.
Authors: Moming Duan, Rui Zhao, Linshan Jiang, Nigel Shadbolt, Bingsheng He
Abstract: As model parameter sizes reach the billion-level range and their training consumes zettaFLOPs of computation, components reuse and collaborative development are become increasingly prevalent in the Machine Learning (ML) community. These components, including models, software, and datasets, may originate from various sources and be published under different licenses, which govern the use and distribution of licensed works and their derivatives. However, commonly chosen licenses, such as GPL and Apache, are software-specific and are not clearly defined or bounded in the context of model publishing. Meanwhile, the reused components may also have free-content licenses and model licenses, which pose a potential risk of license noncompliance and rights infringement within the model production workflow. In this paper, we propose addressing the above challenges along two lines: 1) For license analysis, we have developed a new vocabulary for ML workflow management and encoded license rules to enable ontological reasoning for analyzing rights granting and compliance issues. 2) For standardized model publishing, we have drafted a set of model licenses that provide flexible options to meet the diverse needs of model publishing. Our analysis tool is built on Turtle language and Notation3 reasoning engine, envisioned as a first step toward Linked Open Model Production Data. We have also encoded our proposed model licenses into rules and demonstrated the effects of GPL and other commonly used licenses in model publishing, along with the flexibility advantages of our licenses, through comparisons and experiments.
Authors: Zijian Gu, Jianwei Ma, Yan Huang, Honghao Wei, Zhanye Chen, Hui Zhang, Wei Hong
Abstract: Millimeter-wave radar plays a vital role in 3D object detection for autonomous driving due to its all-weather and all-lighting-condition capabilities for perception. However, radar point clouds suffer from pronounced sparsity and unavoidable angle estimation errors. To address these limitations, incorporating a camera may partially help mitigate the shortcomings. Nevertheless, the direct fusion of radar and camera data can lead to negative or even opposite effects due to the lack of depth information in images and low-quality image features under adverse lighting conditions. Hence, in this paper, we present the radar-camera fusion network with Hybrid Generation and Synchronization (HGSFusion), designed to better fuse radar potentials and image features for 3D object detection. Specifically, we propose the Radar Hybrid Generation Module (RHGM), which fully considers the Direction-Of-Arrival (DOA) estimation errors in radar signal processing. This module generates denser radar points through different Probability Density Functions (PDFs) with the assistance of semantic information. Meanwhile, we introduce the Dual Sync Module (DSM), comprising spatial sync and modality sync, to enhance image features with radar positional information and facilitate the fusion of distinct characteristics in different modalities. Extensive experiments demonstrate the effectiveness of our approach, outperforming the state-of-the-art methods in the VoD and TJ4DRadSet datasets by $6.53\%$ and $2.03\%$ in RoI AP and BEV AP, respectively. The code is available at https://github.com/garfield-cpp/HGSFusion.
Authors: Ziyang Chen, Yiwen Ye, Feilong Tang, Yongsheng Pan, Yong Xia
Abstract: Domain generalization (DG) aims to enhance the ability of models trained on source domains to generalize effectively to unseen domains. Recently, Sharpness-Aware Minimization (SAM) has shown promise in this area by reducing the sharpness of the loss landscape to obtain more generalized models. However, SAM and its variants sometimes fail to guide the model toward a flat minimum, and their training processes exhibit limitations, hindering further improvements in model generalization. In this paper, we first propose an improved model training process aimed at encouraging the model to converge to a flat minima. To achieve this, we design a curvature metric that has a minimal effect when the model is far from convergence but becomes increasingly influential in indicating the curvature of the minima as the model approaches a local minimum. Then we derive a novel algorithm from this metric, called Meta Curvature-Aware Minimization (MeCAM), to minimize the curvature around the local minima. Specifically, the optimization objective of MeCAM simultaneously minimizes the regular training loss, the surrogate gap of SAM, and the surrogate gap of meta-learning. We provide theoretical analysis on MeCAM's generalization error and convergence rate, and demonstrate its superiority over existing DG methods through extensive experiments on five benchmark DG datasets, including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. Code will be available on GitHub.
Authors: Behzad Shayegh, Hobie H. -B. Lee, Xiaodan Zhu, Jackie Chi Kit Cheung, Lili Mou
Abstract: We address unsupervised dependency parsing by building an ensemble of diverse existing models through post hoc aggregation of their output dependency parse structures. We observe that these ensembles often suffer from low robustness against weak ensemble components due to error accumulation. To tackle this problem, we propose an efficient ensemble-selection approach that avoids error accumulation. Results demonstrate that our approach outperforms each individual model as well as previous ensemble techniques. Additionally, our experiments show that the proposed ensemble-selection method significantly enhances the performance and robustness of our ensemble, surpassing previously proposed strategies, which have not accounted for error diversity.
Authors: Sungdong Lee, Joshua Bang, Youngrae Kim, Hyungwon Choi, Sang-Yun Oh, Joong-Ho Won
Abstract: Graphical model estimation from modern multi-omics data requires a balance between statistical estimation performance and computational scalability. We introduce a novel pseudolikelihood-based graphical model framework that reparameterizes the target precision matrix while preserving sparsity pattern and estimates it by minimizing an $\ell_1$-penalized empirical risk based on a new loss function. The proposed estimator maintains estimation and selection consistency in various metrics under high-dimensional assumptions. The associated optimization problem allows for a provably fast computation algorithm using a novel operator-splitting approach and communication-avoiding distributed matrix multiplication. A high-performance computing implementation of our framework was tested in simulated data with up to one million variables demonstrating complex dependency structures akin to biological networks. Leveraging this scalability, we estimated partial correlation network from a dual-omic liver cancer data set. The co-expression network estimated from the ultrahigh-dimensional data showed superior specificity in prioritizing key transcription factors and co-activators by excluding the impact of epigenomic regulation, demonstrating the value of computational scalability in multi-omic data analysis. %derived from the gene expression data.
Authors: Filippo Bigi, Marcel Langer, Michele Ceriotti
Abstract: The use of machine learning to estimate the energy of a group of atoms, and the forces that drive them to more stable configurations, have revolutionized the fields of computational chemistry and materials discovery. In this domain, rigorous enforcement of symmetry and conservation laws has traditionally been considered essential. For this reason, interatomic forces are usually computed as the derivatives of the potential energy, ensuring energy conservation. Several recent works have questioned this physically-constrained approach, suggesting that using the forces as explicit learning targets yields a better trade-off between accuracy and computational efficiency - and that energy conservation can be learned during training. The present work investigates the applicability of such non-conservative models in microscopic simulations. We identify and demonstrate several fundamental issues, from ill-defined convergence of geometry optimization to instability in various types of molecular dynamics. Contrary to the case of rotational symmetry, lack of energy conservation is hard to learn, control, and correct. The best approach to exploit the acceleration afforded by direct force evaluation might be to use it in tandem with a conservative model, reducing - rather than eliminating - the additional cost of backpropagation, but avoiding most of the pathological behavior associated with non-conservative forces.
Authors: Jiale Cheng, Xiao Liu, Cunxiang Wang, Xiaotao Gu, Yida Lu, Dan Zhang, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang
Abstract: Instruction-following is a fundamental capability of language models, requiring the model to recognize even the most subtle requirements in the instructions and accurately reflect them in its output. Such an ability is well-suited for and often optimized by preference learning. However, existing methods often directly sample multiple independent responses from the model when creating preference pairs. Such practice can introduce content variations irrelevant to whether the instruction is precisely followed (e.g., different expressions about the same semantic), interfering with the goal of teaching models to recognize the key differences that lead to improved instruction following. In light of this, we introduce SPaR, a self-play framework integrating tree-search self-refinement to yield valid and comparable preference pairs free from distractions. By playing against itself, an LLM employs a tree-search strategy to refine its previous responses with respect to the instruction while minimizing unnecessary variations. Our experiments show that a LLaMA3-8B model, trained over three iterations guided by SPaR, surpasses GPT-4-Turbo on the IFEval benchmark without losing general capabilities. Furthermore, SPaR demonstrates promising scalability and transferability, greatly enhancing models like GLM-4-9B and LLaMA3-70B. We also identify how inference scaling in tree search would impact model performance. Our code and data are publicly available at https://github.com/thu-coai/SPaR.
Authors: Svetlana Pavlitska, Enrico Eisen, J. Marius Z\"ollner
Abstract: Vulnerability to adversarial attacks is a well-known deficiency of deep neural networks. Larger networks are generally more robust, and ensembling is one method to increase adversarial robustness: each model's weaknesses are compensated by the strengths of others. While an ensemble uses a deterministic rule to combine model outputs, a mixture of experts (MoE) includes an additional learnable gating component that predicts weights for the outputs of the expert models, thus determining their contributions to the final prediction. MoEs have been shown to outperform ensembles on specific tasks, yet their susceptibility to adversarial attacks has not been studied yet. In this work, we evaluate the adversarial vulnerability of MoEs for semantic segmentation of urban and highway traffic scenes. We show that MoEs are, in most cases, more robust to per-instance and universal white-box adversarial attacks and can better withstand transfer attacks. Our code is available at \url{https://github.com/KASTEL-MobilityLab/mixtures-of-experts/}.
URLs: https://github.com/KASTEL-MobilityLab/mixtures-of-experts/
Authors: Ryuhaerang Choi, Taehan Kim, Subin Park, Jennifer G Kim, Sung-Ju Lee
Abstract: Eating disorders (ED) are complex mental health conditions that require long-term management and support. Recent advancements in large language model (LLM)-based chatbots offer the potential to assist individuals in receiving immediate support. Yet, concerns remain about their reliability and safety in sensitive contexts such as ED. We explore the opportunities and potential harms of using LLM-based chatbots for ED recovery. We observe the interactions between 26 participants with ED and an LLM-based chatbot, WellnessBot, designed to support ED recovery, over 10 days. We discovered that our participants have felt empowered in recovery by discussing ED-related stories with the chatbot, which served as a personal yet social avenue. However, we also identified harmful chatbot responses, especially concerning individuals with ED, that went unnoticed partly due to participants' unquestioning trust in the chatbot's reliability. Based on these findings, we provide design implications for safe and effective LLM-based interventions in ED management.
Authors: Julian Glattki, Nikhil Kapila, Tejas Rathi
Abstract: Convolutional Neural Networks (CNNs) have been the standard for image classification tasks for a long time, but more recently attention-based mechanisms have gained traction. This project aims to compare traditional CNNs with attention-augmented CNNs across an image classification task. By evaluating and comparing their performance, accuracy and computational efficiency, the project will highlight benefits and trade-off of the localized feature extraction of traditional CNNs and the global context capture in attention-augmented CNNs. By doing this, we can reveal further insights into their respective strengths and weaknesses, guide the selection of models based on specific application needs and ultimately, enhance understanding of these architectures in the deep learning community. This was our final project for CS7643 Deep Learning course at Georgia Tech.
Authors: Yu Kang, Xianghui Sun, Liangyu Chen, Wei Zou
Abstract: Generating Chain-of-Thought (CoT) before deriving the answer can effectively improve the reasoning capabilities of large language models (LLMs) and significantly improve the accuracy of the generated answer. However, in most cases, the length of the generated CoT is much longer than the desired final answer, which results in additional decoding costs. Furthermore, existing research has discovered that shortening the reasoning steps in CoT, even while preserving the key information, diminishes LLMs' abilities. These phenomena make it difficult to use LLMs and CoT in many real-world applications that only require the final answer and are sensitive to latency, such as search and recommendation. To reduce the costs of model decoding and shorten the length of the generated CoT, this paper presents $\textbf{C}$onditioned $\textbf{C}$ompressed $\textbf{C}$hain-of-$\textbf{T}$hought (C3oT), a CoT compression framework that involves a compressor to compress an original longer CoT into a shorter CoT while maintaining key information and interpretability, a conditioned training method to train LLMs with both longer CoT and shorter CoT simultaneously to learn the corresponding relationships between them, and a conditioned inference method to gain the reasoning ability learned from longer CoT by generating shorter CoT. We conduct experiments over four datasets from arithmetic and commonsense scenarios, showing that the proposed method is capable of compressing the length of generated CoT by up to more than 50% without compromising its effectiveness.
Authors: Chengyue Wang, Haicheng Liao, Bonan Wang, Yanchen Guan, Bin Rao, Ziyuan Pu, Zhiyong Cui, Chengzhong Xu, Zhenning Li
Abstract: Accurate trajectory prediction is essential for the safety and efficiency of autonomous driving. Traditional models often struggle with real-time processing, capturing non-linearity and uncertainty in traffic environments, efficiency in dense traffic, and modeling temporal dynamics of interactions. We introduce NEST (Neuromodulated Small-world Hypergraph Trajectory Prediction), a novel framework that integrates Small-world Networks and hypergraphs for superior interaction modeling and prediction accuracy. This integration enables the capture of both local and extended vehicle interactions, while the Neuromodulator component adapts dynamically to changing traffic conditions. We validate the NEST model on several real-world datasets, including nuScenes, MoCAD, and HighD. The results consistently demonstrate that NEST outperforms existing methods in various traffic scenarios, showcasing its exceptional generalization capability, efficiency, and temporal foresight. Our comprehensive evaluation illustrates that NEST significantly improves the reliability and operational efficiency of autonomous driving systems, making it a robust solution for trajectory prediction in complex traffic environments.
Authors: Luis Romero-Ben, Paul Irofti, Florin Stoican, Vicen\c{c} Puig
Abstract: Leakage in water systems results in significant daily water losses, degrading service quality, increasing costs, and aggravating environmental problems. Most leak localization methods rely solely on pressure data, missing valuable information from other sensor types. This article proposes a hydraulic state estimation methodology based on a dual Unscented Kalman Filter (UKF) approach, which enhances the estimation of both nodal hydraulic heads, critical in localization tasks, and pipe flows, useful for operational purposes. The approach enables the fusion of different sensor types, such as pressure, flow and demand meters. The strategy is evaluated in well-known open source case studies, namely Modena and L-TOWN, showing improvements over other state-of-the-art estimation approaches in terms of interpolation accuracy, as well as more precise leak localization performance in L-TOWN.
Authors: Shixin Jiang, Jiafeng Liang, Ming Liu, Bing Qin
Abstract: From the Specific-MLLM, which excels in single-modal tasks, to the Omni-MLLM, which extends the range of general modalities, this evolution aims to achieve understanding and generation of multimodal information. Omni-MLLM treats the features of different modalities as different "foreign languages," enabling cross-modal interaction and understanding within a unified space. To promote the advancement of related research, we have compiled 47 relevant papers to provide the community with a comprehensive introduction to Omni-MLLM. We first explain the four core components of Omni-MLLM for unified modeling and interaction of multiple modalities. Next, we introduce the effective integration achieved through "alignment pretraining" and "instruction fine-tuning," and discuss open-source datasets and testing of interaction capabilities. Finally, we summarize the main challenges facing current Omni-MLLM and outline future directions.
Authors: Shreya Sinha Roy, Richard G. Everitt, Christian P. Robert, Ritabrata Dutta
Abstract: Bayesian reinforcement learning (BRL) is a method that merges principles from Bayesian statistics and reinforcement learning to make optimal decisions in uncertain environments. Similar to other model-based RL approaches, it involves two key components: (1) Inferring the posterior distribution of the data generating process (DGP) modeling the true environment and (2) policy learning using the learned posterior. We propose to model the dynamics of the unknown environment through deep generative models assuming Markov dependence. In absence of likelihood functions for these models we train them by learning a generalized predictive-sequential (or prequential) scoring rule (SR) posterior. We use sequential Monte Carlo (SMC) samplers to draw samples from this generalized Bayesian posterior distribution. In conjunction, to achieve scalability in the high dimensional parameter space of the neural networks, we use the gradient based Markov chain Monte Carlo (MCMC) kernels within SMC. To justify the use of the prequential scoring rule posterior we prove a Bernstein-von Misses type theorem. For policy learning, we propose expected Thompson sampling (ETS) to learn the optimal policy by maximizing the expected value function with respect to the posterior distribution. This improves upon traditional Thompson sampling (TS) and its extensions which utilize only one sample drawn from the posterior distribution. This improvement is studied both theoretically and using simulation studies assuming discrete action and state-space. Finally we successfully extend our setup for a challenging problem with continuous action space without theoretical guarantees.
Authors: Yanfeng Yang, Shuai Li, Yingjie Zhang, Zhuoran Sun, Hai Shu, Ziqi Chen, Renmin Zhang
Abstract: Conditional independence (CI) testing is a fundamental task in modern statistics and machine learning. The conditional randomization test (CRT) was recently introduced to test whether two random variables, $X$ and $Y$, are conditionally independent given a potentially high-dimensional set of random variables, $Z$. The CRT operates exceptionally well under the assumption that the conditional distribution $X|Z$ is known. However, since this distribution is typically unknown in practice, accurately approximating it becomes crucial. In this paper, we propose using conditional diffusion models (CDMs) to learn the distribution of $X|Z$. Theoretically and empirically, it is shown that CDMs closely approximate the true conditional distribution. Furthermore, CDMs offer a more accurate approximation of $X|Z$ compared to GANs, potentially leading to a CRT that performs better than those based on GANs. To accommodate complex dependency structures, we utilize a computationally efficient classifier-based conditional mutual information (CMI) estimator as our test statistic. The proposed testing procedure performs effectively without requiring assumptions about specific distribution forms or feature dependencies, and is capable of handling mixed-type conditioning sets that include both continuous and discrete variables. Theoretical analysis shows that our proposed test achieves a valid control of the type I error. A series of experiments on synthetic data demonstrates that our new test effectively controls both type-I and type-II errors, even in high dimensional scenarios.
Authors: Jiayu Chen, Chao Yu, Yuqing Xie, Feng Gao, Yinuo Chen, Shu'ang Yu, Wenhao Tang, Shilong Ji, Mo Mu, Yi Wu, Huazhong Yang, Yu Wang
Abstract: Executing precise and agile flight maneuvers is critical for quadrotors in various applications. Traditional quadrotor control approaches are limited by their reliance on flat trajectories or time-consuming optimization, which restricts their flexibility. Recently, RL-based policy has emerged as a promising alternative due to its ability to directly map observations to actions, reducing the need for detailed system knowledge and actuation constraints. However, a significant challenge remains in bridging the sim-to-real gap, where RL-based policies often experience instability when deployed in real world. In this paper, we investigate key factors for learning robust RL-based control policies that are capable of zero-shot deployment in real-world quadrotors. We identify five critical factors and we develop a PPO-based training framework named SimpleFlight, which integrates these five techniques. We validate the efficacy of SimpleFlight on Crazyflie quadrotor, demonstrating that it achieves more than a 50% reduction in trajectory tracking error compared to state-of-the-art RL baselines, and achieves 70% improvement over the traditional MPC. The policy derived by SimpleFlight consistently excels across both smooth polynominal trajectories and challenging infeasible zigzag trajectories on small thrust-to-weight quadrotors. In contrast, baseline methods struggle with high-speed or infeasible trajectories. To support further research and reproducibility, we integrate SimpleFlight into a GPU-based simulator Omnidrones and provide open-source access to the code and model checkpoints. We hope SimpleFlight will offer valuable insights for advancing RL-based quadrotor control. For more details, visit our project website at https://sites.google.com/view/simpleflight/.
Authors: Seonho An, Young Yik Rhim, Min-Soo Kim
Abstract: As social systems become increasingly complex, legal articles are also growing more intricate, making it progressively harder for humans to identify any potential competitions among them, particularly when drafting new laws or applying existing laws. Despite this challenge, no method for detecting such competitions has been proposed so far. In this paper, we propose a new legal AI task called Legal Article Competition Detection (LACD), which aims to identify competing articles within a given law. Our novel retrieval method, CAM-Re2, outperforms existing relevant methods, reducing false positives by 20.8% and false negatives by 8.3%, while achieving a 98.2% improvement in precision@5, for the LACD task. We release our codes at https://github.com/asmath472/LACD-public.
Authors: Wadjih Bencheikh, Jan Finkbeiner, Emre Neftci
Abstract: Recurrent neural networks (RNNs) are valued for their computational efficiency and reduced memory requirements on tasks involving long sequence lengths but require high memory-processor bandwidth to train. Checkpointing techniques can reduce the memory requirements by only storing a subset of intermediate states, the checkpoints, but are still rarely used due to the computational overhead of the additional recomputation phase. This work addresses these challenges by introducing memory-efficient gradient checkpointing strategies tailored for the general class of sparse RNNs and Spiking Neural Networks (SNNs). SNNs are energy efficient alternatives to RNNs thanks to their local, event-driven operation and potential neuromorphic implementation. We use the Intelligence Processing Unit (IPU) as an exemplary platform for architectures with distributed local memory. We exploit its suitability for sparse and irregular workloads to scale SNN training on long sequence lengths. We find that Double Checkpointing emerges as the most effective method, optimizing the use of local memory resources while minimizing recomputation overhead. This approach reduces dependency on slower large-scale memory access, enabling training on sequences over 10 times longer or 4 times larger networks than previously feasible, with only marginal time overhead. The presented techniques demonstrate significant potential to enhance scalability and efficiency in training sparse and recurrent networks across diverse hardware platforms, and highlights the benefits of sparse activations for scalable recurrent neural network training.
Authors: Marcin Wrona, Andrej Pr\v{s}a
Abstract: In modern astronomy, the quantity of data collected has vastly exceeded the capacity for manual analysis, necessitating the use of advanced artificial intelligence (AI) techniques to assist scientists with the most labor-intensive tasks. AI can optimize simulation codes where computational bottlenecks arise from the time required to generate forward models. One such example is PHOEBE, a modeling code for eclipsing binaries (EBs), where simulating individual systems is feasible, but analyzing observables for extensive parameter combinations is highly time-consuming. To address this, we present a fully connected feedforward artificial neural network (ANN) trained on a dataset of over one million synthetic light curves generated with PHOEBE. Optimization of the ANN architecture yielded a model with six hidden layers, each containing 512 nodes, provides an optimized balance between accuracy and computational complexity. Extensive testing enabled us to establish ANN's applicability limits and to quantify the systematic and statistical errors associated with using such networks for EB analysis. Our findings demonstrate the critical role of dilution effects in parameter estimation for EBs, and we outline methods to incorporate these effects in AI-based models. This proposed ANN framework enables a speedup of over four orders of magnitude compared to traditional methods, with systematic errors not exceeding 1\%, and often as low as 0.01\%, across the entire parameter space.
Authors: Lucas Jos\'e da Costa, Vinicius Ruiz Uemoto, Mariana F. N. de Marchi, Renato de Aguiar Hortegal, Renata Valeri de Freitas
Abstract: Use real word data to evaluate the performance of the electrocardiographic markers of GEH as features in a machine learning model with Standard ECG features and Risk Factors in Predicting Outcome of patients in a population referred to a tertiary cardiology hospital. Patients forwarded to specific evaluation in a cardiology specialized hospital performed an ECG and a risk factor anamnesis. A series of follow up attendances occurred in periods of 6 months, 12 months and 15 months to check for cardiovascular related events (mortality or new nonfatal cardiovascular events (Stroke, MI, PCI, CS), as identified during 1-year phone follow-ups. The first attendance ECG was measured by a specialist and processed in order to obtain the global electric heterogeneity (GEH) using the Kors Matriz. The ECG measurements, GEH parameters and risk factors were combined for training multiple instances of XGBoost decision trees models. Each instance were optmized for the AUCPR and the instance with higher AUC is chosen as representative to the model. The importance of each parameter for the winner tree model was compared to better understand the improvement from using GEH parameters. The GEH parameters turned out to have statistical significance for this population specially the QRST angle and the SVG. The combined model with the tree parameters class had the best performance. The findings suggest that using VCG features can facilitate more accurate identification of patients who require tertiary care, thereby optimizing resource allocation and improving patient outcomes. Moreover, the decision tree model's transparency and ability to pinpoint critical features make it a valuable tool for clinical decision-making and align well with existing clinical practices.
Authors: Tiantian Liang, Zhe Yang
Abstract: Session-based recommendation seeks to forecast the next item a user will be interested in, based on their interaction sequences. Due to limited interaction data, session-based recommendation faces the challenge of limited data availability. Traditional methods enhance feature learning by constructing complex models to generate positive and negative samples. This paper proposes a session-based recommendation model using Single Positive optimization loss and Graph Learning (SPGL) to deal with the problem of data sparsity, high model complexity and weak transferability. SPGL utilizes graph convolutional networks to generate global item representations and batch session representations, effectively capturing intrinsic relationships between items. The use of single positive optimization loss improves uniformity of item representations, thereby enhancing recommendation accuracy. In the intent extractor, SPGL considers the hop count of the adjacency matrix when constructing the directed global graph to fully integrate spatial information. It also takes into account the reverse positional information of items when constructing session representations to incorporate temporal information. Comparative experiments across three benchmark datasets, Tmall, RetailRocket and Diginetica, demonstrate the model's effectiveness. The source code can be accessed on https://github.com/liang-tian-tian/SPGL .
Authors: Ramy A. Zeineldin, Franziska Mathis-Ullrich
Abstract: Motivated by the need for advanced solutions in the segmentation and inpainting of glioma-affected brain regions in multi-modal magnetic resonance imaging (MRI), this study presents an integrated approach leveraging the strengths of ensemble learning with hybrid transformer models and convolutional neural networks (CNNs), alongside the innovative application of 3D Pix2Pix Generative Adversarial Network (GAN). Our methodology combines robust tumor segmentation capabilities, utilizing axial attention and transformer encoders for enhanced spatial relationship modeling, with the ability to synthesize biologically plausible brain tissue through 3D Pix2Pix GAN. This integrated approach addresses the BraTS 2023 cluster challenges by offering precise segmentation and realistic inpainting, tailored for diverse tumor types and sub-regions. The results demonstrate outstanding performance, evidenced by quantitative evaluations such as the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD95) for segmentation, and Structural Similarity Index Measure (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Mean-Square Error (MSE) for inpainting. Qualitative assessments further validate the high-quality, clinically relevant outputs. In conclusion, this study underscores the potential of combining advanced machine learning techniques for comprehensive brain tumor analysis, promising significant advancements in clinical decision-making and patient care within the realm of medical imaging.
Authors: Zhenyu Wang, Yifan Hu, Peter B\"uhlmann, Zijian Guo
Abstract: Data from multiple environments offer valuable opportunities to uncover causal relationships among variables. Leveraging the assumption that the causal outcome model remains invariant across heterogeneous environments, state-of-the-art methods attempt to identify causal outcome models by learning invariant prediction models and rely on exhaustive searches over all (exponentially many) covariate subsets. These approaches present two major challenges: 1) determining the conditions under which the invariant prediction model aligns with the causal outcome model, and 2) devising computationally efficient causal discovery algorithms that scale polynomially, instead of exponentially, with the number of covariates. To address both challenges, we focus on the additive intervention regime and propose nearly necessary and sufficient conditions for ensuring that the invariant prediction model matches the causal outcome model. Exploiting the essentially necessary identifiability conditions, we introduce Negative Weight Distributionally Robust Optimization NegDRO a nonconvex continuous minimax optimization whose global optimizer recovers the causal outcome model. Unlike standard group DRO problems that maximize over the simplex, NegDRO allows negative weights on environment losses, which break the convexity. Despite its nonconvexity, we demonstrate that a standard gradient method converges to the causal outcome model, and we establish the convergence rate with respect to the sample size and the number of iterations. Our algorithm avoids exhaustive search, making it scalable especially when the number of covariates is large. The numerical results further validate the efficiency of the proposed method.
Authors: Philipp Reiser, Paul-Christian B\"urkner, Anneli Guthke
Abstract: Surrogate models are often used as computationally efficient approximations to complex simulation models, enabling tasks such as solving inverse problems, sensitivity analysis, and probabilistic forward predictions, which would otherwise be computationally infeasible. During training, surrogate parameters are fitted such that the surrogate reproduces the simulation model's outputs as closely as possible. However, the simulation model itself is merely a simplification of the real-world system, often missing relevant processes or suffering from misspecifications e.g., in inputs or boundary conditions. Hints about these might be captured in real-world measurement data, and yet, we typically ignore those hints during surrogate building. In this paper, we propose two novel probabilistic approaches to integrate simulation data and real-world measurement data during surrogate training. The first method trains separate surrogate models for each data source and combines their predictive distributions, while the second incorporates both data sources by training a single surrogate. We show the conceptual differences and benefits of the two approaches through both synthetic and real-world case studies. The results demonstrate the potential of these methods to improve predictive accuracy, predictive coverage, and to diagnose problems in the underlying simulation model. These insights can improve system understanding and future model development.
Authors: Simon Rampp, Andreas Triantafyllopoulos, Manuel Milling, Bj\"orn W. Schuller
Abstract: This work introduces the key operating principles for autrainer, our new deep learning training framework for computer audition tasks. autrainer is a PyTorch-based toolkit that allows for rapid, reproducible, and easily extensible training on a variety of different computer audition tasks. Concretely, autrainer offers low-code training and supports a wide range of neural networks as well as preprocessing routines. In this work, we present an overview of its inner workings and key capabilities.
Authors: Yuti Liu, Shice Liu, Junyuan Gao, Pengtao Jiang, Hao Zhang, Jinwei Chen, Bo Li
Abstract: Image Aesthetic Assessment (IAA) is a vital and intricate task that entails analyzing and assessing an image's aesthetic values, and identifying its highlights and areas for improvement. Traditional methods of IAA often concentrate on a single aesthetic task and suffer from inadequate labeled datasets, thus impairing in-depth aesthetic comprehension. Despite efforts to overcome this challenge through the application of Multi-modal Large Language Models (MLLMs), such models remain underdeveloped for IAA purposes. To address this, we propose a comprehensive aesthetic MLLM capable of nuanced aesthetic insight. Central to our approach is an innovative multi-scale text-guided self-supervised learning technique. This technique features a multi-scale feature alignment module and capitalizes on a wealth of unlabeled data in a self-supervised manner to structurally and functionally enhance aesthetic ability. The empirical evidence indicates that accompanied with extensive instruct-tuning, our model sets new state-of-the-art benchmarks across multiple tasks, including aesthetic scoring, aesthetic commenting, and personalized image aesthetic assessment. Remarkably, it also demonstrates zero-shot learning capabilities in the emerging task of aesthetic suggesting. Furthermore, for personalized image aesthetic assessment, we harness the potential of in-context learning and showcase its inherent advantages.
Authors: Giordano Cicchetti, Eleonora Grassucci, Luigi Sigillo, Danilo Comminiello
Abstract: Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of modalities via contrastive learning, their solutions are unsuitable when scaling to multiple modalities. These models typically align each modality to a designated anchor without ensuring the alignment of all modalities with each other, leading to suboptimal performance in tasks requiring a joint understanding of multiple modalities. In this paper, we structurally rethink the pairwise conventional approach to multimodal learning and we present the novel Gramian Representation Alignment Measure (GRAM), which overcomes the above-mentioned limitations. GRAM learns and then aligns $n$ modalities directly in the higher-dimensional space in which modality embeddings lie by minimizing the Gramian volume of the $k$-dimensional parallelotope spanned by the modality vectors, ensuring the geometric alignment of all modalities simultaneously. GRAM can replace cosine similarity in any downstream method, holding for 2 to $n$ modality and providing more meaningful alignment with respect to previous similarity measures. The novel GRAM-based contrastive loss function enhances the alignment of multimodal models in the higher-dimensional embedding space, leading to new state-of-the-art performance in downstream tasks such as video-audio-text retrieval and audio-video classification. The project page, the code, and the pretrained models are available at https://ispamm.github.io/GRAM/.
Authors: Whitney Sloneker, Shalin Patel, Michael Wang, Lorin Crawford, Ritambhara Singh
Abstract: Graph neural networks (GNNs) are powerful tools for conducting inference on graph data but are often seen as "black boxes" due to difficulty in extracting meaningful subnetworks driving predictive performance. Many interpretable GNN methods exist, but they cannot quantify uncertainty in edge weights and suffer in predictive accuracy when applied to challenging graph structures. In this work, we proposed BetaExplainer which addresses these issues by using a sparsity-inducing prior to mask unimportant edges during model training. To evaluate our approach, we examine various simulated data sets with diverse real-world characteristics. Not only does this implementation provide a notion of edge importance uncertainty, it also improves upon evaluation metrics for challenging datasets compared to state-of-the art explainer methods.
Authors: Janni Yuval, Ian Langmore, Dmitrii Kochkov, Stephan Hoyer
Abstract: Climate models struggle to accurately simulate precipitation, particularly extremes and the diurnal cycle. Here, we present a hybrid model that is trained directly on satellite-based precipitation observations. Our model runs at 2.8$^\circ$ resolution and is built on the differentiable NeuralGCM framework. The model demonstrates significant improvements over existing general circulation models, the ERA5 reanalysis, and a global cloud-resolving model in simulating precipitation. Our approach yields reduced biases, a more realistic precipitation distribution, improved representation of extremes, and a more accurate diurnal cycle. Furthermore, it outperforms the mid-range precipitation forecast of the ECMWF ensemble. This advance paves the way for more reliable simulations of current climate and demonstrates how training on observations can be used to directly improve GCMs.
Authors: Clement Dinh, Yunhao Fan, Gia-Wei Chern
Abstract: An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer. Compared with other recurrent neural networks, one great advantage of ESN is the simplicity of its training process. Yet, despite the seemingly restricted learnable parameters, ESN has been shown to successfully capture the spatial-temporal dynamics of complex patterns. Here we build an ESN to model the coarsening dynamics of charge-density waves (CDW) in a semi-classical Holstein model, which exhibits a checkerboard electron density modulation at half-filling stabilized by a commensurate lattice distortion. The inputs to the ESN are local CDW order-parameters in a finite neighborhood centered around a given site, while the output is the predicted CDW order of the center site at the next time step. Special care is taken in the design of couplings between hidden layer and input nodes to ensure lattice symmetries are properly incorporated into the ESN model. Since the model predictions depend only on CDW configurations of a finite domain, the ESN is scalable and transferrable in the sense that a model trained on dataset from a small system can be directly applied to dynamical simulations on larger lattices. Our work opens a new avenue for efficient dynamical modeling of pattern formations in functional electron materials.
Authors: Debarshi Kundu
Abstract: Consider the problem: ``If one man and one woman can produce one child in one year, how many children will be produced by one woman and three men in 0.5 years?" Current large language models (LLMs) such as GPT-4o, GPT-o1-preview, and Gemini Flash frequently answer "0.5," which does not make sense. While these models sometimes acknowledge the unrealistic nature of the question, in many cases (8 out of 10 trials), they provide the nonsensical answer of "0.5 child." Additionally, temporal variation has been observed: if an LLM answers correctly once (by recognizing the faulty nature of the question), subsequent responses are more likely to also reflect this understanding. However, this is inconsistent. These types of questions have motivated us to develop a dataset of science questions, SciFaultyQA, where the questions themselves are intentionally faulty. We observed that LLMs often proceed to answer these flawed questions without recognizing their inherent issues, producing results that are logically or scientifically invalid. By analyzing such patterns, we developed a novel method for generating synthetic datasets to evaluate and benchmark the performance of various LLMs in identifying these flawed questions. We have also developed novel approaches to reduce the errors.
Authors: Jiya Manchanda, Laura Boettcher, Matheus Westphalen, Jasser Jasser
Abstract: Large language models (LLMs) mark a key shift in natural language processing (NLP), having advanced text generation, translation, and domain-specific reasoning. Closed-source models like GPT-4, powered by proprietary datasets and extensive computational resources, lead with state-of-the-art performance today. However, they face criticism for their "black box" nature and for limiting accessibility in a manner that hinders reproducibility and equitable AI development. By contrast, open-source initiatives like LLaMA and BLOOM prioritize democratization through community-driven development and computational efficiency. These models have significantly reduced performance gaps, particularly in linguistic diversity and domain-specific applications, while providing accessible tools for global researchers and developers. Notably, both paradigms rely on foundational architectural innovations, such as the Transformer framework by Vaswani et al. (2017). Closed-source models excel by scaling effectively, while open-source models adapt to real-world applications in underrepresented languages and domains. Techniques like Low-Rank Adaptation (LoRA) and instruction-tuning datasets enable open-source models to achieve competitive results despite limited resources. To be sure, the tension between closed-source and open-source approaches underscores a broader debate on transparency versus proprietary control in AI. Ethical considerations further highlight this divide. Closed-source systems restrict external scrutiny, while open-source models promote reproducibility and collaboration but lack standardized auditing documentation frameworks to mitigate biases. Hybrid approaches that leverage the strengths of both paradigms are likely to shape the future of LLM innovation, ensuring accessibility, competitive technical performance, and ethical deployment.
Authors: Nong Minh Hieu, Antoine Ledent, Yunwen Lei, Cheng Yeaw Ku
Abstract: In this paper, we present generalization bounds for the unsupervised risk in the Deep Contrastive Representation Learning framework, which employs deep neural networks as representation functions. We approach this problem from two angles. On the one hand, we derive a parameter-counting bound that scales with the overall size of the neural networks. On the other hand, we provide a norm-based bound that scales with the norms of neural networks' weight matrices. Ignoring logarithmic factors, the bounds are independent of $k$, the size of the tuples provided for contrastive learning. To the best of our knowledge, this property is only shared by one other work, which employed a different proof strategy and suffers from very strong exponential dependence on the depth of the network which is due to a use of the peeling technique. Our results circumvent this by leveraging powerful results on covering numbers with respect to uniform norms over samples. In addition, we utilize loss augmentation techniques to further reduce the dependency on matrix norms and the implicit dependence on network depth. In fact, our techniques allow us to produce many bounds for the contrastive learning setting with similar architectural dependencies as in the study of the sample complexity of ordinary loss functions, thereby bridging the gap between the learning theories of contrastive learning and DNNs.
Authors: Tim Sziburis, Susanne Blex, Tobias Glasmachers, Ioannis Iossifidis
Abstract: The identification of individual movement characteristics sets the foundation for the assessment of personal rehabilitation progress and can provide diagnostic information on levels and stages of movement disorders. This work presents a preliminary study for differentiating individual motion patterns using a dataset of 3D upper-limb transport trajectories measured in task-space. Identifying individuals by deep time series learning can be a key step to abstracting individual motion properties. In this study, a classification accuracy of about 95% is reached for a subset of nine, and about 78% for the full set of 31 individuals. This provides insights into the separability of patient attributes by exerting a simple standardized task to be transferred to portable systems.
Authors: Mohammad Sadegh Salehi, Subhadip Mukherjee, Lindon Roberts, Matthias J. Ehrhardt
Abstract: Bilevel learning has gained prominence in machine learning, inverse problems, and imaging applications, including hyperparameter optimization, learning data-adaptive regularizers, and optimizing forward operators. The large-scale nature of these problems has led to the development of inexact and computationally efficient methods. Existing adaptive methods predominantly rely on deterministic formulations, while stochastic approaches often adopt a doubly-stochastic framework with impractical variance assumptions, enforces a fixed number of lower-level iterations, and requires extensive tuning. In this work, we focus on bilevel learning with strongly convex lower-level problems and a nonconvex sum-of-functions in the upper-level. Stochasticity arises from data sampling in the upper-level which leads to inexact stochastic hypergradients. We establish their connection to state-of-the-art stochastic optimization theory for nonconvex objectives. Furthermore, we prove the convergence of inexact stochastic bilevel optimization under mild assumptions. Our empirical results highlight significant speed-ups and improved generalization in imaging tasks such as image denoising and deblurring in comparison with adaptive deterministic bilevel methods.
Authors: Anja Butter, Fran\c{c}ois Charton, Javier Mari\~no Villadamigo, Ayodele Ore, Tilman Plehn, Jonas Spinner
Abstract: Generative networks are an exciting tool for fast LHC event generation. Usually, they are used to generate configurations with a fixed number of particles. Autoregressive transformers allow us to generate events with variable numbers of particles, very much in line with the physics of QCD jet radiation. We show how they can learn a factorized likelihood for jet radiation and extrapolate in terms of the number of generated jets. For this extrapolation, bootstrapping training data and training with modifications of the likelihood loss can be used.
Authors: Guoxuan Chen, Han Shi, Jiawei Li, Yihang Gao, Xiaozhe Ren, Yimeng Chen, Xin Jiang, Zhenguo Li, Weiyang Liu, Chao Huang
Abstract: Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable challenges, particularly in computational demands and inference speed, due to their quadratic complexity. In this work, we have identified a key pattern: certain seemingly meaningless special tokens (i.e., separators) contribute disproportionately to attention scores compared to semantically meaningful tokens. This observation suggests that information of the segments between these separator tokens can be effectively condensed into the separator tokens themselves without significant information loss. Guided by this insight, we introduce SepLLM, a plug-and-play framework that accelerates inference by compressing these segments and eliminating redundant tokens. Additionally, we implement efficient kernels for training acceleration. Experimental results across training-free, training-from-scratch, and post-training settings demonstrate SepLLM's effectiveness. Notably, using the Llama-3-8B backbone, SepLLM achieves over 50% reduction in KV cache on the GSM8K-CoT benchmark while maintaining comparable performance. Furthermore, in streaming settings, SepLLM effectively processes sequences of up to 4 million tokens or more while maintaining consistent language modeling capabilities.
Authors: Antonio Emanuele Cin\`a, Kathrin Grosse, Sebastiano Vascon, Ambra Demontis, Battista Biggio, Fabio Roli, Marcello Pelillo
Abstract: Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated in a variety of settings and against different models, the factors affecting their effectiveness are still not well understood. In this work, we provide a unifying framework to study the process of backdoor learning under the lens of incremental learning and influence functions. We show that the effectiveness of backdoor attacks depends on: (i) the complexity of the learning algorithm, controlled by its hyperparameters; (ii) the fraction of backdoor samples injected into the training set; and (iii) the size and visibility of the backdoor trigger. These factors affect how fast a model learns to correlate the presence of the backdoor trigger with the target class. Our analysis unveils the intriguing existence of a region in the hyperparameter space in which the accuracy on clean test samples is still high while backdoor attacks are ineffective, thereby suggesting novel criteria to improve existing defenses.
Authors: Maximilian P Niroomand, David J Wales
Abstract: The ability to explain decisions made by machine learning models remains one of the most significant hurdles towards widespread adoption of AI in highly sensitive areas such as medicine, cybersecurity or autonomous driving. Great interest exists in understanding which features of the input data prompt model decision making. In this contribution, we propose a novel approach to identify relevant features of the input data, inspired by methods from the energy landscapes field, developed in the physical sciences. By identifying conserved weights within groups of minima of the loss landscapes, we can identify the drivers of model decision making. Analogues to this idea exist in the molecular sciences, where coordinate invariants or order parameters are employed to identify critical features of a molecule. However, no such approach exists for machine learning loss landscapes. We will demonstrate the applicability of energy landscape methods to machine learning models and give examples, both synthetic and from the real world, for how these methods can help to make models more interpretable.
Authors: Abhinav Bhatia, Samer B. Nashed, Shlomo Zilberstein
Abstract: Meta reinforcement learning (meta-RL) methods such as RL$^2$ have emerged as promising approaches for learning data-efficient RL algorithms tailored to a given task distribution. However, they show poor asymptotic performance and struggle with out-of-distribution tasks because they rely on sequence models, such as recurrent neural networks or transformers, to process experiences rather than summarize them using general-purpose RL components such as value functions. In contrast, traditional RL algorithms are data-inefficient as they do not use domain knowledge, but do converge to an optimal policy in the limit. We propose RL$^3$, a principled hybrid approach that incorporates action-values, learned per task via traditional RL, in the inputs to meta-RL. We show that RL$^3$ earns greater cumulative reward in the long term compared to RL$^2$ while drastically reducing meta-training time and generalizes better to out-of-distribution tasks. Experiments are conducted on both custom and benchmark discrete domains from the meta-RL literature that exhibit a range of short-term, long-term, and complex dependencies.
Authors: Guanghui Zhu, Zhennan Zhu, Hongyang Chen, Chunfeng Yuan, Yihua Huang
Abstract: Heterogeneous graph neural networks (GNNs) have been successful in handling heterogeneous graphs. In existing heterogeneous GNNs, meta-path plays an essential role. However, recent work pointed out that simple homogeneous graph model without meta-path can also achieve comparable results, which calls into question the necessity of meta-path. In this paper, we first present the intrinsic difference about meta-path-based and meta-path-free models, i.e., how to select neighbors for node aggregation. Then, we propose a novel framework to utilize the rich type semantic information in heterogeneous graphs comprehensively, namely HAGNN (Hybrid Aggregation for Heterogeneous GNNs). The core of HAGNN is to leverage the meta-path neighbors and the directly connected neighbors simultaneously for node aggregations. HAGNN divides the overall aggregation process into two phases: meta-path-based intra-type aggregation and meta-path-free inter-type aggregation. During the intra-type aggregation phase, we propose a new data structure called fused meta-path graph and perform structural semantic aware aggregation on it. Finally, we combine the embeddings generated by each phase. Compared with existing heterogeneous GNN models, HAGNN can take full advantage of the heterogeneity in heterogeneous graphs. Extensive experimental results on node classification, node clustering, and link prediction tasks show that HAGNN outperforms the existing modes, demonstrating the effectiveness of HAGNN.
Authors: Zhuang Wang, Zhaozhuo Xu, Jingyi Xi, Yuke Wang, Anshumali Shrivastava, T. S. Eugene Ng
Abstract: Distributed training is the de facto standard to scale up the training of deep learning models with multiple GPUs. Its performance bottleneck lies in communications for gradient synchronization. Although high tensor sparsity is widely observed, the optimal communication scheme to fully leverage sparsity is still missing. This paper aims to bridge this gap. We first analyze the characteristics of sparse tensors in popular models to understand the fundamentals of sparsity. We then systematically explore the design space of communication schemes for sparse tensors and find the optimal ones. These findings give a new understanding and inspire us to develop a holistic gradient synchronization system called Zen for sparse tensors. We demonstrate that Zen can achieve up to 5.09x speedup in communication time and up to $2.48\times$ speedup in training throughput compared to the state-of-the-art methods.
Authors: Jett Janiak, Can Rager, James Dao, Yeu-Tong Lau
Abstract: Prior work suggests that language models manage the limited bandwidth of the residual stream through a "memory management" mechanism, where certain attention heads and MLP layers clear residual stream directions set by earlier layers. Our study provides concrete evidence for this erasure phenomenon in a 4-layer transformer, identifying heads that consistently remove the output of earlier heads. We further demonstrate that direct logit attribution (DLA), a common technique for interpreting the output of intermediate transformer layers, can show misleading results by not accounting for erasure.
Authors: Devvrit, Sneha Kudugunta, Aditya Kusupati, Tim Dettmers, Kaifeng Chen, Inderjit Dhillon, Yulia Tsvetkov, Hannaneh Hajishirzi, Sham Kakade, Ali Farhadi, Prateek Jain
Abstract: Foundation models are applied in a broad spectrum of settings with different inference constraints, from massive multi-accelerator clusters to resource-constrained standalone mobile devices. However, the substantial costs associated with training these models often limit the number of unique model sizes that can be offered. Consequently, practitioners are compelled to select a model that may not be optimally aligned with their specific latency and cost requirements. We present MatFormer, a novel Transformer architecture designed to provide elastic inference across diverse deployment constraints. MatFormer achieves this by incorporating a nested Feed Forward Network (FFN) block structure within a standard Transformer model. During training, we optimize the parameters of multiple nested FFN blocks with varying sizes, enabling the extraction of hundreds of accurate smaller models without incurring additional computational costs. We empirically validate the efficacy of MatFormer across different model classes (decoders and encoders) and modalities (language and vision), demonstrating its potential for real-world deployment. We show that a 850M decoder-only MatFormer language model (MatLM) allows us to extract multiple smaller models spanning from 582M to 850M parameters, each exhibiting better validation loss and one-shot downstream evaluations than independently trained counterparts. Furthermore, we observe that smaller encoders extracted from a universal MatFormer-based ViT (MatViT) encoder preserve the metric-space structure for adaptive large-scale retrieval. Finally, we showcase that speculative decoding with the accurate and consistent submodels extracted from MatFormer can lead to significant reduction in inference latency. Project website: https://devvrit.github.io/matformer/
Authors: Md Ferdous Alam, Parinaz Naghizadeh, David Hoelzle
Abstract: Reinforcement learning (RL) enables sequential decision-making in complex and high-dimensional environments through interaction with the environment. In most real-world applications, however, a high number of interactions are infeasible. In these environments, transfer RL algorithms, which can be used for the transfer of knowledge from one or multiple source environments to a target environment, have been shown to increase learning speed and improve initial and asymptotic performance. However, most existing transfer RL algorithms are on-policy and sample inefficient, fail in adversarial target tasks, and often require heuristic choices in algorithm design. This paper proposes an off-policy Advantage-based Policy Transfer algorithm, APT-RL, for fixed domain environments. Its novelty is in using the popular notion of ``advantage'' as a regularizer, to weigh the knowledge that should be transferred from the source, relative to new knowledge learned in the target, removing the need for heuristic choices. Further, we propose a new transfer performance measure to evaluate the performance of our algorithm and unify existing transfer RL frameworks. Finally, we present a scalable, theoretically-backed task similarity measurement algorithm to illustrate the alignments between our proposed transferability measure and similarities between source and target environments. We compare APT-RL with several baselines, including existing transfer-RL algorithms, in three high-dimensional continuous control tasks. Our experiments demonstrate that APT-RL outperforms existing transfer RL algorithms and is at least as good as learning from scratch in adversarial tasks.
Authors: Chloe Qinyu Zhu, Muhang Tian, Lesia Semenova, Jiachang Liu, Jack Xu, Joseph Scarpa, Cynthia Rudin
Abstract: Prediction of mortality in intensive care unit (ICU) patients typically relies on black box models (that are unacceptable for use in hospitals) or hand-tuned interpretable models (that might lead to the loss in performance). We aim to bridge the gap between these two categories by building on modern interpretable ML techniques to design interpretable mortality risk scores that are as accurate as black boxes. We developed a new algorithm, GroupFasterRisk, which has several important benefits: it uses both hard and soft direct sparsity regularization, it incorporates group sparsity to allow more cohesive models, it allows for monotonicity constraint to include domain knowledge, and it produces many equally-good models, which allows domain experts to choose among them. For evaluation, we leveraged the largest existing public ICU monitoring datasets (MIMIC III and eICU). Models produced by GroupFasterRisk outperformed OASIS and SAPS II scores and performed similarly to APACHE IV/IVa while using at most a third of the parameters. For patients with sepsis/septicemia, acute myocardial infarction, heart failure, and acute kidney failure, GroupFasterRisk models outperformed OASIS and SOFA. Finally, different mortality prediction ML approaches performed better based on variables selected by GroupFasterRisk as compared to OASIS variables. GroupFasterRisk's models performed better than risk scores currently used in hospitals, and on par with black box ML models, while being orders of magnitude sparser. Because GroupFasterRisk produces a variety of risk scores, it allows design flexibility - the key enabler of practical model creation. GroupFasterRisk is a fast, accessible, and flexible procedure that allows learning a diverse set of sparse risk scores for mortality prediction.
Authors: Aristotelis Ballas, Vasileios Papapanagiotou, Christos Diou
Abstract: Despite recent advancements in deep learning, its application in real-world medical settings, such as phonocardiogram (PCG) classification, remains limited. A significant barrier is the lack of high-quality annotated datasets, which hampers the development of robust, generalizable models that can perform well on newly collected, out-of-distribution (OOD) data. Self-Supervised Learning (SSL) contrastive learning, has shown promise in mitigating the issue of data scarcity by using unlabeled data to enhance model robustness. Even though SSL methods have been proposed and researched in other domains, works focusing on the impact of data augmentations on model robustness for PCG classification are limited. In particular, while augmentations are a key component in SSL, selecting the most suitable policy during training is highly challenging. Improper augmentations can lead to substantial performance degradation and even hinder a network's ability to learn meaningful representations. Addressing this gap, our research aims to explore and evaluate a wide range of audio-based augmentations and uncover combinations that enhance SSL model performance in PCG classification. We conduct a comprehensive comparative analysis across multiple datasets, assessing the impact of various augmentations on model performance. Our findings reveal that depending on the training distribution, augmentation choice significantly influences model robustness, with fully-supervised models experiencing up to a 32\% drop in effectiveness when evaluated on unseen data, while SSL models demonstrate greater resilience, losing only 10\% or even improving in some cases. This study also highlights the most promising and appropriate augmentations for PCG signal processing, by calculating their effect size on training. These insights equip researchers with valuable guidelines for developing reliable models in PCG signal processing.
Authors: Jinglong Luo, Yehong Zhang, Zhuo Zhang, Jiaqi Zhang, Xin Mu, Hui Wang, Yue Yu, Zenglin Xu
Abstract: With the growing use of Transformer models hosted on cloud platforms to offer inference services, privacy concerns are escalating, especially concerning sensitive data like investment plans and bank account details. Secure Multi-Party Computing (SMPC) emerges as a promising solution to protect the privacy of inference data and model parameters. However, the application of SMPC in Privacy-Preserving Inference (PPI) for Transformer models often leads to considerable slowdowns or declines in performance. This is largely due to the multitude of nonlinear operations in the Transformer architecture, which are not well-suited to SMPC and difficult to circumvent or optimize effectively. To address this concern, we introduce a comprehensive PPI framework called SecFormer to achieve fast and accurate PPI for Transformer models. We successfully eliminate the high-cost exponential and maximum operations in PPI without sacrificing model performance and develop a suite of efficient SMPC protocols by employing suitable numerical computation methods to boost other complex nonlinear functions in PPI, including GeLU, LayerNorm, and a redesigned Softmax. Our extensive experiments reveal that SecFormer outperforms MPCFormer in performance, showing improvements of $3.4\%$ and $24.7\%$ for BERT$_{\text{BASE}}$ and BERT$_{\text{LARGE}}$, respectively. In terms of efficiency, SecFormer is 3.57 and 3.58 times faster than PUMA for BERT$_{\text{BASE}}$ and BERT$_{\text{LARGE}}$, demonstrating its effectiveness and speed.
Authors: Kuangpu Guo, Yuhe Ding, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
Abstract: Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Although these methods improve the mean accuracy across all classes, we observe that vacant classes-referring to categories absent from a client's data distribution-remain poorly recognized. Besides, there is still a gap in the accuracy of local models on minority classes compared to the global model. This paper introduces FedVLS, a novel approach to label-skewed federated learning that integrates both vacant-class distillation and logit suppression simultaneously. Specifically, vacant-class distillation leverages knowledge distillation during local training on each client to retain essential information related to vacant classes from the global model. Moreover, logit suppression directly penalizes network logits for non-label classes, effectively addressing misclassifications in minority classes that may be biased toward majority classes. Extensive experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods across diverse datasets with varying degrees of label skews. Our code is available at https://github.com/krumpguo/FedVLS.
Authors: Prashansa Panda, Shalabh Bhatnagar
Abstract: Several recent works have focused on carrying out non-asymptotic convergence analyses for AC algorithms. Recently, a two-timescale critic-actor algorithm has been presented for the discounted cost setting in the look-up table case where the timescales of the actor and the critic are reversed and only asymptotic convergence shown. In our work, we present the first two-timescale critic-actor algorithm with function approximation in the long-run average reward setting and present the first finite-time non-asymptotic as well as asymptotic convergence analysis for such a scheme. We obtain optimal learning rates and prove that our algorithm achieves a sample complexity of {$\mathcal{\tilde{O}}(\epsilon^{-(2+\delta)})$ with $\delta >0$ arbitrarily close to zero,} for the mean squared error of the critic to be upper bounded by $\epsilon$ which is better than the one obtained for two-timescale AC in a similar setting. A notable feature of our analysis is that we present the asymptotic convergence analysis of our scheme in addition to the finite-time bounds that we obtain and show the almost sure asymptotic convergence of the (slower) critic recursion to the attractor of an associated differential inclusion with actor parameters corresponding to local maxima of a perturbed average reward objective. We also show the results of numerical experiments on three benchmark settings and observe that our critic-actor algorithm performs the best amongst all algorithms.
Authors: Hyesung Jeon, Yulhwa Kim, Jae-joon Kim
Abstract: Due to the high memory and computational costs associated with large language models (LLMs), model compression techniques such as quantization, which reduces inference costs, and parameter-efficient fine-tuning (PEFT) methods like Low-Rank Adaptation (LoRA), which reduce training costs, have gained significant popularity. This trend has spurred active research into quantization-aware PEFT techniques, aimed at maintaining model accuracy while minimizing memory overhead during both inference and training. Previous quantization-aware PEFT methods typically apply post-training quantization (PTQ) to pre-trained LLMs, followed by PEFT to recover accuracy loss. Meanwhile, this approach has limitations in recovering the accuracy loss. In this paper, we propose L4Q, a method that integrates Quantization-Aware Training (QAT) with LoRA. By employing a memory-optimized layer design, L4Q significantly reduces QAT's memory overhead, making its training cost comparable to LoRA, while preserving the advantage of QAT in producing fully quantized LLMs with high accuracy. Our experiments demonstrate that this combined approach to quantization and fine-tuning achieves superior accuracy compared to decoupled fine-tuning schemes, particularly in 4-bit and 3-bit quantization, positioning L4Q as an efficient QAT solution. Using the LLaMA and Mistral models with instructional datasets, we showcase L4Q's capabilities in language tasks and few-shot learning.
Authors: Zihao Luo, Xilie Xu, Feng Liu, Yun Sing Koh, Di Wang, Jingfeng Zhang
Abstract: Low-rank adaptation (LoRA) is an efficient strategy for adapting latent diffusion models (LDMs) on a private dataset to generate specific images by minimizing the adaptation loss. However, the LoRA-adapted LDMs are vulnerable to membership inference (MI) attacks that can judge whether a particular data point belongs to the private dataset, thus leading to the privacy leakage. To defend against MI attacks, we first propose a straightforward solution: Membership-Privacy-preserving LoRA (MP-LoRA). MP-LoRA is formulated as a min-max optimization problem where a proxy attack model is trained by maximizing its MI gain while the LDM is adapted by minimizing the sum of the adaptation loss and the MI gain of the proxy attack model. However, we empirically find that MP-LoRA has the issue of unstable optimization, and theoretically analyze that the potential reason is the unconstrained local smoothness, which impedes the privacy-preserving adaptation. To mitigate this issue, we further propose a Stable Membership-Privacy-preserving LoRA (SMP-LoRA) that adapts the LDM by minimizing the ratio of the adaptation loss to the MI gain. Besides, we theoretically prove that the local smoothness of SMP-LoRA can be constrained by the gradient norm, leading to improved convergence. Our experimental results corroborate that SMP-LoRA can indeed defend against MI attacks and generate high-quality images. Our Code is available at \url{https://github.com/WilliamLUO0/StablePrivateLoRA}.
Authors: Mingyue Cheng, Jiqian Yang, Tingyue Pan, Qi Liu, Zhi Li
Abstract: Designing effective models for learning time series representations is foundational for time series analysis. Many previous works have explored time series representation modeling approaches and have made progress in this area. Despite their effectiveness, they lack adaptive perception of local patterns in temporally dependent basic units and fail to capture the multi-scale dependency among these units. Instead of relying on prevalent methods centered around self-attention mechanisms, we propose ConvTimeNet, a hierarchical pure convolutional model designed for time series analysis. ConvTimeNet introduces a deformable patch layer that adaptively perceives local patterns of temporally dependent basic units in a data-driven manner. Based on the extracted local patterns, hierarchical pure convolutional blocks are designed to capture dependency relationships among the representations of basic units at different scales. Moreover, a large kernel mechanism is employed to ensure that convolutional blocks can be deeply stacked, thereby achieving a larger receptive field. In this way, local patterns and their multi-scale dependencies can be effectively modeled within a single model. Extensive experiments comparing a wide range of different types of models demonstrate that pure convolutional models still exhibit strong viability, effectively addressing the aforementioned two challenges and showing superior performance across multiple tasks. The code is available for reproducibility.
Authors: Keiyu Nosaka, Yuichi Takano, Akiko Yoshise
Abstract: The Data Collaboration (DC) framework provides a privacy-preserving solution for multi-source data fusion, enabling the joint analysis of data from multiple sources to achieve enhanced insights. It utilizes linear transformations with secretly selected bases to ensure privacy guarantees through non-iterative communication. Despite its strengths, the DC framework often encounters performance instability due to theoretical challenges in aligning the bases used for mapping raw data. This study addresses these challenges by establishing a rigorous theoretical foundation for basis alignment within the DC framework, formulating it as an optimization problem over orthogonal matrices. Under specific assumptions, we demonstrate that this problem can be reduced to the Orthogonal Procrustes Problem, which has a well-known analytical solution. Extensive empirical evaluations across diverse datasets reveal that the proposed alignment method significantly enhances model performance and computational efficiency, outperforming existing approaches. Additionally, it demonstrates robustness across varying levels of differential privacy, thus enabling practical and reliable implementations of the DC framework.
Authors: Agniv Bandyopadhyay, Sandeep Juneja, Shubhada Agrawal
Abstract: Top-$2$ methods have become popular in solving the best arm identification (BAI) problem. The best arm, or the arm with the largest mean amongst finitely many, is identified through an algorithm that at any sequential step independently pulls the empirical best arm, with a fixed probability $\beta$, and pulls the best challenger arm otherwise. The probability of incorrect selection is guaranteed to lie below a specified $\delta >0$. Information theoretic lower bounds on sample complexity are well known for BAI problem and are matched asymptotically as $\delta \rightarrow 0$ by computationally demanding plug-in methods. The above top 2 algorithm for any $\beta \in (0,1)$ has sample complexity within a constant of the lower bound. However, determining the optimal $\beta$ that matches the lower bound has proven difficult. In this paper, we address this and propose an optimal top-2 type algorithm. We consider a function of allocations anchored at a threshold. If it exceeds the threshold then the algorithm samples the empirical best arm. Otherwise, it samples the challenger arm. We show that the proposed algorithm is optimal as $\delta \rightarrow 0$. Our analysis relies on identifying a limiting fluid dynamics of allocations that satisfy a series of ordinary differential equations pasted together and that describe the asymptotic path followed by our algorithm. We rely on the implicit function theorem to show existence and uniqueness of these fluid ode's and to show that the proposed algorithm remains close to the ode solution.
Authors: Yunrui Li, Hao Xu, Ambrish Kumar, Duosheng Wang, Christian Heiss, Parastoo Azadi, Pengyu Hong
Abstract: Nuclear Magnetic Resonance (NMR) spectroscopy is essential for revealing molecular structure, electronic environment, and dynamics. Accurate NMR shift prediction allows researchers to validate structures by comparing predicted and observed shifts. While Machine Learning (ML) has improved one-dimensional (1D) NMR shift prediction, predicting 2D NMR remains challenging due to limited annotated data. To address this, we introduce an unsupervised training framework for predicting cross-peaks in 2D NMR, specifically Heteronuclear Single Quantum Coherence (HSQC).Our approach pretrains an ML model on an annotated 1D dataset of 1H and 13C shifts, then finetunes it in an unsupervised manner using unlabeled HSQC data, which simultaneously generates cross-peak annotations. Our model also adjusts for solvent effects. Evaluation on 479 expert-annotated HSQC spectra demonstrates our model's superiority over traditional methods (ChemDraw and Mestrenova), achieving Mean Absolute Errors (MAEs) of 2.05 ppm and 0.165 ppm for 13C shifts and 1H shifts respectively. Our algorithmic annotations show a 95.21% concordance with experts' assignments, underscoring the approach's potential for structural elucidation in fields like organic chemistry, pharmaceuticals, and natural products.
Authors: Pavlin G. Poli\v{c}ar, Bla\v{z} Zupan
Abstract: With the increasing availability of high-dimensional data, analysts often rely on exploratory data analysis to understand complex data sets. A key approach to exploring such data is dimensionality reduction, which embeds high-dimensional data in two dimensions to enable visual exploration. However, popular embedding techniques, such as t-SNE and UMAP, typically assume that data points are independent. When this assumption is violated, as in time-series data, the resulting visualizations may fail to reveal important temporal patterns and trends. To address this, we propose a formal extension to existing dimensionality reduction methods that incorporates two temporal loss terms that explicitly highlight temporal progression in the embedded visualizations. Through a series of experiments on both synthetic and real-world datasets, we demonstrate that our approach effectively uncovers temporal patterns and improves the interpretability of the visualizations. Furthermore, the method improves temporal coherence while preserving the fidelity of the embeddings, providing a robust tool for dynamic data analysis.
Authors: Weihua Hu, Yiwen Yuan, Zecheng Zhang, Akihiro Nitta, Kaidi Cao, Vid Kocijan, Jinu Sunil, Jure Leskovec, Matthias Fey
Abstract: We present PyTorch Frame, a PyTorch-based framework for deep learning over multi-modal tabular data. PyTorch Frame makes tabular deep learning easy by providing a PyTorch-based data structure to handle complex tabular data, introducing a model abstraction to enable modular implementation of tabular models, and allowing external foundation models to be incorporated to handle complex columns (e.g., LLMs for text columns). We demonstrate the usefulness of PyTorch Frame by implementing diverse tabular models in a modular way, successfully applying these models to complex multi-modal tabular data, and integrating our framework with PyTorch Geometric, a PyTorch library for Graph Neural Networks (GNNs), to perform end-to-end learning over relational databases.
Authors: Shuo Chen, Zhen Han, Bailan He, Zifeng Ding, Wenqian Yu, Philip Torr, Volker Tresp, Jindong Gu
Abstract: Various jailbreak attacks have been proposed to red-team Large Language Models (LLMs) and revealed the vulnerable safeguards of LLMs. Besides, some methods are not limited to the textual modality and extend the jailbreak attack to Multimodal Large Language Models (MLLMs) by perturbing the visual input. However, the absence of a universal evaluation benchmark complicates the performance reproduction and fair comparison. Besides, there is a lack of comprehensive evaluation of closed-source state-of-the-art (SOTA) models, especially MLLMs, such as GPT-4V. To address these issues, this work first builds a comprehensive jailbreak evaluation dataset with 1445 harmful questions covering 11 different safety policies. Based on this dataset, extensive red-teaming experiments are conducted on 11 different LLMs and MLLMs, including both SOTA proprietary models and open-source models. We then conduct a deep analysis of the evaluated results and find that (1) GPT4 and GPT-4V demonstrate better robustness against jailbreak attacks compared to open-source LLMs and MLLMs. (2) Llama2 and Qwen-VL-Chat are more robust compared to other open-source models. (3) The transferability of visual jailbreak methods is relatively limited compared to textual jailbreak methods. The dataset and code can be found https://github.com/chenxshuo/RedTeamingGPT4V
Authors: Yuri Kinoshita, Taro Toyoizumi
Abstract: While neural networks can enjoy an outstanding flexibility and exhibit unprecedented performance, the mechanism behind their behavior is still not well-understood. To tackle this fundamental challenge, researchers have tried to restrict and manipulate some of their properties in order to gain new insights and better control on them. Especially, throughout the past few years, the concept of \emph{bi-Lipschitzness} has been proved as a beneficial inductive bias in many areas. However, due to its complexity, the design and control of bi-Lipschitz architectures are falling behind, and a model that is precisely designed for bi-Lipschitzness realizing a direct and simple control of the constants along with solid theoretical analysis is lacking. In this work, we investigate and propose a novel framework for bi-Lipschitzness that can achieve such a clear and tight control based on convex neural networks and the Legendre-Fenchel duality. Its desirable properties are illustrated with concrete experiments. We also apply this framework to uncertainty estimation and monotone problem settings to illustrate its broad range of applications.
Authors: William Watson, Nicole Cho, Nishan Srishankar
Abstract: Hallucination continues to be one of the most critical challenges in the institutional adoption journey of Large Language Models (LLMs). While prior studies have primarily focused on the post-generation analysis and refinement of outputs, this paper centers on the effectiveness of queries in eliciting accurate responses from LLMs. We present HalluciBot, a model that estimates the query's propensity to hallucinate before generation, without invoking any LLMs during inference. HalluciBot can serve as a proxy reward model for query rewriting, offering a general framework to estimate query quality based on accuracy and consensus. In essence, HalluciBot investigates how poorly constructed queries can lead to erroneous outputs - moreover, by employing query rewriting guided by HalluciBot's empirical estimates, we demonstrate that 95.7% output accuracy can be achieved for Multiple Choice questions. The training procedure for HalluciBot consists of perturbing 369,837 queries n times, employing n+1 independent LLM agents, sampling an output from each query, conducting a Multi-Agent Monte Carlo simulation on the sampled outputs, and training an encoder classifier. The idea of perturbation is the outcome of our ablation studies that measures the increase in output diversity (+12.5 agreement spread) by perturbing a query in lexically different but semantically similar ways. Therefore, HalluciBot paves the way to ratiocinate (76.0% test F1 score, 46.6% in saved computation on hallucinatory queries), rewrite (+30.2% positive class transition from hallucinatory to non-hallucinatory), rank (+50.6% positive class transition from hallucinatory to non-hallucinatory), and route queries to effective pipelines.
Authors: Sibo Gai, Donglin Wang
Abstract: In this work, we propose a new setting of continual learning: data-incremental continual offline reinforcement learning (DICORL), in which an agent is asked to learn a sequence of datasets of a single offline reinforcement learning (RL) task continually, instead of learning a sequence of offline RL tasks with respective datasets. Then, we propose that this new setting will introduce a unique challenge to continual learning: active forgetting, which means that the agent will forget the learnt skill actively. The main reason for active forgetting is conservative learning used by offline RL, which is used to solve the overestimation problem. With conservative learning, the offline RL method will suppress the value of all actions, learnt or not, without selection, unless it is in the just learning dataset. Therefore, inferior data may overlay premium data because of the learning sequence. To solve this problem, we propose a new algorithm, called experience-replay-based ensemble implicit Q-learning (EREIQL), which introduces multiple value networks to reduce the initial value and avoid using conservative learning, and the experience replay to relieve catastrophic forgetting. Our experiments show that EREIQL relieves active forgetting in DICORL and performs well.
Authors: Xuyang Zhong, Yixiao Huang, Chen Liu
Abstract: This work studies sparse adversarial perturbations bounded by $l_0$ norm. We propose a white-box PGD-like attack method named sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine sparse-PGD with a black-box attack to comprehensively and more reliably evaluate the models' robustness against $l_0$ bounded adversarial perturbations. Moreover, the efficiency of sparse-PGD enables us to conduct adversarial training to build robust models against sparse perturbations. Extensive experiments demonstrate that our proposed attack algorithm exhibits strong performance in different scenarios. More importantly, compared with other robust models, our adversarially trained model demonstrates state-of-the-art robustness against various sparse attacks. Codes are available at https://github.com/CityU-MLO/sPGD.
Authors: Katsiaryna Haitsiukevich, Onur Poyraz, Pekka Marttinen, Alexander Ilin
Abstract: This paper explores the efficacy of diffusion-based generative models as neural operators for partial differential equations (PDEs). Neural operators are neural networks that learn a mapping from the parameter space to the solution space of PDEs from data, and they can also solve the inverse problem of estimating the parameter from the solution. Diffusion models excel in many domains, but their potential as neural operators has not been thoroughly explored. In this work, we show that diffusion-based generative models exhibit many properties favourable for neural operators, and they can effectively generate the solution of a PDE conditionally on the parameter or recover the unobserved parts of the system. We propose to train a single model adaptable to multiple tasks, by alternating between the tasks during training. In our experiments with multiple realistic dynamical systems, diffusion models outperform other neural operators. Furthermore, we demonstrate how the probabilistic diffusion model can elegantly deal with systems which are only partially identifiable, by producing samples corresponding to the different possible solutions.
Authors: Zhicheng Zhang, Yong Wang, Shaoqi Tan, Bowei Xia, Yujie Luo
Abstract: Recently, Transformer-based models for long sequence time series forecasting have demonstrated promising results. The self-attention mechanism as the core component of these Transformer-based models exhibits great potential in capturing various dependencies among data points. Despite these advancements, it has been a subject of concern to improve the efficiency of the self-attention mechanism. Unfortunately, current specific optimization methods are facing the challenges in applicability and scalability for the future design of long sequence time series forecasting models. Hence, in this article, we propose a novel architectural framework that enhances Transformer-based models through the integration of Surrogate Attention Blocks (SAB) and Surrogate Feed-Forward Neural Network Blocks (SFB). The framework reduces both time and space complexity by the replacement of the self-attention and feed-forward layers with SAB and SFB while maintaining their expressive power and architectural advantages. The equivalence of this substitution is fully demonstrated. The extensive experiments on 10 Transformer-based models across five distinct time series tasks demonstrate an average performance improvement of 12.4%, alongside 61.3% reduction in parameter counts.
Authors: Haocong Rao, Minlin Zeng, Xuejiao Zhao, Chunyan Miao
Abstract: Recent years have witnessed an increasing global population affected by neurodegenerative diseases (NDs), which traditionally require extensive healthcare resources and human effort for medical diagnosis and monitoring. As a crucial disease-related motor symptom, human gait can be exploited to characterize different NDs. The current advances in artificial intelligence (AI) models enable automatic gait analysis for NDs identification and classification, opening a new avenue to facilitate faster and more cost-effective diagnosis of NDs. In this paper, we provide a comprehensive survey on recent progress of machine learning and deep learning based AI techniques applied to diagnosis of five typical NDs through gait. We provide an overview of the process of AI-assisted NDs diagnosis, and present a systematic taxonomy of existing gait data and AI models. Meanwhile, a novel quality evaluation criterion is proposed to quantitatively assess the quality of existing studies. Through an extensive review and analysis of 169 studies, we present recent technical advancements, discuss existing challenges, potential solutions, and future directions in this field. Finally, we envision the prospective utilization of 3D skeleton data for human gait representation and the development of more efficient AI models for NDs diagnosis.
Authors: Zavareh Bozorgasl, Hao Chen
Abstract: This paper presents a novel approach to enhance communication efficiency in federated learning through clipped uniform quantization. By leveraging optimal clipping thresholds and client-specific adaptive quantization schemes, the proposed method significantly reduces bandwidth and memory requirements for model weight transmission between clients and the server while maintaining competitive accuracy. We investigate the effects of symmetric clipping and uniform quantization on model performance, emphasizing the role of stochastic quantization in mitigating artifacts and improving robustness. Extensive simulations demonstrate that the method achieves near-full-precision performance with substantial communication savings. Moreover, the proposed approach facilitates efficient weight averaging based on the inverse of the mean squared quantization errors, effectively balancing the trade-off between communication efficiency and model accuracy. Moreover, in contrast to federated averaging, this design obviates the need to disclose client-specific data volumes to the server, thereby enhancing client privacy. Comparative analysis with conventional quantization methods further confirms the efficacy of the proposed scheme.
Authors: Robert Wang, Aseem Baranwal, Kimon Fountoulakis
Abstract: Machine learning for node classification on graphs is a prominent area driven by applications such as recommendation systems. State-of-the-art models often use multiple graph convolutions on the data, as empirical evidence suggests they can enhance performance. However, it has been shown empirically and theoretically, that too many graph convolutions can degrade performance significantly, a phenomenon known as oversmoothing. In this paper, we provide a rigorous theoretical analysis, based on the two-class contextual stochastic block model (CSBM), of the performance of vanilla graph convolution from which we remove the principal eigenvector to avoid oversmoothing. We perform a spectral analysis for $k$ rounds of corrected graph convolutions, and we provide results for partial and exact classification. For partial classification, we show that each round of convolution can reduce the misclassification error exponentially up to a saturation level, after which performance does not worsen. We also extend this analysis to the multi-class setting with features distributed according to a Gaussian mixture model. For exact classification, we show that the separability threshold can be improved exponentially up to $O({\log{n}}/{\log\log{n}})$ corrected convolutions.
Authors: Shutong Ding, Ke Hu, Zhenhao Zhang, Kan Ren, Weinan Zhang, Jingyi Yu, Jingya Wang, Ye Shi
Abstract: Diffusion models have garnered widespread attention in Reinforcement Learning (RL) for their powerful expressiveness and multimodality. It has been verified that utilizing diffusion policies can significantly improve the performance of RL algorithms in continuous control tasks by overcoming the limitations of unimodal policies, such as Gaussian policies, and providing the agent with enhanced exploration capabilities. However, existing works mainly focus on the application of diffusion policies in offline RL, while their incorporation into online RL is less investigated. The training objective of the diffusion model, known as the variational lower bound, cannot be optimized directly in online RL due to the unavailability of 'good' actions. This leads to difficulties in conducting diffusion policy improvement. To overcome this, we propose a novel model-free diffusion-based online RL algorithm, Q-weighted Variational Policy Optimization (QVPO). Specifically, we introduce the Q-weighted variational loss, which can be proved to be a tight lower bound of the policy objective in online RL under certain conditions. To fulfill these conditions, the Q-weight transformation functions are introduced for general scenarios. Additionally, to further enhance the exploration capability of the diffusion policy, we design a special entropy regularization term. We also develop an efficient behavior policy to enhance sample efficiency by reducing the variance of the diffusion policy during online interactions. Consequently, the QVPO algorithm leverages the exploration capabilities and multimodality of diffusion policies, preventing the RL agent from converging to a sub-optimal policy. To verify the effectiveness of QVPO, we conduct comprehensive experiments on MuJoCo benchmarks. The final results demonstrate that QVPO achieves state-of-the-art performance on both cumulative reward and sample efficiency.
Authors: Yifeng Peng, Xinyi Li, Zhiding Liang, Ying Wang
Abstract: Open set anomaly detection (OSAD) is a crucial task that aims to identify abnormal patterns or behaviors in data sets, especially when the anomalies observed during training do not represent all possible classes of anomalies. The recent advances in quantum computing in handling complex data structures and improving machine learning models herald a paradigm shift in anomaly detection methodologies. This study proposes a Quantum Scoring Module (Qsco), embedding quantum variational circuits into neural networks to enhance the model's processing capabilities in handling uncertainty and unlabeled data. Extensive experiments conducted across eight real-world anomaly detection datasets demonstrate our model's superior performance in detecting anomalies across varied settings and reveal that integrating quantum simulators does not result in prohibitive time complexities. Our study validates the feasibility of quantum-enhanced anomaly detection methods in practical applications.
Authors: Dariush Wahdany, Matthew Jagielski, Adam Dziedzic, Franziska Boenisch
Abstract: Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has become the standard solution to bound leakage from the models. Despite recent improvements, DP-SGD-based approaches for private learning still usually struggle in the high privacy ($\varepsilon\le1)$ and low data regimes, and when the private training datasets are imbalanced. To overcome these limitations, we propose Differentially Private Prototype Learning (DPPL) as a new paradigm for private transfer learning. DPPL leverages publicly pre-trained encoders to extract features from private data and generates DP prototypes that represent each private class in the embedding space and can be publicly released for inference. Since our DP prototypes can be obtained from only a few private training data points and without iterative noise addition, they offer high-utility predictions and strong privacy guarantees even under the notion of \textit{pure DP}. We additionally show that privacy-utility trade-offs can be further improved when leveraging the public data beyond pre-training of the encoder: in particular, we can privately sample our DP prototypes from the publicly available data points used to train the encoder. Our experimental evaluation with four state-of-the-art encoders, four vision datasets, and under different data and imbalancedness regimes demonstrate DPPL's high performance under strong privacy guarantees in challenging private learning setups
Authors: Chen Henry Wu, Rishi Shah, Jing Yu Koh, Ruslan Salakhutdinov, Daniel Fried, Aditi Raghunathan
Abstract: As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components, which existing LM safety evaluations do not adequately address. To bridge this gap, we manually create 200 targeted adversarial tasks and evaluation functions in a realistic threat model on top of VisualWebArena, a real environment for web-based agents. In order to systematically examine the robustness of various multimodal we agents, we propose the Agent Robustness Evaluation (ARE) framework. ARE views the agent as a graph showing the flow of intermediate outputs between components and decomposes robustness as the flow of adversarial information on the graph. First, we find that we can successfully break a range of the latest agents that use black-box frontier LLMs, including those that perform reflection and tree-search. With imperceptible perturbations to a single product image (less than 5% of total web page pixels), an attacker can hijack these agents to execute targeted adversarial goals with success rates up to 67%. We also use ARE to rigorously evaluate how the robustness changes as new components are added. We find that new components that typically improve benign performance can open up new vulnerabilities and harm robustness. An attacker can compromise the evaluator used by the reflexion agent and the value function of the tree search agent, which increases the attack success relatively by 15% and 20%. Our data and code for attacks, defenses, and evaluation are available at https://github.com/ChenWu98/agent-attack
Authors: Yujing Wang, Hainan Zhang, Sijia Wen, Wangjie Qiu, Binghui Guo
Abstract: Federated learning is highly susceptible to model poisoning attacks, especially those meticulously crafted for servers. Traditional defense methods mainly focus on updating assessments or robust aggregation against manually crafted myopic attacks. When facing advanced attacks, their defense stability is notably insufficient. Therefore, it is imperative to develop adaptive defenses against such advanced poisoning attacks. We find that benign clients exhibit significantly higher data distribution stability than malicious clients in federated learning in both CV and NLP tasks. Therefore, the malicious clients can be recognized by observing the stability of their data distribution. In this paper, we propose AdaAggRL, an RL-based Adaptive Aggregation method, to defend against sophisticated poisoning attacks. Specifically, we first utilize distribution learning to simulate the clients' data distributions. Then, we use the maximum mean discrepancy (MMD) to calculate the pairwise similarity of the current local model data distribution, its historical data distribution, and global model data distribution. Finally, we use policy learning to adaptively determine the aggregation weights based on the above similarities. Experiments on four real-world datasets demonstrate that the proposed defense model significantly outperforms widely adopted defense models for sophisticated attacks.
Authors: Amrutha Varshini Ramesh, Vignesh Ganapathiraman, Issam H. Laradji, Mark Schmidt
Abstract: Training large language models (LLMs) for pretraining or adapting to new tasks and domains has become increasingly critical as their applications expand. However, as the model and the data sizes grow, the training process presents significant memory challenges, often requiring a prohibitive amount of GPU memory that may not be readily available. Existing methods such as low-rank adaptation (LoRA) add trainable low-rank matrix factorizations, altering the training dynamics and limiting the model's parameter search to a low-rank subspace. GaLore, a more recent method, employs Gradient Low-Rank Projection to reduce the memory footprint, in the full parameter training setting. However GaLore can only be applied to a subset of the LLM layers that satisfy the "reversibility" property, thus limiting their applicability. In response to these challenges, we introduce BlockLLM, an approach inspired by block coordinate descent. Our method carefully selects and updates a very small subset of the trainable parameters without altering any part of its architecture and training procedure. BlockLLM achieves state-of-the-art performance in both finetuning and pretraining tasks, while reducing the memory footprint of the underlying optimization process. Our experiments demonstrate that fine-tuning with only less than 5% of the parameters, BlockLLM achieves state-of-the-art perplexity scores on the GLUE benchmarks. On Llama model pretrained on C4 dataset, BlockLLM is able to train with significantly less memory than the state-of-the-art, while still maintaining competitive performance.
Authors: Rayna Andreeva, Benjamin Dupuis, Rik Sarkar, Tolga Birdal, Umut \c{S}im\c{s}ekli
Abstract: We present a novel set of rigorous and computationally efficient topology-based complexity notions that exhibit a strong correlation with the generalization gap in modern deep neural networks (DNNs). DNNs show remarkable generalization properties, yet the source of these capabilities remains elusive, defying the established statistical learning theory. Recent studies have revealed that properties of training trajectories can be indicative of generalization. Building on this insight, state-of-the-art methods have leveraged the topology of these trajectories, particularly their fractal dimension, to quantify generalization. Most existing works compute this quantity by assuming continuous- or infinite-time training dynamics, complicating the development of practical estimators capable of accurately predicting generalization without access to test data. In this paper, we respect the discrete-time nature of training trajectories and investigate the underlying topological quantities that can be amenable to topological data analysis tools. This leads to a new family of reliable topological complexity measures that provably bound the generalization error, eliminating the need for restrictive geometric assumptions. These measures are computationally friendly, enabling us to propose simple yet effective algorithms for computing generalization indices. Moreover, our flexible framework can be extended to different domains, tasks, and architectures. Our experimental results demonstrate that our new complexity measures correlate highly with generalization error in industry-standards architectures such as transformers and deep graph networks. Our approach consistently outperforms existing topological bounds across a wide range of datasets, models, and optimizers, highlighting the practical relevance and effectiveness of our complexity measures.
Authors: Kaifu Wang, Efthymia Tsamoura, Dan Roth
Abstract: *Multi-Instance Partial Label Learning* (MI-PLL) is a weakly-supervised learning setting encompassing *partial label learning*, *latent structural learning*, and *neurosymbolic learning*. Unlike supervised learning, in MI-PLL, the inputs to the classifiers at training-time are tuples of instances $\mathbf{x}$. At the same time, the supervision signal is generated by a function $\sigma$ over the (hidden) gold labels of $\mathbf{x}$. In this work, we make multiple contributions towards addressing a problem that hasn't been studied so far in the context of MI-PLL: that of characterizing and mitigating *learning imbalances*, i.e., major differences in the errors occurring when classifying instances of different classes (aka *class-specific risks*). In terms of theory, we derive class-specific risk bounds for MI-PLL, while making minimal assumptions. Our theory reveals a unique phenomenon: that $\sigma$ can greatly impact learning imbalances. This result is in sharp contrast with previous research on supervised and weakly-supervised learning, which only studies learning imbalances under the prism of data imbalances. On the practical side, we introduce a technique for estimating the marginal of the hidden labels using only MI-PLL data. Then, we introduce algorithms that mitigate imbalances at training- and testing-time, by treating the marginal of the hidden labels as a constraint. We demonstrate the effectiveness of our techniques using strong baselines from neurosymbolic and long-tail learning, suggesting performance improvements of up to 14\%.
Authors: Mohammed Alruqimi, Luca Di Persio
Abstract: Accurate crude oil price forecasting is crucial for various economic activities, including energy trading, risk management, and investment planning. Although deep learning models have emerged as powerful tools for crude oil price forecasting, achieving accurate forecasts remains challenging. Deep learning models' performance is heavily influenced by hyperparameters tuning, and they are expected to perform differently under various circumstances. Furthermore, price volatility is also sensitive to external factors such as world events. To address these limitations, we propose a hybrid approach that integrates metaheuristic optimization with an ensemble of five widely used neural network architectures for time series forecasting. Unlike existing methods that apply metaheuristics to optimise hyperparameters within the neural network architecture, we exploit the GWO metaheuristic optimiser at four levels: feature selection, data preparation, model training, and forecast blending. The proposed approach has been evaluated for forecasting three-ahead days using real-world Brent crude oil price data, and the obtained results demonstrate that the proposed approach improves the forecasting performance measured using various benchmarks, achieving 0.000127 of MSE.
Authors: Daniel Tan, David Chanin, Aengus Lynch, Dimitrios Kanoulas, Brooks Paige, Adria Garriga-Alonso, Robert Kirk
Abstract: Steering vectors (SVs) have been proposed as an effective approach to adjust language model behaviour at inference time by intervening on intermediate model activations. They have shown promise in terms of improving both capabilities and model alignment. However, the reliability and generalisation properties of this approach are unknown. In this work, we rigorously investigate these properties, and show that steering vectors have substantial limitations both in- and out-of-distribution. In-distribution, steerability is highly variable across different inputs. Depending on the concept, spurious biases can substantially contribute to how effective steering is for each input, presenting a challenge for the widespread use of steering vectors. Out-of-distribution, while steering vectors often generalise well, for several concepts they are brittle to reasonable changes in the prompt, resulting in them failing to generalise well. Overall, our findings show that while steering can work well in the right circumstances, there remain technical difficulties of applying steering vectors to guide models' behaviour at scale. Our code is available at https://github.com/dtch1997/steering-bench
Authors: Christof Sch\"otz, Alistair White, Maximilian Gelbrecht, Niklas Boers
Abstract: Predicting chaotic dynamical systems is critical in many scientific fields, such as weather forecasting, but challenging due to the characteristic sensitive dependence on initial conditions. Traditional modeling approaches require extensive domain knowledge, often leading to a shift towards data-driven methods using machine learning. However, existing research provides inconclusive results on which machine learning methods are best suited for predicting chaotic systems. In this paper, we compare different lightweight and heavyweight machine learning architectures using extensive existing benchmark databases, as well as a newly introduced database that allows for uncertainty quantification in the benchmark results. In addition to state-of-the-art methods from the literature, we also present new advantageous variants of established methods. Hyperparameter tuning is adjusted based on computational cost, with more tuning allocated to less costly methods. Furthermore, we introduce the cumulative maximum error, a novel metric that combines desirable properties of traditional metrics and is tailored for chaotic systems. Our results show that well-tuned simple methods, as well as untuned baseline methods, often outperform state-of-the-art deep learning models, but their performance can vary significantly with different experimental setups. These findings highlight the importance of aligning prediction methods with data characteristics and caution against the indiscriminate use of overly complex models.
Authors: Feiyang Kang, Yifan Sun, Bingbing Wen, Si Chen, Dawn Song, Rafid Mahmood, Ruoxi Jia
Abstract: Domain reweighting is an emerging research area aimed at adjusting the relative weights of different data sources to improve the effectiveness and efficiency of language model pre-training. This paper demonstrates that the optimal composition of training data from different domains is scale-dependent, challenging the existing practice of determining optimal mixtures through small-scale experiments and directly applying them at larger scales. We derive an analytical model for the dependence of optimal weights on data scale and introduce *AutoScale*, a novel, practical approach for optimizing data compositions at potentially large training data scales. *AutoScale* first uses a principled optimization framework to find optimal compositions at smaller, feasible scales, then predicts optimal compositions at larger scales using our derived model. Our evaluation on GPT-2 Large and BERT pre-training demonstrates *AutoScale*'s effectiveness in improving training convergence and downstream performance. Particularly, for GPT-2 Large on RedPajama, *AutoScale* decreases validation perplexity 28% faster than baselines, with up to 38% speed-up over unweighted training, achieving the best performance across downstream tasks. This work provides insights into the varying benefits of data sources across training scales for language models, contributing to the burgeoning research on scale-dependent data curation. Code is open-sourced.
Authors: Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar
Abstract: Despite their widespread adoption, large language models (LLMs) remain prohibitive to use under resource constraints, with their ever growing sizes only increasing the barrier for use. One noted issue is the high latency associated with auto-regressive generation, rendering large LLMs use dependent on advanced computing infrastructure. Assisted decoding, where a smaller draft model guides a larger target model's generation, has helped alleviate this, but remains dependent on alignment between the two models. Thus if the draft model is insufficiently capable on some domain relative to the target model, performance can degrade. Alternatively, one can leverage multiple draft models to better cover the expertise of the target, but when multiple black-box draft models are available, selecting an assistant without details about its construction can be difficult. To better understand this decision making problem, we observe it as a contextual bandit, where a policy must choose a draft model based on a context. We show that even without prior knowledge of the draft models, creating an offline dataset from only outputs of independent draft/target models and training a policy over the alignment of these outputs can accelerate performance on multiple domains provided the candidates are effective. Further results show this to hold on various settings with multiple assisted decoding candidates, highlighting its flexibility and the advantageous role that such decision making can play.
Authors: Yi Li, Shichao Zhang, Guixian Zhang, Debo Cheng
Abstract: Graph unlearning technology has become increasingly important since the advent of the `right to be forgotten' and the growing concerns about the privacy and security of artificial intelligence. Graph unlearning aims to quickly eliminate the effects of specific data on graph neural networks (GNNs). However, most existing deterministic graph unlearning frameworks follow a balanced partition-submodel training-aggregation paradigm, resulting in a lack of structural information between subgraph neighborhoods and redundant unlearning parameter calculations. To address this issue, we propose a novel Graph Structure Mapping Unlearning paradigm (GSMU) and a novel method based on it named Community-centric Graph Eraser (CGE). CGE maps community subgraphs to nodes, thereby enabling the reconstruction of a node-level unlearning operation within a reduced mapped graph. CGE makes the exponential reduction of both the amount of training data and the number of unlearning parameters. Extensive experiments conducted on five real-world datasets and three widely used GNN backbones have verified the high performance and efficiency of our CGE method, highlighting its potential in the field of graph unlearning.
Authors: Xiao Han, Zijian Zhang, Xiangyu Zhao, Yuanshao Zhu, Guojiang Shen, Xiangjie Kong, Xuetao Wei, Liqiang Nie, Jieping Ye
Abstract: As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services. However, current vehicle dispatch systems struggle to navigate the complexities of urban traffic dynamics, including unpredictable traffic conditions, diverse driver behaviors, and fluctuating supply and demand patterns. These challenges have resulted in travel difficulties for passengers in certain areas, while many drivers in other areas are unable to secure orders, leading to a decline in the overall quality of urban transportation services. To address these issues, this paper introduces GARLIC: a framework of GPT-Augmented Reinforcement Learning with Intelligent Control for vehicle dispatching. GARLIC utilizes multiview graphs to capture hierarchical traffic states, and learns a dynamic reward function that accounts for individual driving behaviors. The framework further integrates a GPT model trained with a custom loss function to enable high-precision predictions and optimize dispatching policies in real-world scenarios. Experiments conducted on two real-world datasets demonstrate that GARLIC effectively aligns with driver behaviors while reducing the empty load rate of vehicles.
Authors: Zheshun Wu, Junfan Li, Zenglin Xu, Sumei Sun, Jie Liu
Abstract: Machine learning techniques have garnered great interest in designing communication systems owing to their capacity in tacking with channel uncertainty. To provide theoretical guarantees for learning-based communication systems, some recent works analyze generalization bounds for devised methods based on the assumption of Independently and Identically Distributed (I.I.D.) channels, a condition rarely met in practical scenarios. In this paper, we drop the I.I.D. channel assumption and study an online optimization problem of learning to communicate over time-correlated channels. To address this issue, we further focus on two specific tasks: optimizing channel decoders for time-correlated fading channels and selecting optimal codebooks for time-correlated additive noise channels. For utilizing temporal dependence of considered channels to better learn communication systems, we develop two online optimization algorithms based on the optimistic online mirror descent framework. Furthermore, we provide theoretical guarantees for proposed algorithms via deriving sub-linear regret bound on the expected error probability of learned systems. Extensive simulation experiments have been conducted to validate that our presented approaches can leverage the channel correlation to achieve a lower average symbol error rate compared to baseline methods, consistent with our theoretical findings.
Authors: Fenglei Fan, Juntong Fan, Dayang Wang, Jingbo Zhang, Zelin Dong, Shijun Zhang, Ge Wang, Tieyong Zeng
Abstract: The rapid growth of large models' size has far outpaced that of GPU memory. To bridge this gap, inspired by the parsimonious relationship between genotype and phenotype, we turn the model compression problem into the issue of parameter representation to propose the so-called hyper-compression. The hyper-compression uses a hyperfunction to represent the parameters of the target network per ergodic theory, that addresses the following approximation problem: if a low-dimensional dynamic system can fill the high-dimensional space eventually. Empirically, the proposed hyper-compression enjoys the following merits: 1) \textbf{P}referable compression ratio; 2) \textbf{N}o post-hoc retraining; 3) \textbf{A}ffordable inference time; and 4) \textbf{S}hort compression time. It compresses LLaMA2-7B in an hour and achieves close-to-int4-quantization performance, without retraining and with a performance drop of less than 1\%. Our work can facilitate the harmony between the scaling law and the stagnation of hardware upgradation in terms of saving both computation and data. We have open-sourced our \href{https://github.com/Juntongkuki/Hyper-Compression.git}{code} for readers' free download and evaluation.
Authors: Jiarong Yang, Yuan Liu
Abstract: Split Federated Learning (SFL) splits and collaboratively trains a shared model between clients and server, where clients transmit activations and client-side models to server for updates. Recent SFL studies assume synchronous transmission of activations and client-side models from clients to server. However, due to significant variations in computational and communication capabilities among clients, activations and client-side models arrive at server asynchronously. The delay caused by asynchrony significantly degrades the performance of SFL. To address this issue, we consider an asynchronous SFL framework, where an activation buffer and a model buffer are embedded on the server to manage the asynchronously transmitted activations and client-side models, respectively. Furthermore, as asynchronous activation transmissions cause the buffer to frequently receive activations from resource-rich clients, leading to biased updates of the server-side model, we propose Generative activations-aided Asynchronous SFL (GAS). In GAS, the server maintains an activation distribution for each label based on received activations and generates activations from these distributions according to the degree of bias. These generative activations are then used to assist in updating the server-side model, ensuring more accurate updates. We derive a tighter convergence bound, and our experiments demonstrate the effectiveness of the proposed method. The code is available at https://github.com/eejiarong/GAS.
Authors: Zhao Shan, Chenyou Fan, Shuang Qiu, Jiyuan Shi, Chenjia Bai
Abstract: Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with human intents in various tasks. To achieve this, previous methods conduct return-conditioned policy generation or Reinforcement Learning (RL)-based policy optimization, while they both rely on pre-defined reward functions. In this work, we propose a novel framework, Forward KL regularized Preference optimization for aligning Diffusion policies, to align the diffusion policy with preferences directly. We first train a diffusion policy from the offline dataset without considering the preference, and then align the policy to the preference data via direct preference optimization. During the alignment phase, we formulate direct preference learning in a diffusion policy, where the forward KL regularization is employed in preference optimization to avoid generating out-of-distribution actions. We conduct extensive experiments for MetaWorld manipulation and D4RL tasks. The results show our method exhibits superior alignment with preferences and outperforms previous state-of-the-art algorithms.
Authors: Jiahao Lai, Jiaqi Li, Jian Xu, Yanru Wu, Boshi Tang, Siqi Chen, Yongfeng Huang, Wenbo Ding, Yang Li
Abstract: Federated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server. Traditional methods, such as Federated Averaging (FedAvg), linearly aggregate these parameters which are usually trained on heterogeneous data distributions, potentially overlooking the complex, high-dimensional nature of the parameter space. This can result in degraded performance of the aggregated model. While personalized FL approaches can mitigate the heterogeneous data issue to some extent, the limitation of linear aggregation remains unresolved. To alleviate this issue, we investigate the generative approach of diffusion model and propose a novel generative parameter aggregation framework for personalized FL, \texttt{pFedGPA}. In this framework, we deploy a diffusion model on the server to integrate the diverse parameter distributions and propose a parameter inversion method to efficiently generate a set of personalized parameters for each client. This inversion method transforms the uploaded parameters into a latent code, which is then aggregated through denoising sampling to produce the final personalized parameters. By encoding the dependence of a client's model parameters on the specific data distribution using the high-capacity diffusion model, \texttt{pFedGPA} can effectively decouple the complexity of the overall distribution of all clients' model parameters from the complexity of each individual client's parameter distribution. Our experimental results consistently demonstrate the superior performance of the proposed method across multiple datasets, surpassing baseline approaches.
Authors: Taslim Murad, Prakash Chourasia, Sarwan Ali, Imdad Ullah Khan, Murray Patterson
Abstract: Cancer is a complex disease characterized by uncontrolled cell growth. T cell receptors (TCRs), crucial proteins in the immune system, play a key role in recognizing antigens, including those associated with cancer. Recent advancements in sequencing technologies have facilitated comprehensive profiling of TCR repertoires, uncovering TCRs with potent anti-cancer activity and enabling TCR-based immunotherapies. However, analyzing these intricate biomolecules necessitates efficient representations that capture their structural and functional information. T-cell protein sequences pose unique challenges due to their relatively smaller lengths compared to other biomolecules. An image-based representation approach becomes a preferred choice for efficient embeddings, allowing for the preservation of essential details and enabling comprehensive analysis of T-cell protein sequences. In this paper, we propose to generate images from the protein sequences using the idea of Chaos Game Representation (CGR) using the Kaleidoscopic images approach. This Deep Learning Assisted Analysis of Protein Sequences Using Chaos Enhanced Kaleidoscopic Images (called DANCE) provides a unique way to visualize protein sequences by recursively applying chaos game rules around a central seed point. we perform the classification of the T cell receptors (TCRs) protein sequences in terms of their respective target cancer cells, as TCRs are known for their immune response against cancer disease. The TCR sequences are converted into images using the DANCE method. We employ deep-learning vision models to perform the classification to obtain insights into the relationship between the visual patterns observed in the generated kaleidoscopic images and the underlying protein properties. By combining CGR-based image generation with deep learning classification, this study opens novel possibilities in the protein analysis domain.
Authors: Keyu Wang, Abdullah Norozi Iranzad, Scott Schaffter, Meg Risdal, Doina Precup, Jonathan Lebensold
Abstract: Research and industry are rapidly advancing the innovation and adoption of foundation model-based systems, yet the tools for managing these models have not kept pace. Understanding the provenance and lineage of models is critical for researchers, industry, regulators, and public trust. While model cards and system cards were designed to provide transparency, they fall short in key areas: tracing model genealogy, enabling machine readability, offering reliable centralized management systems, and fostering consistent creation incentives. This challenge mirrors issues in software supply chain security, but AI/ML remains at an earlier stage of maturity. Addressing these gaps requires industry-standard tooling that can be adopted by foundation model publishers, open-source model innovators, and major distribution platforms. We propose a machine-readable model specification format to simplify the creation of model records, thereby reducing error-prone human effort, notably when a new model inherits most of its design from a foundation model. Our solution explicitly traces relationships between upstream and downstream models, enhancing transparency and traceability across the model lifecycle. To facilitate the adoption, we introduce the unified model record (UMR) repository , a semantically versioned system that automates the publication of model records to multiple formats (PDF, HTML, LaTeX) and provides a hosted web interface (https://modelrecord.com/). This proof of concept aims to set a new standard for managing foundation models, bridging the gap between innovation and responsible model management.
Authors: Qiang Xie
Abstract: To enhance the accuracy of power load forecasting in wind farms, this study introduces an advanced combined forecasting method that integrates Variational Mode Decomposition (VMD) with an Improved Particle Swarm Optimization (IPSO) algorithm to optimize the Extreme Learning Machine (ELM). Initially, the VMD algorithm is employed to perform high-precision modal decomposition of the original power load data, which is then categorized into high-frequency and low-frequency sequences based on mutual information entropy theory. Subsequently, this research profoundly modifies the traditional multiverse optimizer by incorporating Tent chaos mapping, exponential travel distance rate, and an elite reverse learning mechanism, developing the IPSO-ELM prediction model. This model independently predicts the high and low-frequency sequences and reconstructs the data to achieve the final forecasting results. Simulation results indicate that the proposed method significantly improves prediction accuracy and convergence speed compared to traditional ELM, PSO-ELM, and PSO-ELM methods.
Authors: Maximilian Xiling Li, Korbinian Franz Rudolf, Nils Blank, Rudolf Lioutikov
Abstract: Prototype Learning methods provide an interpretable alternative to black-box deep learning models. Approaches such as ProtoPNet learn, which part of a test image "look like" known prototypical parts from training images, combining predictive power with the inherent interpretability of case-based reasoning. However, existing approaches have two main drawbacks: A) They rely solely on deterministic similarity scores without statistical confidence. B) The prototypes are learned in a black-box manner without human input. This work introduces HyperPg, a new prototype representation leveraging Gaussian distributions on a hypersphere in latent space, with learnable mean and variance. HyperPg prototypes adapt to the spread of clusters in the latent space and output likelihood scores. The new architecture, HyperPgNet, leverages HyperPg to learn prototypes aligned with human concepts from pixel-level annotations. Consequently, each prototype represents a specific concept such as color, image texture, or part of the image subject. A concept extraction pipeline built on foundation models provides pixel-level annotations, significantly reducing human labeling effort. Experiments on CUB-200-2011 and Stanford Cars datasets demonstrate that HyperPgNet outperforms other prototype learning architectures while using fewer parameters and training steps. Additionally, the concept-aligned HyperPg prototypes are learned transparently, enhancing model interpretability.
Authors: Jingxuan Fan, Sarah Martinson, Erik Y. Wang, Kaylie Hausknecht, Jonah Brenner, Danxian Liu, Nianli Peng, Corey Wang, Michael P. Brenner
Abstract: Advanced applied mathematics problems are underrepresented in existing Large Language Model (LLM) benchmark datasets. To address this, we introduce HARDMath, a dataset inspired by a graduate course on asymptotic methods, featuring challenging applied mathematics problems that require analytical approximation techniques. These problems demand a combination of mathematical reasoning, computational tools, and subjective judgment, making them difficult for LLMs. Our framework auto-generates a large number of problems with solutions validated against numerical ground truths. We evaluate both open- and closed-source LLMs on HARDMath-mini, a sub-sampled test set of 366 problems, as well as on 40 word problems formulated in applied science contexts. Even leading closed-source models like GPT-4 achieve only 43.8% overall accuracy with few-shot Chain-of-Thought prompting, and all models demonstrate significantly lower performance compared to results on existing mathematics benchmark datasets. We additionally conduct a detailed error analysis to gain insights into the failure cases of LLMs. These results demonstrate limitations of current LLM performance on advanced graduate-level applied math problems and underscore the importance of datasets like HARDMath to advance mathematical abilities of LLMs.
Authors: Minkyu Kim, Suan Lee, Jinho Kim
Abstract: Transparent models, which are machine learning models that produce inherently interpretable predictions, are receiving significant attention in high-stakes domains. However, despite much real-world data being collected as time series, there is a lack of studies on transparent time series models. To address this gap, we propose a novel transparent neural network model for time series called Generalized Additive Time Series Model (GATSM). GATSM consists of two parts: 1) independent feature networks to learn feature representations, and 2) a transparent temporal module to learn temporal patterns across different time steps using the feature representations. This structure allows GATSM to effectively capture temporal patterns and handle dynamic-length time series while preserving transparency. Empirical experiments show that GATSM significantly outperforms existing generalized additive models and achieves comparable performance to black-box time series models, such as recurrent neural networks and Transformer. In addition, we demonstrate that GATSM finds interesting patterns in time series. The source code is available at https://github.com/gim4855744/GATSM.
Authors: Anh Bui, Long Vuong, Khanh Doan, Trung Le, Paul Montague, Tamas Abraham, Dinh Phung
Abstract: Diffusion models excel at generating visually striking content from text but can inadvertently produce undesirable or harmful content when trained on unfiltered internet data. A practical solution is to selectively removing target concepts from the model, but this may impact the remaining concepts. Prior approaches have tried to balance this by introducing a loss term to preserve neutral content or a regularization term to minimize changes in the model parameters, yet resolving this trade-off remains challenging. In this work, we propose to identify and preserving concepts most affected by parameter changes, termed as \textit{adversarial concepts}. This approach ensures stable erasure with minimal impact on the other concepts. We demonstrate the effectiveness of our method using the Stable Diffusion model, showing that it outperforms state-of-the-art erasure methods in eliminating unwanted content while maintaining the integrity of other unrelated elements. Our code is available at \url{https://github.com/tuananhbui89/Erasing-Adversarial-Preservation}.
URLs: https://github.com/tuananhbui89/Erasing-Adversarial-Preservation
Authors: Joshua Kazdan, Rylan Schaeffer, Apratim Dey, Matthias Gerstgrasser, Rafael Rafailov, David L. Donoho, Sanmi Koyejo
Abstract: The increasing presence of AI-generated content on the internet raises a critical question: What happens when generative machine learning models are pretrained on web-scale datasets containing data created by earlier models? Some authors prophesy \textit{model collapse} under a `{\it replace}' scenario: a sequence of models, the first trained with real data and each later one trained {\it only on} synthetic data from its preceding model. In this scenario, models successively degrade. Others see collapse as avoidable; in an `{\it accumulate}' scenario, a sequence of models is trained, but each training uses all real and synthetic data generated so far. In this work, we deepen and extend the study of these contrasting scenarios. First, collapse versus avoidance of collapse is studied by comparing the replace and accumulate scenarios on each of three prominent generative modeling settings; we find the same contrast emerges in all three settings. Second, we study a compromise scenario; the available data remains the same as in the {\it accumulate} scenario -- but unlike {\it accumulate} and like {\it replace}, each model is trained using a fixed compute budget; we demonstrate that model test loss on real data is larger than in the {\it accumulate} scenario, but apparently plateaus, unlike the divergence seen with {\it replace}. Third, we study the relative importance of cardinality and proportion of real data for avoiding model collapse. Surprisingly, we find a non-trivial interaction between real and synthetic data, where the value of synthetic data for reducing test loss depends on the absolute quantity of real data. Our insights are particularly important when forecasting whether future frontier generative models will collapse or thrive, and our results open avenues for empirically and mathematically studying the context-dependent value of synthetic data.
Authors: Woosung Koh, Jang Han Yoon, MinHyung Lee, Youngjin Song, Jaegwan Cho, Jaehyun Kang, Taehyeon Kim, Se-young Yun, Youngjae Yu, Bongshin Lee
Abstract: Generating high-quality charts with Large Language Models (LLMs) presents significant challenges due to limited data and the high cost of scaling through human curation. $\langle \text{instruction}, \text{data}, \text{code} \rangle$ triplets are scarce and expensive to manually curate as their creation demands technical expertise. To address this scalability challenge, we introduce a reference-free automatic feedback generator, which eliminates the need for costly human intervention. Our novel framework, C$^2$, consists of (1) an automatic feedback provider (ChartAF) and (2) a diverse, reference-free dataset (ChartUIE-8K). The results are compelling: in our first experiment, 74% of respondents strongly preferred, and 10% preferred, the results after feedback. The second post-feedback experiment demonstrates that ChartAF outperform nine baselines. Moreover, ChartUIE-8K significantly improves data diversity by increasing queries, datasets, and chart types by 5982%, 1936%, and 91%, respectively, over benchmarks. Finally, a study of LLM users revealed that 94% of participants preferred ChartUIE-8K's queries, with 93% deeming them aligned with real-world use cases. Core contributions are available as open-source at chartsquared.github.io, with ample qualitative examples.
Authors: Shuhang Tan, Jayson Sia, Paul Bogdan, Radoslav Ivanov
Abstract: This paper presents a new look at the neural network (NN) robustness problem, from the point of view of graph theory analysis, specifically graph curvature. Graph curvature (e.g., Ricci curvature) has been used to analyze system dynamics and identify bottlenecks in many domains, including road traffic analysis and internet routing. We define the notion of neural Ricci curvature and use it to identify bottleneck NN edges that are heavily used to ``transport data" to the NN outputs. We provide an evaluation on MNIST that illustrates that such edges indeed occur more frequently for inputs where NNs are less robust. These results will serve as the basis for an alternative method of robust training, by minimizing the number of bottleneck edges.
Authors: Ruihuai Liang, Bo Yang, Pengyu Chen, Xianjin Li, Yifan Xue, Zhiwen Yu, Xuelin Cao, Yan Zhang, M\'erouane Debbah, H. Vincent Poor, Chau Yuen
Abstract: Network optimization is a fundamental challenge in the Internet of Things (IoT) network, often characterized by complex features that make it difficult to solve these problems. Recently, generative diffusion models (GDMs) have emerged as a promising new approach to network optimization, with the potential to directly address these optimization problems. However, the application of GDMs in this field is still in its early stages, and there is a noticeable lack of theoretical research and empirical findings. In this study, we first explore the intrinsic characteristics of generative models. Next, we provide a concise theoretical proof and intuitive demonstration of the advantages of generative models over discriminative models in network optimization. Based on this exploration, we implement GDMs as optimizers aimed at learning high-quality solution distributions for given inputs, sampling from these distributions during inference to approximate or achieve optimal solutions. Specifically, we utilize denoising diffusion probabilistic models (DDPMs) and employ a classifier-free guidance mechanism to manage conditional guidance based on input parameters. We conduct extensive experiments across three challenging network optimization problems. By investigating various model configurations and the principles of GDMs as optimizers, we demonstrate the ability to overcome prediction errors and validate the convergence of generated solutions to optimal solutions.We provide code and data at https://github.com/qiyu3816/DiffSG.
Authors: Changyuan Zhao, Hongyang Du, Guangyuan Liu, Dusit Niyato
Abstract: Score-based generative models can effectively learn the distribution of data by estimating the gradient of the distribution. Due to the multi-step denoising characteristic, researchers have recently considered combining score-based generative models with the gradient boosting algorithm, a multi-step supervised learning algorithm, to solve supervised learning tasks. However, existing generative model algorithms are often limited by the stochastic nature of the models and the long inference time, impacting prediction performances. Therefore, we propose a Supervised Score-based Model (SSM), which can be viewed as a gradient boosting algorithm combining score matching. We provide a theoretical analysis of learning and sampling for SSM to balance inference time and prediction accuracy. Via the ablation experiment in selected examples, we demonstrate the outstanding performances of the proposed techniques. Additionally, we compare our model with other probabilistic models, including Natural Gradient Boosting (NGboost), Classification and Regression Diffusion Models (CARD), Diffusion Boosted Trees (DBT), and non-probabilistic GBM models. The experimental results show that our model outperforms existing models in both accuracy and inference time.
Authors: Shlomo Libo Feigin, Maximilian Fleissner, Debarghya Ghoshdastidar
Abstract: Understanding the role of data augmentations is critical for applying Self-Supervised Learning (SSL) methods in new domains. Data augmentations are commonly understood as encoding invariances into the learned representations. This interpretation suggests that SSL would require diverse augmentations that resemble the original data. However, in practice, augmentations do not need to be similar to the original data nor be diverse, and can be neither at the same time. We provide a theoretical insight into this phenomenon. We show that for different SSL losses, any non-redundant representation can be learned with a single suitable augmentation. We provide an algorithm to reconstruct such augmentations and give insights into augmentation choices in SSL.
Authors: Yushi Yang, Filip Sondej, Harry Mayne, Adam Mahdi
Abstract: Safety fine-tuning algorithms are widely used to reduce harmful outputs in language models, but how they achieve this remain unclear. Studying the Direct Preference Optimization (DPO) algorithm for toxicity reduction, current explanations claim that DPO achieves this by dampening the activations of toxic MLP neurons. However, through activation patching, we show that this explanation is incomplete. Projections onto a toxicity probe's direction show that only 4.9% of toxicity reduction comes from dampened toxic neurons. Instead, DPO reduces toxicity through distributed activation shifts across a majority of neurons, progressively shifting MLP layer outputs away from toxicity. These shifts accumulate across four neuron groups: two reducing toxicity and two promoting anti-toxicity. Activation patching validates the cumulative roles of these groups, where patching all identified groups effectively replicates DPO's effects. These findings illustrate DPO's mechanism: it reduces toxicity by accumulating small activation shifts across many neurons throughout the layers. Our findings provide new mechanistic insights into how safety fine-tuning reduces harmful outputs in language 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: Cem \"Uy\"uk, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou
Abstract: Large neural networks achieve remarkable performance, but their size hinders deployment on resource-constrained devices. While various compression techniques exist, parameter sharing remains relatively unexplored. This paper introduces Fine-grained Parameter Sharing (FiPS), a novel algorithm that leverages the relationship between parameter sharing, tensor decomposition, and sparsity to efficiently compress large vision transformer models. FiPS employs a shared base and sparse factors to represent shared neurons across multi-layer perception (MLP) modules. Shared parameterization is initialized via Singular Value Decomposition (SVD) and optimized by minimizing block-wise reconstruction error. Experiments demonstrate that FiPS compresses DeiT-B and Swin-L MLPs to 25-40% of their original parameter count while maintaining accuracy within 1 percentage point of the original models.
Authors: Corrado Coppola, Lorenzo Papa, Irene Amerini, Laura Palagi
Abstract: Adaptive gradient methods have been increasingly adopted by deep learning community due to their fast convergence and reduced sensitivity to hyper-parameters. However, these methods come with limitations, such as increased memory requirements for elements like moving averages and a poorly understood convergence theory. To overcome these challenges, we introduce F-CMA, a Fast-Controlled Mini-batch Algorithm with a random reshuffling method featuring a sufficient decrease condition and a line-search procedure to ensure loss reduction per epoch, along with its deterministic proof of global convergence to a stationary point. To evaluate the F-CMA, we integrate it into conventional training protocols for classification tasks involving both convolutional neural networks and vision transformer models, allowing for a direct comparison with popular optimizers. Computational tests show significant improvements, including a decrease in the overall training time by up to 68%, an increase in per-epoch efficiency by up to 20%, and in model accuracy by up to 5%.
Authors: Leonid Kotyuzanskiy, Artem Klimov
Abstract: The transformer architecture has become an integral part of the field of modern neural networks, playing a crucial role in a variety of tasks, such as text generation, machine translation, image and audio processing, among others. There is also an alternative approach to building intelligent systems, proposed by Jeff Hawkins and inspired by the processes occurring in the neocortex. In our article we want to combine some of these ideas and to propose the use of homeostasis mechanisms, such as RFB-kWTA and "Smart" Inhibition, in the attention mechanism of the transformer and at the output of the transformer block, as well as conducting an experiment involving the introduction of sparse distributed representations of the transformer at various points. RFB-kWTA utilizes statistics of layer activations across time to adjust the entire layer, enhancing the values of rare activations while reducing those of frequent ones. "Smart" Inhibition also uses activation statistics to sample sparsity masks, with rarer activation times are more likely to be activated. Our proposed mechanisms significantly outperform the classical transformer 0.2768 BLEU and a model that only makes use of dropout in the attention mechanism and output of the transformer block 0.3007 BLEU, achieving a score of 0.3062 on the Multi30K dataset.
Authors: Daiheng Zhang, Yan Zeng, Xinyu Hong, Jinbo Xu
Abstract: Accurately predicting protein melting temperature changes (Delta Tm) is fundamental for assessing protein stability and guiding protein engineering. Leveraging multi-modal protein representations has shown great promise in capturing the complex relationships among protein sequences, structures, and functions. In this study, we develop models based on powerful protein language models, including ESM-2, ESM-3 and AlphaFold, using various feature extraction methods to enhance prediction accuracy. By utilizing the ESM-3 model, we achieve a new state-of-the-art performance on the s571 test dataset, obtaining a Pearson correlation coefficient (PCC) of 0.50. Furthermore, we conduct a fair evaluation to compare the performance of different protein language models in the Delta Tm prediction task. Our results demonstrate that integrating multi-modal protein representations could advance the prediction of protein melting temperatures.
Authors: Yongxuan Chen, Dianhui Wang
Abstract: Stochastic configuration networks (SCNs), as a class of randomized learner models, are featured by its way of random parameters assignment in the light of a supervisory mechanism, resulting in the universal approximation property at algorithmic level. This paper presents a kernel version of SCNs, termed KSCNs, aiming to enhance model's representation learning capability and performance stability. The random bases of a built SCN model can be used to span a reproducing kernel Hilbert space (RKHS), followed by our proposed algorithm for constructing KSCNs. It is shown that the data distribution in the reconstructive space is favorable for regression solving and the proposed KSCN learner models hold the universal approximation property. Three benchmark datasets including two industrial datasets are used in this study for performance evaluation. Experimental results with comparisons against existing solutions clearly demonstrate that the proposed KSCN remarkably outperforms the original SCNs and some typical kernel methods for resolving nonlinear regression problems in terms of the learning performance, the model's stability and robustness with respect to the kernel parameter settings.
Authors: Weichao Xu, Huaxin Pei, Jingxuan Yang, Yuchen Shi, Yi Zhang, Qianchuan Zhao
Abstract: Recent advances in decision-making policies have led to significant progress in fields such as autonomous driving and robotics. However, testing these policies remains crucial with the existence of critical scenarios that may threaten their reliability. Despite ongoing research, challenges such as low testing efficiency and limited diversity persist due to the complexity of the decision-making policies and their environments. To address these challenges, this paper proposes an adaptable Large Language Model (LLM)-driven online testing framework to explore critical and diverse testing scenarios for decision-making policies. Specifically, we design a "generate-test-feedback" pipeline with templated prompt engineering to harness the world knowledge and reasoning abilities of LLMs. Additionally, a multi-scale scenario generation strategy is proposed to address the limitations of LLMs in making fine-grained adjustments, further enhancing testing efficiency. Finally, the proposed LLM-driven method is evaluated on five widely recognized benchmarks, and the experimental results demonstrate that our method significantly outperforms baseline methods in uncovering both critical and diverse scenarios. These findings suggest that LLM-driven methods hold significant promise for advancing the testing of decision-making policies.
Authors: Junwei Su, Shan Wu
Abstract: Temporal Graph Neural Networks (TGNNs) are a family of graph neural networks designed to model and learn dynamic information from temporal graphs. Given their substantial empirical success, there is an escalating interest in TGNNs within the research community. However, the majority of these efforts have been channelled towards algorithm and system design, with the evaluation metrics receiving comparatively less attention. Effective evaluation metrics are crucial for providing detailed performance insights, particularly in the temporal domain. This paper investigates the commonly used evaluation metrics for TGNNs and illustrates the failure mechanisms of these metrics in capturing essential temporal structures in the predictive behaviour of TGNNs. We provide a mathematical formulation of existing performance metrics and utilize an instance-based study to underscore their inadequacies in identifying volatility clustering (the occurrence of emerging errors within a brief interval). This phenomenon has profound implications for both algorithm and system design in the temporal domain. To address this deficiency, we introduce a new volatility-aware evaluation metric (termed volatility cluster statistics), designed for a more refined analysis of model temporal performance. Additionally, we demonstrate how this metric can serve as a temporal-volatility-aware training objective to alleviate the clustering of temporal errors. Through comprehensive experiments on various TGNN models, we validate our analysis and the proposed approach. The empirical results offer revealing insights: 1) existing TGNNs are prone to making errors with volatility clustering, and 2) TGNNs with different mechanisms to capture temporal information exhibit distinct volatility clustering patterns. Our empirical findings demonstrate that our proposed training objective effectively reduces volatility clusters in error.
Authors: Hongshu Guo, Zeyuan Ma, Jiacheng Chen, Yining Ma, Zhiguang Cao, Xinglin Zhang, Yue-Jiao Gong
Abstract: Recent advances in Meta-learning for Black-Box Optimization (MetaBBO) have shown the potential of using neural networks to dynamically configure evolutionary algorithms (EAs), enhancing their performance and adaptability across various BBO instances. However, they are often tailored to a specific EA, which limits their generalizability and necessitates retraining or redesigns for different EAs and optimization problems. To address this limitation, we introduce ConfigX, a new paradigm of the MetaBBO framework that is capable of learning a universal configuration agent (model) for boosting diverse EAs. To achieve so, our ConfigX first leverages a novel modularization system that enables the flexible combination of various optimization sub-modules to generate diverse EAs during training. Additionally, we propose a Transformer-based neural network to meta-learn a universal configuration policy through multitask reinforcement learning across a designed joint optimization task space. Extensive experiments verify that, our ConfigX, after large-scale pre-training, achieves robust zero-shot generalization to unseen tasks and outperforms state-of-the-art baselines. Moreover, ConfigX exhibits strong lifelong learning capabilities, allowing efficient adaptation to new tasks through fine-tuning. Our proposed ConfigX represents a significant step toward an automatic, all-purpose configuration agent for EAs.
Authors: Santiago Aranguri, Francesco Insulla
Abstract: We analyze the training of a two-layer autoencoder used to parameterize a flow-based generative model for sampling from a high-dimensional Gaussian mixture. Previous work shows that the phase where the relative probability between the modes is learned disappears as the dimension goes to infinity without an appropriate time schedule. We introduce a time dilation that solves this problem. This enables us to characterize the learned velocity field, finding a first phase where the probability of each mode is learned and a second phase where the variance of each mode is learned. We find that the autoencoder representing the velocity field learns to simplify by estimating only the parameters relevant to each phase. Turning to real data, we propose a method that, for a given feature, finds intervals of time where training improves accuracy the most on that feature. Since practitioners take a uniform distribution over training times, our method enables more efficient training. We provide preliminary experiments validating this approach.
Authors: Ren Fujiwara, Yasuko Matsubara, Yasushi Sakurai
Abstract: We study the problem of modeling a non-linear dynamical system when given a time series by deriving equations directly from the data. Despite the fact that time series data are given as input, models for dynamics and estimation algorithms that incorporate long-term temporal dependencies are largely absent from existing studies. In this paper, we introduce a latent state to allow time-dependent modeling and formulate this problem as a dynamics estimation problem in latent states. We face multiple technical challenges, including (1) modeling latent non-linear dynamics and (2) solving circular dependencies caused by the presence of latent states. To tackle these challenging problems, we propose a new method, Latent Non-Linear equation modeling (LaNoLem), that can model a latent non-linear dynamical system and a novel alternating minimization algorithm for effectively estimating latent states and model parameters. In addition, we introduce criteria to control model complexity without human intervention. Compared with the state-of-the-art model, LaNoLem achieves competitive performance for estimating dynamics while outperforming other methods in prediction.
Authors: Haonan Yuan, Qingyun Sun, Zhaonan Wang, Xingcheng Fu, Cheng Ji, Yongjian Wang, Bo Jin, Jianxin Li
Abstract: Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks (DGNNs). Dynamic Graph Structure Learning (DGSL) offers a promising way to optimize graph structures. However, aside from encountering unacceptable quadratic complexity, it overly relies on heuristic priors, making it hard to discover underlying predictive patterns. How to efficiently refine the dynamic structures, capture intrinsic dependencies, and learn robust representations, remains under-explored. In this work, we propose the novel DG-Mamba, a robust and efficient Dynamic Graph structure learning framework with the Selective State Space Models (Mamba). To accelerate the spatio-temporal structure learning, we propose a kernelized dynamic message-passing operator that reduces the quadratic time complexity to linear. To capture global intrinsic dynamics, we establish the dynamic graph as a self-contained system with State Space Model. By discretizing the system states with the cross-snapshot graph adjacency, we enable the long-distance dependencies capturing with the selective snapshot scan. To endow learned dynamic structures more expressive with informativeness, we propose the self-supervised Principle of Relevant Information for DGSL to regularize the most relevant yet least redundant information, enhancing global robustness. Extensive experiments demonstrate the superiority of the robustness and efficiency of our DG-Mamba compared with the state-of-the-art baselines against adversarial attacks.
Authors: Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu, Baoyu Jing, Yikun Ban, Jingrui He, Jiawei Han
Abstract: While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over Internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of three fundamental issues: the scarcity of labeled data and text supervision, different levels of downstream tasks, and the conceptual gaps between domains. In this work, to address these issues, we leverage multi-modal prompt learning to effectively adapt pre-trained GNN to downstream tasks and data, given only a few semantically labeled samples, each with extremely weak text supervision. Our new paradigm embeds the graphs directly in the same space as the Large Language Models (LLMs) by learning both graph prompts and text prompts simultaneously. To accomplish this, we improve state-of-the-art graph prompt method, and then propose the first graph-language multi-modal prompt learning approach for exploiting the knowledge in pre-trained models. Notably, due to the insufficient supervision for fine-tuning, in our paradigm, the pre-trained GNN and the LLM are kept frozen, so the learnable parameters are much fewer than fine-tuning any pre-trained model. Through extensive experiments on real-world datasets, we demonstrate the superior performance of our paradigm in few-shot, multi-task-level, and cross-domain settings. Moreover, we build the first CLIP-style zero-shot classification prototype that can generalize GNNs to unseen classes with extremely weak text supervision.
Authors: Lifan Zhao, Yanyan Shen
Abstract: Time series forecasting always faces the challenge of concept drift, where data distributions evolve over time, leading to a decline in forecast model performance. Existing solutions are based on online learning, which continually organize recent time series observations as new training samples and update model parameters according to the forecasting feedback on recent data. However, they overlook a critical issue: obtaining ground-truth future values of each sample should be delayed until after the forecast horizon. This delay creates a temporal gap between the training samples and the test sample. Our empirical analysis reveals that the gap can introduce concept drift, causing forecast models to adapt to outdated concepts. In this paper, we present \textsc{Proceed}, a novel proactive model adaptation framework for online time series forecasting. \textsc{Proceed} first estimates the concept drift between the recently used training samples and the current test sample. It then employs an adaptation generator to efficiently translate the estimated drift into parameter adjustments, proactively adapting the model to the test sample. To enhance the generalization capability of the framework, \textsc{Proceed} is trained on synthetic diverse concept drifts. Extensive experiments on five real-world datasets across various forecast models demonstrate that \textsc{Proceed} brings more performance improvements than the state-of-the-art online learning methods, significantly facilitating forecast models' resilience against concept drifts. Code is available at \url{https://github.com/SJTU-DMTai/OnlineTSF}.
Authors: Hao Kang, Srikant Bharadwaj, James Hensman, Tushar Krishna, Victor Ruhle, Saravan Rajmohan
Abstract: Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved efficiency of the overall inference, they address different aspects of the problem: quantization focuses on weight-activation operations, while FlashAttention improves execution but requires high-precision formats. Recent Key-value (KV) cache quantization reduces memory bandwidth but still needs floating-point dequantization for attention operation. We present TurboAttention, a comprehensive approach to enable quantized execution of attention that simultaneously addresses both memory and computational efficiency. Our solution introduces two key innovations: FlashQ, a headwise attention quantization technique that enables both compression of KV cache and quantized execution of activation-activation multiplication, and Sparsity-based Softmax Approximation (SAS), which eliminates the need for dequantization to FP32 during exponentiation operation in attention. Experimental results demonstrate that TurboAttention achieves 1.2-1.8x speedup in attention, reduces the KV cache size by over 4.4x, and enables up to 2.37x maximum throughput over the FP16 baseline while outperforming state-of-the-art quantization and compression techniques across various datasets and models.
Authors: Haodong Feng, Yue Wang, Dixia Fan
Abstract: In science and engineering, machine learning techniques are increasingly successful in physical systems modeling (predicting future states of physical systems). Effectively integrating PDE loss as a constraint of system transition can improve the model's prediction by overcoming generalization issues due to data scarcity, especially when data acquisition is costly. However, in many real-world scenarios, due to sensor limitations, the data we can obtain is often only partial observation, making the calculation of PDE loss seem to be infeasible, as the PDE loss heavily relies on high-resolution states. We carefully study this problem and propose a novel framework named Re-enable PDE Loss under Partial Observation (RPLPO). The key idea is that although enabling PDE loss to constrain system transition solely is infeasible, we can re-enable PDE loss by reconstructing the learnable high-resolution state and constraining system transition simultaneously. Specifically, RPLPO combines an encoding module for reconstructing learnable high-resolution states with a transition module for predicting future states. The two modules are jointly trained by data and PDE loss. We conduct experiments in various physical systems to demonstrate that RPLPO has significant improvement in generalization, even when observation is sparse, irregular, noisy, and PDE is inaccurate.
Authors: Abdessalam Ed-dib, Zhanibek Datbayev, Amine Mohamed Aboussalah
Abstract: Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a trade-off between expressivity and computational cost: lower ranks reduce resources but limit expressiveness, while higher ranks enhance expressivity at increased cost. Despite recent advances in adaptive LoRA techniques, existing methods fail to provide a theoretical basis for optimizing the trade-off between model performance and efficiency. We propose Geometric Low-Rank Adaptation (GeLoRA), a novel framework that computes the intrinsic dimensionality of hidden state representations to adaptively select LoRA ranks. We demonstrate that the intrinsic dimension provides a lower bound for the optimal rank of LoRA matrices, allowing for a principled selection that balances efficiency and expressivity. GeLoRA dynamically adjusts the rank for each layer based on the intrinsic dimensionality of its input and output representations, recognizing that not all model parameters equally impact fine-tuning. Empirical validation on multiple tasks shows that GeLoRA consistently outperforms recent baselines within the same parameter budget.
Authors: Lyudmila Grigoryeva, Hannah Lim Jing Ting, Juan-Pablo Ortega
Abstract: Next-generation reservoir computing (NG-RC) has attracted much attention due to its excellent performance in spatio-temporal forecasting of complex systems and its ease of implementation. This paper shows that NG-RC can be encoded as a kernel ridge regression that makes training efficient and feasible even when the space of chosen polynomial features is very large. Additionally, an extension to an infinite number of covariates is possible, which makes the methodology agnostic with respect to the lags into the past that are considered as explanatory factors, as well as with respect to the number of polynomial covariates, an important hyperparameter in traditional NG-RC. We show that this approach has solid theoretical backing and good behavior based on kernel universality properties previously established in the literature. Various numerical illustrations show that these generalizations of NG-RC outperform the traditional approach in several forecasting applications.
Authors: Jaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong Cho
Abstract: We explore the use of Residual Vector Quantization (RVQ) for high-fidelity generation in vector-quantized generative models. This quantization technique maintains higher data fidelity by employing more in-depth tokens. However, increasing the token number in generative models leads to slower inference speeds. To this end, we introduce ResGen, an efficient RVQ-based discrete diffusion model that generates high-fidelity samples without compromising sampling speed. Our key idea is a direct prediction of vector embedding of collective tokens rather than individual ones. Moreover, we demonstrate that our proposed token masking and multi-token prediction method can be formulated within a principled probabilistic framework using a discrete diffusion process and variational inference. We validate the efficacy and generalizability of the proposed method on two challenging tasks across different modalities: conditional image generation} on ImageNet 256x256 and zero-shot text-to-speech synthesis. Experimental results demonstrate that ResGen outperforms autoregressive counterparts in both tasks, delivering superior performance without compromising sampling speed. Furthermore, as we scale the depth of RVQ, our generative models exhibit enhanced generation fidelity or faster sampling speeds compared to similarly sized baseline models. The project page can be found at https://resgen-genai.github.io
Authors: Mingtian Zhang, Thomas Bird, Raza Habib, Tianlin Xu, David Barber
Abstract: Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks, alternative non-likelihood training criteria have been proposed. Whilst not necessarily statistically efficient, these alternatives may better match user requirements such as sharp image generation. A general variational method for training probabilistic latent variable models using maximum likelihood is well established; however, how to train latent variable models using other f-divergences is comparatively unknown. We discuss a variational approach that, when combined with the recently introduced Spread Divergence, can be applied to train a large class of latent variable models using any f-divergence.
Authors: Chung-Chin Shih, Ti-Rong Wu, Ting Han Wei, I-Chen Wu
Abstract: Goal-achieving problems are puzzles that set up a specific situation with a clear objective. An example that is well-studied is the category of life-and-death (L&D) problems for Go, which helps players hone their skill of identifying region safety. Many previous methods like lambda search try null moves first, then derive so-called relevance zones (RZs), outside of which the opponent does not need to search. This paper first proposes a novel RZ-based approach, called the RZ-Based Search (RZS), to solving L&D problems for Go. RZS tries moves before determining whether they are null moves post-hoc. This means we do not need to rely on null move heuristics, resulting in a more elegant algorithm, so that it can also be seamlessly incorporated into AlphaZero's super-human level play in our solver. To repurpose AlphaZero for solving, we also propose a new training method called Faster to Life (FTL), which modifies AlphaZero to entice it to win more quickly. We use RZS and FTL to solve L&D problems on Go, namely solving 68 among 106 problems from a professional L&D book while a previous program solves 11 only. Finally, we discuss that the approach is generic in the sense that RZS is applicable to solving many other goal-achieving problems for board games.
Authors: Zakhar Popovych, Kurt Jacobs, Georgios Korpas, Jakub Marecek, Denys I. Bondar
Abstract: Accurate models of the dynamics of quantum circuits are essential for optimizing and advancing quantum devices. Since first-principles models of environmental noise and dissipation in real quantum systems are often unavailable, deriving accurate models from measured time-series data is critical. However, identifying open quantum systems poses significant challenges: powerful methods from systems engineering can perform poorly beyond weak damping (as we show) because they fail to incorporate essential constraints required for quantum evolution (e.g., positivity). Common methods that can include these constraints are typically multi-step, fitting linear models to physically grounded master equations, often resulting in non-convex functions in which local optimization algorithms get stuck in local extrema (as we show). In this work, we solve these problems by formulating quantum system identification directly from data as a polynomial optimization problem, enabling the use of recently developed global optimization methods. These methods are essentially guaranteed to reach global optima, allowing us for the first time to efficiently obtain the most accurate Markovian model for a given system. In addition to its practical importance, this allows us to take the error of these Markovian models as an alternative (operational) measure of the non-Markovianity of a system. We test our method with the spin-boson model -- a two-level system coupled to a bath of harmonic oscillators -- for which we obtain the exact evolution using matrix-product-state techniques. We show that polynomial optimization using moment/sum-of-squares approaches significantly outperforms traditional optimization algorithms, and we show that even for strong damping Lindblad-form master equations can provide accurate models of the spin-boson system.
Authors: Thejan Rajapakshe, Rajib Rana, Sara Khalifa, Bjorn W. Schuller
Abstract: Computers can understand and then engage with people in an emotionally intelligent way thanks to speech-emotion recognition (SER). However, the performance of SER in cross-corpus and real-world live data feed scenarios can be significantly improved. The inability to adapt an existing model to a new domain is one of the shortcomings of SER methods. To address this challenge, researchers have developed domain adaptation techniques that transfer knowledge learnt by a model across the domain. Although existing domain adaptation techniques have improved performances across domains, they can be improved to adapt to a real-world live data feed situation where a model can self-tune while deployed. In this paper, we present a deep reinforcement learning-based strategy (RL-DA) for adapting a pre-trained model to a real-world live data feed setting while interacting with the environment and collecting continual feedback. RL-DA is evaluated on SER tasks, including cross-corpus and cross-language domain adaption schema. Evaluation results show that in a live data feed setting, RL-DA outperforms a baseline strategy by 11% and 14% in cross-corpus and cross-language scenarios, respectively.
Authors: Andrei T. Patrascu
Abstract: Neural networks are being used to improve the probing of the state spaces of many particle systems as approximations to wavefunctions and in order to avoid the recurring sign problem of quantum monte-carlo. One may ask whether the usual classical neural networks have some actual hidden quantum properties that make them such suitable tools for a highly coupled quantum problem. I discuss here what makes a system quantum and to what extent we can interpret a neural network as having quantum remnants. I suggest that a system can be quantum both due to its fundamental quantum constituents and due to the rules of its functioning, therefore, we can obtain entanglement both due to the quantum constituents' nature and due to the functioning rules, or, in category theory terms, both due to the quantum nature of the objects of a category and of the maps. From a practical point of view, I suggest a possible experiment that could extract entanglement from the quantum functioning rules (maps) of an otherwise classical (from the point of view of the constituents) neural network.
Authors: Kunal Mukherjee, Joshua Wiedemeier, Tianhao Wang, Muhyun Kim, Feng Chen, Murat Kantarcioglu, Kangkook Jee
Abstract: Advanced cyber threats (e.g., Fileless Malware and Advanced Persistent Threat (APT)) have driven the adoption of provenance-based security solutions. These solutions employ Machine Learning (ML) models for behavioral modeling and critical security tasks such as malware and anomaly detection. However, the opacity of ML-based security models limits their broader adoption, as the lack of transparency in their decision-making processes restricts explainability and verifiability. We tailored our solution towards Graph Neural Network (GNN)-based security solutions since recent studies employ GNNs to comprehensively digest system provenance graphs for security critical tasks. To enhance the explainability of GNN-based security models, we introduce PROVEXPLAINER, a framework offering instance-level security-aware explanations using an interpretable surrogate model. PROVEXPLAINER's interpretable feature space consists of discriminant subgraph patterns and graph structural features, which can be directly mapped to the system provenance problem space, making the explanations human understandable. By considering prominent GNN architectures (e.g., GAT and GraphSAGE) for anomaly detection tasks, we show how PROVEXPLAINER synergizes with current state-of-the-art (SOTA) GNN explainers to deliver domain and instance-specific explanations. We measure the explanation quality using the fidelity+/fidelity- metric as used by traditional GNN explanation literature, and we incorporate the precision/recall metric where we consider the accuracy of the explanation against the ground truth. On malware and APT datasets, PROVEXPLAINER achieves up to 29%/27%/25% higher fidelity+, precision and recall, and 12% lower fidelity- respectively, compared to SOTA GNN explainers.
Authors: Vinoth Nandakumar, Qiang Qu, Peng Mi, Tongliang Liu
Abstract: Recent advancements in recurrent neural networks (RNNs) have reinvigorated interest in their application to natural language processing tasks, particularly with the development of more efficient and parallelizable variants known as state space models (SSMs), which have shown competitive performance against transformer models while maintaining a lower memory footprint. While RNNs and SSMs (e.g., Mamba) have been empirically more successful than rule-based systems based on $n$-gram models, a rigorous theoretical explanation for this success has not yet been developed, as it is unclear how these models encode the combinatorial rules that govern the next-word prediction task. In this paper, we construct state space language models that can solve the next-word prediction task for languages generated from $n$-gram rules, thereby showing that the former are more expressive. Our proof shows how SSMs can encode $n$-gram rules using new theoretical results on their memorization capacity, and demonstrates how their context window can be controlled by restricting the spectrum of the hidden weight matrix. We conduct experiments with a small dataset generated from $n$-gram rules to show how our framework can be applied to SSMs and RNNs obtained through gradient-based optimization.
Authors: Chenyang Qiu, Guoshun Nan, Hongrui Xia, Zheng Weng, Xueting Wang, Meng Shen, Xiaofeng Tao, Jun Liu
Abstract: Network-based intrusion detection system (NIDS) monitors network traffic for malicious activities, forming the frontline defense against increasing attacks over information infrastructures. Although promising, our quantitative analysis shows that existing methods perform inconsistently in declaring various attacks, and perform poorly in few-shot intrusion detections. We reveal that the underlying cause is entangled distributions of flow features. This motivates us to propose DIDS-MFL, a disentangled intrusion detection method to handle various intrusion detection scenarios. DIDS-MFL involves two key components, respectively: a double Disentanglementbased Intrusion Detection System (DIDS) and a plug-and-play Multi-scale Few-shot Learning-based (MFL) intrusion detection module. Specifically, the proposed DIDS first disentangles traffic features by a non-parameterized optimization, automatically differentiating tens and hundreds of complex features of various attacks. Such differentiated features will be further disentangled to highlight the attack-specific features. Our DIDS additionally uses a novel graph diffusion method that dynamically fuses the network topology in evolving data streams. Furthermore, the proposed MFL involves an alternating optimization framework to address the entangled representations in few-shot traffic threats with rigorous derivation. MFL first captures multiscale information in latent space to distinguish attack-specific information and then optimizes the disentanglement term to highlight the attack-specific information. Finally, MFL fuses and alternately solves them in an end-to-end way. Experiments show the superiority of our proposed DIDS-MFL. Our code is available at https://github.com/qcydm/DIDS-MFL
Authors: Farina Riaz, Shahab Abdulla, Hajime Suzuki, Srinjoy Ganguly, Ravinesh C. Deo, Susan Hopkins
Abstract: Over the past few years, there has been significant interest in Quantum Machine Learning (QML) among researchers, as it has the potential to transform the field of machine learning. Several models that exploit the properties of quantum mechanics have been developed for practical applications. In this study, we investigated the application of our previously proposed quantum pre-processing filter (QPF) to binary image classification. We evaluated the QPF on four datasets: MNIST (handwritten digits), EMNIST (handwritten digits and alphabets), CIFAR-10 (photographic images) and GTSRB (real-life traffic sign images). Similar to our previous multi-class classification results, the application of QPF improved the binary image classification accuracy using neural network against MNIST, EMNIST, and CIFAR-10 from 98.9% to 99.2%, 97.8% to 98.3%, and 71.2% to 76.1%, respectively, but degraded it against GTSRB from 93.5% to 92.0%. We then applied QPF in cases using a smaller number of training and testing samples, i.e. 80 and 20 samples per class, respectively. In order to derive statistically stable results, we conducted the experiment with 100 trials choosing randomly different training and testing samples and averaging the results. The result showed that the application of QPF did not improve the image classification accuracy against MNIST and EMNIST but improved it against CIFAR-10 and GTSRB from 65.8% to 67.2% and 90.5% to 91.8%, respectively. Further research will be conducted as part of future work to investigate the potential of QPF to assess the scalability of the proposed approach to larger and complex datasets.
Authors: Siavash Golkar, Mariel Pettee, Michael Eickenberg, Alberto Bietti, Miles Cranmer, Geraud Krawezik, Francois Lanusse, Michael McCabe, Ruben Ohana, Liam Parker, Bruno R\'egaldo-Saint Blancard, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho
Abstract: Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific datasets. Rendering datasets as text, however, could help aggregate diverse and multi-modal scientific data into a single training corpus, thereby potentially facilitating the development of foundation models for science. In this work, we introduce xVal, a strategy for continuously tokenizing numbers within language models that results in a more appropriate inductive bias for scientific applications. By training specially-modified language models from scratch on a variety of scientific datasets formatted as text, we find that xVal generally outperforms other common numerical tokenization strategies on metrics including out-of-distribution generalization and computational efficiency.
Authors: Jian Cheng Wong, Chin Chun Ooi, Abhishek Gupta, Pao-Hsiung Chiu, Joshua Shao Zheng Low, My Ha Dao, Yew-Soon Ong
Abstract: Physics-informed neural networks (PINNs) are at the forefront of scientific machine learning, making possible the creation of machine intelligence that is cognizant of physical laws and able to accurately simulate them. However, today's PINNs are often trained for a single physics task and require computationally expensive re-training for each new task, even for tasks from similar physics domains. To address this limitation, this paper proposes a pioneering approach to advance the generalizability of PINNs through the framework of Baldwinian evolution. Drawing inspiration from the neurodevelopment of precocial species that have evolved to learn, predict and react quickly to their environment, we envision PINNs that are pre-wired with connection strengths inducing strong biases towards efficient learning of physics. A novel two-stage stochastic programming formulation coupling evolutionary selection pressure (based on proficiency over a distribution of physics tasks) with lifetime learning (to specialize on a sampled subset of those tasks) is proposed to instantiate the Baldwin effect. The evolved Baldwinian-PINNs demonstrate fast and physics-compliant prediction capabilities across a range of empirically challenging problem instances with more than an order of magnitude improvement in prediction accuracy at a fraction of the computation cost compared to state-of-the-art gradient-based meta-learning methods. For example, when solving the diffusion-reaction equation, a 70x improvement in accuracy was obtained while taking 700x less computational time. This paper thus marks a leap forward in the meta-learning of PINNs as generalizable physics solvers. Sample codes are available at \url{https://github.com/chiuph/Baldwinian-PINN}.
Authors: Sarthak Choudhary, Aashish Kolluri, Prateek Saxena
Abstract: Training modern neural networks or models typically requires averaging over a sample of high-dimensional vectors. Poisoning attacks can skew or bias the average vectors used to train the model, forcing the model to learn specific patterns or avoid learning anything useful. Byzantine robust aggregation is a principled algorithmic defense against such biasing. Robust aggregators can bound the maximum bias in computing centrality statistics, such as mean, even when some fraction of inputs are arbitrarily corrupted. Designing such aggregators is challenging when dealing with high dimensions. However, the first polynomial-time algorithms with strong theoretical bounds on the bias have recently been proposed. Their bounds are independent of the number of dimensions, promising a conceptual limit on the power of poisoning attacks in their ongoing arms race against defenses. In this paper, we show a new attack called HIDRA on practical realization of strong defenses which subverts their claim of dimension-independent bias. HIDRA highlights a novel computational bottleneck that has not been a concern of prior information-theoretic analysis. Our experimental evaluation shows that our attacks almost completely destroy the model performance, whereas existing attacks with the same goal fail to have much effect. Our findings leave the arms race between poisoning attacks and provable defenses wide open.
Authors: Hanxi Liu, Xiaokai Mao, Haocheng Xia, Jian Lou, Jinfei Liu, Kui Ren
Abstract: Large language models (LLMs) excel on new tasks without additional training, simply by providing natural language prompts that demonstrate how the task should be performed. Prompt ensemble methods comprehensively harness the knowledge of LLMs while mitigating individual biases and errors and further enhancing performance. However, more prompts do not necessarily lead to better results, and not all prompts are beneficial. A small number of high-quality prompts often outperform many low-quality prompts. Currently, there is a lack of a suitable method for evaluating the impact of prompts on the results. In this paper, we utilize the Shapley value to fairly quantify the contributions of prompts, helping to identify beneficial or detrimental prompts, and potentially guiding prompt valuation in data markets. Through extensive experiments employing various ensemble methods and utility functions on diverse tasks, we validate the effectiveness of using the Shapley value method for prompts as it effectively distinguishes and quantifies the contributions of each prompt.
Authors: Andr\'e Silva, Sen Fang, Martin Monperrus
Abstract: Automated Program Repair (APR) has evolved significantly with the advent of Large Language Models (LLMs). Fine-tuning LLMs for program repair is a recent avenue of research, with many dimensions which have not been explored. Existing work mostly fine-tune LLMs with naive code representations and does not scale to frontier models. To address this problem, we propose RepairLLaMA, a novel program repair approach that 1) identifies optimal code representations for APR with fine-tuned models, and 2) pioneers state-of-the-art parameter-efficient fine-tuning technique (PEFT) for program repair. This results in RepairLLaMA producing a highly effective `program repair adapter' for fixing bugs with AI. Our experiments demonstrate the validity of both concepts. First, fine-tuning adapters with program repair specific code representations enables the model to use meaningful repair signals and produce better patches. Second, parameter-efficient fine-tuning helps fine-tuning to converge and clearly contributes to the effectiveness of RepairLLaMA in fixing bugs outside the fine-tuning data distribution. Overall, RepairLLaMA correctly fixes 144 Defects4J v2, 109 HumanEval-Java, and 20 GitBug-Java bugs, outperforming all baselines.
Authors: Sergei Shumilin, Alexander Ryabov, Serguei Barannikov, Evgeny Burnaev, Vladimir Vanovskii
Abstract: Voronoi tessellation, also known as Voronoi diagram, is an important computational geometry technique that has applications in various scientific disciplines. It involves dividing a given space into regions based on the proximity to a set of points. Autodifferentiation is a powerful tool for solving optimization tasks. Autodifferentiation assumes constructing a computational graph that allows to compute gradients using backpropagation algorithm. However, often the Voronoi tessellation remains the only non-differentiable part of a pipeline, prohibiting end-to-end differentiation. We present the method for autodifferentiation of the 2D Voronoi tessellation. The method allows one to construct the Voronoi tessellation and pass gradients, making the construction end-to-end differentiable. We provide the implementation details and present several important applications. To the best of our knowledge this is the first autodifferentiable realization of the Voronoi tessellation providing full set of Voronoi geometrical parameters in a differentiable way.
Authors: Haoxiong Liu, Yifan Zhang, Yifan Luo, Andrew Chi-Chih Yao
Abstract: Despite the advancements in large language models (LLMs) for mathematical reasoning, solving competition-level math problems remains a significant challenge, especially for open-source LLMs without external tools. We introduce the MMIQC dataset, comprising a mixture of processed web data and synthetic question-response pairs, aimed at enhancing the mathematical reasoning capabilities of base language models. Models fine-tuned on MMIQC consistently surpass their counterparts in performance on the MATH benchmark across various model sizes. Notably, Qwen-72B-MMIQC achieves a 45.0% accuracy, exceeding the previous open-source state-of-the-art by 8.2% and outperforming the initial version GPT-4 released in 2023. Extensive evaluation results on Hungarian high school finals suggest that such improvement can generalize to unseen data. Our ablation study on MMIQC reveals that a large part of the improvement can be attributed to our novel augmentation method, Iterative Question Composing (IQC), which involves iteratively composing new questions from seed problems using an LLM and applying rejection sampling through another LLM.
Authors: Roi Naveiro, Becky Tang
Abstract: Bayesian Optimization (BO) is a powerful method for optimizing black-box functions by combining prior knowledge with ongoing function evaluations. BO constructs a probabilistic surrogate model of the objective function given the covariates, which is in turn used to inform the selection of future evaluation points through an acquisition function. For smooth continuous search spaces, Gaussian Processes (GPs) are commonly used as the surrogate model as they offer analytical access to posterior predictive distributions, thus facilitating the computation and optimization of acquisition functions. However, in complex scenarios involving optimization over categorical or mixed covariate spaces, GPs may not be ideal. This paper introduces Simulation Based Bayesian Optimization (SBBO) as a novel approach to optimizing acquisition functions that only requires sampling-based access to posterior predictive distributions. SBBO allows the use of surrogate probabilistic models tailored for combinatorial spaces with discrete variables. Any Bayesian model in which posterior inference is carried out through Markov chain Monte Carlo can be selected as the surrogate model in SBBO. We demonstrate empirically the effectiveness of SBBO using various choices of surrogate models in applications involving combinatorial optimization. choices of surrogate models.
Authors: Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, Yang Zhang
Abstract: Jailbreak attacks aim to bypass the safeguards of LLMs. While researchers have studied different jailbreak attacks in depth, they have done so in isolation -- either with unaligned experiment settings or comparing a limited range of methods. To fill this gap, we present the first large-scale measurement of various jailbreak attack methods. We collect 17 cutting-edge jailbreak methods, summarize their features, and establish a novel jailbreak attack taxonomy. Based on eight popular censored LLMs and 160 questions from 16 violation categories, we conduct a unified and impartial assessment of attack effectiveness as well as a comprehensive ablation study. Our extensive experimental results demonstrate that all the jailbreak attacks have a powerful effect on the LLMs. This indicates that all LLMs fail to cover all the violation categories, and they are susceptible to significant jailbreak risks, with even the well-aligned Llama3 facing a maximum attack success rate of 0.88. Additionally, we test jailbreak attacks under eight advanced external defenses and find none of the defenses could mitigate the jailbreak attacks entirely. Our study offers valuable insights for future research on jailbreak attacks and defenses and serves as a benchmark tool for researchers and practitioners to evaluate them effectively.
Authors: Fali Wang, Runxue Bao, Suhang Wang, Wenchao Yu, Yanchi Liu, Wei Cheng, Haifeng Chen
Abstract: Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating knowledge have been developed, which augment LLMs with domain-specific knowledge graphs through external modules. These approaches, however, face data inefficiency issues as they necessitate the processing of both known and unknown knowledge for fine-tuning. Thus, our research focuses on a novel problem: efficiently integrating unknown knowledge into LLMs without unnecessary overlap of known knowledge. A risk of introducing new knowledge is the potential forgetting of existing knowledge. To mitigate this risk, we propose the innovative {\method} framework. This framework employs transformer internal states to determine when to enrich LLM outputs with additional information, effectively preventing knowledge forgetting. Performance evaluations using the UMLS-2.5k and MetaQA domain knowledge graphs reveal that {\method} not only successfully integrates new knowledge but also outperforms state-of-the-art baselines, reducing knowledge forgetting by 9\% and 6\%, respectively.
Authors: Dmitrijs Trizna, Luca Demetrio, Battista Biggio, Fabio Roli
Abstract: Living-off-the-land (LOTL) techniques pose a significant challenge to security operations, exploiting legitimate tools to execute malicious commands that evade traditional detection methods. To address this, we present a robust augmentation framework for cyber defense systems as Security Information and Event Management (SIEM) solutions, enabling the detection of LOTL attacks such as reverse shells through machine learning. Leveraging real-world threat intelligence and adversarial training, our framework synthesizes diverse malicious datasets while preserving the variability of legitimate activity, ensuring high accuracy and low false-positive rates. We validate our approach through extensive experiments on enterprise-scale datasets, achieving a 90\% improvement in detection rates over non-augmented baselines at an industry-grade False Positive Rate (FPR) of $10^{-5}$. We define black-box data-driven attacks that successfully evade unprotected models, and develop defenses to mitigate them, producing adversarially robust variants of ML models. Ethical considerations are central to this work; we discuss safeguards for synthetic data generation and the responsible release of pre-trained models across four best performing architectures, including both adversarially and regularly trained variants: https://huggingface.co/dtrizna/quasarnix. Furthermore, we provide a malicious LOTL dataset containing over 1 million augmented attack variants to enable reproducible research and community collaboration: https://huggingface.co/datasets/dtrizna/QuasarNix. This work offers a reproducible, scalable, and production-ready defense against evolving LOTL threats.
URLs: https://huggingface.co/dtrizna/quasarnix., https://huggingface.co/datasets/dtrizna/QuasarNix.
Authors: Neha Verma, Maha Elbayad
Abstract: Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer architecture, despite its dominant popularity in the language domain. Therefore, in this work, we investigate the extent to which separate Transformer minima learn similar features, and propose a model merging technique to investigate the relationship between these minima in the loss landscape. The specifics of the architecture, like its residual connections, multi-headed attention, and discrete, sequential input, require specific interventions in order to compute model permutations that remain within the same functional equivalence class. In merging these models with our method, we consistently find lower loss barriers between minima compared to model averaging, across models trained on a masked-language modeling task or fine-tuned on a language understanding benchmark. Our results show that the minima of these models are less sharp and isolated than previously understood, and provide a basis for future work on merging separately trained Transformer models.
Authors: Masoud Shokrnezhad, Hao Yu, Tarik Taleb, Richard Li, Kyunghan Lee, Jaeseung Song, Cedric Westphal
Abstract: In the context of advancing 6G, a substantial paradigm shift is anticipated, highlighting comprehensive everything-to-everything interactions characterized by numerous connections and stringent adherence to Quality of Service/Experience (QoS/E) prerequisites. The imminent challenge stems from resource scarcity, prompting a deliberate transition to Computing-Network Convergence (CNC) as an auspicious approach for joint resource orchestration. While CNC-based mechanisms have garnered attention, their effectiveness in realizing future services, particularly in use cases like the Metaverse, may encounter limitations due to the continually changing nature of users, services, and resources. Hence, this paper presents the concept of Adaptable CNC (ACNC) as an autonomous Machine Learning (ML)-aided mechanism crafted for the joint orchestration of computing and network resources, catering to dynamic and voluminous user requests with stringent requirements. ACNC encompasses two primary functionalities: state recognition and context detection. Given the intricate nature of the user-service-computing-network space, the paper employs dimension reduction to generate live, holistic, abstract system states in a hierarchical structure. To address the challenges posed by dynamic changes, Continual Learning (CL) is employed, classifying the system state into contexts controlled by dedicated ML agents, enabling them to operate efficiently. These two functionalities are intricately linked within a closed loop overseen by the End-to-End (E2E) orchestrator to allocate resources. The paper introduces the components of ACNC, proposes a Metaverse scenario to exemplify ACNC's role in resource provisioning with Segment Routing v6 (SRv6), outlines ACNC's workflow, details a numerical analysis for efficiency assessment, and concludes with discussions on relevant challenges and potential avenues for future research.
Authors: Simon Briend, Christophe Giraud, G\'abor Lugosi, D\'eborah Sulem
Abstract: This paper studies the problem of estimating the order of arrival of the vertices in a random recursive tree. Specifically, we study two fundamental models: the uniform attachment model and the linear preferential attachment model. We propose an order estimator based on the Jordan centrality measure and define a family of risk measures to quantify the quality of the ordering procedure. Moreover, we establish a minimax lower bound for this problem, and prove that the proposed estimator is nearly optimal. Finally, we numerically demonstrate that the proposed estimator outperforms degree-based and spectral ordering procedures.
Authors: Yunfei Cheng, Aonan Zhang, Xuanyu Zhang, Chong Wang, Yi Wang
Abstract: We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a recurrent neural network (RNN) as the draft model conditioning on LLM's hidden states, (2) applying a dynamic tree attention algorithm over beam search results to eliminate duplicated prefixes in candidate sequences, and (3) training through knowledge distillation from the LLM. ReDrafter accelerates Vicuna inference in MT-Bench by up to 2.8x with a PyTorch implementation on Nvidia H100 GPUs. To demonstrate its practicality in real environments, we also validated its effectiveness for on-device applications by implementing the approach in MLX and benchmarking performance on Metal GPUs in Apple Silicon chips, achieving up to 2.3x speedup.
Authors: Jun Liu, Zhenglun Kong, Pu Zhao, Changdi Yang, Hao Tang, Xuan Shen, Geng Yuan, Wei Niu, Wenbin Zhang, Xue Lin, Dong Huang, Yanzhi Wang
Abstract: Structured pruning for large language models (LLMs) has garnered significant academic interest due to its ability to efficiently compress and accelerate LLMs by eliminating redundant weight groups at a coarse-grained granularity. Current structured pruning methods for LLMs typically depend on a singular granularity for assessing weight importance, resulting in notable performance degradation in downstream tasks. Intriguingly, our empirical investigations reveal that utilizing unstructured pruning, which achieves better performance retention by pruning weights at a finer granularity, \emph{i.e.}, individual weights, yields significantly varied sparse LLM structures when juxtaposed to structured pruning. This suggests that evaluating both holistic and individual assessment for weight importance is essential for LLM pruning. Building on this insight, we introduce the Hybrid-grained Weight Importance Assessment (HyWIA), a novel method that merges fine-grained and coarse-grained evaluations of weight importance for the pruning of LLMs. Leveraging an attention mechanism, HyWIA adaptively determines the optimal blend of granularity in weight importance assessments in an end-to-end pruning manner. Extensive experiments on LLaMA-V1/V2, Vicuna, Baichuan, and Bloom across various benchmarks demonstrate the effectiveness of HyWIA in pruning LLMs. For example, HyWIA surpasses the cutting-edge LLM-Pruner by an average margin of 2.82\% in accuracy across seven downstream tasks when pruning LLaMA-7B by 50\%.
Authors: Ruozhen He, Ziyan Yang, Paola Cascante-Bonilla, Alexander C. Berg, Vicente Ordonez
Abstract: This paper extensively investigates the effectiveness of synthetic training data to improve the capabilities of vision-and-language models for grounding textual descriptions to image regions. We explore various strategies to best generate image-text pairs and image-text-box triplets using a series of pretrained models under different settings and varying degrees of reliance on real data. Through comparative analyses with synthetic, real, and web-crawled data, we identify factors that contribute to performance differences, and propose SynGround, an effective pipeline for generating useful synthetic data for visual grounding. Our findings show that SynGround can improve the localization capabilities of off-the-shelf vision-and-language models and offers the potential for arbitrarily large scale data generation. Particularly, data generated with SynGround improves the pointing game accuracy of a pretrained ALBEF and BLIP models by 4.81% and 17.11% absolute percentage points, respectively, across the RefCOCO+ and the Flickr30k benchmarks.
Authors: Leying Zhang, Yao Qian, Long Zhou, Shujie Liu, Dongmei Wang, Xiaofei Wang, Midia Yousefi, Yanmin Qian, Jinyu Li, Lei He, Sheng Zhao, Michael Zeng
Abstract: Recent advancements in zero-shot text-to-speech (TTS) modeling have led to significant strides in generating high-fidelity and diverse speech. However, dialogue generation, along with achieving human-like naturalness in speech, continues to be a challenge. In this paper, we introduce CoVoMix: Conversational Voice Mixture Generation, a novel model for zero-shot, human-like, multi-speaker, multi-round dialogue speech generation. CoVoMix first converts dialogue text into multiple streams of discrete tokens, with each token stream representing semantic information for individual talkers. These token streams are then fed into a flow-matching based acoustic model to generate mixed mel-spectrograms. Finally, the speech waveforms are produced using a HiFi-GAN model. Furthermore, we devise a comprehensive set of metrics for measuring the effectiveness of dialogue modeling and generation. Our experimental results show that CoVoMix can generate dialogues that are not only human-like in their naturalness and coherence but also involve multiple talkers engaging in multiple rounds of conversation. This is exemplified by instances generated in a single channel where one speaker's utterance is seamlessly mixed with another's interjections or laughter, indicating the latter's role as an attentive listener. Audio samples are available at https://aka.ms/covomix.
URLs: https://aka.ms/covomix.
Authors: Juan-Pablo Ortega, Florian Rossmannek
Abstract: A probabilistic framework to study the dependence structure induced by deterministic discrete-time state-space systems between input and output processes is introduced. General sufficient conditions are formulated under which output processes exist and are unique once an input process has been fixed, a property that in the deterministic state-space literature is known as the echo state property. When those conditions are satisfied, the given state-space system becomes a generative model for probabilistic dependences between two sequence spaces. Moreover, those conditions guarantee that the output depends continuously on the input when using the Wasserstein metric. The output processes whose existence is proved are shown to be causal in a specific sense and to generalize those studied in purely deterministic situations. The results in this paper constitute a significant stochastic generalization of sufficient conditions for the deterministic echo state property to hold, in the sense that the stochastic echo state property can be satisfied under contractivity conditions that are strictly weaker than those in deterministic situations. This means that state-space systems can induce a purely probabilistic dependence structure between input and output sequence spaces even when there is no functional relation between those two spaces.
Authors: Adrian de Wynter, Ishaan Watts, Tua Wongsangaroonsri, Minghui Zhang, Noura Farra, Nektar Ege Alt{\i}ntoprak, Lena Baur, Samantha Claudet, Pavel Gajdusek, Can G\"oren, Qilong Gu, Anna Kaminska, Tomasz Kaminski, Ruby Kuo, Akiko Kyuba, Jongho Lee, Kartik Mathur, Petter Merok, Ivana Milovanovi\'c, Nani Paananen, Vesa-Matti Paananen, Anna Pavlenko, Bruno Pereira Vidal, Luciano Strika, Yueh Tsao, Davide Turcato, Oleksandr Vakhno, Judit Velcsov, Anna Vickers, St\'ephanie Visser, Herdyan Widarmanto, Andrey Zaikin, Si-Qing Chen
Abstract: Large language models (LLMs) and small language models (SLMs) are being adopted at remarkable speed, although their safety still remains a serious concern. With the advent of multilingual S/LLMs, the question now becomes a matter of scale: can we expand multilingual safety evaluations of these models with the same velocity at which they are deployed? To this end, we introduce RTP-LX, a human-transcreated and human-annotated corpus of toxic prompts and outputs in 28 languages. RTP-LX follows participatory design practices, and a portion of the corpus is especially designed to detect culturally-specific toxic language. We evaluate 10 S/LLMs on their ability to detect toxic content in a culturally-sensitive, multilingual scenario. We find that, although they typically score acceptably in terms of accuracy, they have low agreement with human judges when scoring holistically the toxicity of a prompt; and have difficulty discerning harm in context-dependent scenarios, particularly with subtle-yet-harmful content (e.g. microaggressions, bias). We release this dataset to contribute to further reduce harmful uses of these models and improve their safe deployment.
Authors: Hiroki Waida, Kimihiro Yamazaki, Atsushi Tokuhisa, Mutsuyo Wada, Yuichiro Wada
Abstract: Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.
Authors: Justin K. Miller, Tristram J. Alexander
Abstract: Clustering short text is a difficult problem, due to the low word co-occurrence between short text documents. This work shows that large language models (LLMs) can overcome the limitations of traditional clustering approaches by generating embeddings that capture the semantic nuances of short text. In this study clusters are found in the embedding space using Gaussian Mixture Modelling (GMM). The resulting clusters are found to be more distinctive and more human-interpretable than clusters produced using the popular methods of doc2vec and Latent Dirichlet Allocation (LDA). The success of the clustering approach is quantified using human reviewers and through the use of a generative LLM. The generative LLM shows good agreement with the human reviewers, and is suggested as a means to bridge the `validation gap' which often exists between cluster production and cluster interpretation. The comparison between LLM-coding and human-coding reveals intrinsic biases in each, challenging the conventional reliance on human coding as the definitive standard for cluster validation.
Authors: Yufan Zhang, Honglin Wen, Yuexin Bian, Yuanyuan Shi
Abstract: Large penetration of renewable energy sources (RESs) brings huge uncertainty into the electricity markets. The current deterministic clearing approach in the day-ahead (DA) market, where RESs participate based on expected production, has been criticized for causing a lack of coordination between the DA and real-time (RT) markets, leading to high overall operating costs. Previous works indicate that improving day-ahead RES entering quantities can significantly mitigate the drawbacks of deterministic clearing. In this work, we propose using a trained forecasting model, referred to as value-oriented forecasting, to determine RES Improved Entering Quantities (RIEQ) more efficiently during the operational phase. Unlike traditional models that minimize statistical forecasting errors, our approach trains model parameters to minimize the expected overall operating costs across both DA and RT markets. We derive the exact form of the loss function used for training, which becomes piecewise linear when market clearing is modeled by linear programs. Additionally, we provide the analytical gradient of the loss function with respect to the forecast, enabling an efficient training strategy. Numerical studies demonstrate that our forecasts significantly reduce overall operating costs for deterministic market clearing compared to conventional forecasts based on expected RES production.
Authors: Zijian Zhou, Xiaoqiang Lin, Xinyi Xu, Alok Prakash, Daniela Rus, Bryan Kian Hsiang Low
Abstract: In-context learning (ICL) allows transformer-based language models that are pre-trained on general text to quickly learn a specific task with a few "task demonstrations" without updating their parameters, significantly boosting their flexibility and generality. ICL possesses many distinct characteristics from conventional machine learning, thereby requiring new approaches to interpret this learning paradigm. Taking the viewpoint of recent works showing that transformers learn in context by formulating an internal optimizer, we propose an influence function-based attribution technique, DETAIL, that addresses the specific characteristics of ICL. We empirically verify the effectiveness of our approach for demonstration attribution while being computationally efficient. Leveraging the results, we then show how DETAIL can help improve model performance in real-world scenarios through demonstration reordering and curation. Finally, we experimentally prove the wide applicability of DETAIL by showing our attribution scores obtained on white-box models are transferable to black-box models in improving model performance.
Authors: Rohan Chandra, Haresh Karnan, Negar Mehr, Peter Stone, Joydeep Biswas
Abstract: Social robot navigation in crowded public spaces such as university campuses, restaurants, grocery stores, and hospitals, is an increasingly important area of research. One of the core strategies for achieving this goal is to understand humans' intent--underlying psychological factors that govern their motion--by learning their reward functions, typically via inverse reinforcement learning (IRL). Despite significant progress in IRL, learning reward functions of multiple agents simultaneously in dense unstructured pedestrian crowds has remained intractable due to the nature of the tightly coupled social interactions that occur in these scenarios \textit{e.g.} passing, intersections, swerving, weaving, etc. In this paper, we present a new multi-agent maximum entropy inverse reinforcement learning algorithm for real world unstructured pedestrian crowds. Key to our approach is a simple, but effective, mathematical trick which we name the so-called tractability-rationality trade-off trick that achieves tractability at the cost of a slight reduction in accuracy. We compare our approach to the classical single-agent MaxEnt IRL as well as state-of-the-art trajectory prediction methods on several datasets including the ETH, UCY, SCAND, JRDB, and a new dataset, called Speedway, collected at a busy intersection on a University campus focusing on dense, complex agent interactions. Our key findings show that, on the dense Speedway dataset, our approach ranks 1st among top 7 baselines with >2X improvement over single-agent IRL, and is competitive with state-of-the-art large transformer-based encoder-decoder models on sparser datasets such as ETH/UCY (ranks 3rd among top 7 baselines).
Authors: Cong Zhang, Derrick Goh Xin Deik, Dexun Li, Hao Zhang, Yong Liu
Abstract: The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligence (AGI) due to their superior reasoning and generalization capabilities. Effective planning is crucial for the success of LLM agents in real-world tasks, making it a highly pursued topic in the community. Current planning methods typically translate tasks into executable action sequences. However, determining a feasible or optimal sequence for complex tasks with multiple constraints at fine granularity, which often requires compositing long chains of heterogeneous actions, remains challenging. This paper introduces Planning with Multi-Constraints (PMC), a zero-shot methodology for collaborative LLM-based multi-agent systems that simplifies complex task planning with constraints by decomposing it into a hierarchy of subordinate tasks. Each subtask is then mapped into executable actions. PMC was assessed on two constraint-intensive benchmarks, TravelPlanner and API-Bank. Notably, PMC achieved an average 42.68% success rate on TravelPlanner, significantly higher than GPT-4 (2.92%), and outperforming GPT-4 with ReAct on API-Bank by 13.64%, showing the immense potential of integrating LLM with multi-agent systems. We also show that PMC works with small LLM as the planning core, e.g., LLaMA-3.1-8B.
Authors: H. L. Dao
Abstract: In this work, we report the results of applying deep learning based on hybrid convolutional-recurrent and purely recurrent neural network architectures to the dataset of almost one million complete intersection Calabi-Yau four-folds (CICY4) to machine-learn their four Hodge numbers $h^{1,1}, h^{2,1}, h^{3,1}, h^{2,2}$. In particular, we explored and experimented with twelve different neural network models, nine of which are convolutional-recurrent (CNN-RNN) hybrids with the RNN unit being either GRU (Gated Recurrent Unit) or Long Short Term Memory (LSTM). The remaining four models are purely recurrent neural networks based on LSTM. In terms of the $h^{1,1}, h^{2,1}, h^{3,1}, h^{2,2}$ prediction accuracies, at 72% training ratio, our best performing individual model is CNN-LSTM-400, a hybrid CNN-LSTM with the LSTM hidden size of 400, which obtained 99.74%, 98.07%, 95.19%, 81.01%, our second best performing individual model is LSTM-448, an LSTM-based model with the hidden size of 448, which obtained 99.74%, 97.51%, 94.24%, and 78.63%. These results were improved by forming ensembles of the top two, three or even four models. Our best ensemble, consisting of the top four models, achieved the accuracies of 99.84%, 98.71%, 96.26%, 85.03%. At 80% training ratio, the top two performing models LSTM-448 and LSTM-424 are both LSTM-based with the hidden sizes of 448 and 424. Compared with the 72% training ratio, there is a significant improvement of accuracies, which reached 99.85%, 98.66%, 96.26%, 84.77% for the best individual model and 99.90%, 99.03%, 97.97%, 87.34% for the best ensemble. By nature a proof of concept, the results of this work conclusively established the utility of RNN-based architectures and demonstrated their effective performances compared to the well-explored purely CNN-based architectures in the problem of deep learning Calabi Yau manifolds.
Authors: Mohammad Amir Fallah, Mehdi Monemi, Mehdi Rasti, Matti Latva-Aho
Abstract: Three-dimensional (3D) spot beamfocusing (SBF), in contrast to conventional angular-domain beamforming, concentrates radiating power within a very small volume in both radial and angular domains in the near-field zone. Recently the implementation of channel-state-information (CSI)-independent machine learning (ML)-based approaches have been developed for effective SBF using extremely large-scale programmable metasurface (ELPMs). These methods involve dividing the ELPMs into subarrays and independently training them with Deep Reinforcement Learning to jointly focus the beam at the desired focal point (DFP). This paper explores near-field SBF using ELPMs, addressing challenges associated with lengthy training times resulting from independent training of subarrays. To achieve a faster CSI-independent solution, inspired by the correlation between the beamfocusing matrices of the subarrays, we leverage transfer learning techniques. First, we introduce a novel similarity criterion based on the phase distribution image (PDI) of subarray apertures. Then we devise a subarray policy propagation scheme that transfers the knowledge from trained to untrained subarrays. We further enhance learning by introducing quasi-liquid layers as a revised version of the adaptive policy reuse technique. We show through simulations that the proposed scheme improves the training speed about 5 times. Furthermore, for dynamic DFP management, we devised a DFP policy blending process, which augments the convergence rate up to 8-fold.
Authors: Venkata Sai Pranav Bachina, Ankit Gangwal, Aaryan Ajay Sharma, Charu Sharma
Abstract: Graph Neural Networks (GNNs) have become invaluable intellectual property in graph-based machine learning. However, their vulnerability to model stealing attacks when deployed within Machine Learning as a Service (MLaaS) necessitates robust Ownership Demonstration (OD) techniques. Watermarking is a promising OD framework for Deep Neural Networks, but existing methods fail to generalize to GNNs due to the non-Euclidean nature of graph data. Previous works on GNN watermarking have primarily focused on node and graph classification, overlooking Link Prediction (LP). In this paper, we propose GENIE (watermarking Graph nEural Networks for lInk prEdiction), the first-ever scheme to watermark GNNs for LP. GENIE creates a novel backdoor for both node-representation and subgraph-based LP methods, utilizing a unique trigger set and a secret watermark vector. Our OD scheme is equipped with Dynamic Watermark Thresholding (DWT), ensuring high verification probability (>99.99%) while addressing practical issues in existing watermarking schemes. We extensively evaluate GENIE across 4 model architectures (i.e., SEAL, GCN, GraphSAGE and NeoGNN) and 7 real-world datasets. Furthermore, we validate the robustness of GENIE against 11 state-of-the-art watermark removal techniques and 3 model extraction attacks. We also show GENIE's resilience against ownership piracy attacks. Finally, we discuss a defense strategy to counter adaptive attacks against GENIE.
Authors: Zimin Zhang, Qianli Wu, Botao Xia, Fang Sun, Ziniu Hu, Yizhou Sun, Shichang Zhang
Abstract: Artificial intelligence (AI) is transforming scientific research, with explainable AI methods like concept-based models (CMs) showing promise for new discoveries. However, in molecular science, CMs are less common than black-box models like Graph Neural Networks (GNNs), due to their need for predefined concepts and manual labeling. This paper introduces the Automated Molecular Concept (AutoMolCo) framework, which leverages Large Language Models (LLMs) to automatically generate and label predictive molecular concepts. Through iterative concept refinement, AutoMolCo enables simple linear models to outperform GNNs and LLM in-context learning on several benchmarks. The framework operates without human knowledge input, overcoming limitations of existing CMs while maintaining explainability and allowing easy intervention. Experiments on MoleculeNet and High-Throughput Experimentation (HTE) datasets demonstrate that AutoMolCo-induced explainable CMs are beneficial for molecular science research.
Authors: Hugues Turb\'e, Mina Bjelogrlic, Gianmarco Mengaldo, Christian Lovis
Abstract: Prototypical networks aim to build intrinsically explainable models based on the linear summation of concepts. Concepts are coherent entities that we, as humans, can recognize and associate with a certain object or entity. However, important challenges remain in the fair evaluation of explanation quality provided by these models. This work first proposes an extensive set of quantitative and qualitative metrics which allow to identify drawbacks in current prototypical networks. It then introduces a novel architecture which provides compact explanations, outperforming current prototypical models in terms of explanation quality. Overall, the proposed architecture demonstrates how frozen pre-trained ViT backbones can be effectively turned into prototypical models for both general and domain-specific tasks, in our case biomedical image classifiers. Code is available at \url{https://github.com/hturbe/protosvit}.
Authors: Soroush Saghafian, Lihi Idan
Abstract: Advanced analytics science methods have enabled combining the power of artificial and human intelligence, creating \textit{centaurs} that allow superior decision-making. Centaurs are hybrid human-algorithm models that combine both formal analytics and human intuition in a symbiotic manner within their learning and reasoning process. We argue that the future of AI development and use in many domains needs to focus more on centaurs as opposed to other AI approaches. This paradigm shift towards centaur-based AI methods raises some fundamental questions: How are centaurs different from other human-in-the-loop methods? What are the most effective methods for creating centaurs? When should centaurs be used, and when should the lead be given to pure AI models? Doesn't the incorporation of human intuition -- which at times can be misleading -- in centaurs' decision-making process degrade its performance compared to pure AI methods? This work aims to address these fundamental questions, focusing on recent advancements in generative AI, and especially in Large Language Models (LLMs), as a main case study to illustrate centaurs' critical essentiality to future AI endeavors.
Authors: Yangyi Chen, Xingyao Wang, Hao Peng, Heng Ji
Abstract: We present SOLO, a single transformer for Scalable visiOn-Language mOdeling. Current large vision-language models (LVLMs) such as LLaVA mostly employ heterogeneous architectures that connect pre-trained visual encoders with large language models (LLMs) to facilitate visual recognition and complex reasoning. Although achieving remarkable performance with relatively lightweight training, we identify four primary scalability limitations: (1) The visual capacity is constrained by pre-trained visual encoders, which are typically an order of magnitude smaller than LLMs. (2) The heterogeneous architecture complicates the use of established hardware and software infrastructure. (3) Study of scaling laws on such architecture must consider three separate components - visual encoder, connector, and LLMs, which complicates the analysis. (4) The use of existing visual encoders typically requires following a pre-defined specification of image inputs pre-processing, for example, by reshaping inputs to fixed-resolution square images, which presents difficulties in processing and training on high-resolution images or those with unusual aspect ratio. A unified single Transformer architecture, like SOLO, effectively addresses these scalability concerns in LVLMs; however, its limited adoption in the modern context likely stems from the absence of reliable training recipes that balance both modalities and ensure stable training for billion-scale models. In this paper, we introduce the first open-source training recipe for developing SOLO, an open-source 7B LVLM using moderate academic resources. The training recipe involves initializing from LLMs, sequential pre-training on ImageNet and web-scale data, and instruction fine-tuning on our curated high-quality datasets. On extensive evaluation, SOLO demonstrates performance comparable to LLaVA-v1.5-7B, particularly excelling in visual mathematical reasoning.
Authors: Sascha Caron, Nadezhda Dobreva, Antonio Ferrer S\'anchez, Jos\'e D. Mart\'in-Guerrero, Uraz Odyurt, Roberto Ruiz de Austri Bazan, Zef Wolffs, Yue Zhao
Abstract: High-Energy Physics experiments are facing a multi-fold data increase with every new iteration. This is certainly the case for the upcoming High-Luminosity LHC upgrade. Such increased data processing requirements forces revisions to almost every step of the data processing pipeline. One such step in need of an overhaul is the task of particle track reconstruction, a.k.a., tracking. A Machine Learning-assisted solution is expected to provide significant improvements, since the most time-consuming step in tracking is the assignment of hits to particles or track candidates. This is the topic of this paper. We take inspiration from large language models. As such, we consider two approaches: the prediction of the next word in a sentence (next hit point in a track), as well as the one-shot prediction of all hits within an event. In an extensive design effort, we have experimented with three models based on the Transformer architecture and one model based on the U-Net architecture, performing track association predictions for collision event hit points. In our evaluation, we consider a spectrum of simple to complex representations of the problem, eliminating designs with lower metrics early on. We report extensive results, covering both prediction accuracy (score) and computational performance. We have made use of the REDVID simulation framework, as well as reductions applied to the TrackML data set, to compose five data sets from simple to complex, for our experiments. The results highlight distinct advantages among different designs in terms of prediction accuracy and computational performance, demonstrating the efficiency of our methodology. Most importantly, the results show the viability of a one-shot encoder-classifier based Transformer solution as a practical approach for the task of tracking.
Authors: Qifan Zhang, Yunhui Guo, Yu Xiang
Abstract: Knowledge Distillation (KD) focuses on using a teacher model to improve a student model. Traditionally, KD is studied in an offline fashion, where a training dataset is available before learning. In this work, we introduce the problem of Continual Distillation Learning (CDL) that considers KD in the Continual Learning (CL) setup. A teacher model and a student model need to learn a sequence of tasks, and the knowledge of the teacher model will be distilled to the student to improve the student model in an online fashion. The CDL problem is valuable to study since for prompt-based continual learning methods, using a larger vision transformer (ViT) leads to better performance in continual learning. Distilling the knowledge from a large ViT to a small ViT can improve inference efficiency for promptbased CL models. To this end, we conducted experiments to study the CDL problem with three prompt-based CL models, i.e., L2P, DualPrompt and CODA-Prompt, where we utilized logit distillation, feature distillation and prompt distillation for knowledge distillation from a teacher model to a student model. Our findings of this study can serve as baselines for future CDL work.
Authors: Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Crist\'obal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez
Abstract: The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of vision-language models (VLMs) that generate text outputs conditioned on visual and textual inputs. We conducted a large-scale empirical study to assess the transferability of gradient-based universal image ``jailbreaks" using a diverse set of over 40 open-parameter VLMs, including 18 new VLMs that we publicly release. Overall, we find that transferable gradient-based image jailbreaks are extremely difficult to obtain. When an image jailbreak is optimized against a single VLM or against an ensemble of VLMs, the jailbreak successfully jailbreaks the attacked VLM(s), but exhibits little-to-no transfer to any other VLMs; transfer is not affected by whether the attacked and target VLMs possess matching vision backbones or language models, whether the language model underwent instruction-following and/or safety-alignment training, or many other factors. Only two settings display partially successful transfer: between identically-pretrained and identically-initialized VLMs with slightly different VLM training data, and between different training checkpoints of a single VLM. Leveraging these results, we then demonstrate that transfer can be significantly improved against a specific target VLM by attacking larger ensembles of ``highly-similar" VLMs. These results stand in stark contrast to existing evidence of universal and transferable text jailbreaks against language models and transferable adversarial attacks against image classifiers, suggesting that VLMs may be more robust to gradient-based transfer attacks.
Authors: Peyman Hosseini, Ignacio Castro, Iacopo Ghinassi, Matthew Purver
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in comprehending and analyzing lengthy sequential inputs, owing to their extensive context windows that allow processing millions of tokens in a single forward pass. However, this paper uncovers a surprising limitation: LLMs fall short when handling long input sequences. We investigate this issue using three datasets and two tasks (sentiment analysis and news categorization) across various LLMs, including Claude 3, Gemini Pro, GPT 3.5 Turbo, Llama 3 Instruct, and Mistral Instruct models. To address this limitation, we propose and evaluate ad-hoc solutions that substantially enhance LLMs' performance on long input sequences by up to 50%, while reducing API cost and latency by up to 93% and 50%, respectively.
Authors: Zijian Wang, Bin Wang, Haifeng Jing, Huayu Li, Hongbo Dou
Abstract: Recent years, multi-hop reasoning has been widely studied for knowledge graph (KG) reasoning due to its efficacy and interpretability. However, previous multi-hop reasoning approaches are subject to two primary shortcomings. First, agents struggle to learn effective and robust policies at the early phase due to sparse rewards. Second, these approaches often falter on specific datasets like sparse knowledge graphs, where agents are required to traverse lengthy reasoning paths. To address these problems, we propose a multi-hop reasoning model with dual agents based on hierarchical reinforcement learning (HRL), which is named FULORA. FULORA tackles the above reasoning challenges by eFficient GUidance-ExpLORAtion between dual agents. The high-level agent walks on the simplified knowledge graph to provide stage-wise hints for the low-level agent walking on the original knowledge graph. In this framework, the low-level agent optimizes a value function that balances two objectives: (1) maximizing return, and (2) integrating efficient guidance from the high-level agent. Experiments conducted on three real-word knowledge graph datasets demonstrate that FULORA outperforms RL-based baselines, especially in the case of long-distance reasoning.
Authors: Alexander Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan
Abstract: Recent years have seen substantial advances in our understanding of high-dimensional ridge regression, but existing theories assume that training examples are independent. By leveraging techniques from random matrix theory and free probability, we provide sharp asymptotics for the in- and out-of-sample risks of ridge regression when the data points have arbitrary correlations. We demonstrate that in this setting, the generalized cross validation estimator (GCV) fails to correctly predict the out-of-sample risk. However, in the case where the noise residuals have the same correlations as the data points, one can modify the GCV to yield an efficiently-computable unbiased estimator that concentrates in the high-dimensional limit, which we dub CorrGCV. We further extend our asymptotic analysis to the case where the test point has nontrivial correlations with the training set, a setting often encountered in time series forecasting. Assuming knowledge of the correlation structure of the time series, this again yields an extension of the GCV estimator, and sharply characterizes the degree to which such test points yield an overly optimistic prediction of long-time risk. We validate the predictions of our theory across a variety of high dimensional data.
Authors: Yamin Sepehri, Pedram Pad, Pascal Frossard, L. Andrea Dunbar
Abstract: The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training dataset contains sensitive content, e.g., facial or medical images. In this work, we propose a method to perform the training phase of a deep learning model on both an edge device and a cloud server that prevents sensitive content being transmitted to the cloud while retaining the desired information. The proposed privacy-preserving method uses adversarial early exits to suppress the sensitive content at the edge and transmits the task-relevant information to the cloud. This approach incorporates noise addition during the training phase to provide a differential privacy guarantee. We extensively test our method on different facial and medical datasets with diverse attributes using various deep learning architectures, showcasing its outstanding performance. We also demonstrate the effectiveness of privacy preservation through successful defenses against different white-box, deep and GAN-based reconstruction attacks. This approach is designed for resource-constrained edge devices, ensuring minimal memory usage and computational overhead.
Authors: Guiomar Pescador-Barrios, Sarah Filippi, Mark van der Wilk
Abstract: Many machine learning models require setting a parameter that controls their size before training, e.g.~number of neurons in DNNs, or inducing points in GPs. Increasing capacity typically improves performance until all the information from the dataset is captured. After this point, computational cost keeps increasing without improved performance. This leads to the question ``How big is big enough?'' We investigate this problem for Gaussian processes (single-layer neural networks) in continual learning. Here, data becomes available incrementally, and the final dataset size will therefore not be known before training, preventing the use of heuristics for setting a fixed model size. We develop a method to automatically adjust model size while maintaining near-optimal performance. Our experimental procedure follows the constraint that any hyperparameters must be set without seeing dataset properties. For our method, a single hyperparameter setting works well across diverse datasets, showing that it requires less tuning compared to others.
Authors: Eshwar Ram Arunachaleswaran, Natalie Collina, Sampath Kannan, Aaron Roth, Juba Ziani
Abstract: There has been substantial recent concern that pricing algorithms might learn to ``collude.'' Supra-competitive prices can emerge as a Nash equilibrium of repeated pricing games, in which sellers play strategies which threaten to punish their competitors who refuse to support high prices, and these strategies can be automatically learned. In fact, a standard economic intuition is that supra-competitive prices emerge from either the use of threats, or a failure of one party to optimize their payoff. Is this intuition correct? Would preventing threats in algorithmic decision-making prevent supra-competitive prices when sellers are optimizing for their own revenue? No. We show that supra-competitive prices can emerge even when both players are using algorithms which do not encode threats, and which optimize for their own revenue. We study sequential pricing games in which a first mover deploys an algorithm and then a second mover optimizes within the resulting environment. We show that if the first mover deploys any algorithm with a no-regret guarantee, and then the second mover even approximately optimizes within this now static environment, monopoly-like prices arise. The result holds for any no-regret learning algorithm deployed by the first mover and for any pricing policy of the second mover that obtains them profit at least as high as a random pricing would -- and hence the result applies even when the second mover is optimizing only within a space of non-responsive pricing distributions which are incapable of encoding threats. In fact, there exists a set of strategies, neither of which explicitly encode threats that form a Nash equilibrium of the simultaneous pricing game in algorithm space, and lead to near monopoly prices. This suggests that the definition of ``algorithmic collusion'' may need to be expanded, to include strategies without explicitly encoded threats.
Authors: Nikit Srivastava, Denis Kuchelev, Tatiana Moteu Ngoli, Kshitij Shetty, Michael R\"oder, Hamada Zahera, Diego Moussallem, Axel-Cyrille Ngonga Ngomo
Abstract: This paper presents LOLA, a massively multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. Our architectural and implementation choices address the challenge of harnessing linguistic diversity while maintaining efficiency and avoiding the common pitfalls of multilinguality. Our analysis of the evaluation results shows competitive performance in natural language generation and understanding tasks. Additionally, we demonstrate how the learned expert-routing mechanism exploits implicit phylogenetic linguistic patterns to potentially alleviate the curse of multilinguality. We provide an in-depth look at the training process, an analysis of the datasets, and a balanced exploration of the model's strengths and limitations. As an open-source model, LOLA promotes reproducibility and serves as a robust foundation for future research. Our findings enable the development of compute-efficient multilingual models with strong, scalable performance across languages.
Authors: Xinlei Huang, Zhiqi Ma, Dian Meng, Yanran Liu, Shiwei Ruan, Qingqiang Sun, Xubin Zheng, Ziyue Qiao
Abstract: Spatial multi-modal omics technology, highlighted by Nature Methods as an advanced biological technique in 2023, plays a critical role in resolving biological regulatory processes with spatial context. Recently, graph neural networks based on K-nearest neighbor (KNN) graphs have gained prominence in spatial multi-modal omics methods due to their ability to model semantic relations between sequencing spots. However, the fixed KNN graph fails to capture the latent semantic relations hidden by the inevitable data perturbations during the biological sequencing process, resulting in the loss of semantic information. In addition, the common lack of spot annotation and class number priors in practice further hinders the optimization of spatial multi-modal omics models. Here, we propose a novel spatial multi-modal omics resolved framework, termed PRototype-Aware Graph Adaptative Aggregation for Spatial Multi-modal Omics Analysis (PRAGA). PRAGA constructs a dynamic graph to capture latent semantic relations and comprehensively integrate spatial information and feature semantics. The learnable graph structure can also denoise perturbations by learning cross-modal knowledge. Moreover, a dynamic prototype contrastive learning is proposed based on the dynamic adaptability of Bayesian Gaussian Mixture Models to optimize the multi-modal omics representations for unknown biological priors. Quantitative and qualitative experiments on simulated and real datasets with 7 competing methods demonstrate the superior performance of PRAGA. Code is available at https://github.com/Xubin-s-Lab/PRAGA.
Authors: Anmol Mekala, Vineeth Dorna, Shreya Dubey, Abhishek Lalwani, David Koleczek, Mukund Rungta, Sadid Hasan, Elita Lobo
Abstract: Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely solely on negative feedback to suppress responses related to the forget set, which often results in nonsensical or inconsistent outputs, diminishing model utility and posing potential privacy risks. To address this limitation, we propose a novel approach called Alternate Preference Optimization (AltPO), which combines negative feedback with in-domain positive feedback on the forget set. Additionally, we introduce new evaluation metrics to assess the quality of responses related to the forget set. Extensive experiments show that our approach not only enables effective unlearning but also avoids undesirable model behaviors while maintaining overall model performance. Our implementation can be found at https://github.com/molereddy/AlternatePreference-Optimization
URLs: https://github.com/molereddy/AlternatePreference-Optimization
Authors: Clemens Arndt, Judith Nickel
Abstract: Learning-based methods have demonstrated remarkable performance in solving inverse problems, particularly in image reconstruction tasks. Despite their success, these approaches often lack theoretical guarantees, which are crucial in sensitive applications such as medical imaging. Recent works by Arndt et al (2023 Inverse Problems 39 125018, 2024 Inverse Problems 40 045021) addressed this gap by analyzing a data-driven reconstruction method based on invertible residual networks (iResNets). They revealed that, under reasonable assumptions, this approach constitutes a convergent regularization scheme. However, the performance of the reconstruction method was only validated on academic toy problems and small-scale iResNet architectures. In this work, we address this gap by evaluating the performance of iResNets on two real-world imaging tasks: a linear blurring operator and a nonlinear diffusion operator. To do so, we extend some of the theoretical results from Arndt et al to encompass nonlinear inverse problems and offer insights for the design of large-scale performant iResNet architectures. Through numerical experiments, we compare the performance of our iResNet models against state-of-the-art neural networks, confirming their efficacy. Additionally, we numerically investigate the theoretical guarantees of this approach and demonstrate how the invertibility of the network enables a deeper analysis of the learned forward operator and its learned regularization.
Authors: Georg Velev, Stefan Lessmann
Abstract: Nonlinear causal discovery from observational data imposes strict identifiability assumptions on the formulation of structural equations utilized in the data generating process. The evaluation of structure learning methods under assumption violations requires a rigorous and interpretable approach, which quantifies both the structural similarity of the estimation with the ground truth and the capacity of the discovered graphs to be used for causal inference. Motivated by the lack of unified performance assessment framework, we introduce an interpretable, six-dimensional evaluation metric, i.e., distance to optimal solution (DOS), which is specifically tailored to the field of causal discovery. Furthermore, this is the first research to assess the performance of structure learning algorithms from seven different families on increasing percentage of non-identifiable, nonlinear causal patterns, inspired by real-world processes. Our large-scale simulation study, which incorporates seven experimental factors, shows that besides causal order-based methods, amortized causal discovery delivers results with comparatively high proximity to the optimal solution.
Authors: Xinlei Niu, Jing Zhang, Charles Patrick Martin
Abstract: We present SoundMorpher, an open-world sound morphing method designed to generate perceptually uniform morphing trajectories. Traditional sound morphing techniques typically assume a linear relationship between the morphing factor and sound perception, achieving smooth transitions by linearly interpolating the semantic features of source and target sounds while gradually adjusting the morphing factor. However, these methods oversimplify the complexities of sound perception, resulting in limitations in morphing quality. In contrast, SoundMorpher explores an explicit relationship between the morphing factor and the perception of morphed sounds, leveraging log Mel-spectrogram features. This approach further refines the morphing sequence by ensuring a constant target perceptual difference for each transition and determining the corresponding morphing factors using binary search. To address the lack of a formal quantitative evaluation framework for sound morphing, we propose a set of metrics based on three established objective criteria. These metrics enable comprehensive assessment of morphed results and facilitate direct comparisons between methods, fostering advancements in sound morphing research. Extensive experiments demonstrate the effectiveness and versatility of SoundMorpher in real-world scenarios, showcasing its potential in applications such as creative music composition, film post-production, and interactive audio technologies. Our demonstration and codes are available at~\url{https://xinleiniu.github.io/SoundMorpher-demo/}.
Authors: Esteban Garces Arias, Meimingwei Li, Christian Heumann, Matthias A{\ss}enmacher
Abstract: Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these strategies aim to transform the raw probability distributions produced by language models into coherent, fluent text. In this study, we undertake a large-scale empirical assessment of a range of decoding methods, open-source LLMs, textual domains, and evaluation protocols to determine how hyperparameter choices shape the outputs. Our experiments include both factual (e.g., news) and creative (e.g., fiction) domains, and incorporate a broad suite of automatic evaluation metrics alongside human judgments. Through extensive sensitivity analyses, we distill practical recommendations for selecting and tuning hyperparameters, noting that optimal configurations vary across models and tasks. By synthesizing these insights, this study provides actionable guidance for refining decoding strategies, enabling researchers and practitioners to achieve higher-quality, more reliable, and context-appropriate text generation outcomes.
Authors: Qingni Wang, Tiantian Geng, Zhiyuan Wang, Teng Wang, Bo Fu, Feng Zheng
Abstract: Multimodal Large Language Models (MLLMs) exhibit promising advancements across various tasks, yet they still encounter significant trustworthiness issues. Prior studies apply Split Conformal Prediction (SCP) in language modeling to construct prediction sets with statistical guarantees. However, these methods typically rely on internal model logits or are restricted to multiple-choice settings, which hampers their generalizability and adaptability in dynamic, open-ended environments. In this paper, we introduce TRON, a two-step framework for risk control and assessment, applicable to any MLLM that supports sampling in both open-ended and closed-ended scenarios. TRON comprises two main components: (1) a novel conformal score to sample response sets of minimum size, and (2) a nonconformity score to identify high-quality responses based on self-consistency theory, controlling the error rates by two specific risk levels. Furthermore, we investigate semantic redundancy in prediction sets within open-ended contexts for the first time, leading to a promising evaluation metric for MLLMs based on average set size. Our comprehensive experiments across four Video Question-Answering (VideoQA) datasets utilizing eight MLLMs show that TRON achieves desired error rates bounded by two user-specified risk levels. Additionally, deduplicated prediction sets maintain adaptiveness while being more efficient and stable for risk assessment under different risk levels.
Authors: Jinjin Cai, Ruiqi Wang, Dezhong Zhao, Ziqin Yuan, Victoria McKenna, Aaron Friedman, Rachel Foot, Susan Storey, Ryan Boente, Sudip Vhaduri, Byung-Cheol Min
Abstract: Audio-based disease prediction is emerging as a promising supplement to traditional medical diagnosis methods, facilitating early, convenient, and non-invasive disease detection and prevention. Multimodal fusion, which integrates features from various domains within or across bio-acoustic modalities, has proven effective in enhancing diagnostic performance. However, most existing methods in the field employ unilateral fusion strategies that focus solely on either intra-modal or inter-modal fusion. This approach limits the full exploitation of the complementary nature of diverse acoustic feature domains and bio-acoustic modalities. Additionally, the inadequate and isolated exploration of latent dependencies within modality-specific and modality-shared spaces curtails their capacity to manage the inherent heterogeneity in multimodal data. To fill these gaps, we propose a transformer-based hierarchical fusion network designed for general multimodal audio-based disease prediction. Specifically, we seamlessly integrate intra-modal and inter-modal fusion in a hierarchical manner and proficiently encode the necessary intra-modal and inter-modal complementary correlations, respectively. Comprehensive experiments demonstrate that our model achieves state-of-the-art performance in predicting three diseases: COVID-19, Parkinson's disease, and pathological dysarthria, showcasing its promising potential in a broad context of audio-based disease prediction tasks. Additionally, extensive ablation studies and qualitative analyses highlight the significant benefits of each main component within our model.
Authors: Ali Kashefi
Abstract: Kolmogorov-Arnold Networks (KANs) have recently gained attention as an alternative to traditional Multilayer Perceptrons (MLPs) in deep learning frameworks. KANs have been integrated into various deep learning architectures such as convolutional neural networks, graph neural networks, and transformers, with their performance evaluated. However, their effectiveness within point-cloud-based neural networks remains unexplored. To address this gap, we incorporate KANs into PointNet for the first time to evaluate their performance on 3D point cloud classification and segmentation tasks. Specifically, we introduce PointNet-KAN, built upon two key components. First, it employs KANs instead of traditional MLPs. Second, it retains the core principle of PointNet by using shared KAN layers and applying symmetric functions for global feature extraction, ensuring permutation invariance with respect to the input features. In traditional MLPs, the goal is to train the weights and biases with fixed activation functions; however, in KANs, the goal is to train the activation functions themselves. We use Jacobi polynomials to construct the KAN layers. We extensively and systematically evaluate PointNet-KAN across various polynomial degrees and special types such as the Lagrange, Chebyshev, and Gegenbauer polynomials. Our results show that PointNet-KAN achieves competitive performance compared to PointNet with MLPs on benchmark datasets for 3D object classification and segmentation, despite employing a shallower and simpler network architecture. We hope this work serves as a foundation and provides guidance for integrating KANs, as an alternative to MLPs, into more advanced point cloud processing architectures.
Authors: Kazuki Irie, Brenden M. Lake
Abstract: Since the earliest proposals for neural network models of the mind and brain, critics have pointed out key weaknesses in these models compared to human cognitive abilities. Here we review recent work that uses metalearning to overcome several classic challenges by addressing the Problem of Incentive and Practice -- that is, providing machines with both incentives to improve specific skills and opportunities to practice those skills. This explicit optimization contrasts with more conventional approaches that hope the desired behavior will emerge through optimizing related but different objectives. We review applications of this principle to addressing four classic challenges for neural networks: systematic generalization, catastrophic forgetting, few-shot learning and multi-step reasoning. We also discuss the prospects for understanding aspects of human development through this framework, and whether natural environments provide the right incentives and practice for learning how to make challenging generalizations.
Authors: Kostas E. Bekris, Joe Doerr, Patrick Meng, Sumanth Tangirala
Abstract: This paper reviews the large spectrum of methods for generating robot motion proposed over the 50 years of robotics research culminating in recent developments. It crosses the boundaries of methodologies, typically not surveyed together, from those that operate over explicit models to those that learn implicit ones. The paper discusses the current state-of-the-art as well as properties of varying methodologies, highlighting opportunities for integration.
Authors: Shreya Saha, Ishaan Chadha, Meenakshi khosla
Abstract: Over the past decade, predictive modeling of neural responses in the primate visual system has advanced significantly, largely driven by various DNN approaches. These include models optimized directly for visual recognition, cross-modal alignment through contrastive objectives, neural response prediction from scratch, and large language model embeddings.Likewise, different readout mechanisms, ranging from fully linear to spatial-feature factorized methods have been explored for mapping network activations to neural responses. Despite the diversity of these approaches, it remains unclear which method performs best across different visual regions. In this study, we systematically compare these approaches for modeling the human visual system and investigate alternative strategies to improve response predictions. Our findings reveal that for early to mid-level visual areas, response-optimized models with visual inputs offer superior prediction accuracy, while for higher visual regions, embeddings from LLMs based on detailed contextual descriptions of images and task-optimized models pretrained on large vision datasets provide the best fit. Through comparative analysis of these modeling approaches, we identified three distinct regions in the visual cortex: one sensitive primarily to perceptual features of the input that are not captured by linguistic descriptions, another attuned to fine-grained visual details representing semantic information, and a third responsive to abstract, global meanings aligned with linguistic content. We also highlight the critical role of readout mechanisms, proposing a novel scheme that modulates receptive fields and feature maps based on semantic content, resulting in an accuracy boost of 3-23% over existing SOTAs for all models and brain regions. Together, these findings offer key insights into building more precise models of the visual system.
Authors: B\'alint M\'at\'e, Fran\c{c}ois Fleuret, Tristan Bereau
Abstract: We present a method for computing free-energy differences using thermodynamic integration with a neural network potential that interpolates between two target Hamiltonians. The interpolation is defined at the sample distribution level, and the neural network potential is optimized to match the corresponding equilibrium potential at every intermediate time-step. Once the interpolating potentials and samples are well-aligned, the free-energy difference can be estimated using (neural) thermodynamic integration. To target molecular systems, we simultaneously couple Lennard-Jones and electrostatic interactions and model the rigid-body rotation of molecules. We report accurate results for several benchmark systems: a Lennard-Jones particle in a Lennard-Jones fluid, as well as the insertion of both water and methane solutes in a water solvent at atomistic resolution using a simple three-body neural-network potential.
Authors: Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Boxing Chen, Sarath Chandar
Abstract: The growth in prominence of large language models (LLMs) in everyday life can be largely attributed to their generative abilities, yet some of this is also owed to the risks and costs associated with their use. On one front is their tendency to \textit{hallucinate} false or misleading information, limiting their reliability. On another is the increasing focus on the computational limitations associated with traditional self-attention based LLMs, which has brought about new alternatives, in particular recurrent models, meant to overcome them. Yet it remains uncommon to consider these two concerns simultaneously. Do changes in architecture exacerbate/alleviate existing concerns about hallucinations? Do they affect how and where they occur? Through an extensive evaluation, we study how these architecture-based inductive biases affect the propensity to hallucinate. While hallucination remains a general phenomenon not limited to specific architectures, the situations in which they occur and the ease with which specific types of hallucinations can be induced can significantly differ based on the model architecture. These findings highlight the need for better understanding both these problems in conjunction with each other, as well as consider how to design more universal techniques for handling hallucinations.
Authors: Sebasti\'an Espinel-R\'ios, Jos\'e Monta\~no L\'opez, Jos\'e L. Avalos
Abstract: This work presents an omics-driven modeling pipeline that integrates machine-learning tools to facilitate the dynamic modeling of multiscale biological systems. Random forests and permutation feature importance are proposed to mine omics datasets, guiding feature selection and dimensionality reduction for dynamic modeling. Continuous and differentiable machine-learning functions can be trained to link the reduced omics feature set to key components of the dynamic model, resulting in a hybrid model. As proof of concept, we apply this framework to a high-dimensional proteomics dataset of $\textit{Saccharomyces cerevisiae}$. After identifying key intracellular proteins that correlate with cell growth, targeted dynamic experiments are designed, and key model parameters are captured as functions of the selected proteins using Gaussian processes. This approach captures the dynamic behavior of yeast strains under varying proteome profiles while estimating the uncertainty in the hybrid model's predictions. The outlined modeling framework is adaptable to other scenarios, such as integrating additional layers of omics data for more advanced multiscale biological systems, or employing alternative machine-learning methods to handle larger datasets. Overall, this study outlines a strategy for leveraging omics data to inform multiscale dynamic modeling in systems biology and bioprocess engineering.
Authors: Israel Fama, B\'arbara Bueno, Alexandre Alcoforado, Thomas Palmeira Ferraz, Arnold Moya, Anna Helena Reali Costa
Abstract: In a context where the Brazilian judiciary system, the largest in the world, faces a crisis due to the slow processing of millions of cases, it becomes imperative to develop efficient methods for analyzing legal texts. We introduce uBERT, a hybrid model that combines Transformer and Recurrent Neural Network architectures to effectively handle long legal texts. Our approach processes the full text regardless of its length while maintaining reasonable computational overhead. Our experiments demonstrate that uBERT achieves superior performance compared to BERT+LSTM when overlapping input is used and is significantly faster than ULMFiT for processing long legal documents.
Authors: Shauli Ravfogel, Anej Svete, V\'esteinn Sn{\ae}bjarnarson, Ryan Cotterell
Abstract: Understanding and manipulating the causal generation mechanisms in language models is essential for controlling their behavior. Previous work has primarily relied on techniques such as representation surgery -- e.g., model ablations or manipulation of linear subspaces tied to specific concepts -- to \emph{intervene} on these models. To understand the impact of interventions precisely, it is useful to examine counterfactuals -- e.g., how a given sentence would have appeared had it been generated by the model following a specific intervention. We highlight that counterfactual reasoning is conceptually distinct from interventions, as articulated in Pearl's causal hierarchy. Based on this observation, we propose a framework for generating true string counterfactuals by reformulating language models as a structural equation model using the Gumbel-max trick, which we called Gumbel counterfactual generation. This reformulation allows us to model the joint distribution over original strings and their counterfactuals resulting from the same instantiation of the sampling noise. We develop an algorithm based on hindsight Gumbel sampling that allows us to infer the latent noise variables and generate counterfactuals of observed strings. Our experiments demonstrate that the approach produces meaningful counterfactuals while at the same time showing that commonly used intervention techniques have considerable undesired side effects.
Authors: Chaymae El Jabri, Marc Frappier, Pierre-Martin Tardif
Abstract: This paper investigates the use of the ASTD language for ensemble anomaly detection in data logs. It uses a sliding window technique for continuous learning in data streams, coupled with updating learning models upon the completion of each window to maintain accurate detection and align with current data trends. It proposes ASTD patterns for combining learning models, especially in the context of unsupervised learning, which is commonly used for data streams. To facilitate this, a new ASTD operator is proposed, the Quantified Flow, which enables the seamless combination of learning models while ensuring that the specification remains concise. Our contribution is a specification pattern, highlighting the capacity of ASTDs to abstract and modularize anomaly detection systems. The ASTD language provides a unique approach to develop data flow anomaly detection systems, grounded in the combination of processes through the graphical representation of the language operators. This simplifies the design task for developers, who can focus primarily on defining the functional operations that constitute the system.
Authors: Xiaodong Chen, Yuxuan Hu, Xiaokang Zhang, Yanling Wang, Cuiping Li, Hong Chen, Jing Zhang
Abstract: Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs). To recover model performance after pruning, post-training is commonly employed to mitigate the resulting performance degradation. While post-training benefits from larger datasets, once the dataset size is already substantial, increasing the training data provides only limited performance gains. To balance post-training cost and model performance, it is necessary to explore the optimal amount of post-training data.Through extensive experiments on the Llama-3 and Qwen-2.5 series models, pruned using various common pruning methods, we uncover the scaling \textbf{Law} for \textbf{P}ost-training after model \textbf{P}runing, referred to as the P$^2$ Law.This law identifies four key factors for predicting the pruned model's post-training loss: the model size before pruning, the number of post-training tokens, the pruning rate, and the model's loss before pruning. Moreover, P$^2$ Law can generalize to larger dataset sizes, larger model sizes, and higher pruning rates, offering valuable insights for the post-training of pruned LLMs.
Authors: Jan Pfister, Julia Wunderle, Andreas Hotho
Abstract: We create two German-only decoder models, LL\"aMmlein 120M and 1B, transparently from scratch and publish them, along with the training data, for the German NLP research community to use. The model training involved several key steps, including extensive data preprocessing, the creation of a custom German tokenizer, the training itself, as well as the evaluation of the final models on various benchmarks. Throughout the training process, multiple checkpoints were saved and analyzed using the SuperGLEBer benchmark to monitor the models' learning dynamics. Compared to state-of-the-art models on the SuperGLEBer benchmark, both LL\"aMmlein models performed competitively, consistently matching or surpassing models with similar parameter sizes. The results show that the models' quality scales with size as expected, but performance improvements on some tasks plateaued early, offering valuable insights into resource allocation for future model development.
Authors: Praveen Srinivasa Varadhan, Amogh Gulati, Ashwin Sankar, Srija Anand, Anirudh Gupta, Anirudh Mukherjee, Shiva Kumar Marepally, Ankur Bhatia, Saloni Jaju, Suvrat Bhooshan, Mitesh M. Khapra
Abstract: Despite rapid advancements in TTS models, a consistent and robust human evaluation framework is still lacking. For example, MOS tests fail to differentiate between similar models, and CMOS's pairwise comparisons are time-intensive. The MUSHRA test is a promising alternative for evaluating multiple TTS systems simultaneously, but in this work we show that its reliance on matching human reference speech unduly penalises the scores of modern TTS systems that can exceed human speech quality. More specifically, we conduct a comprehensive assessment of the MUSHRA test, focusing on its sensitivity to factors such as rater variability, listener fatigue, and reference bias. Based on our extensive evaluation involving 492 human listeners across Hindi and Tamil we identify two primary shortcomings: (i) reference-matching bias, where raters are unduly influenced by the human reference, and (ii) judgement ambiguity, arising from a lack of clear fine-grained guidelines. To address these issues, we propose two refined variants of the MUSHRA test. The first variant enables fairer ratings for synthesized samples that surpass human reference quality. The second variant reduces ambiguity, as indicated by the relatively lower variance across raters. By combining these approaches, we achieve both more reliable and more fine-grained assessments. We also release MANGO, a massive dataset of 246,000 human ratings, the first-of-its-kind collection for Indian languages, aiding in analyzing human preferences and developing automatic metrics for evaluating TTS systems.
Authors: Thomas Flynn, Patrick Johnstone, Shinjae Yoo
Abstract: In distributed optimization, the communication of model updates can be a performance bottleneck. Consequently, gradient compression has been proposed as a means of increasing optimization throughput. In general, due to information loss, compression introduces a penalty on the number of iterations needed to reach a solution. In this work, we investigate how the iteration penalty depends on the interaction between compression and problem structure, in the context of non-convex stochastic optimization. We focus on linear compression schemes, where compression and decompression can be modeled as multiplication with a random matrix. We consider several distributions of matrices, among them random orthogonal matrices and matrices with random Gaussian entries. We find that in each case, the impact of compression on convergence can be quantified in terms of the norm of the Hessian of the objective, using a norm defined by the compression scheme. The analysis reveals that in certain cases, compression performance is related to low-rank structure or other spectral properties of the problem. In these cases, our bounds predict that the penalty introduced by compression is significantly reduced compared to worst-case bounds that only consider the compression level, ignoring problem data. We verify the theoretical findings on several optimization problems, including fine-tuning an image classification model.
Authors: Utsab Saha, Tanvir Muntakim Tonoy, Hafiz Imtiaz
Abstract: In recent years, the growth of data across various sectors, including healthcare, security, finance, and education, has created significant opportunities for analysis and informed decision-making. However, these datasets often contain sensitive and personal information, which raises serious privacy concerns. Protecting individual privacy is crucial, yet many existing machine learning and data publishing algorithms struggle with high-dimensional data, facing challenges related to computational efficiency and privacy preservation. To address these challenges, we introduce an effective data publishing algorithm \emph{DP-CDA}. Our proposed algorithm generates synthetic datasets by randomly mixing data in a class-specific manner, and inducing carefully-tuned randomness to ensure formal privacy guarantees. Our comprehensive privacy accounting shows that DP-CDA provides a stronger privacy guarantee compared to existing methods, allowing for better utility while maintaining strict level of privacy. To evaluate the effectiveness of DP-CDA, we examine the accuracy of predictive models trained on the synthetic data, which serves as a measure of dataset utility. Importantly, we identify an optimal order of mixing that balances privacy guarantee with predictive accuracy. Our results indicate that synthetic datasets produced using the DP-CDA can achieve superior utility compared to those generated by traditional data publishing algorithms, even when subject to the same privacy requirements.
Authors: Ammar Fayad
Abstract: Gravitational waves (GW), predicted by Einstein's General Theory of Relativity, provide a powerful probe of astrophysical phenomena and fundamental physics. In this work, we propose an unsupervised anomaly detection method using variational autoencoders (VAEs) to analyze GW time-series data. By training on noise-only data, the VAE accurately reconstructs noise inputs while failing to reconstruct anomalies, such as GW signals, which results in measurable spikes in the reconstruction error. The method was applied to data from the LIGO H1 and L1 detectors. Evaluation on testing datasets containing both noise and GW events demonstrated reliable detection, achieving an area under the ROC curve (AUC) of 0.89. This study introduces VAEs as a robust, unsupervised approach for identifying anomalies in GW data, which offers a scalable framework for detecting known and potentially new phenomena in physics.
Authors: Liqiang Zhang, Ye Tian, Dongyan Wei
Abstract: With the development of smart cities, the demand for continuous pedestrian navigation in large-scale urban environments has significantly increased. While global navigation satellite systems (GNSS) provide low-cost and reliable positioning services, they are often hindered in complex urban canyon environments. Thus, exploring opportunistic signals for positioning in urban areas has become a key solution. Augmented reality (AR) allows pedestrians to acquire real-time visual information. Accordingly, we propose a low-cost visual-inertial positioning solution. This method comprises a lightweight multi-scale group convolution (MSGC)-based visual place recognition (VPR) neural network, a pedestrian dead reckoning (PDR) algorithm, and a visual/inertial fusion approach based on a Kalman filter with gross error suppression. The VPR serves as a conditional observation to the Kalman filter, effectively correcting the errors accumulated through the PDR method. This enables the entire algorithm to ensure the reliability of long-term positioning in GNSS-denied areas. Extensive experimental results demonstrate that our method maintains stable positioning during large-scale movements. Compared to the lightweight MobileNetV3-based VPR method, our proposed VPR solution improves Recall@1 by at least 3\% on two public datasets while reducing the number of parameters by 63.37\%. It also achieves performance that is comparable to the VGG16-based method. The VPR-PDR algorithm improves localization accuracy by more than 40\% compared to the original PDR.
Authors: Jordan Jomsky, Zongyu Li, Yiren Zhang, Tal Nuriel, Jia Guo
Abstract: The increasing global aging population necessitates improved methods to assess brain aging and its related neurodegenerative changes. Brain Age Gap Estimation (BrainAGE) offers a neuroimaging biomarker for understanding these changes by predicting brain age from MRI scans. Current approaches primarily use T1-weighted magnetic resonance imaging (T1w MRI) data, capturing only structural brain information. To address this limitation, AI-generated Cerebral Blood Volume (AICBV) data, synthesized from non-contrast MRI scans, offers functional insights by revealing subtle blood-tissue contrasts otherwise undetectable in standard imaging. We integrated AICBV with T1w MRI to predict brain age, combining both structural and functional metrics. We developed a deep learning model using a VGG-based architecture for both modalities and combined their predictions using linear regression. Our model achieved a mean absolute error (MAE) of 3.95 years and an $R^2$ of 0.943 on the test set ($n = 288$), outperforming existing models trained on similar data. We have further created gradient-based class activation maps (Grad-CAM) to visualize the regions of the brain that most influenced the model's predictions, providing interpretable insights into the structural and functional contributors to brain aging.
Authors: Xiaowen Ye, Yuyi Mao, Xianghao Yu, Shu Sun, Liqun Fu, Jie Xu
Abstract: This paper studies an integrated sensing and communications (ISAC) system for low-altitude economy (LAE), where a ground base station (GBS) provides communication and navigation services for authorized unmanned aerial vehicles (UAVs), while sensing the low-altitude airspace to monitor the unauthorized mobile target. The expected communication sum-rate over a given flight period is maximized by jointly optimizing the beamforming at the GBS and UAVs' trajectories, subject to the constraints on the average signal-to-noise ratio requirement for sensing, the flight mission and collision avoidance of UAVs, as well as the maximum transmit power at the GBS. Typically, this is a sequential decision-making problem with the given flight mission. Thus, we transform it to a specific Markov decision process (MDP) model called episode task. Based on this modeling, we propose a novel LAE-oriented ISAC scheme, referred to as Deep LAE-ISAC (DeepLSC), by leveraging the deep reinforcement learning (DRL) technique. In DeepLSC, a reward function and a new action selection policy termed constrained noise-exploration policy are judiciously designed to fulfill various constraints. To enable efficient learning in episode tasks, we develop a hierarchical experience replay mechanism, where the gist is to employ all experiences generated within each episode to jointly train the neural network. Besides, to enhance the convergence speed of DeepLSC, a symmetric experience augmentation mechanism, which simultaneously permutes the indexes of all variables to enrich available experience sets, is proposed. Simulation results demonstrate that compared with benchmarks, DeepLSC yields a higher sum-rate while meeting the preset constraints, achieves faster convergence, and is more robust against different settings.
Authors: Puxuan Yu, Luke Merrick, Gaurav Nuti, Daniel Campos
Abstract: This paper presents the training methodology of Arctic-Embed 2.0, a set of open-source text embedding models built for accurate and efficient multilingual retrieval. While prior works have suffered from degraded English retrieval quality, Arctic-Embed 2.0 delivers competitive retrieval quality on multilingual and English-only benchmarks, and supports Matryoshka Representation Learning (MRL) for efficient embedding storage with significantly lower compressed quality degradation compared to alternatives. We detail the design and implementation, presenting several important open research questions that arose during model development. We conduct experiments exploring these research questions and include extensive discussion aimed at fostering further discussion in this field.
Authors: Yongxin Wang, Meng Cao, Haokun Lin, Mingfei Han, Liang Ma, Jin Jiang, Yuhao Cheng, Xiaodan Liang
Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress on various visual question answering and reasoning tasks leveraging instruction fine-tuning specific datasets. They can also learn from preference data annotated by human to enhance their reasoning ability and mitigate hallucinations. Most of preference data is generated from the model itself. However, existing methods require high-quality critical labels, which are costly and rely on human or proprietary models like GPT-4V. In this work, we propose Enhancing Alignment in MLLMs via Critical Observation (EACO), which aligns MLLMs by self-generated preference data using only 5k images economically. Our approach begins with collecting and refining a Scoring Evaluation Instruction-tuning dataset to train a critical evaluation model, termed the Critic. This Critic observes model responses across multiple dimensions, selecting preferred and non-preferred outputs for refined Direct Preference Optimization (DPO) tuning. To further enhance model performance, we employ an additional supervised fine-tuning stage after preference tuning. EACO reduces the overall hallucinations by 65.6% on HallusionBench and improves the reasoning ability by 21.8% on MME-Cognition. EACO achieves an 8.5% improvement over LLaVA-v1.6-Mistral-7B across multiple benchmarks. Remarkably, EACO also shows the potential critical ability in open-source MLLMs, demonstrating that EACO is a viable path to boost the competence of MLLMs.
Authors: Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, Yongbin Li
Abstract: Large language models (LLMs) have made dialogue one of the central modes in human-machine interaction, leading to the vast amounts of conversation logs and increasing demand for dialogue generation. The dialogue's life-cycle spans from the $\textit{Prelude}$ through the $\textit{Interlocution}$ to the $\textit{Epilogue}$, encompassing rich dialogue elements. Despite the large volumes of dialogue-related studies, there is a lack of benchmark that encompasses comprehensive dialogue elements, which hinders precise modeling, generation and systematic evaluation. To bridge this gap, in this paper, we introduce a new research task $\textbf{D}$ialogue $\textbf{E}$lement $\textbf{MO}$deling, including $\textit{Element Awareness}$ and $\textit{Dialogue Agent Interaction}$, and propose a novel benchmark, $\textbf{DEMO}$, designed for a comprehensive dialogue modeling and assessment. On this basis, we further build the DEMO agent with the adept ability to model dialogue elements via imitation learning. Extensive experiments on DEMO indicate that current representative LLMs still have considerable potential for enhancement, and our DEMO agent performs well in both dialogue element modeling and out-of-domain tasks.
Authors: Bharath Raj S, Garvit Suri, Vikrant Dewangan, Raghav Sonavane
Abstract: Traditional greedy tokenization methods have been a critical step in Natural Language Processing (NLP), influencing how text is converted into tokens and directly impacting model performance. While subword tokenizers like Byte-Pair Encoding (BPE) are widely used, questions remain about their optimality across model scales and languages. In this work, we demonstrate through extensive experiments that an optimal BPE configuration significantly reduces token count compared to greedy segmentation, yielding improvements in token-saving percentages and performance benefits, particularly for smaller models. We evaluate tokenization performance across various intrinsic and extrinsic tasks, including generation and classification. Our findings suggest that compression-optimized tokenization strategies could provide substantial advantages for multilingual and low-resource language applications, highlighting a promising direction for further research and inclusive NLP.
Authors: Ziqi Gao, Weikai Huang, Jieyu Zhang, Aniruddha Kembhavi, Ranjay Krishna
Abstract: DALL-E and Sora have gained attention by producing implausible images, such as "astronauts riding a horse in space." Despite the proliferation of text-to-vision models that have inundated the internet with synthetic visuals, from images to 3D assets, current benchmarks predominantly evaluate these models on real-world scenes paired with captions. We introduce Generate Any Scene, a framework that systematically enumerates scene graphs representing a vast array of visual scenes, spanning realistic to imaginative compositions. Generate Any Scene leverages 'scene graph programming', a method for dynamically constructing scene graphs of varying complexity from a structured taxonomy of visual elements. This taxonomy includes numerous objects, attributes, and relations, enabling the synthesis of an almost infinite variety of scene graphs. Using these structured representations, Generate Any Scene translates each scene graph into a caption, enabling scalable evaluation of text-to-vision models through standard metrics. We conduct extensive evaluations across multiple text-to-image, text-to-video, and text-to-3D models, presenting key findings on model performance. We find that DiT-backbone text-to-image models align more closely with input captions than UNet-backbone models. Text-to-video models struggle with balancing dynamics and consistency, while both text-to-video and text-to-3D models show notable gaps in human preference alignment. We demonstrate the effectiveness of Generate Any Scene by conducting three practical applications leveraging captions generated by Generate Any Scene: 1) a self-improving framework where models iteratively enhance their performance using generated data, 2) a distillation process to transfer specific strengths from proprietary models to open-source counterparts, and 3) improvements in content moderation by identifying and generating challenging synthetic data.
Authors: Ruihuai Liang, Bo Yang, Pengyu Chen, Xuelin Cao, Zhiwen Yu, M\'erouane Debbah, Dusit Niyato, H. Vincent Poor, Chau Yuen
Abstract: Optimization is crucial for MEC networks to function efficiently and reliably, most of which are NP-hard and lack efficient approximation algorithms. This leads to a paucity of optimal solution, constraining the effectiveness of conventional deep learning approaches. Most existing learning-based methods necessitate extensive optimal data and fail to exploit the potential benefits of suboptimal data that can be obtained with greater efficiency and effectiveness. Taking the multi-server multi-user computation offloading (MSCO) problem, which is widely observed in systems like Internet-of-Vehicles (IoV) and Unmanned Aerial Vehicle (UAV) networks, as a concrete scenario, we present a Graph Diffusion-based Solution Generation (GDSG) method. This approach is designed to work with suboptimal datasets while converging to the optimal solution large probably. We transform the optimization issue into distribution-learning and offer a clear explanation of learning from suboptimal training datasets. We build GDSG as a multi-task diffusion model utilizing a Graph Neural Network (GNN) to acquire the distribution of high-quality solutions. We use a simple and efficient heuristic approach to obtain a sufficient amount of training data composed entirely of suboptimal solutions. In our implementation, we enhance the backbone GNN and achieve improved generalization. GDSG also reaches nearly 100\% task orthogonality, ensuring no interference between the discrete and continuous generation tasks. We further reveal that this orthogonality arises from the diffusion-related training loss, rather than the neural network architecture itself. The experiments demonstrate that GDSG surpasses other benchmark methods on both the optimal and suboptimal training datasets. The MSCO datasets has open-sourced at http://ieee-dataport.org/13824, as well as the GDSG algorithm codes at https://github.com/qiyu3816/GDSG.
URLs: http://ieee-dataport.org/13824,, https://github.com/qiyu3816/GDSG.
Authors: Xiayin Lou, Peng Luo, Liqiu Meng
Abstract: Spatial prediction is a fundamental task in geography. In recent years, with advances in geospatial artificial intelligence (GeoAI), numerous models have been developed to improve the accuracy of geographic variable predictions. Beyond achieving higher accuracy, it is equally important to obtain predictions with uncertainty measures to enhance model credibility and support responsible spatial prediction. Although geostatistic methods like Kriging offer some level of uncertainty assessment, such as Kriging variance, these measurements are not always accurate and lack general applicability to other spatial models. To address this issue, we propose a model-agnostic uncertainty assessment method called GeoConformal Prediction, which incorporates geographical weighting into conformal prediction. We applied it to two classic spatial prediction cases, spatial regression and spatial interpolation, to evaluate its reliability. First, in the spatial regression case, we used XGBoost to predict housing prices, followed by GeoConformal to calculate uncertainty. Our results show that GeoConformal achieved a coverage rate of 93.67%, while Bootstrap methods only reached a maximum coverage of 81.00% after 2000 runs. Next, we applied GeoConformal to spatial interpolation models. We found that the uncertainty obtained from GeoConformal aligned closely with the variance in Kriging. Finally, using GeoConformal, we analyzed the sources of uncertainty in spatial prediction. We found that explicitly including local features in AI models can significantly reduce prediction uncertainty, especially in areas with strong local dependence. Our findings suggest that GeoConformal holds potential not only for geographic knowledge discovery but also for guiding the design of future GeoAI models, paving the way for more reliable and interpretable spatial prediction frameworks.
Authors: Tianyang Wang, Ziqian Bi, Yichao Zhang, Ming Liu, Weiche Hsieh, Pohsun Feng, Lawrence K. Q. Yan, Yizhu Wen, Benji Peng, Junyu Liu, Keyu Chen, Sen Zhang, Ming Li, Chuanqi Jiang, Xinyuan Song, Junjie Yang, Bowen Jing, Jintao Ren, Junhao Song, Hong-Ming Tseng, Silin Chen, Yunze Wang, Chia Xin Liang, Jiawei Xu, Xuanhe Pan, Jinlang Wang, Qian Niu
Abstract: Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact on model integrity and confidentiality. Practical implementations, including adversarial examples, label flipping, and backdoor attacks, are explored alongside defenses such as adversarial training, differential privacy, and federated learning, highlighting their strengths and limitations. Advanced methods like contrastive and self-supervised learning are presented for enhancing robustness. The survey concludes with future directions, emphasizing automated defenses, zero-trust architectures, and the security challenges of large AI models. A balanced approach to performance and security is essential for developing reliable deep learning systems.
Authors: Bofang Jia, Pengxiang Ding, Can Cui, Mingyang Sun, Pengfang Qian, Siteng Huang, Zhaoxin Fan, Donglin Wang
Abstract: Visual-motor policy learning has advanced with architectures like diffusion-based policies, known for modeling complex robotic trajectories. However, their prolonged inference times hinder high-frequency control tasks requiring real-time feedback. While consistency distillation (CD) accelerates inference, it introduces errors that compromise action quality. To address these limitations, we propose the Score and Distribution Matching Policy (SDM Policy), which transforms diffusion-based policies into single-step generators through a two-stage optimization process: score matching ensures alignment with true action distributions, and distribution matching minimizes KL divergence for consistency. A dual-teacher mechanism integrates a frozen teacher for stability and an unfrozen teacher for adversarial training, enhancing robustness and alignment with target distributions. Evaluated on a 57-task simulation benchmark, SDM Policy achieves a 6x inference speedup while having state-of-the-art action quality, providing an efficient and reliable framework for high-frequency robotic tasks.
Authors: Ziyuan Chen, Fang Yao
Abstract: Noisy matrix completion has attracted significant attention due to its applications in recommendation systems, signal processing and image restoration. Most existing works rely on (weighted) least squares methods under various low-rank constraints. However, minimizing the sum of squared residuals is not always efficient, as it may ignore the potential structural information in the residuals. In this study, we propose a novel residual spectral matching criterion that incorporates not only the numerical but also locational information of residuals. This criterion is the first in noisy matrix completion to adopt the perspective of low-rank perturbation of random matrices and exploit the spectral properties of sparse random matrices. We derive optimal statistical properties by analyzing the spectral properties of sparse random matrices and bounding the effects of low-rank perturbations and partial observations. Additionally, we propose algorithms that efficiently approximate solutions by constructing easily computable pseudo-gradients. The iterative process of the proposed algorithms ensures convergence at a rate consistent with the optimal statistical error bound. Our method and algorithms demonstrate improved numerical performance in both simulated and real data examples, particularly in environments with high noise levels.