Authors: Siyu Chen, Heejune Sheen, Tianhao Wang, Zhuoran Yang
Abstract: In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architectures. In particular, most existing work only theoretically explains how the attention mechanism facilitates ICL under certain data models. It remains unclear how the other building blocks of the transformer contribute to ICL. To address this question, we study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data, where each token in the Markov chain statistically depends on the previous $n$ tokens. We analyze a sophisticated transformer model featuring relative positional embedding, multi-head softmax attention, and a feed-forward layer with normalization. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model that performs a generalized version of the induction head mechanism with a learned feature, resulting from the congruous contribution of all the building blocks. In the limiting model, the first attention layer acts as a $\mathit{copier}$, copying past tokens within a given window to each position, and the feed-forward network with normalization acts as a $\mathit{selector}$ that generates a feature vector by only looking at informationally relevant parents from the window. Finally, the second attention layer is a $\mathit{classifier}$ that compares these features with the feature at the output position, and uses the resulting similarity scores to generate the desired output. Our theory is further validated by experiments.
Authors: Vidhisha Balachandran, Jingya Chen, Neel Joshi, Besmira Nushi, Hamid Palangi, Eduardo Salinas, Vibhav Vineet, James Woffinden-Luey, Safoora Yousefi
Abstract: Rigorous and reproducible evaluation is critical for assessing the state of the art and for guiding scientific advances in Artificial Intelligence. Evaluation is challenging in practice due to several reasons, including benchmark saturation, lack of transparency in methods used for measurement, development challenges in extracting measurements for generative tasks, and, more generally, the extensive number of capabilities required for a well-rounded comparison across models. We make three contributions to alleviate the above challenges. First, we present Eureka, an open-source framework for standardizing evaluations of large foundation models beyond single-score reporting and rankings. Second, we introduce Eureka-Bench as an extensible collection of benchmarks testing capabilities that (i) are still challenging for state-of-the-art models and (ii) represent fundamental but overlooked language and multimodal capabilities. The inherent space for improvement in non-saturated benchmarks enables us to discover meaningful differences between models at a capability level. Third, using Eureka, we conduct an analysis of 12 state-of-the-art models, providing in-depth insights into failure understanding and model comparison, which can be leveraged to plan targeted improvements. In contrast to recent trends in reports and leaderboards showing absolute rankings and claims for one model or another to be the best, our analysis shows that there is no such best model. Different models have different strengths, but there are models that appear more often than others as best performers for some capabilities. Despite the recent improvements, current models still struggle with several fundamental capabilities including detailed image understanding, benefiting from multimodal input when available rather than fully relying on language, factuality and grounding for information retrieval, and over refusals.
Authors: Cong Kong, Rui Xu, Weixi Chen, Jiawei Chen, Zhaoxia Yin
Abstract: Pre-training language models followed by fine-tuning on specific tasks is standard in NLP, but traditional models often underperform when applied to the medical domain, leading to the development of specialized medical pre-trained language models (Med-PLMs). These models are valuable assets but are vulnerable to misuse and theft, requiring copyright protection. However, no existing watermarking methods are tailored for Med-PLMs, and adapting general PLMs watermarking techniques to the medical domain faces challenges such as task incompatibility, loss of fidelity, and inefficiency. To address these issues, we propose the first training-free backdoor watermarking method for Med-PLMs. Our method uses rare special symbols as trigger words, which do not impact downstream task performance, embedding watermarks by replacing their original embeddings with those of specific medical terms in the Med-PLMs' word embeddings layer. After fine-tuning the watermarked Med-PLMs on various medical downstream tasks, the final models (FMs) respond to the trigger words in the same way they would to the corresponding medical terms. This property can be utilized to extract the watermark. Experiments demonstrate that our method achieves high fidelity while effectively extracting watermarks across various medical downstream tasks. Additionally, our method demonstrates robustness against various attacks and significantly enhances the efficiency of watermark embedding, reducing the embedding time from 10 hours to 10 seconds.
Authors: Ruoyu Wang, Jiachen Sun, Shaowei Hua, Quan Fang
Abstract: Direct Preference Optimization (DPO) is a method for enhancing model performance by directly optimizing for the preferences or rankings of outcomes, instead of traditional loss functions. This approach has proven effective in aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across various tasks, DPO has been criticized for its sensitivity to the effectiveness of Supervised Fine-Tuning (SFT) and its limitations in enabling models to learn human-preferred responses, leading to less satisfactory performance. To address these limitations, we propose Aligned Supervised Fine-Tuning (ASFT), an effective approach that better aligns LLMs with pair-wise datasets by optimizing absolute likelihood for each response, rather than using the Bradley-Terry model, and eliminates the need for a reference model. Through theoretical gradient analysis, we demonstrate that ASFT mitigates the issue where the DPO loss function decreases the probability of generating human-dispreferred data at a faster rate than it increases the probability of producing preferred data. Additionally, we compare ASFT to DPO and its latest variants, such as the single-step approach ORPO, using the latest instruction-tuned model Llama3, which has been fine-tuned on UltraFeedback and HH-RLHF. We evaluated performance on instruction-following benchmarks like MT-Bench and traditional text generation metrics such as BLEU-4 and ROUGE-L. Extensive experiments demonstrate that ASFT is an effective alignment approach, consistently outperforming existing methods.
Authors: Ahmed Alaa, Bin Yu
Abstract: The advent of foundation models (FMs) such as large language models (LLMs) has led to a cultural shift in data science, both in medicine and beyond. This shift involves moving away from specialized predictive models trained for specific, well-defined domain questions to generalist FMs pre-trained on vast amounts of unstructured data, which can then be adapted to various clinical tasks and questions. As a result, the standard data science workflow in medicine has been fundamentally altered; the foundation model lifecycle (FMLC) now includes distinct upstream and downstream processes, in which computational resources, model and data access, and decision-making power are distributed among multiple stakeholders. At their core, FMs are fundamentally statistical models, and this new workflow challenges the principles of Veridical Data Science (VDS), hindering the rigorous statistical analysis expected in transparent and scientifically reproducible data science practices. We critically examine the medical FMLC in light of the core principles of VDS: predictability, computability, and stability (PCS), and explain how it deviates from the standard data science workflow. Finally, we propose recommendations for a reimagined medical FMLC that expands and refines the PCS principles for VDS including considering the computational and accessibility constraints inherent to FMs.
Authors: S. R. Eshwar, Mayank Motwani, Nibedita Roy, Gugan Thoppe
Abstract: Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which has a bias towards immediate gratification. Quasi-Hyperbolic (QH) discounting is a simple alternative for modeling this bias. Unlike in traditional discounting, though, the optimal QH-policy, starting from some time $t_1,$ can be different to the one starting from $t_2.$ Hence, the future self of an agent, if it is naive or impatient, can deviate from the policy that is optimal at the start, leading to sub-optimal overall returns. To prevent this behavior, an alternative is to work with a policy anchored in a Markov Perfect Equilibrium (MPE). In this work, we propose the first model-free algorithm for finding an MPE. Using a two-timescale analysis, we show that, if our algorithm converges, then the limit must be an MPE. We also validate this claim numerically for the standard inventory system with stochastic demands. Our work significantly advances the practical application of reinforcement learning.
Authors: Aron Distelzweig, Eitan Kosman, Andreas Look, Faris Janjo\v{s}, Denesh K. Manivannan, Abhinav Valada
Abstract: Forecasting the future trajectories of surrounding agents is crucial for autonomous vehicles to ensure safe, efficient, and comfortable route planning. While model ensembling has improved prediction accuracy in various fields, its application in trajectory prediction is limited due to the multi-modal nature of predictions. In this paper, we propose a novel sampling method applicable to trajectory prediction based on the predictions of multiple models. We first show that conventional sampling based on predicted probabilities can degrade performance due to missing alignment between models. To address this problem, we introduce a new method that generates optimal trajectories from a set of neural networks, framing it as a risk minimization problem with a variable loss function. By using state-of-the-art models as base learners, our approach constructs diverse and effective ensembles for optimal trajectory sampling. Extensive experiments on the nuScenes prediction dataset demonstrate that our method surpasses current state-of-the-art techniques, achieving top ranks on the leaderboard. We also provide a comprehensive empirical study on ensembling strategies, offering insights into their effectiveness. Our findings highlight the potential of advanced ensembling techniques in trajectory prediction, significantly improving predictive performance and paving the way for more reliable predicted trajectories.
Authors: Jesse van Remmerden, Zaharah Bukhsh, Yingqian Zhang
Abstract: The Job Shop Scheduling Problem (JSSP) is a complex combinatorial optimization problem. There has been growing interest in using online Reinforcement Learning (RL) for JSSP. While online RL can quickly find acceptable solutions, especially for larger problems, it produces lower-quality results than traditional methods like Constraint Programming (CP). A significant downside of online RL is that it cannot learn from existing data, such as solutions generated from CP, requiring them to train from scratch, leading to sample inefficiency and making them unable to learn from more optimal examples. We introduce Offline Reinforcement Learning for Learning to Dispatch (Offline-LD), a novel approach for JSSP that addresses these limitations. Offline-LD adapts two CQL-based Q-learning methods (mQRDQN and discrete mSAC) for maskable action spaces, introduces a new entropy bonus modification for discrete SAC, and exploits reward normalization through preprocessing. Our experiments show that Offline-LD outperforms online RL on both generated and benchmark instances. By introducing noise into the dataset, we achieve similar or better results than those obtained from the expert dataset, indicating that a more diverse training set is preferable because it contains counterfactual information.
Authors: Luning Wang, Shiyao Li, Xuefei Ning, Zhihang Yuan, Shengen Yan, Guohao Dai, Yu Wang
Abstract: Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache compression methods typically focus on quantization and token pruning, which have compression limits, and excessive sparsity can lead to severe performance degradation. Other methods design new architectures with less KV overhead but require significant training overhead. To address the above two drawbacks, we further explore the redundancy in the channel dimension and apply an architecture-level design with minor training costs. Therefore, we introduce CSKV, a training-efficient Channel Shrinking technique for KV cache compression: (1) We first analyze the singular value distribution of the KV cache, revealing significant redundancy and compression potential along the channel dimension. Based on this observation, we propose using low-rank decomposition for key and value layers and storing the low-dimension features. (2) To preserve model performance, we introduce a bi-branch KV cache, including a window-based full-precision KV cache and a low-precision compressed KV cache. (3) To reduce the training costs, we minimize the layer-wise reconstruction loss for the compressed KV cache instead of retraining the entire LLMs. Extensive experiments show that CSKV can reduce the memory overhead of the KV cache by 80% while maintaining the model's long-context capability. Moreover, we show that our method can be seamlessly combined with quantization to further reduce the memory overhead, achieving a compression ratio of up to 95%.
Authors: Xingyi Yang, Xinchao Wang
Abstract: Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model. Integrating KANs into transformers, however, is no easy feat, especially when scaled up. Specifically, we identify three key challenges: (C1) Base function. The standard B-spline function used in KANs is not optimized for parallel computing on modern hardware, resulting in slower inference speeds. (C2) Parameter and Computation Inefficiency. KAN requires a unique function for each input-output pair, making the computation extremely large. (C3) Weight initialization. The initialization of weights in KANs is particularly challenging due to their learnable activation functions, which are critical for achieving convergence in deep neural networks. To overcome the aforementioned challenges, we propose three key solutions: (S1) Rational basis. We replace B-spline functions with rational functions to improve compatibility with modern GPUs. By implementing this in CUDA, we achieve faster computations. (S2) Group KAN. We share the activation weights through a group of neurons, to reduce the computational load without sacrificing performance. (S3) Variance-preserving initialization. We carefully initialize the activation weights to make sure that the activation variance is maintained across layers. With these designs, KAT scales effectively and readily outperforms traditional MLP-based transformers.
Authors: Haolin Chen, Philip N. Garner
Abstract: Motivated by the sensitivity-based importance score of the adaptive low-rank adaptation (AdaLoRA), we utilize more theoretically supported metrics, including the signal-to-noise ratio (SNR), along with the Improved Variational Online Newton (IVON) optimizer, for adaptive parameter budget allocation. The resulting Bayesian counterpart not only has matched or surpassed the performance of using the sensitivity-based importance metric but is also a faster alternative to AdaLoRA with Adam. Our theoretical analysis reveals a significant connection between the two metrics, providing a Bayesian perspective on the efficacy of sensitivity as an importance score. Furthermore, our findings suggest that the magnitude, rather than the variance, is the primary indicator of the importance of parameters.
Authors: Rachel Pfeifer, Sudip Vhaduri, Mark Wilson, Julius Keller
Abstract: While researchers have been trying to understand the stress and fatigue among pilots, especially pilot trainees, and to develop stress/fatigue models to automate the process of detecting stress/fatigue, they often do not consider biases such as sex in those models. However, in a critical profession like aviation, where the demographic distribution is disproportionately skewed to one sex, it is urgent to mitigate biases for fair and safe model predictions. In this work, we investigate the perceived stress/fatigue of 69 college students, including 40 pilot trainees with around 63% male. We construct models with decision trees first without bias mitigation and then with bias mitigation using a threshold optimizer with demographic parity and equalized odds constraints 30 times with random instances. Using bias mitigation, we achieve improvements of 88.31% (demographic parity difference) and 54.26% (equalized odds difference), which are also found to be statistically significant.
Authors: Rachel Pfeifer, Sudip Vhaduri, James Eric Dietz
Abstract: In the healthcare industry, researchers have been developing machine learning models to automate diagnosing patients with respiratory illnesses based on their breathing patterns. However, these models do not consider the demographic biases, particularly sex bias, that often occur when models are trained with a skewed patient dataset. Hence, it is essential in such an important industry to reduce this bias so that models can make fair diagnoses. In this work, we examine the bias in models used to detect breathing patterns of two major respiratory diseases, i.e., chronic obstructive pulmonary disease (COPD) and COVID-19. Using decision tree models trained with audio recordings of breathing patterns obtained from two open-source datasets consisting of 29 COPD and 680 COVID-19-positive patients, we analyze the effect of sex bias on the models. With a threshold optimizer and two constraints (demographic parity and equalized odds) to mitigate the bias, we witness 81.43% (demographic parity difference) and 71.81% (equalized odds difference) improvements. These findings are statistically significant.
Authors: Xiaoyu Wang, Ayal Taitler, Scott Sanner, Baher Abdulhai
Abstract: Efficient traffic signal control is essential for managing urban transportation, minimizing congestion, and improving safety and sustainability. Reinforcement Learning (RL) has emerged as a promising approach to enhancing adaptive traffic signal control (ATSC) systems, allowing controllers to learn optimal policies through interaction with the environment. However, challenges arise due to partial observability (PO) in traffic networks, where agents have limited visibility, hindering effectiveness. This paper presents the integration of Transformer-based controllers into ATSC systems to address PO effectively. We propose strategies to enhance training efficiency and effectiveness, demonstrating improved coordination capabilities in real-world scenarios. The results showcase the Transformer-based model's ability to capture significant information from historical observations, leading to better control policies and improved traffic flow. This study highlights the potential of leveraging the advanced Transformer architecture to enhance urban transportation management.
Authors: Edvin Listo Zec, Tom Hagander, Eric Ihre-Thomason, Sarunas Girdzijauskas
Abstract: Decentralized Learning (DL) enables privacy-preserving collaboration among organizations or users to enhance the performance of local deep learning models. However, model aggregation becomes challenging when client data is heterogeneous, and identifying compatible collaborators without direct data exchange remains a pressing issue. In this paper, we investigate the effectiveness of various similarity metrics in DL for identifying peers for model merging, conducting an empirical analysis across multiple datasets with distribution shifts. Our research provides insights into the performance of these metrics, examining their role in facilitating effective collaboration. By exploring the strengths and limitations of these metrics, we contribute to the development of robust DL methods.
Authors: Zikai Zhang, Suman Rath, Jiaohao Xu, Tingsong Xiao
Abstract: The Smart Grid (SG) is a critical energy infrastructure that collects real-time electricity usage data to forecast future energy demands using information and communication technologies (ICT). Due to growing concerns about data security and privacy in SGs, federated learning (FL) has emerged as a promising training framework. FL offers a balance between privacy, efficiency, and accuracy in SGs by enabling collaborative model training without sharing private data from IoT devices. In this survey, we thoroughly review recent advancements in designing FL-based SG systems across three stages: generation, transmission and distribution, and consumption. Additionally, we explore potential vulnerabilities that may arise when implementing FL in these stages. Finally, we discuss the gap between state-of-the-art FL research and its practical applications in SGs and propose future research directions. These focus on potential attack and defense strategies for FL-based SG systems and the need to build a robust FL-based SG infrastructure. Unlike traditional surveys that address security issues in centralized machine learning methods for SG systems, this survey specifically examines the applications and security concerns in FL-based SG systems for the first time. Our aim is to inspire further research into applications and improvements in the robustness of FL-based SG systems.
Authors: Woojin Chae, Dabeen Lee
Abstract: This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear Markov decision processes (MDPs) and linear mixture MDPs under the Bellman optimality condition. While guaranteeing computational efficiency, our algorithm for linear MDPs achieves the best-known regret upper bound of $\widetilde{\mathcal{O}}(d^{3/2}\mathrm{sp}(v^*)\sqrt{T})$ over $T$ time steps where $\mathrm{sp}(v^*)$ is the span of the optimal bias function $v^*$ and $d$ is the dimension of the feature mapping. For linear mixture MDPs, our algorithm attains a regret bound of $\widetilde{\mathcal{O}}(d\cdot\mathrm{sp}(v^*)\sqrt{T})$. The algorithm applies novel techniques to control the covering number of the value function class and the span of optimistic estimators of the value function, which is of independent interest.
Authors: Xiaoran Cheng, Sen Na
Abstract: Physics-Informed Neural Networks (PINNs) represent a significant advancement in Scientific Machine Learning (SciML), which integrate physical domain knowledge into an empirical loss function as soft constraints and apply existing machine learning methods to train the model. However, recent research has noted that PINNs may fail to learn relatively complex Partial Differential Equations (PDEs). This paper addresses the failure modes of PINNs by introducing a novel, hard-constrained deep learning method -- trust-region Sequential Quadratic Programming (trSQP-PINN). In contrast to directly training the penalized soft-constrained loss as in PINNs, our method performs a linear-quadratic approximation of the hard-constrained loss, while leveraging the soft-constrained loss to adaptively adjust the trust-region radius. We only trust our model approximations and make updates within the trust region, and such an updating manner can overcome the ill-conditioning issue of PINNs. We also address the computational bottleneck of second-order SQP methods by employing quasi-Newton updates for second-order information, and importantly, we introduce a simple pretraining step to further enhance training efficiency of our method. We demonstrate the effectiveness of trSQP-PINN through extensive experiments. Compared to existing hard-constrained methods for PINNs, such as penalty methods and augmented Lagrangian methods, trSQP-PINN significantly improves the accuracy of the learned PDE solutions, achieving up to 1-3 orders of magnitude lower errors. Additionally, our pretraining step is generally effective for other hard-constrained methods, and experiments have shown the robustness of our method against both problem-specific parameters and algorithm tuning parameters.
Authors: Zeheng Wang, Fangzhou Wang, Liang Li, Zirui Wang, Timothy van der Laan, Ross C. C. Leon, Jing-Kai Huang, Muhammad Usman
Abstract: This paper pioneers the use of quantum machine learning (QML) for modeling the Ohmic contact process in GaN high-electron-mobility transistors (HEMTs) for the first time. Utilizing data from 159 devices and variational auto-encoder-based augmentation, we developed a quantum kernel-based regressor (QKR) with a 2-level ZZ-feature map. Benchmarking against six classical machine learning (CML) models, our QKR consistently demonstrated the lowest mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE). Repeated statistical analysis confirmed its robustness. Additionally, experiments verified an MAE of 0.314 ohm-mm, underscoring the QKR's superior performance and potential for semiconductor applications, and demonstrating significant advancements over traditional CML methods.
Authors: Sia Gupta, Simeon Sayer
Abstract: In recent years, urban safety has become a paramount concern for city planners and law enforcement agencies. Accurate prediction of likely crime occurrences can significantly enhance preventive measures and resource allocation. However, many law enforcement departments lack the tools to analyze and apply advanced AI and ML techniques that can support city planners, watch programs, and safety leaders to take proactive steps towards overall community safety. This paper explores the effectiveness of ML techniques to predict spatial and temporal patterns of crimes in urban areas. Leveraging police dispatch call data from San Jose, CA, the research goal is to achieve a high degree of accuracy in categorizing calls into priority levels particularly for more dangerous situations that require an immediate law enforcement response. This categorization is informed by the time, place, and nature of the call. The research steps include data extraction, preprocessing, feature engineering, exploratory data analysis, implementation, optimization and tuning of different supervised machine learning models and neural networks. The accuracy and precision are examined for different models and features at varying granularity of crime categories and location precision. The results demonstrate that when compared to a variety of other models, Random Forest classification models are most effective in identifying dangerous situations and their corresponding priority levels with high accuracy (Accuracy = 85%, AUC = 0.92) at a local level while ensuring a minimum amount of false negatives. While further research and data gathering is needed to include other social and economic factors, these results provide valuable insights for law enforcement agencies to optimize resources, develop proactive deployment approaches, and adjust response patterns to enhance overall public safety outcomes in an unbiased way.
Authors: Willa Potosnak, Cristian Challu, Mononito Goswami, Micha{\l} Wili\'nski, Nina \.Zukowska
Abstract: Recently, time series foundation models have shown promising zero-shot forecasting performance on time series from a wide range of domains. However, it remains unclear whether their success stems from a true understanding of temporal dynamics or simply from memorizing the training data. While implicit reasoning in language models has been studied, similar evaluations for time series models have been largely unexplored. This work takes an initial step toward assessing the reasoning abilities of deep time series forecasting models. We find that certain linear, MLP-based, and patch-based Transformer models generalize effectively in systematically orchestrated out-of-distribution scenarios, suggesting underexplored reasoning capabilities beyond simple pattern memorization.
Authors: Thore Gerlach, Nico Piatkowski
Abstract: The demand for high-performance computing in machine learning and artificial intelligence has led to the development of specialized hardware accelerators like Tensor Processing Units (TPUs), Graphics Processing Units (GPUs), and Field-Programmable Gate Arrays (FPGAs). A key strategy to enhance these accelerators is the reduction of precision in arithmetic operations, which increases processing speed and lowers latency - crucial for real-time AI applications. Precision reduction minimizes memory bandwidth requirements and energy consumption, essential for large-scale and mobile deployments, and increases throughput by enabling more parallel operations per cycle, maximizing hardware resource utilization. This strategy is equally vital for solving NP-hard quadratic unconstrained binary optimization (QUBO) problems common in machine learning, which often require high precision for accurate representation. Special hardware solvers, such as quantum annealers, benefit significantly from precision reduction. This paper introduces a fully principled Branch-and-Bound algorithm for reducing precision needs in QUBO problems by utilizing dynamic range as a measure of complexity. Experiments validate our algorithm's effectiveness on an actual quantum annealer.
Authors: Shuowei Jin, Francis Y. Yan, Cheng Tan, Anuj Kalia, Xenofon Foukas, Z. Morley Mao
Abstract: The increasing adoption of neural networks in learning-augmented systems highlights the importance of model safety and robustness, particularly in safety-critical domains. Despite progress in the formal verification of neural networks, current practices require users to manually define model specifications -- properties that dictate expected model behavior in various scenarios. This manual process, however, is prone to human error, limited in scope, and time-consuming. In this paper, we introduce AutoSpec, the first framework to automatically generate comprehensive and accurate specifications for neural networks in learning-augmented systems. We also propose the first set of metrics for assessing the accuracy and coverage of model specifications, establishing a benchmark for future comparisons. Our evaluation across four distinct applications shows that AutoSpec outperforms human-defined specifications as well as two baseline approaches introduced in this study.
Authors: Biplov Paneru, Bishwash Paneru
Abstract: Ensuring a safe and uncontaminated water supply is contingent upon the monitoring of water quality, especially in developing countries such as Nepal, where water sources are susceptible to pollution. This paper presents a hybrid deep learning model for predicting Nepal's seasonal water quality using a small dataset with many water quality parameters. The model integrates convolutional neural networks (CNN) and recurrent neural networks (RNN) to exploit temporal and spatial patterns in the data. The results demonstrate significant improvements in forecast accuracy over traditional methods, providing a reliable tool for proactive control of water quality. The model that used WQI parameters to classify people into good, poor, and average groups performed 92% of the time in testing. Similarly, the R2 score was 0.97 and the root mean square error was 2.87 when predicting WQI values using regression analysis. Additionally, a multifunctional application that uses both a regression and a classification approach is built to predict WQI values.
Authors: Shivprasad Kathane (Indian Institute of Technology Bombay Mumbai India), Shyamprasad Karagadde (Indian Institute of Technology Bombay Mumbai India)
Abstract: Physics-Informed Neural Network (PINN) is a novel multi-task learning framework useful for solving physical problems modeled using differential equations (DEs) by integrating the knowledge of physics and known constraints into the components of deep learning. A large class of physical problems in materials science and mechanics involve moving boundaries, where interface flux balance conditions are to be satisfied while solving DEs. Examples of such systems include free surface flows, shock propagation, solidification of pure and alloy systems etc. While recent research works have explored applicability of PINNs for an uncoupled system (such as solidification of pure system), the present work reports a PINN-based approach to solve coupled systems involving multiple governing parameters (energy and species, along with multiple interface balance equations). This methodology employs an architecture consisting of a separate network for each variable with a separate treatment of each phase, a training strategy which alternates between temporal learning and adaptive loss weighting, and a scheme which progressively reduces the optimisation space. While solving the benchmark problem of binary alloy solidification, it is distinctly successful at capturing the complex composition profile, which has a characteristic discontinuity at the interface and the resulting predictions align well with the analytical solutions. The procedure can be generalised for solving other transient multiphysics problems especially in the low-data regime and in cases where measurements can reveal new physics.
Authors: Mehroush Banday, Sherin Zafar, Parul Agarwal, M Afshar Alam, Abubeker K M
Abstract: Coronary heart disease (CHD) is a severe cardiac disease, and hence, its early diagnosis is essential as it improves treatment results and saves money on medical care. The prevailing development of quantum computing and machine learning (ML) technologies may bring practical improvement to the performance of CHD diagnosis. Quantum machine learning (QML) is receiving tremendous interest in various disciplines due to its higher performance and capabilities. A quantum leap in the healthcare industry will increase processing power and optimise multiple models. Techniques for QML have the potential to forecast cardiac disease and help in early detection. To predict the risk of coronary heart disease, a hybrid approach utilizing an ensemble machine learning model based on QML classifiers is presented in this paper. Our approach, with its unique ability to address multidimensional healthcare data, reassures the method's robustness by fusing quantum and classical ML algorithms in a multi-step inferential framework. The marked rise in heart disease and death rates impacts worldwide human health and the global economy. Reducing cardiac morbidity and mortality requires early detection of heart disease. In this research, a hybrid approach utilizes techniques with quantum computing capabilities to tackle complex problems that are not amenable to conventional machine learning algorithms and to minimize computational expenses. The proposed method has been developed in the Raspberry Pi 5 Graphics Processing Unit (GPU) platform and tested on a broad dataset that integrates clinical and imaging data from patients suffering from CHD and healthy controls. Compared to classical machine learning models, the accuracy, sensitivity, F1 score, and specificity of the proposed hybrid QML model used with CHD are manifold higher.
Authors: Riya Samanta, Bidyut Saha, Soumya K. Ghosh, Ram Babu Roy
Abstract: Tiny Machine Learning (TinyML) enables efficient, lowcost, and privacy preserving machine learning inference directly on microcontroller units (MCUs) connected to sensors. Optimizing models for these constrained environments is crucial. This paper investigates how reducing data acquisition rates affects TinyML models for time series classification, focusing on resource-constrained, battery operated IoT devices. By lowering data sampling frequency, we aim to reduce computational demands RAM usage, energy consumption, latency, and MAC operations by approximately fourfold while maintaining similar classification accuracies. Our experiments with six benchmark datasets (UCIHAR, WISDM, PAMAP2, MHEALTH, MITBIH, and PTB) showed that reducing data acquisition rates significantly cut energy consumption and computational load, with minimal accuracy loss. For example, a 75\% reduction in acquisition rate for MITBIH and PTB datasets led to a 60\% decrease in RAM usage, 75\% reduction in MAC operations, 74\% decrease in latency, and 70\% reduction in energy consumption, without accuracy loss. These results offer valuable insights for deploying efficient TinyML models in constrained environments.
Authors: Jiaxing Xu, Kai He, Mengcheng Lan, Qingtian Bian, Wei Li, Tieying Li, Yiping Ke, Miao Qiao
Abstract: Understanding neurological disorder is a fundamental problem in neuroscience, which often requires the analysis of brain networks derived from functional magnetic resonance imaging (fMRI) data. Despite the prevalence of Graph Neural Networks (GNNs) and Graph Transformers in various domains, applying them to brain networks faces challenges. Specifically, the datasets are severely impacted by the noises caused by distribution shifts across sub-populations and the neglect of node identities, both obstruct the identification of disease-specific patterns. To tackle these challenges, we propose Contrasformer, a novel contrastive brain network Transformer. It generates a prior-knowledge-enhanced contrast graph to address the distribution shifts across sub-populations by a two-stream attention mechanism. A cross attention with identity embedding highlights the identity of nodes, and three auxiliary losses ensure group consistency. Evaluated on 4 functional brain network datasets over 4 different diseases, Contrasformer outperforms the state-of-the-art methods for brain networks by achieving up to 10.8\% improvement in accuracy, which demonstrates its efficacy in neurological disorder identification. Case studies illustrate its interpretability, especially in the context of neuroscience. This paper provides a solution for analyzing brain networks, offering valuable insights into neurological disorders. Our code is available at \url{https://github.com/AngusMonroe/Contrasformer}.
Authors: Ziwei Wu, Lecheng Zheng, Yuancheng Yu, Ruizhong Qiu, John Birge, Jingrui He
Abstract: Anomaly detection (AD) has been widely studied for decades in many real-world applications, including fraud detection in finance, and intrusion detection for cybersecurity, etc. Due to the imbalanced nature between protected and unprotected groups and the imbalanced distributions of normal examples and anomalies, the learning objectives of most existing anomaly detection methods tend to solely concentrate on the dominating unprotected group. Thus, it has been recognized by many researchers about the significance of ensuring model fairness in anomaly detection. However, the existing fair anomaly detection methods tend to erroneously label most normal examples from the protected group as anomalies in the imbalanced scenario where the unprotected group is more abundant than the protected group. This phenomenon is caused by the improper design of learning objectives, which statistically focus on learning the frequent patterns (i.e., the unprotected group) while overlooking the under-represented patterns (i.e., the protected group). To address these issues, we propose FairAD, a fairness-aware anomaly detection method targeting the imbalanced scenario. It consists of a fairness-aware contrastive learning module and a rebalancing autoencoder module to ensure fairness and handle the imbalanced data issue, respectively. Moreover, we provide the theoretical analysis that shows our proposed contrastive learning regularization guarantees group fairness. Empirical studies demonstrate the effectiveness and efficiency of FairAD across multiple real-world datasets.
Authors: Alejandro Garc\'ia-Castellanos, Giovanni Luca Marchetti, Danica Kragic, Martina Scolamiero
Abstract: Relative representations are an established approach to zero-shot model stitching, consisting of a non-trainable transformation of the latent space of a deep neural network. Based on insights of topological and geometric nature, we propose two improvements to relative representations. First, we introduce a normalization procedure in the relative transformation, resulting in invariance to non-isotropic rescalings and permutations. The latter coincides with the symmetries in parameter space induced by common activation functions. Second, we propose to deploy topological densification when fine-tuning relative representations, a topological regularization loss encouraging clustering within classes. We provide an empirical investigation on a natural language task, where both the proposed variations yield improved performance on zero-shot model stitching.
Authors: Ali Royat, Seyed Mohamad Moghadas, Lesley De Cruz, Adrian Munteanu
Abstract: Deep neural networks (DNNs) have demonstrated remarkable performance across various domains, yet their application to temporal graph regression tasks faces significant challenges regarding interpretability. This critical issue, rooted in the inherent complexity of both DNNs and underlying spatio-temporal patterns in the graph, calls for innovative solutions. While interpretability concerns in Graph Neural Networks (GNNs) mirror those of DNNs, to the best of our knowledge, no notable work has addressed the interpretability of temporal GNNs using a combination of Information Bottleneck (IB) principles and prototype-based methods. Our research introduces a novel approach that uniquely integrates these techniques to enhance the interpretability of temporal graph regression models. The key contributions of our work are threefold: We introduce the \underline{G}raph \underline{IN}terpretability in \underline{T}emporal \underline{R}egression task using \underline{I}nformation bottleneck and \underline{P}rototype (GINTRIP) framework, the first combined application of IB and prototype-based methods for interpretable temporal graph tasks. We derive a novel theoretical bound on mutual information (MI), extending the applicability of IB principles to graph regression tasks. We incorporate an unsupervised auxiliary classification head, fostering multi-task learning and diverse concept representation, which enhances the model bottleneck's interpretability. Our model is evaluated on real-world traffic datasets, outperforming existing methods in both forecasting accuracy and interpretability-related metrics.
Authors: Priscilla Ong, Manuel Hau{\ss}mann, Otto L\"onnroth, Harri L\"ahdesm\"aki
Abstract: Modelling longitudinal data is an important yet challenging task. These datasets can be high-dimensional, contain non-linear effects and time-varying covariates. Gaussian process (GP) prior-based variational autoencoders (VAEs) have emerged as a promising approach due to their ability to model time-series data. However, they are costly to train and struggle to fully exploit the rich covariates characteristic of longitudinal data, making them difficult for practitioners to use effectively. In this work, we leverage linear mixed models (LMMs) and amortized variational inference to provide conditional priors for VAEs, and propose LMM-VAE, a scalable, interpretable and identifiable model. We highlight theoretical connections between it and GP-based techniques, providing a unified framework for this class of methods. Our proposal performs competitively compared to existing approaches across simulated and real-world datasets.
Authors: Xiaobao Song, Hao Wang, Liwei Deng, Yuxin He, Wenming Cao, Chi-Sing Leungc
Abstract: Time position embeddings capture the positional information of time steps, often serving as auxiliary inputs to enhance the predictive capabilities of time series models. However, existing models exhibit limitations in capturing intricate time positional information and effectively utilizing these embeddings. To address these limitations, this paper proposes a novel model called D2Vformer. Unlike typical prediction methods that rely on RNNs or Transformers, this approach can directly handle scenarios where the predicted sequence is not adjacent to the input sequence or where its length dynamically changes. In comparison to conventional methods, D2Vformer undoubtedly saves a significant amount of training resources. In D2Vformer, the Date2Vec module uses the timestamp information and feature sequences to generate time position embeddings. Afterward, D2Vformer introduces a new fusion block that utilizes an attention mechanism to explore the similarity in time positions between the embeddings of the input sequence and the predicted sequence, thereby generating predictions based on this similarity. Through extensive experiments on six datasets, we demonstrate that Date2Vec outperforms other time position embedding methods, and D2Vformer surpasses state-of-the-art methods in both fixed-length and variable-length prediction tasks.
Authors: Andr\'es Corrada-Emmanuel, Ilya Parker, Ramesh Bharadwaj
Abstract: If two agents disagree in their decisions, we may suspect they are not both correct. This intuition is formalized for evaluating agents that have carried out a binary classification task. Their agreements and disagreements on a joint test allow us to establish the only group evaluations logically consistent with their responses. This is done by establishing a set of axioms (algebraic relations) that must be universally obeyed by all evaluations of binary responders. A complete set of such axioms are possible for each ensemble of size N. The axioms for $N = 1, 2$ are used to construct a fully logical alarm - one that can prove that at least one ensemble member is malfunctioning using only unlabeled data. The similarities of this approach to formal software verification and its utility for recent agendas of safe guaranteed AI are discussed.
Authors: Mingyue Cheng, Jintao Zhang, Zhiding Liu, Chunli Liu, Yanhu Xie
Abstract: Intraoperative hypotension (IOH) prediction using Mean Arterial Pressure (MAP) is a critical research area with significant implications for patient outcomes during surgery. However, existing approaches predominantly employ static modeling paradigms that overlook the dynamic nature of physiological signals. In this paper, we introduce a novel Hybrid Multi-Factor (HMF) framework that reformulates IOH prediction as a blood pressure forecasting task. Our framework leverages a Transformer encoder, specifically designed to effectively capture the temporal evolution of MAP series through a patch-based input representation, which segments the input physiological series into informative patches for accurate analysis. To address the challenges of distribution shift in physiological series, our approach incorporates two key innovations: (1) Symmetric normalization and de-normalization processes help mitigate distributional drift in statistical properties, thereby ensuring the model's robustness across varying conditions, and (2) Sequence decomposition, which disaggregates the input series into trend and seasonal components, allowing for a more precise modeling of inherent sequence dependencies. Extensive experiments conducted on two real-world datasets demonstrate the superior performance of our approach compared to competitive baselines, particularly in capturing the nuanced variations in input series that are crucial for accurate IOH prediction.
Authors: Nazim Bendib, Iheb Nassim Aouadj, Riyadh Baghdadi
Abstract: Code optimization is a crucial task aimed at enhancing code performance. However, this process is often tedious and complex, highlighting the necessity for automatic code optimization techniques. Reinforcement Learning (RL), a machine learning technique, has emerged as a promising approach for tackling such complex optimization problems. In this project, we introduce the first RL environment for the MLIR compiler, dedicated to facilitating MLIR compiler research, and enabling automatic code optimization using Multi-Action Reinforcement Learning. We also propose a novel formulation of the action space as a Cartesian product of simpler action subspaces, enabling more efficient and effective optimizations. Experimental results demonstrate that our proposed environment allows for an effective optimization of MLIR operations, and yields comparable performance to TensorFlow, surpassing it in multiple cases, highlighting the potential of RL-based optimization in compiler frameworks.
Authors: Andrew Antonopoulos
Abstract: This study was the 2nd part of my dissertation for my master degree and compared the power consumption using the Comma-Separated-Values (CSV) and parquet dataset format with the default floating point (32bit) and Nvidia mixed precision (16bit and 32bit) while training a regression ML model. The same custom PC as per the 1st part, which was dedicated to the classification testing and analysis, was built to perform the experiments, and different ML hyper-parameters, such as batch size, neurons, and epochs, were chosen to build Deep Neural Networks (DNN). A benchmarking test with default hyper-parameter values for the DNN was used as a reference, while the experiments used a combination of different settings. The results were recorded in Excel, and descriptive statistics were chosen to calculate the mean between the groups and compare them using graphs and tables. The outcome was positive when using mixed precision combined with specific hyper-parameters. Compared to the benchmarking, optimising the regression models reduced the power consumption between 7 and 11 Watts. The regression results show that while mixed precision can help improve power consumption, we must carefully consider the hyper-parameters. A high number of batch sizes and neurons will negatively affect power consumption. However, this research required inferential statistics, specifically ANOVA and T-test, to compare the relationship between the means. The results reported no statistical significance between the means in the regression tests and accepted H0. Therefore, choosing different ML techniques and the Parquet dataset format will not improve the computational power consumption and the overall ML carbon footprint. However, a more extensive implementation with a cluster of GPUs can increase the sample size significantly, as it is an essential factor and can change the outcome of the statistical analysis.
Authors: Alejandro Polo-Molina, David Alfaya, Jose Portela
Abstract: Artificial Neural Networks (ANNs) have significantly advanced various fields by effectively recognizing patterns and solving complex problems. Despite these advancements, their interpretability remains a critical challenge, especially in applications where transparency and accountability are essential. To address this, explainable AI (XAI) has made progress in demystifying ANNs, yet interpretability alone is often insufficient. In certain applications, model predictions must align with expert-imposed requirements, sometimes exemplified by partial monotonicity constraints. While monotonic approaches are found in the literature for traditional Multi-layer Perceptrons (MLPs), they still face difficulties in achieving both interpretability and certified partial monotonicity. Recently, the Kolmogorov-Arnold Network (KAN) architecture, based on learnable activation functions parametrized as splines, has been proposed as a more interpretable alternative to MLPs. Building on this, we introduce a novel ANN architecture called MonoKAN, which is based on the KAN architecture and achieves certified partial monotonicity while enhancing interpretability. To achieve this, we employ cubic Hermite splines, which guarantee monotonicity through a set of straightforward conditions. Additionally, by using positive weights in the linear combinations of these splines, we ensure that the network preserves the monotonic relationships between input and output. Our experiments demonstrate that MonoKAN not only enhances interpretability but also improves predictive performance across the majority of benchmarks, outperforming state-of-the-art monotonic MLP approaches.
Authors: Carine Hue, Marc Boull\'e
Abstract: We study supervised classification for datasets with a very large number of input variables. The na\"ive Bayes classifier is attractive for its simplicity, scalability and effectiveness in many real data applications. When the strong na\"ive Bayes assumption of conditional independence of the input variables given the target variable is not valid, variable selection and model averaging are two common ways to improve the performance. In the case of the na\"ive Bayes classifier, the resulting weighting scheme on the models reduces to a weighting scheme on the variables. Here we focus on direct estimation of variable weights in such a weighted na\"ive Bayes classifier. We propose a sparse regularization of the model log-likelihood, which takes into account prior penalization costs related to each input variable. Compared to averaging based classifiers used up until now, our main goal is to obtain parsimonious robust models with less variables and equivalent performance. The direct estimation of the variable weights amounts to a non-convex optimization problem for which we propose and compare several two-stage algorithms. First, the criterion obtained by convex relaxation is minimized using several variants of standard gradient methods. Then, the initial non-convex optimization problem is solved using local optimization methods initialized with the result of the first stage. The various proposed algorithms result in optimization-based weighted na\"ive Bayes classifiers, that are evaluated on benchmark datasets and positioned w.r.t. to a reference averaging-based classifier.
Authors: Nikolai Merkel, Pierre Toussing, Ruben Mayer, Hans-Arno Jacobsen
Abstract: Graph neural networks (GNNs) are a type of neural network capable of learning on graph-structured data. However, training GNNs on large-scale graphs is challenging due to iterative aggregations of high-dimensional features from neighboring vertices within sparse graph structures combined with neural network operations. The sparsity of graphs frequently results in suboptimal memory access patterns and longer training time. Graph reordering is an optimization strategy aiming to improve the graph data layout. It has shown to be effective to speed up graph analytics workloads, but its effect on the performance of GNN training has not been investigated yet. The generalization of reordering to GNN performance is nontrivial, as multiple aspects must be considered: GNN hyper-parameters such as the number of layers, the number of hidden dimensions, and the feature size used in the GNN model, neural network operations, large intermediate vertex states, and GPU acceleration. In our work, we close this gap by performing an empirical evaluation of 12 reordering strategies in two state-of-the-art GNN systems, PyTorch Geometric and Deep Graph Library. Our results show that graph reordering is effective in reducing training time for CPU- and GPU-based training, respectively. Further, we find that GNN hyper-parameters influence the effectiveness of reordering, that reordering metrics play an important role in selecting a reordering strategy, that lightweight reordering performs better for GPU-based than for CPU-based training, and that invested reordering time can in many cases be amortized.
Authors: Harsh Choudhary, Chandan Gupta, Vyacheslav kungrutsev, Melvin Leok, Georgios Korpas
Abstract: Many important physical systems can be described as the evolution of a Hamiltonian system, which has the important property of being conservative, that is, energy is conserved throughout the evolution. Physics Informed Neural Networks and in particular Hamiltonian Neural Networks have emerged as a mechanism to incorporate structural inductive bias into the NN model. By ensuring physical invariances are conserved, the models exhibit significantly better sample complexity and out-of-distribution accuracy than standard NNs. Learning the Hamiltonian as a function of its canonical variables, typically position and velocity, from sample observations of the system thus becomes a critical task in system identification and long-term prediction of system behavior. However, to truly preserve the long-run physical conservation properties of Hamiltonian systems, one must use symplectic integrators for a forward pass of the system's simulation. While symplectic schemes have been used in the literature, they are thus far limited to situations when they reduce to explicit algorithms, which include the case of separable Hamiltonians or augmented non-separable Hamiltonians. We extend it to generalized non-separable Hamiltonians, and noting the self-adjoint property of symplectic integrators, we bypass computationally intensive backpropagation through an ODE solver. We show that the method is robust to noise and provides a good approximation of the system Hamiltonian when the state variables are sampled from a noisy observation. In the numerical results, we show the performance of the method concerning Hamiltonian reconstruction and conservation, indicating its particular advantage for non-separable systems.
Authors: Xin Li, Anand Sarwate
Abstract: Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs, VQ-GANs, etc.), which has demonstrated state-of-the-art performance in many modern generative modeling applications. Quantizing the latent space has been justified by the assumption that the data themselves are inherently discrete in the latent space (like pixel values). In this paper, we propose an alternative representation of the latent space by relaxing the structural assumption than the VQ formulation. Specifically, we assume that the latent space can be approximated by a union of subspaces model corresponding to a dictionary-based representation under a sparsity constraint. The dictionary is learned/updated during the training process. We apply this approach to look at two models: Dictionary Learning Variational Autoencoders (DL-VAEs) and DL-VAEs with Generative Adversarial Networks (DL-GANs). We show empirically that our more latent space is more expressive and has leads to better representations than the VQ approach in terms of reconstruction quality at the expense of a small computational overhead for the latent space computation. Our results thus suggest that the true benefit of the VQ approach might not be from discretization of the latent space, but rather the lossy compression of the latent space. We confirm this hypothesis by showing that our sparse representations also address the codebook collapse issue as found common in VQ-family models.
Authors: Aidan J. Hughes, Keith Worden, Nikolaos Dervilis, Timothy J. Rogers
Abstract: Classification models are a key component of structural digital twin technologies used for supporting asset management decision-making. An important consideration when developing classification models is the dimensionality of the input, or feature space, used. If the dimensionality is too high, then the `curse of dimensionality' may rear its ugly head; manifesting as reduced predictive performance. To mitigate such effects, practitioners can employ dimensionality reduction techniques. The current paper formulates a decision-theoretic approach to dimensionality reduction for structural asset management. In this approach, the aim is to keep incurred misclassification costs to a minimum, as the dimensionality is reduced and discriminatory information may be lost. This formulation is constructed as an eigenvalue problem, with separabilities between classes weighted according to the cost of misclassifying them when considered in the context of a decision process. The approach is demonstrated using a synthetic case study.
Authors: Yipeng Liang, Qimei Chen, Hao Jiang
Abstract: With the emergence of integrated sensing, communication, and computation (ISCC) in the upcoming 6G era, federated learning with ISCC (FL-ISCC), integrating sample collection, local training, and parameter exchange and aggregation, has garnered increasing interest for enhancing training efficiency. Currently, FL-ISCC primarily includes two algorithms: FedAVG-ISCC and FedSGD-ISCC. However, the theoretical understanding of the performance and advantages of these algorithms remains limited. To address this gap, we investigate a general FL-ISCC framework, implementing both FedAVG-ISCC and FedSGD-ISCC. We experimentally demonstrate the substantial potential of the ISCC framework in reducing latency and energy consumption in FL. Furthermore, we provide a theoretical analysis and comparison. The results reveal that:1) Both sample collection and communication errors negatively impact algorithm performance, highlighting the need for careful design to optimize FL-ISCC applications. 2) FedAVG-ISCC performs better than FedSGD-ISCC under IID data due to its advantage with multiple local updates. 3) FedSGD-ISCC is more robust than FedAVG-ISCC under non-IID data, where the multiple local updates in FedAVG-ISCC worsen performance as non-IID data increases. FedSGD-ISCC maintains performance levels similar to IID conditions. 4) FedSGD-ISCC is more resilient to communication errors than FedAVG-ISCC, which suffers from significant performance degradation as communication errors increase.Extensive simulations confirm the effectiveness of the FL-ISCC framework and validate our theoretical analysis.
Authors: Dahlia Devapriya, Sheetal Kalyani
Abstract: In reconfigurable intelligent surface (RIS) aided systems, the joint optimization of the precoder matrix at the base station and the phase shifts of the RIS elements involves significant complexity. In this paper, we propose a complex-valued, geometry aware meta-learning neural network that maximizes the weighted sum rate in a multi-user multiple input single output system. By leveraging the complex circle geometry for phase shifts and spherical geometry for the precoder, the optimization occurs on Riemannian manifolds, leading to faster convergence. We use a complex-valued neural network for phase shifts and an Euler inspired update for the precoder network. Our approach outperforms existing neural network-based algorithms, offering higher weighted sum rates, lower power consumption, and significantly faster convergence. Specifically, it converges faster by nearly 100 epochs, with a 0.7 bps improvement in weighted sum rate and a 1.8 dBm power gain when compared with existing work.
Authors: Divij Gupta, Anubhav Bhatti, Surajsinh Parmar
Abstract: Time Series Foundation Models (TSFMs) have recently garnered attention for their ability to model complex, large-scale time series data across domains such as retail, finance, and transportation. However, their application to sensitive, domain-specific fields like healthcare remains challenging, primarily due to the difficulty of fine-tuning these models for specialized, out-of-domain tasks with scarce publicly available datasets. In this work, we explore the use of Parameter-Efficient Fine-Tuning (PEFT) techniques to address these limitations, focusing on healthcare applications, particularly ICU vitals forecasting for sepsis patients. We introduce and evaluate two selective (BitFit and LayerNorm Tuning) and two additive (VeRA and FourierFT) PEFT techniques on multiple configurations of the Chronos TSFM for forecasting vital signs of sepsis patients. Our comparative analysis demonstrates that some of these PEFT methods outperform LoRA in terms of parameter efficiency and domain adaptation, establishing state-of-the-art (SOTA) results in ICU vital forecasting tasks. Interestingly, FourierFT applied to the Chronos (Tiny) variant surpasses the SOTA model while fine-tuning only 2,400 parameters compared to the 700K parameters of the benchmark.
Authors: Nikhil Vyas, Depen Morwani, Rosie Zhao, Itai Shapira, David Brandfonbrener, Lucas Janson, Sham Kakade
Abstract: There is growing evidence of the effectiveness of Shampoo, a higher-order preconditioning method, over Adam in deep learning optimization tasks. However, Shampoo's drawbacks include additional hyperparameters and computational overhead when compared to Adam, which only updates running averages of first- and second-moment quantities. This work establishes a formal connection between Shampoo (implemented with the 1/2 power) and Adafactor -- a memory-efficient approximation of Adam -- showing that Shampoo is equivalent to running Adafactor in the eigenbasis of Shampoo's preconditioner. This insight leads to the design of a simpler and computationally efficient algorithm: $\textbf{S}$hampo$\textbf{O}$ with $\textbf{A}$dam in the $\textbf{P}$reconditioner's eigenbasis (SOAP). With regards to improving Shampoo's computational efficiency, the most straightforward approach would be to simply compute Shampoo's eigendecomposition less frequently. Unfortunately, as our empirical results show, this leads to performance degradation that worsens with this frequency. SOAP mitigates this degradation by continually updating the running average of the second moment, just as Adam does, but in the current (slowly changing) coordinate basis. Furthermore, since SOAP is equivalent to running Adam in a rotated space, it introduces only one additional hyperparameter (the preconditioning frequency) compared to Adam. We empirically evaluate SOAP on language model pre-training with 360m and 660m sized models. In the large batch regime, SOAP reduces the number of iterations by over 40% and wall clock time by over 35% compared to AdamW, with approximately 20% improvements in both metrics compared to Shampoo. An implementation of SOAP is available at https://github.com/nikhilvyas/SOAP.
Authors: Winnie Chow, Lauren Gardiner, Haraldur T. Hallgr\'imsson, Maxwell A. Xu, Shirley You Ren
Abstract: Multi-modal large language models (MLLMs) have enabled numerous advances in understanding and reasoning in domains like vision, but we have not yet seen this broad success for time-series. Although prior works on time-series MLLMs have shown promising performance in time-series forecasting, very few works show how an LLM could be used for time-series reasoning in natural language. We propose a novel multi-modal time-series LLM approach that learns generalizable information across various domains with powerful zero-shot performance. First, we train a lightweight time-series encoder on top of an LLM to directly extract time-series information. Then, we fine-tune our model with chain-of-thought augmented time-series tasks to encourage the model to generate reasoning paths. We show that our model learns a latent representation that reflects specific time-series features (e.g. slope, frequency), as well as outperforming GPT-4o on a set of zero-shot reasoning tasks on a variety of domains.
Authors: Jiaqi Ding, Tingting Dan, Ziquan Wei, Hyuna Cho, Paul J. Laurienti, Won Hwa Kim, Guorong Wu
Abstract: An unprecedented amount of existing functional Magnetic Resonance Imaging (fMRI) data provides a new opportunity to understand the relationship between functional fluctuation and human cognition/behavior using a data-driven approach. To that end, tremendous efforts have been made in machine learning to predict cognitive states from evolving volumetric images of blood-oxygen-level-dependent (BOLD) signals. Due to the complex nature of brain function, however, the evaluation on learning performance and discoveries are not often consistent across current state-of-the-arts (SOTA). By capitalizing on large-scale existing neuroimaging data (34,887 data samples from six public databases), we seek to establish a well-founded empirical guideline for designing deep models for functional neuroimages by linking the methodology underpinning with knowledge from the neuroscience domain. Specifically, we put the spotlight on (1) What is the current SOTA performance in cognitive task recognition and disease diagnosis using fMRI? (2) What are the limitations of current deep models? and (3) What is the general guideline for selecting the suitable machine learning backbone for new neuroimaging applications? We have conducted a comprehensive evaluation and statistical analysis, in various settings, to answer the above outstanding questions.
Authors: Alexandre Benatti, Luciano da F. Costa
Abstract: The subject of features normalization plays an important central role in data representation, characterization, visualization, analysis, comparison, classification, and modeling, as it can substantially influence and be influenced by all of these activities and respective aspects. The selection of an appropriate normalization method needs to take into account the type and characteristics of the involved features, the methods to be used subsequently for the just mentioned data processing, as well as the specific questions being considered. After briefly considering how normalization constitutes one of the many interrelated parts typically involved in data analysis and modeling, the present work addressed the important issue of feature normalization from the perspective of uniform and proportional (right skewed) features and comparison operations. More general right skewed features are also considered in an approximated manner. Several concepts, properties, and results are described and discussed, including the description of a duality relationship between uniform and proportional feature spaces and respective comparisons, specifying conditions for consistency between comparisons in each of the two domains. Two normalization possibilities based on non-centralized dispersion of features are also presented, and also described is a modified version of the Jaccard similarity index which incorporates intrinsically normalization. Preliminary experiments are presented in order to illustrate the developed concepts and methods.
Authors: Panfeng Li, Mohamed Abouelenien, Rada Mihalcea, Zhicheng Ding, Qikai Yang, Yiming Zhou
Abstract: Deception detection is gaining increasing interest due to ethical and security concerns. This paper explores the application of convolutional neural networks for the purpose of multimodal deception detection. We use a dataset built by interviewing 104 subjects about two topics, with one truthful and one falsified response from each subject about each topic. In particular, we make three main contributions. First, we extract linguistic and physiological features from this data to train and construct the neural network models. Second, we propose a fused convolutional neural network model using both modalities in order to achieve an improved overall performance. Third, we compare our new approach with earlier methods designed for multimodal deception detection. We find that our system outperforms regular classification methods; our results indicate the feasibility of using neural networks for deception detection even in the presence of limited amounts of data.
Authors: Houssem Gasmi (DISP), Jannik Laval (DISP), Abdelaziz Bouras (DISP)
Abstract: The automated and timely conversion of cybersecurity information from unstructured online sources, such as blogs and articles to more formal representations has become a necessity for many applications in the domain nowadays. Named Entity Recognition (NER) is one of the early phases towards this goal. It involves the detection of the relevant domain entities, such as product, version, attack name, etc. in technical documents. Although generally considered a simple task in the information extraction field, it is quite challenging in some domains like cybersecurity because of the complex structure of its entities. The state of the art methods require time-consuming and labor intensive feature engineering that describes the properties of the entities, their context, domain knowledge, and linguistic characteristics. The model demonstrated in this paper is domain independent and does not rely on any features specific to the entities in the cybersecurity domain, hence does not require expert knowledge to perform feature engineering. The method used relies on a type of recurrent neural networks called Long Short-Term Memory (LSTM) and the Conditional Random Fields (CRFs) method. The results we obtained showed that this method outperforms the state of the art methods given an annotated corpus of a decent size.
Authors: Wenjia Xie, Rui Zhou, Hao Wang, Tingjia Shen, Enhong Chen
Abstract: Sequential recommendation has attracted increasing attention due to its ability to accurately capture the dynamic changes in user interests. We have noticed that generative models, especially diffusion models, which have achieved significant results in fields like image and audio, hold considerable promise in the field of sequential recommendation. However, existing sequential recommendation methods based on diffusion models are constrained by a prior distribution limited to Gaussian distribution, hindering the possibility of introducing user-specific information for each recommendation and leading to information loss. To address these issues, we introduce the Schr\"odinger Bridge into diffusion-based sequential recommendation models, creating the SdifRec model. This allows us to replace the Gaussian prior of the diffusion model with the user's current state, directly modeling the process from a user's current state to the target recommendation. Additionally, to better utilize collaborative information in recommendations, we propose an extended version of SdifRec called con-SdifRec, which utilizes user clustering information as a guiding condition to further enhance the posterior distribution. Finally, extensive experiments on multiple public benchmark datasets have demonstrated the effectiveness of SdifRec and con-SdifRec through comparison with several state-of-the-art methods. Further in-depth analysis has validated their efficiency and robustness.
Authors: Jonathan Wellington Morris, Vishrut Shah, Alex Besanceney, Daksh Shah, Leilani H. Gilpin
Abstract: Sim-to real gap in Reinforcement Learning is when a model trained in a simulator does not translate to the real world. This is a problem for Autonomous Vehicles (AVs) as vehicle dynamics can vary from simulation to reality, and also from vehicle to vehicle. Slug Mobile is a one tenth scale autonomous vehicle created to help address the sim-to-real gap for AVs by acting as a test-bench to develop models that can easily scale from one vehicle to another. In addition to traditional sensors found in other one tenth scale AVs, we have also included a Dynamic Vision Sensor so we can train Spiking Neural Networks running on neuromorphic hardware.
Authors: Shu Hu, George H. Chen
Abstract: We propose a general approach for encouraging fairness in survival analysis models based on minimizing a worst-case error across all subpopulations that occur with at least a user-specified probability. This approach can be used to convert many existing survival analysis models into ones that simultaneously encourage fairness, without requiring the user to specify which attributes or features to treat as sensitive in the training loss function. From a technical standpoint, our approach applies recent developments of distributionally robust optimization (DRO) to survival analysis. The complication is that existing DRO theory uses a training loss function that decomposes across contributions of individual data points, i.e., any term that shows up in the loss function depends only on a single training point. This decomposition does not hold for commonly used survival loss functions, including for the Cox proportional hazards model, its deep neural network variants, and many other recently developed models that use loss functions involving ranking or similarity score calculations. We address this technical hurdle using a sample splitting strategy. We demonstrate our sample splitting DRO approach by using it to create fair versions of a diverse set of existing survival analysis models including the Cox model (and its deep variant DeepSurv), the discrete-time model DeepHit, and the neural ODE model SODEN. We also establish a finite-sample theoretical guarantee to show what our sample splitting DRO loss converges to. For the Cox model, we further derive an exact DRO approach that does not use sample splitting. For all the models that we convert into DRO variants, we show that the DRO variants often score better on recently established fairness metrics (without incurring a significant drop in accuracy) compared to existing survival analysis fairness regularization techniques.
Authors: Leand Thaqi, Arbnor Halili, Kamer Vishi, Blerim Rexha
Abstract: The growth of digitalization services via web browsers has simplified our daily routine of doing business. But at the same time, it has made the web browser very attractive for several cyber-attacks. Web phishing is a well-known cyberattack that is used by attackers camouflaging as trustworthy web servers to obtain sensitive user information such as credit card numbers, bank information, personal ID, social security number, and username and passwords. In recent years many techniques have been developed to identify the authentic web pages that users visit and warn them when the webpage is phishing. In this paper, we have developed an extension for Chrome the most favorite web browser, that will serve as a middleware between the user and phishing websites. The Chrome extension named "NoPhish" shall identify a phishing webpage based on several Machine Learning techniques. We have used the training dataset from "PhishTank" and extracted the 22 most popular features as rated by the Alexa database. The training algorithms used are Random Forest, Support Vector Machine, and k-Nearest Neighbor. The performance results show that Random Forest delivers the best precision.
Authors: Alec Wilson, William Holmes, Ryan Menzies, Kez Smithson Whitehead
Abstract: In previous work, the IPMSRL environment (Integrated Platform Management System Reinforcement Learning environment) was developed with the aim of training defensive RL agents in a simulator representing a subset of an IPMS on a maritime vessel under a cyber-attack. This paper extends the use of IPMSRL to enhance realism including the additional dynamics of false positive alerts and alert delay. Applying curriculum learning, in the most difficult environment tested, resulted in an episode reward mean increasing from a baseline result of -2.791 to -0.569. Applying action masking, in the most difficult environment tested, resulted in an episode reward mean increasing from a baseline result of -2.791 to -0.743. Importantly, this level of performance was reached in less than 1 million timesteps, which was far more data efficient than vanilla PPO which reached a lower level of performance after 2.5 million timesteps. The training method which resulted in the highest level of performance observed in this paper was a combination of the application of curriculum learning and action masking, with a mean episode reward of 0.137. This paper also introduces a basic hardcoded defensive agent encoding a representation of cyber security best practice, which provides context to the episode reward mean figures reached by the RL agents. The hardcoded agent managed an episode reward mean of -1.895. This paper therefore shows that applications of curriculum learning and action masking, both independently and in tandem, present a way to overcome the complex real-world dynamics that are present in operational technology cyber security threat remediation.
Authors: Ming-Jian Li, Yanping Lian, Zhanshan Cheng, Lehui Li, Zhidong Wang, Ruxin Gao, Daining Fang
Abstract: Numerical simulation is powerful to study nonlinear solid mechanics problems. However, mesh-based or particle-based numerical methods suffer from the common shortcoming of being time-consuming, particularly for complex problems with real-time analysis requirements. This study presents a clustering adaptive Gaussian process regression (CAG) method aiming for real-time prediction for nonlinear structural responses in solid mechanics. It is a data-driven machine learning method featuring a small sample size, high accuracy, and high efficiency, leveraging nonlinear structural response patterns. Similar to the traditional Gaussian process regression (GPR) method, it operates in offline and online stages. In the offline stage, an adaptive sample generation technique is introduced to cluster datasets into distinct patterns for demand-driven sample allocation. This ensures comprehensive coverage of the critical samples for the solution space of interest. In the online stage, following the divide-and-conquer strategy, a pre-prediction classification categorizes problems into predefined patterns sequentially predicted by the trained multi-pattern Gaussian process regressor. In addition, dimension reduction and restoration techniques are employed in the proposed method to enhance its efficiency. A set of problems involving material, geometric, and boundary condition nonlinearities is presented to demonstrate the CAG method's abilities. The proposed method can offer predictions within a second and attain high precision with only about 20 samples within the context of this study, outperforming the traditional GPR using uniformly distributed samples for error reductions ranging from 1 to 3 orders of magnitude. The CAG method is expected to offer a powerful tool for real-time prediction of nonlinear solid mechanical problems and shed light on the complex nonlinear structural response pattern.
Authors: Md Tauseef Alam, Raju Halder, Abyayananda Maiti
Abstract: The large-scale deployment of Solidity smart contracts on the Ethereum mainnet has increasingly attracted financially-motivated attackers in recent years. A few now-infamous attacks in Ethereum's history includes DAO attack in 2016 (50 million dollars lost), Parity Wallet hack in 2017 (146 million dollars locked), Beautychain's token BEC in 2018 (900 million dollars market value fell to 0), and NFT gaming blockchain breach in 2022 ($600 million in Ether stolen). This paper presents a comprehensive investigation of the use of large language models (LLMs) and their capabilities in detecting OWASP Top Ten vulnerabilities in Solidity. We introduce a novel, class-balanced, structured, and labeled dataset named VulSmart, which we use to benchmark and compare the performance of open-source LLMs such as CodeLlama, Llama2, CodeT5 and Falcon, alongside closed-source models like GPT-3.5 Turbo and GPT-4o Mini. Our proposed SmartVD framework is rigorously tested against these models through extensive automated and manual evaluations, utilizing BLEU and ROUGE metrics to assess the effectiveness of vulnerability detection in smart contracts. We also explore three distinct prompting strategies-zero-shot, few-shot, and chain-of-thought-to evaluate the multi-class classification and generative capabilities of the SmartVD framework. Our findings reveal that SmartVD outperforms its open-source counterparts and even exceeds the performance of closed-source base models like GPT-3.5 and GPT-4 Mini. After fine-tuning, the closed-source models, GPT-3.5 Turbo and GPT-4o Mini, achieved remarkable performance with 99% accuracy in detecting vulnerabilities, 94% in identifying their types, and 98% in determining severity. Notably, SmartVD performs best with the `chain-of-thought' prompting technique, whereas the fine-tuned closed-source models excel with the `zero-shot' prompting approach.
Authors: Mohamed Sobhi Jabal, Pranav Warman, Jikai Zhang, Kartikeye Gupta, Ayush Jain, Maciej Mazurowski, Walter Wiggins, Kirti Magudia, Evan Calabrese
Abstract: Purpose: To develop and evaluate an automated system for extracting structured clinical information from unstructured radiology and pathology reports using open-weights large language models (LMs) and retrieval augmented generation (RAG), and to assess the effects of model configuration variables on extraction performance. Methods and Materials: The study utilized two datasets: 7,294 radiology reports annotated for Brain Tumor Reporting and Data System (BT-RADS) scores and 2,154 pathology reports annotated for isocitrate dehydrogenase (IDH) mutation status. An automated pipeline was developed to benchmark the performance of various LMs and RAG configurations. The impact of model size, quantization, prompting strategies, output formatting, and inference parameters was systematically evaluated. Results: The best performing models achieved over 98% accuracy in extracting BT-RADS scores from radiology reports and over 90% for IDH mutation status extraction from pathology reports. The top model being medical fine-tuned llama3. Larger, newer, and domain fine-tuned models consistently outperformed older and smaller models. Model quantization had minimal impact on performance. Few-shot prompting significantly improved accuracy. RAG improved performance for complex pathology reports but not for shorter radiology reports. Conclusions: Open LMs demonstrate significant potential for automated extraction of structured clinical data from unstructured clinical reports with local privacy-preserving application. Careful model selection, prompt engineering, and semi-automated optimization using annotated data are critical for optimal performance. These approaches could be reliable enough for practical use in research workflows, highlighting the potential for human-machine collaboration in healthcare data extraction.
Authors: Justin Lyu Kim, Kyoungwan Woo
Abstract: In the age of powerful diffusion models such as DALL-E and Stable Diffusion, many in the digital art community have suffered style mimicry attacks due to fine-tuning these models on their works. The ability to mimic an artist's style via text-to-image diffusion models raises serious ethical issues, especially without explicit consent. Glaze, a tool that applies various ranges of perturbations to digital art, has shown significant success in preventing style mimicry attacks, at the cost of artifacts ranging from imperceptible noise to severe quality degradation. The release of Glaze has sparked further discussions regarding the effectiveness of similar protection methods. In this paper, we propose GLEAN- applying I2I generative networks to strip perturbations from Glazed images, evaluating the performance of style mimicry attacks before and after GLEAN on the results of Glaze. GLEAN aims to support and enhance Glaze by highlighting its limitations and encouraging further development.
Authors: Binghao Yan, Yunbi Nam, Lingyao Li, Rebecca A. Deek, Hongzhe Li, Siyuan Ma
Abstract: Recent advancements in deep learning, particularly large language models (LLMs), made a significant impact on how researchers study microbiome and metagenomics data. Microbial protein and genomic sequences, like natural languages, form a language of life, enabling the adoption of LLMs to extract useful insights from complex microbial ecologies. In this paper, we review applications of deep learning and language models in analyzing microbiome and metagenomics data. We focus on problem formulations, necessary datasets, and the integration of language modeling techniques. We provide an extensive overview of protein/genomic language modeling and their contributions to microbiome studies. We also discuss applications such as novel viromics language modeling, biosynthetic gene cluster prediction, and knowledge integration for metagenomics studies.
Authors: Pranav Jeevan, Neeraj Nixon, Amit Sethi
Abstract: Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks ($4\times$). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR.
Authors: Shengchao Liu, Divin Yan, Weitao Du, Weiyang Liu, Zhuoxinran Li, Hongyu Guo, Christian Borgs, Jennifer Chayes, Anima Anandkumar
Abstract: Artificial intelligence models have shown great potential in structure-based drug design, generating ligands with high binding affinities. However, existing models have often overlooked a crucial physical constraint: atoms must maintain a minimum pairwise distance to avoid separation violation, a phenomenon governed by the balance of attractive and repulsive forces. To mitigate such separation violations, we propose NucleusDiff. It models the interactions between atomic nuclei and their surrounding electron clouds by enforcing the distance constraint between the nuclei and manifolds. We quantitatively evaluate NucleusDiff using the CrossDocked2020 dataset and a COVID-19 therapeutic target, demonstrating that NucleusDiff reduces violation rate by up to 100.00% and enhances binding affinity by up to 22.16%, surpassing state-of-the-art models for structure-based drug design. We also provide qualitative analysis through manifold sampling, visually confirming the effectiveness of NucleusDiff in reducing separation violations and improving binding affinities.
Authors: Anna Glazkova, Dmitry Morozov
Abstract: Keyphrase selection plays a pivotal role within the domain of scholarly texts, facilitating efficient information retrieval, summarization, and indexing. In this work, we explored how to apply fine-tuned generative transformer-based models to the specific task of keyphrase selection within Russian scientific texts. We experimented with four distinct generative models, such as ruT5, ruGPT, mT5, and mBART, and evaluated their performance in both in-domain and cross-domain settings. The experiments were conducted on the texts of Russian scientific abstracts from four domains: mathematics \& computer science, history, medicine, and linguistics. The use of generative models, namely mBART, led to gains in in-domain performance (up to 4.9\% in BERTScore, 9.0\% in ROUGE-1, and 12.2\% in F1-score) over three keyphrase extraction baselines for the Russian language. Although the results for cross-domain usage were significantly lower, they still demonstrated the capability to surpass baseline performances in several cases, underscoring the promising potential for further exploration and refinement in this research field.
Authors: Jonathan Rosenthal, Shanchao Liang, Kevin Zhang, Lin Tan
Abstract: Machine Learning as a Service (MLaaS) is often provided as a pay-per-query, black-box system to clients. Such a black-box approach not only hinders open replication, validation, and interpretation of model results, but also makes it harder for white-hat researchers to identify vulnerabilities in the MLaaS systems. Model extraction is a promising technique to address these challenges by reverse-engineering black-box models. Since training data is typically unavailable for MLaaS models, this paper focuses on the realistic version of it: data-free model extraction. We propose a data-free model extraction approach, CaBaGe, to achieve higher model extraction accuracy with a small number of queries. Our innovations include (1) a novel experience replay for focusing on difficult training samples; (2) an ensemble of generators for steadily producing diverse synthetic data; and (3) a selective filtering process for querying the victim model with harder, more balanced samples. In addition, we create a more realistic setting, for the first time, where the attacker has no knowledge of the number of classes in the victim training data, and create a solution to learn the number of classes on the fly. Our evaluation shows that CaBaGe outperforms existing techniques on seven datasets -- MNIST, FMNIST, SVHN, CIFAR-10, CIFAR-100, ImageNet-subset, and Tiny ImageNet -- with an accuracy improvement of the extracted models by up to 43.13%. Furthermore, the number of queries required to extract a clone model matching the final accuracy of prior work is reduced by up to 75.7%.
Authors: Raika Karimi, Faezeh Faez, Yingxue Zhang, Xing Li, Lei Chen, Mingxuan Yuan, Mahdi Biparva
Abstract: Contemporary hardware design benefits from the abstraction provided by high-level logic gates, streamlining the implementation of logic circuits. Logic Synthesis Optimization (LSO) operates at one level of abstraction within the Electronic Design Automation (EDA) workflow, targeting improvements in logic circuits with respect to performance metrics such as size and speed in the final layout. Recent trends in the field show a growing interest in leveraging Machine Learning (ML) for EDA, notably through ML-guided logic synthesis utilizing policy-based Reinforcement Learning (RL) methods.Despite these advancements, existing models face challenges such as overfitting and limited generalization, attributed to constrained public circuits and the expressiveness limitations of graph encoders. To address these hurdles, and tackle data scarcity issues, we introduce LSOformer, a novel approach harnessing Autoregressive transformer models and predictive SSL to predict the trajectory of Quality of Results (QoR). LSOformer integrates cross-attention modules to merge insights from circuit graphs and optimization sequences, thereby enhancing prediction accuracy for QoR metrics. Experimental studies validate the effectiveness of LSOformer, showcasing its superior performance over baseline architectures in QoR prediction tasks, where it achieves improvements of 5.74%, 4.35%, and 17.06% on the EPFL, OABCD, and proprietary circuits datasets, respectively, in inductive setup.
Authors: Etron Yee Chun Tsoi
Abstract: Windstorms significantly impact the UK, causing extensive damage to property, disrupting society, and potentially resulting in loss of life. Accurate modelling and understanding of such events are essential for effective risk assessment and mitigation. However, the rarity of extreme windstorms results in limited observational data, which poses significant challenges for comprehensive analysis and insurance modelling. This dissertation explores the application of generative models to produce realistic synthetic wind field data, aiming to enhance the robustness of current CAT models used in the insurance industry. The study utilises hourly reanalysis data from the ERA5 dataset, which covers the period from 1940 to 2022. Three models, including standard GANs, WGAN-GP, and U-net diffusion models, were employed to generate high-quality wind maps of the UK. These models are then evaluated using multiple metrics, including SSIM, KL divergence, and EMD, with some assessments performed in a reduced dimensionality space using PCA. The results reveal that while all models are effective in capturing the general spatial characteristics, each model exhibits distinct strengths and weaknesses. The standard GAN introduced more noise compared to the other models. The WGAN-GP model demonstrated superior performance, particularly in replicating statistical distributions. The U-net diffusion model produced the most visually coherent outputs but struggled slightly in replicating peak intensities and their statistical variability. This research underscores the potential of generative models in supplementing limited reanalysis datasets with synthetic data, providing valuable tools for risk assessment and catastrophe modelling. However, it is important to select appropriate evaluation metrics that assess different aspects of the generated outputs. Future work could refine these models and incorporate more ...
Authors: Yifan Wang, David Stevens, Pranay Shah, Wenwen Jiang, Miao Liu, Xu Chen, Robert Kuo, Na Li, Boying Gong, Daniel Lee, Jiabo Hu, Ning Zhang, Bob Kamma
Abstract: The growing demand for AI training data has transformed data annotation into a global industry, but traditional approaches relying on human annotators are often time-consuming, labor-intensive, and prone to inconsistent quality. We propose the Model-in-the-Loop (MILO) framework, which integrates AI/ML models into the annotation process. Our research introduces a collaborative paradigm that leverages the strengths of both professional human annotators and large language models (LLMs). By employing LLMs as pre-annotation and real-time assistants, and judges on annotator responses, MILO enables effective interaction patterns between human annotators and LLMs. Three empirical studies on multimodal data annotation demonstrate MILO's efficacy in reducing handling time, improving data quality, and enhancing annotator experiences. We also introduce quality rubrics for flexible evaluation and fine-grained feedback on open-ended annotations. The MILO framework has implications for accelerating AI/ML development, reducing reliance on human annotation alone, and promoting better alignment between human and machine values.
Authors: Yanan Jian, Fuxun Yu, Qi Zhang, William Levine, Brandon Dubbs, Nikolaos Karianakis
Abstract: This paper presents a novel way of online adapting any off-the-shelf object detection model to a novel domain without retraining the detector model. Inspired by how humans quickly learn knowledge of a new subject (e.g., memorization), we allow the detector to look up similar object concepts from memory during test time. This is achieved through a retrieval augmented classification (RAC) module together with a memory bank that can be flexibly updated with new domain knowledge. We experimented with various off-the-shelf open-set detector and close-set detectors. With only a tiny memory bank (e.g., 10 images per category) and being training-free, our online learning method could significantly outperform baselines in adapting a detector to novel domains.
Authors: Som Sagar, Aditya Taparia, Harsh Mankodiya, Pranav Bidare, Yifan Zhou, Ransalu Senanayake
Abstract: Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies, lack insights into the neural networks' decision-making process. Presently, explainable AI is primarily tailored to natural language processing and computer vision, falling short in two critical aspects when applied in robots: grounding in decision-making tasks and the ability to assess trustworthiness of their explanations. In this paper, we introduce a trustworthy explainable robotics technique based on human-interpretable, high-level concepts that attribute to the decisions made by the neural network. Our proposed technique provides explanations with associated uncertainty scores by matching neural network's activations with human-interpretable visualizations. To validate our approach, we conducted a series of experiments with various simulated and real-world robot decision-making models, demonstrating the effectiveness of the proposed approach as a post-hoc, human-friendly robot learning diagnostic tool.
Authors: Kaleb Kassaw, Francesco Luzi, Leslie M. Collins, Jordan M. Malof
Abstract: Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from the view of a camera. Methods to improve performance under occlusion, including data augmentation, part-based clustering, and more inherently robust architectures, including Vision Transformer (ViT) models, have, to some extent, been evaluated on their ability to classify objects under partial occlusion. However, evaluations of these methods have largely relied on images containing artificial occlusion, which are typically computer-generated and therefore inexpensive to label. Additionally, methods are rarely compared against each other, and many methods are compared against early, now outdated, deep learning models. We contribute the Image Recognition Under Occlusion (IRUO) dataset, based on the recently developed Occluded Video Instance Segmentation (OVIS) dataset (arXiv:2102.01558). IRUO utilizes real-world and artificially occluded images to test and benchmark leading methods' robustness to partial occlusion in visual recognition tasks. In addition, we contribute the design and results of a human study using images from IRUO that evaluates human classification performance at multiple levels and types of occlusion. We find that modern CNN-based models show improved recognition accuracy on occluded images compared to earlier CNN-based models, and ViT-based models are more accurate than CNN-based models on occluded images, performing only modestly worse than human accuracy. We also find that certain types of occlusion, including diffuse occlusion, where relevant objects are seen through "holes" in occluders such as fences and leaves, can greatly reduce the accuracy of deep recognition models as compared to humans, especially those with CNN backbones.
Authors: Hao Fang, Zhe Liu, Yi Feng, Zhen Qiu, Pierre Bagnaninchi, Yunjie Yang
Abstract: Multi-frequency Electrical Impedance Tomography (mfEIT) is a promising biomedical imaging technique that estimates tissue conductivities across different frequencies. Current state-of-the-art (SOTA) algorithms, which rely on supervised learning and Multiple Measurement Vectors (MMV), require extensive training data, making them time-consuming, costly, and less practical for widespread applications. Moreover, the dependency on training data in supervised MMV methods can introduce erroneous conductivity contrasts across frequencies, posing significant concerns in biomedical applications. To address these challenges, we propose a novel unsupervised learning approach based on Multi-Branch Attention Image Prior (MAIP) for mfEIT reconstruction. Our method employs a carefully designed Multi-Branch Attention Network (MBA-Net) to represent multiple frequency-dependent conductivity images and simultaneously reconstructs mfEIT images by iteratively updating its parameters. By leveraging the implicit regularization capability of the MBA-Net, our algorithm can capture significant inter- and intra-frequency correlations, enabling robust mfEIT reconstruction without the need for training data. Through simulation and real-world experiments, our approach demonstrates performance comparable to, or better than, SOTA algorithms while exhibiting superior generalization capability. These results suggest that the MAIP-based method can be used to improve the reliability and applicability of mfEIT in various settings.
Authors: Rafael C. Pinto, Anderson R. Tavares
Abstract: This paper demonstrates that a single-layer neural network using Parametric Rectified Linear Unit (PReLU) activation can solve the XOR problem, a simple fact that has been overlooked so far. We compare this solution to the multi-layer perceptron (MLP) and the Growing Cosine Unit (GCU) activation function and explain why PReLU enables this capability. Our results show that the single-layer PReLU network can achieve 100\% success rate in a wider range of learning rates while using only three learnable parameters.
Authors: Shahnewaz Karim Sakib, Anindya Bijoy Das
Abstract: Large Language Model (LLM)-based recommendation systems provide more comprehensive recommendations than traditional systems by deeply analyzing content and user behavior. However, these systems often exhibit biases, favoring mainstream content while marginalizing non-traditional options due to skewed training data. This study investigates the intricate relationship between bias and LLM-based recommendation systems, with a focus on music, song, and book recommendations across diverse demographic and cultural groups. Through a comprehensive analysis conducted over different LLM-models, this paper evaluates the impact of bias on recommendation outcomes. Our findings reveal that bias is so deeply ingrained within these systems that even a simpler intervention like prompt engineering can significantly reduce bias, underscoring the pervasive nature of the issue. Moreover, factors like intersecting identities and contextual information, such as socioeconomic status, further amplify these biases, demonstrating the complexity and depth of the challenges faced in creating fair recommendations across different groups.
Authors: Phillip Long, Zachary Novack, Taylor Berg-Kirkpatrick, Julian McAuley
Abstract: The recent explosion of generative AI-Music systems has raised numerous concerns over data copyright, licensing music from musicians, and the conflict between open-source AI and large prestige companies. Such issues highlight the need for publicly available, copyright-free musical data, in which there is a large shortage, particularly for symbolic music data. To alleviate this issue, we present PDMX: a large-scale open-source dataset of over 250K public domain MusicXML scores collected from the score-sharing forum MuseScore, making it the largest available copyright-free symbolic music dataset to our knowledge. PDMX additionally includes a wealth of both tag and user interaction metadata, allowing us to efficiently analyze the dataset and filter for high quality user-generated scores. Given the additional metadata afforded by our data collection process, we conduct multitrack music generation experiments evaluating how different representative subsets of PDMX lead to different behaviors in downstream models, and how user-rating statistics can be used as an effective measure of data quality. Examples can be found at https://pnlong.github.io/PDMX.demo/.
Authors: S. Rohollah Hosseyni, Ali Ahmad Rahmani, S. Jamal Seyedmohammadi, Sanaz Seyedin, Arash Mohammadi
Abstract: Autoregressive models excel in modeling sequential dependencies by enforcing causal constraints, yet they struggle to capture complex bidirectional patterns due to their unidirectional nature. In contrast, mask-based models leverage bidirectional context, enabling richer dependency modeling. However, they often assume token independence during prediction, which undermines the modeling of sequential dependencies. Additionally, the corruption of sequences through masking or absorption can introduce unnatural distortions, complicating the learning process. To address these issues, we propose Bidirectional Autoregressive Diffusion (BAD), a novel approach that unifies the strengths of autoregressive and mask-based generative models. BAD utilizes a permutation-based corruption technique that preserves the natural sequence structure while enforcing causal dependencies through randomized ordering, enabling the effective capture of both sequential and bidirectional relationships. Comprehensive experiments show that BAD outperforms autoregressive and mask-based models in text-to-motion generation, suggesting a novel pre-training strategy for sequence modeling. The codebase for BAD is available on https://github.com/RohollahHS/BAD.
Authors: Xuanmeng Sha, Liyun Zhang, Tomohiro Mashita, Yuki Uranishi
Abstract: Audio-driven 3D facial animation has made immersive progress both in research and application developments. The newest approaches focus on Transformer-based methods and diffusion-based methods, however, there is still gap in the vividness and emotional expression between the generated animation and real human face. To tackle this limitation, we propose 3DFacePolicy, a diffusion policy model for 3D facial animation prediction. This method generates variable and realistic human facial movements by predicting the 3D vertex trajectory on the 3D facial template with diffusion policy instead of facial generation for every frame. It takes audio and vertex states as observations to predict the vertex trajectory and imitate real human facial expressions, which keeps the continuous and natural flow of human emotions. The experiments show that our approach is effective in variable and dynamic facial motion synthesizing.
Authors: Prateek Verma, Mert Pilanci
Abstract: Transformer architectures are the backbone of the modern AI revolution. However, they are based on simply stacking the same blocks in dozens of layers and processing information sequentially from one block to another. In this paper, we propose to challenge this and introduce adaptive computations for LLM-like setups, which allow the final layer to attend to all of the intermediate layers as it deems fit through the attention mechanism, thereby introducing computational \textbf{attention shortcuts}. These shortcuts can thus make the architecture depth and context adaptive. We showcase four different datasets, namely acoustic tokens, natural language, and symbolic music, and we achieve superior performance for GPT-like architecture. We give evidence via attention maps that the models learn complex dependencies across layers that are adaptive in context and depth depending on the input tokens.
Authors: Hadley Black, Euiwoong Lee, Arya Mazumdar, Barna Saha
Abstract: Recovering the underlying clustering of a set $U$ of $n$ points by asking pair-wise same-cluster queries has garnered significant interest in the last decade. Given a query $S \subset U$, $|S|=2$, the oracle returns yes if the points are in the same cluster and no otherwise. For adaptive algorithms with pair-wise queries, the number of required queries is known to be $\Theta(nk)$, where $k$ is the number of clusters. However, non-adaptive schemes require $\Omega(n^2)$ queries, which matches the trivial $O(n^2)$ upper bound attained by querying every pair of points. To break the quadratic barrier for non-adaptive queries, we study a generalization of this problem to subset queries for $|S|>2$, where the oracle returns the number of clusters intersecting $S$. Allowing for subset queries of unbounded size, $O(n)$ queries is possible with an adaptive scheme (Chakrabarty-Liao, 2024). However, the realm of non-adaptive algorithms is completely unknown. In this paper, we give the first non-adaptive algorithms for clustering with subset queries. Our main result is a non-adaptive algorithm making $O(n \log k \cdot (\log k + \log\log n)^2)$ queries, which improves to $O(n \log \log n)$ when $k$ is a constant. We also consider algorithms with a restricted query size of at most $s$. In this setting we prove that $\Omega(\max(n^2/s^2,n))$ queries are necessary and obtain algorithms making $\tilde{O}(n^2k/s^2)$ queries for any $s \leq \sqrt{n}$ and $\tilde{O}(n^2/s)$ queries for any $s \leq n$. We also consider the natural special case when the clusters are balanced, obtaining non-adaptive algorithms which make $O(n \log k) + \tilde{O}(k)$ and $O(n\log^2 k)$ queries. Finally, allowing two rounds of adaptivity, we give an algorithm making $O(n \log k)$ queries in the general case and $O(n \log \log k)$ queries when the clusters are balanced.
Authors: Haichao Yang, Chang Eun Song, Weihong Xu, Behnam Khaleghi, Uday Mallappa, Monil Shah, Keming Fan, Mingu Kang, Tajana Rosing
Abstract: This paper introduces FSL-HDnn, an energy-efficient accelerator that implements the end-to-end pipeline of feature extraction, classification, and on-chip few-shot learning (FSL) through gradient-free learning techniques in a 40 nm CMOS process. At its core, FSL-HDnn integrates two low-power modules: Weight clustering feature extractor and Hyperdimensional Computing (HDC). Feature extractor utilizes advanced weight clustering and pattern reuse strategies for optimized CNN-based feature extraction. Meanwhile, HDC emerges as a novel approach for lightweight FSL classifier, employing hyperdimensional vectors to improve training accuracy significantly compared to traditional distance-based approaches. This dual-module synergy not only simplifies the learning process by eliminating the need for complex gradients but also dramatically enhances energy efficiency and performance. Specifically, FSL-HDnn achieves an Intensity unprecedented energy efficiency of 5.7 TOPS/W for feature 1 extraction and 0.78 TOPS/W for classification and learning Training Intensity phases, achieving improvements of 2.6X and 6.6X, respectively, Storage over current state-of-the-art CNN and FSL processors.
Authors: Kairi Furui, Masahito Ohue
Abstract: Accurate prediction and optimization of protein-protein binding affinity is crucial for therapeutic antibody development. Although machine learning-based prediction methods $\Delta\Delta G$ are suitable for large-scale mutant screening, they struggle to predict the effects of multiple mutations for targets without existing binders. Energy function-based methods, though more accurate, are time consuming and not ideal for large-scale screening. To address this, we propose an active learning workflow that efficiently trains a deep learning model to learn energy functions for specific targets, combining the advantages of both approaches. Our method integrates the RDE-Network deep learning model with Rosetta's energy function-based Flex ddG to efficiently explore mutants that bind to Flex ddG. In a case study targeting HER2-binding Trastuzumab mutants, our approach significantly improved the screening performance over random selection and demonstrated the ability to identify mutants with better binding properties without experimental $\Delta\Delta G$ data. This workflow advances computational antibody design by combining machine learning, physics-based computations, and active learning to achieve more efficient antibody development.
Authors: Harish Thangaraj, Ananya Chenat, Jaskaran Singh Walia, Vukosi Marivate
Abstract: Large multilingual models have significantly advanced natural language processing (NLP) research. However, their high resource demands and potential biases from diverse data sources have raised concerns about their effectiveness across low-resource languages. In contrast, monolingual models, trained on a single language, may better capture the nuances of the target language, potentially providing more accurate results. This study benchmarks the cross-lingual transfer capabilities from a high-resource language to a low-resource language for both, monolingual and multilingual models, focusing on Kinyarwanda and Kirundi, two Bantu languages. We evaluate the performance of transformer based architectures like Multilingual BERT (mBERT), AfriBERT, and BantuBERTa against neural-based architectures such as BiGRU, CNN, and char-CNN. The models were trained on Kinyarwanda and tested on Kirundi, with fine-tuning applied to assess the extent of performance improvement and catastrophic forgetting. AfriBERT achieved the highest cross-lingual accuracy of 88.3% after fine-tuning, while BiGRU emerged as the best-performing neural model with 83.3% accuracy. We also analyze the degree of forgetting in the original language post-fine-tuning. While monolingual models remain competitive, this study highlights that multilingual models offer strong cross-lingual transfer capabilities in resource limited settings.
Authors: Sawan Kumar, Rajdip Nayek, Souvik Chakraborty
Abstract: The growing demand for accurate, efficient, and scalable solutions in computational mechanics highlights the need for advanced operator learning algorithms that can efficiently handle large datasets while providing reliable uncertainty quantification. This paper introduces a novel Gaussian Process (GP) based neural operator for solving parametric differential equations. The approach proposed leverages the expressive capability of deterministic neural operators and the uncertainty awareness of conventional GP. In particular, we propose a ``neural operator-embedded kernel'' wherein the GP kernel is formulated in the latent space learned using a neural operator. Further, we exploit a stochastic dual descent (SDD) algorithm for simultaneously training the neural operator parameters and the GP hyperparameters. Our approach addresses the (a) resolution dependence and (b) cubic complexity of traditional GP models, allowing for input-resolution independence and scalability in high-dimensional and non-linear parametric systems, such as those encountered in computational mechanics. We apply our method to a range of non-linear parametric partial differential equations (PDEs) and demonstrate its superiority in both computational efficiency and accuracy compared to standard GP models and wavelet neural operators. Our experimental results highlight the efficacy of this framework in solving complex PDEs while maintaining robustness in uncertainty estimation, positioning it as a scalable and reliable operator-learning algorithm for computational mechanics.
Authors: Jaime Garcia-Martinez, David Diaz-Guerra, Archontis Politis, Tuomas Virtanen, Julio J. Carabias-Orti, Pedro Vera-Candeas
Abstract: Recent advancements in music source separation have significantly progressed, particularly in isolating vocals, drums, and bass elements from mixed tracks. These developments owe much to the creation and use of large-scale, multitrack datasets dedicated to these specific components. However, the challenge of extracting similarly sounding sources from orchestra recordings has not been extensively explored, largely due to a scarcity of comprehensive and clean (i.e bleed-free) multitrack datasets. In this paper, we introduce a novel multitrack dataset called SynthSOD, developed using a set of simulation techniques to create a realistic (i.e. using high-quality soundfonts), musically motivated, and heterogeneous training set comprising different dynamics, natural tempo changes, styles, and conditions. Moreover, we demonstrate the application of a widely used baseline music separation model trained on our synthesized dataset w.r.t to the well-known EnsembleSet, and evaluate its performance under both synthetic and real-world conditions.
Authors: David Pape, Thorsten Eisenhofer, Lea Sch\"onherr
Abstract: System prompts that include detailed instructions to describe the task performed by the underlying large language model (LLM) can easily transform foundation models into tools and services with minimal overhead. Because of their crucial impact on the utility, they are often considered intellectual property, similar to the code of a software product. However, extracting system prompts is easily possible by using prompt injection. As of today, there is no effective countermeasure to prevent the stealing of system prompts and all safeguarding efforts could be evaded with carefully crafted prompt injections that bypass all protection mechanisms.In this work, we propose an alternative to conventional system prompts. We introduce prompt obfuscation to prevent the extraction of the system prompt while maintaining the utility of the system itself with only little overhead. The core idea is to find a representation of the original system prompt that leads to the same functionality, while the obfuscated system prompt does not contain any information that allows conclusions to be drawn about the original system prompt. We implement an optimization-based method to find an obfuscated prompt representation while maintaining the functionality. To evaluate our approach, we investigate eight different metrics to compare the performance of a system using the original and the obfuscated system prompts, and we show that the obfuscated version is constantly on par with the original one. We further perform three different deobfuscation attacks and show that with access to the obfuscated prompt and the LLM itself, we are not able to consistently extract meaningful information. Overall, we showed that prompt obfuscation can be an effective method to protect intellectual property while maintaining the same utility as the original system prompt.
Authors: Ali Moltajaei Farid, Jafar Roshanian, Malek Mouhoub
Abstract: Unmanned aerial vehicles (UAVs) have become increasingly popular in various fields, including precision agriculture, search and rescue, and remote sensing. However, exploring unknown environments remains a significant challenge. This study aims to address this challenge by utilizing on-policy Reinforcement Learning (RL) with Proximal Policy Optimization (PPO) to explore the {two dimensional} area of interest with multiple UAVs. The UAVs will avoid collision with obstacles and each other and do the exploration in a distributed manner. The proposed solution includes actor-critic networks using deep convolutional neural networks {(CNN)} and long short-term memory (LSTM) for identifying the UAVs and areas that have already been covered. Compared to other RL techniques, such as policy gradient (PG) and asynchronous advantage actor-critic (A3C), the simulation results demonstrate the superiority of the proposed PPO approach. Also, the results show that combining LSTM with CNN in critic can improve exploration. Since the proposed exploration has to work in unknown environments, the results showed that the proposed setup can complete the coverage when we have new maps that differ from the trained maps. Finally, we showed how tuning hyper parameters may affect the overall performance.
Authors: Bilal Faye, Hanane Azzag, Mustapha Lebbah
Abstract: Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling applications such as visual question answering and audiovisual content analysis. Current techniques rely on large modality-specific encoders, necessitating fine-tuning or training from scratch on vast aligned datasets (e.g., text-image, text-audio, image-audio). This approach has limitations: (i) it is very expensive due to the need for training large encoders on extensive datasets, (ii) acquiring aligned large paired datasets is challenging, and (iii) adding new modalities requires retraining the entire framework to incorporate these modalities. To address these issues, we propose OneEncoder, a lightweight framework that progressively represents and aligns four modalities (image, text, audio, video). Initially, we train a lightweight Universal Projection module (UP) to align image and text modalities. Then, we freeze the pretrained UP and progressively align future modalities to those already aligned. OneEncoder operates efficiently and cost-effectively, even in scenarios where vast aligned datasets are unavailable, due to its lightweight design. Trained on small paired datasets, it shows strong performance in tasks like classification, querying, and visual question answering, surpassing methods that rely on large datasets and specialized encoders.
Authors: David A. Robb, Donald Risbridger, Ben Mills, Ildar Rakhmatulin, Xianwen Kong, Mustafa Erden, M. J. Daniel Esser, Richard M. Carter, Mike J. Chantler
Abstract: The alignment of optical systems is a critical step in their manufacture. Alignment normally requires considerable knowledge and expertise of skilled operators. The automation of such processes has several potential advantages, but requires additional resource and upfront costs. Through a case study of a simple two mirror system we identify and examine three different automation approaches. They are: artificial neural networks; practice-led, which mimics manual alignment practices; and design-led, modelling from first principles. We find that these approaches make use of three different types of knowledge 1) basic system knowledge (of controls, measurements and goals); 2) behavioural skills and expertise, and 3) fundamental system design knowledge. We demonstrate that the different automation approaches vary significantly in human resources, and measurement sampling budgets. This will have implications for practitioners and management considering the automation of such tasks.
Authors: Paul D\"utting, Thomas Kesselheim, Brendan Lucier, Rebecca Reiffenh\"auser, Sahil Singla
Abstract: In online combinatorial allocations/auctions, n bidders sequentially arrive, each with a combinatorial valuation (such as submodular/XOS) over subsets of m indivisible items. The aim is to immediately allocate a subset of the remaining items to maximize the total welfare, defined as the sum of bidder valuations. A long line of work has studied this problem when the bidder valuations come from known independent distributions. In particular, for submodular/XOS valuations, we know 2-competitive algorithms/mechanisms that set a fixed price for each item and the arriving bidders take their favorite subset of the remaining items given these prices. However, these algorithms traditionally presume the availability of the underlying distributions as part of the input to the algorithm. Contrary to this assumption, practical scenarios often require the learning of distributions, a task complicated by limited sample availability. This paper investigates the feasibility of achieving O(1)-competitive algorithms under the realistic constraint of having access to only a limited number of samples from the underlying bidder distributions. Our first main contribution shows that a mere single sample from each bidder distribution is sufficient to yield an O(1)-competitive algorithm for submodular/XOS valuations. This result leverages a novel extension of the secretary-style analysis, employing the sample to have the algorithm compete against itself. Although online, this first approach does not provide an online truthful mechanism. Our second main contribution shows that a polynomial number of samples suffices to yield a $(2+\epsilon)$-competitive online truthful mechanism for submodular/XOS valuations and any constant $\epsilon>0$. This result is based on a generalization of the median-based algorithm for the single-item prophet inequality problem to combinatorial settings with multiple items.
Authors: Thien-Minh Nguyen, Yizhuo Yang, Tien-Dat Nguyen, Shenghai Yuan, Lihua Xie
Abstract: While UWB-based methods can achieve high localization accuracy in small-scale areas, their accuracy and reliability are significantly challenged in large-scale environments. In this paper, we propose a learning-based framework named ULOC for Ultra-Wideband (UWB) based localization in such complex large-scale environments. First, anchors are deployed in the environment without knowledge of their actual position. Then, UWB observations are collected when the vehicle travels in the environment. At the same time, map-consistent pose estimates are developed from registering (onboard self-localization) data with the prior map to provide the training labels. We then propose a network based on MAMBA that learns the ranging patterns of UWBs over a complex large-scale environment. The experiment demonstrates that our solution can ensure high localization accuracy on a large scale compared to the state-of-the-art. We release our source code to benefit the community at https://github.com/brytsknguyen/uloc.
Authors: Debarpan Bhattacharya, Amir H. Poorjam, Deepak Mittal, Sriram Ganapathy
Abstract: The recent advancements in artificial intelligence (AI), with the release of several large models having only query access, make a strong case for explainability of deep models in a post-hoc gradient free manner. In this paper, we propose a framework, named distillation aided explainability (DAX), that attempts to generate a saliency-based explanation in a model agnostic gradient free application. The DAX approach poses the problem of explanation in a learnable setting with a mask generation network and a distillation network. The mask generation network learns to generate the multiplier mask that finds the salient regions of the input, while the student distillation network aims to approximate the local behavior of the black-box model. We propose a joint optimization of the two networks in the DAX framework using the locally perturbed input samples, with the targets derived from input-output access to the black-box model. We extensively evaluate DAX across different modalities (image and audio), in a classification setting, using a diverse set of evaluations (intersection over union with ground truth, deletion based and subjective human evaluation based measures) and benchmark it with respect to $9$ different methods. In these evaluations, the DAX significantly outperforms the existing approaches on all modalities and evaluation metrics.
Authors: Orion Weller, Benjamin Van Durme, Dawn Lawrie, Ashwin Paranjape, Yuhao Zhang, Jack Hessel
Abstract: Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be prompted like an LM. To train Promptriever, we curate and release a new instance-level instruction training set from MS MARCO, spanning nearly 500k instances. Promptriever not only achieves strong performance on standard retrieval tasks, but also follows instructions. We observe: (1) large gains (reaching SoTA) on following detailed relevance instructions (+14.3 p-MRR / +3.1 nDCG on FollowIR), (2) significantly increased robustness to lexical choices/phrasing in the query+instruction (+12.9 Robustness@10 on InstructIR), and (3) the ability to perform hyperparameter search via prompting to reliably improve retrieval performance (+1.4 average increase on BEIR). Promptriever demonstrates that retrieval models can be controlled with prompts on a per-query basis, setting the stage for future work aligning LM prompting techniques with information retrieval.
Authors: Andrzej Perzanowski, Tony Lindeberg
Abstract: This paper presents an in-depth analysis of the scale generalisation properties of the scale-covariant and scale-invariant Gaussian derivative networks, complemented with both conceptual and algorithmic extensions. For this purpose, Gaussian derivative networks are evaluated on new rescaled versions of the Fashion-MNIST and the CIFAR-10 datasets, with spatial scaling variations over a factor of 4 in the testing data, that are not present in the training data. Additionally, evaluations on the previously existing STIR datasets show that the Gaussian derivative networks achieve better scale generalisation than previously reported for these datasets for other types of deep networks. We first experimentally demonstrate that the Gaussian derivative networks have quite good scale generalisation properties on the new datasets, and that average pooling of feature responses over scales may sometimes also lead to better results than the previously used approach of max pooling over scales. Then, we demonstrate that using a spatial max pooling mechanism after the final layer enables localisation of non-centred objects in image domain, with maintained scale generalisation properties. We also show that regularisation during training, by applying dropout across the scale channels, referred to as scale-channel dropout, improves both the performance and the scale generalisation. In additional ablation studies, we demonstrate that discretisations of Gaussian derivative networks, based on the discrete analogue of the Gaussian kernel in combination with central difference operators, perform best or among the best, compared to a set of other discrete approximations of the Gaussian derivative kernels. Finally, by visualising the activation maps and the learned receptive fields, we demonstrate that the Gaussian derivative networks have very good explainability properties.
Authors: Nicolas Chatzikiriakos, Andrea Iannelli
Abstract: This paper considers a finite sample perspective on the problem of identifying an LTI system from a finite set of possible systems using trajectory data. To this end, we use the maximum likelihood estimator to identify the true system and provide an upper bound for its sample complexity. Crucially, the derived bound does not rely on a potentially restrictive stability assumption. Additionally, we leverage tools from information theory to provide a lower bound to the sample complexity that holds independently of the used estimator. The derived sample complexity bounds are analyzed analytically and numerically.
Authors: Paul Werner L\"odige, Maximilian Xiling Li, Rudolf Lioutikov
Abstract: Movement Primitives (MPs) are a well-established method for representing and generating modular robot trajectories. This work presents FA-ProDMP, a new approach which introduces force awareness to Probabilistic Dynamic Movement Primitives (ProDMP). FA-ProDMP adapts the trajectory during runtime to account for measured and desired forces. It offers smooth trajectories and captures position and force correlations over multiple trajectories, e.g. a set of human demonstrations. FA-ProDMP supports multiple axes of force and is thus agnostic to cartesian or joint space control. This makes FA-ProDMP a valuable tool for learning contact rich manipulation tasks such as polishing, cutting or industrial assembly from demonstration. In order to reliably evaluate FA-ProDMP, this work additionally introduces a modular, 3D printed task suite called POEMPEL, inspired by the popular Lego Technic pins. POEMPEL mimics industrial peg-in-hole assembly tasks with force requirements. It offers multiple parameters of adjustment, such as position, orientation and plug stiffness level, thus varying the direction and amount of required forces. Our experiments show that FA-ProDMP outperforms other MP formulations on the POEMPEL setup and a electrical power plug insertion task, due to its replanning capabilities based on the measured forces. These findings highlight how FA-ProDMP enhances the performance of robotic systems in contact-rich manipulation tasks.
Authors: Tushar Dhyani, Florian Lux, Michele Mancusi, Giorgio Fabbro, Fritz Hohl, Ngoc Thang Vu
Abstract: Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and high-frequency harmonics, leading to breathing and gasping artifacts that reduce the intelligibility of reconstructed speech. These models are also computationally demanding, and many solutions are restricted to producing outputs in the wide-band frequency range, which limits their suitability for professional applications. To address these challenges, we propose Hi-ResLDM, a novel generative model based on latent diffusion designed to remove multiple distortions and restore speech recordings to studio quality, sampled at 48kHz. We benchmark Hi-ResLDM against state-of-the-art methods that leverage GAN and Conditional Flow Matching (CFM) components, demonstrating superior performance in regenerating high-frequency-band details. Hi-ResLDM not only excels in non-instrusive metrics but is also consistently preferred in human evaluation and performs competitively on intrusive evaluations, making it ideal for high-resolution speech restoration.
Authors: Bin Xiao, Lei Su
Abstract: In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in substantial underutilization of computing resources during the communication phase. To mitigate this inefficiency, various techniques have been developed to optimize the use of computational power throughout the communication process. These strategies primarily involve overlapping matrix computations and communications, as well as interleaving micro-batches across different requests. Nonetheless, these approaches either fall short of achieving ideal overlap or impose certain limitations on their application. To overcome these challenges, this paper introduces a novel strategy for computation-communication overlap that operates at the sequence level. This method not only enhances the degree of overlap but also minimizes the constraints on its applicability. Experimental evaluations conducted using 30b/70b models have demonstrated significant improvements in efficiency. Specifically, the proposed technique has been shown to reduce time consumption by approximately 35% on 4090 GPU and by roughly 15% on A800 GPU during the prefill stage of LLM inference.
Authors: Gabriele Sartor, Matteo Salis, Stefano Pinardi, Ozgur Saracik, Rosa Meo
Abstract: Deforestation is gaining an increasingly importance due to its strong influence on the sorrounding environment, especially in developing countries where population has a disadvantaged economic condition and agriculture is the main source of income. In Ivory Coast, for instance, where the cocoa production is the most remunerative activity, it is not rare to assist to the replacement of portion of ancient forests with new cocoa plantations. In order to monitor this type of deleterious activities, satellites can be employed to recognize the disappearance of the forest to prevent it from expand its area of interest. In this study, Forest-Non-Forest map (FNF) has been used as ground truth for models based on Sentinel images input. State-of-the-art models U-Net, Attention U-Net, Segnet and FCN32 are compared over different years combining Sentinel-1, Sentinel-2 and cloud probability to create forest/non-forest segmentation. Although Ivory Coast lacks of forest coverage datasets and is partially covered by Sentinel images, it is demonstrated the feasibility to create models classifying forest and non-forests pixels over the area using open datasets to predict where deforestation could have occurred. Although a significant portion of the deforestation research is carried out on visible bands, SAR acquisitions are employed to overcome the limits of RGB images over areas often covered by clouds. Finally, the most promising model is employed to estimate the hectares of forest has been cut between 2019 and 2020.
Authors: Lameya Aldhaheri, Noor Alshehhi, Irfana Ilyas Jameela Manzil, Ruhul Amin Khalil, Shumaila Javaid, Nasir Saeed, Mohamed-Slim Alouini
Abstract: The emerging field of smart agriculture leverages the Internet of Things (IoT) to revolutionize farming practices. This paper investigates the transformative potential of Long Range (LoRa) technology as a key enabler of long-range wireless communication for agricultural IoT systems. By reviewing existing literature, we identify a gap in research specifically focused on LoRa's prospects and challenges from a communication perspective in smart agriculture. We delve into the details of LoRa-based agricultural networks, covering network architecture design, Physical Layer (PHY) considerations tailored to the agricultural environment, and channel modeling techniques that account for soil characteristics. The paper further explores relaying and routing mechanisms that address the challenges of extending network coverage and optimizing data transmission in vast agricultural landscapes. Transitioning to practical aspects, we discuss sensor deployment strategies and energy management techniques, offering insights for real-world deployments. A comparative analysis of LoRa with other wireless communication technologies employed in agricultural IoT applications highlights its strengths and weaknesses in this context. Furthermore, the paper outlines several future research directions to leverage the potential of LoRa-based agriculture 4.0. These include advancements in channel modeling for diverse farming environments, novel relay routing algorithms, integrating emerging sensor technologies like hyper-spectral imaging and drone-based sensing, on-device Artificial Intelligence (AI) models, and sustainable solutions. This survey can guide researchers, technologists, and practitioners to understand, implement, and propel smart agriculture initiatives using LoRa technology.
Authors: Tianqi Chen, Shujian Zhang, Mingyuan Zhou
Abstract: The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and trustworthy GenAI models. Traditional MU methods often rely on stringent assumptions and require access to real data. This paper introduces Score Forgetting Distillation (SFD), an innovative MU approach that promotes the forgetting of undesirable information in diffusion models by aligning the conditional scores of ``unsafe'' classes or concepts with those of ``safe'' ones. To eliminate the need for real data, our SFD framework incorporates a score-based MU loss into the score distillation objective of a pretrained diffusion model. This serves as a regularization term that preserves desired generation capabilities while enabling the production of synthetic data through a one-step generator. Our experiments on pretrained label-conditional and text-to-image diffusion models demonstrate that our method effectively accelerates the forgetting of target classes or concepts during generation, while preserving the quality of other classes or concepts. This unlearned and distilled diffusion not only pioneers a novel concept in MU but also accelerates the generation speed of diffusion models. Our experiments and studies on a range of diffusion models and datasets confirm that our approach is generalizable, effective, and advantageous for MU in diffusion models.
Authors: Xiaoyu Bie, Xubo Liu, Ga\"el Richard
Abstract: Neural audio codecs have significantly advanced audio compression by efficiently converting continuous audio signals into discrete tokens. These codecs preserve high-quality sound and enable sophisticated sound generation through generative models trained on these tokens. However, existing neural codec models are typically trained on large, undifferentiated audio datasets, neglecting the essential discrepancies between sound domains like speech, music, and environmental sound effects. This oversight complicates data modeling and poses additional challenges to the controllability of sound generation. To tackle these issues, we introduce the Source-Disentangled Neural Audio Codec (SD-Codec), a novel approach that combines audio coding and source separation. By jointly learning audio resynthesis and separation, SD-Codec explicitly assigns audio signals from different domains to distinct codebooks, sets of discrete representations. Experimental results indicate that SD-Codec not only maintains competitive resynthesis quality but also, supported by the separation results, demonstrates successful disentanglement of different sources in the latent space, thereby enhancing interpretability in audio codec and providing potential finer control over the audio generation process.
Authors: Jake Welde, Nishanth Rao, Pratik Kunapuli, Dinesh Jayaraman, Vijay Kumar
Abstract: Tracking controllers enable robotic systems to accurately follow planned reference trajectories. In particular, reinforcement learning (RL) has shown promise in the synthesis of controllers for systems with complex dynamics and modest online compute budgets. However, the poor sample efficiency of RL and the challenges of reward design make training slow and sometimes unstable, especially for high-dimensional systems. In this work, we leverage the inherent Lie group symmetries of robotic systems with a floating base to mitigate these challenges when learning tracking controllers. We model a general tracking problem as a Markov decision process (MDP) that captures the evolution of both the physical and reference states. Next, we prove that symmetry in the underlying dynamics and running costs leads to an MDP homomorphism, a mapping that allows a policy trained on a lower-dimensional "quotient" MDP to be lifted to an optimal tracking controller for the original system. We compare this symmetry-informed approach to an unstructured baseline, using Proximal Policy Optimization (PPO) to learn tracking controllers for three systems: the Particle (a forced point mass), the Astrobee (a fullyactuated space robot), and the Quadrotor (an underactuated system). Results show that a symmetry-aware approach both accelerates training and reduces tracking error after the same number of training steps.
Authors: Xing Yi Liu, Homayoon Beigi
Abstract: Presently, punctuation restoration models are evaluated almost solely on well-structured, scripted corpora. On the other hand, real-world ASR systems and post-processing pipelines typically apply towards spontaneous speech with significant irregularities, stutters, and deviations from perfect grammar. To address this discrepancy, we introduce SponSpeech, a punctuation restoration dataset derived from informal speech sources, which includes punctuation and casing information. In addition to publicly releasing the dataset, we contribute a filtering pipeline that can be used to generate more data. Our filtering pipeline examines the quality of both speech audio and transcription text. We also carefully construct a ``challenging" test set, aimed at evaluating models' ability to leverage audio information to predict otherwise grammatically ambiguous punctuation. SponSpeech is available at https://github.com/GitHubAccountAnonymous/PR, along with all code for dataset building and model runs.
Authors: Kyle Stein, Andrew A. Mahyari, Guillermo Francia III, Eman El-Sheikh
Abstract: As the complexity and connectivity of networks increase, the need for novel malware detection approaches becomes imperative. Traditional security defenses are becoming less effective against the advanced tactics of today's cyberattacks. Deep Packet Inspection (DPI) has emerged as a key technology in strengthening network security, offering detailed analysis of network traffic that goes beyond simple metadata analysis. DPI examines not only the packet headers but also the payload content within, offering a thorough insight into the data traversing the network. This study proposes a novel approach that leverages a large language model (LLM) and few-shot learning to accurately recognizes novel, unseen malware types with few labels samples. Our proposed approach uses a pretrained LLM on known malware types to extract the embeddings from packets. The embeddings are then used alongside few labeled samples of an unseen malware type. This technique is designed to acclimate the model to different malware representations, further enabling it to generate robust embeddings for each trained and unseen classes. Following the extraction of embeddings from the LLM, few-shot learning is utilized to enhance performance with minimal labeled data. Our evaluation, which utilized two renowned datasets, focused on identifying malware types within network traffic and Internet of Things (IoT) environments. Our approach shows promising results with an average accuracy of 86.35% and F1-Score of 86.40% on different malware types across the two datasets.
Authors: Charilaos Papaioannou, Emmanouil Benetos, Alexandros Potamianos
Abstract: We introduce Label-Combination Prototypical Networks (LC-Protonets) to address the problem of multi-label few-shot classification, where a model must generalize to new classes based on only a few available examples. Extending Prototypical Networks, LC-Protonets generate one prototype per label combination, derived from the power set of labels present in the limited training items, rather than one prototype per label. Our method is applied to automatic audio tagging across diverse music datasets, covering various cultures and including both modern and traditional music, and is evaluated against existing approaches in the literature. The results demonstrate a significant performance improvement in almost all domains and training setups when using LC-Protonets for multi-label classification. In addition to training a few-shot learning model from scratch, we explore the use of a pre-trained model, obtained via supervised learning, to embed items in the feature space. Fine-tuning improves the generalization ability of all methods, yet LC-Protonets achieve high-level performance even without fine-tuning, in contrast to the comparative approaches. We finally analyze the scalability of the proposed method, providing detailed quantitative metrics from our experiments. The implementation and experimental setup are made publicly available, offering a benchmark for future research.
Authors: Caio Fabio Oliveira da Silva, Azita Dabiri, Bart De Schutter
Abstract: This work proposes an approach that integrates reinforcement learning and model predictive control (MPC) to efficiently solve finite-horizon optimal control problems in mixed-logical dynamical systems. Optimization-based control of such systems with discrete and continuous decision variables entails the online solution of mixed-integer quadratic or linear programs, which suffer from the curse of dimensionality. Our approach aims at mitigating this issue by effectively decoupling the decision on the discrete variables and the decision on the continuous variables. Moreover, to mitigate the combinatorial growth in the number of possible actions due to the prediction horizon, we conceive the definition of decoupled Q-functions to make the learning problem more tractable. The use of reinforcement learning reduces the online optimization problem of the MPC controller from a mixed-integer linear (quadratic) program to a linear (quadratic) program, greatly reducing the computational time. Simulation experiments for a microgrid, based on real-world data, demonstrate that the proposed method significantly reduces the online computation time of the MPC approach and that it generates policies with small optimality gaps and high feasibility rates.
Authors: Nikit Srivastava, Denis Kuchelev, Tatiana Moteu, Kshitij Shetty, Michael Roeder, Diego Moussallem, Hamada Zahera, 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: Marcel Lamott, Muhammad Armaghan Shakir
Abstract: The surge of digital documents in various formats, including less standardized documents such as business reports and environmental assessments, underscores the growing importance of Document Understanding. While Large Language Models (LLMs) have showcased prowess across diverse natural language processing tasks, their direct application to Document Understanding remains a challenge. Previous research has demonstrated the utility of LLMs in this domain, yet their significant computational demands make them challenging to deploy effectively. Additionally, proprietary Blackbox LLMs often outperform their open-source counterparts, posing a barrier to widespread accessibility. In this paper, we delve into the realm of document understanding, leveraging distillation methods to harness the power of large LLMs while accommodating computational limitations. Specifically, we present a novel approach wherein we distill document understanding knowledge from the proprietary LLM ChatGPT into FLAN-T5. Our methodology integrates labeling and curriculum-learning mechanisms to facilitate efficient knowledge transfer. This work contributes to the advancement of document understanding methodologies by offering a scalable solution that bridges the gap between resource-intensive LLMs and practical applications. Our findings underscore the potential of distillation techniques in facilitating the deployment of sophisticated language models in real-world scenarios, thereby fostering advancements in natural language processing and document comprehension domains.
Authors: Zeyi Liao, Lingbo Mo, Chejian Xu, Mintong Kang, Jiawei Zhang, Chaowei Xiao, Yuan Tian, Bo Li, Huan Sun
Abstract: Generalist web agents have evolved rapidly and demonstrated remarkable potential. However, there are unprecedented safety risks associated with these them, which are nearly unexplored so far. In this work, we aim to narrow this gap by conducting the first study on the privacy risks of generalist web agents in adversarial environments. First, we present a threat model that discusses the adversarial targets, constraints, and attack scenarios. Particularly, we consider two types of adversarial targets: stealing users' specific personally identifiable information (PII) or stealing the entire user request. To achieve these objectives, we propose a novel attack method, termed Environmental Injection Attack (EIA). This attack injects malicious content designed to adapt well to different environments where the agents operate, causing them to perform unintended actions. This work instantiates EIA specifically for the privacy scenario. It inserts malicious web elements alongside persuasive instructions that mislead web agents into leaking private information, and can further leverage CSS and JavaScript features to remain stealthy. We collect 177 actions steps that involve diverse PII categories on realistic websites from the Mind2Web dataset, and conduct extensive experiments using one of the most capable generalist web agent frameworks to date, SeeAct. The results demonstrate that EIA achieves up to 70% ASR in stealing users' specific PII. Stealing full user requests is more challenging, but a relaxed version of EIA can still achieve 16% ASR. Despite these concerning results, it is important to note that the attack can still be detectable through careful human inspection, highlighting a trade-off between high autonomy and security. This leads to our detailed discussion on the efficacy of EIA under different levels of human supervision as well as implications on defenses for generalist web agents.
Authors: Bowen Dong, Pan Zhou, Wangmeng Zuo
Abstract: We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of three core components. The first is a universal long-tailed adaptation module, which aggregates long-tailed prompts and visual adapters to adapt the pretrained model to the target domain, meanwhile improving its discriminative ability. The second is the mixture of long-tailed experts framework with a mixture-of-experts (MoE) scorer, which adaptively calculates reweighting coefficients for confidence scores from both visual-only and visual-language (VL) model experts to generate more accurate predictions. Finally, LPT++ employs a three-phase training framework, wherein each critical module is learned separately, resulting in a stable and effective long-tailed classification training paradigm. Besides, we also propose the simple version of LPT++ namely LPT, which only integrates visual-only pretrained ViT and long-tailed prompts to formulate a single model method. LPT can clearly illustrate how long-tailed prompts works meanwhile achieving comparable performance without VL pretrained models. Experiments show that, with only ~1% extra trainable parameters, LPT++ achieves comparable accuracy against all the counterparts.
Authors: Reza Sadeghi Hafshejani, Mohamad Kazem Shirani Fradonbeh
Abstract: We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the possibly unstable open-loop matrix by employing properly randomized control inputs. Then, we establish theoretical performance guarantees showing that the estimation error decays with trajectory length, a measure of excitability, and the signal-to-noise ratio, while it grows with dimension. Numerical illustrations that showcase the rates of learning the dynamics, will be provided as well. To perform the theoretical analysis, we develop new technical tools that are of independent interest. That includes non-asymptotic stochastic bounds for highly non-stationary martingales and generalized laws of iterated logarithms, among others.
Authors: Lauren M. Zuromski, Jacob Durtschi, Aimal Aziz, Jeffrey Chumley, Mark Dewey, Paul English, Muir Morrison, Keith Simmon, Blaine Whipple, Brendan O'Fallon, David P. Ng
Abstract: Machine-learning (ML) models in flow cytometry have the potential to reduce error rates, increase reproducibility, and boost the efficiency of clinical labs. While numerous ML models for flow cytometry data have been proposed, few studies have described the clinical deployment of such models. Realizing the potential gains of ML models in clinical labs requires not only an accurate model, but infrastructure for automated inference, error detection, analytics and monitoring, and structured data extraction. Here, we describe an ML model for detection of Acute Myeloid Leukemia (AML), along with the infrastructure supporting clinical implementation. Our infrastructure leverages the resilience and scalability of the cloud for model inference, a Kubernetes-based workflow system that provides model reproducibility and resource management, and a system for extracting structured diagnoses from full-text reports. We also describe our model monitoring and visualization platform, an essential element for ensuring continued model accuracy. Finally, we present a post-deployment analysis of impacts on turn-around time and compare production accuracy to the original validation statistics.
Authors: Bhavika Devnani, Skyler Seto, Zakaria Aldeneh, Alessandro Toso, Elena Menyaylenko, Barry-John Theobald, Jonathan Sheaffer, Miguel Sarabia
Abstract: Humans can picture a sound scene given an imprecise natural language description. For example, it is easy to imagine an acoustic environment given a phrase like "the lion roar came from right behind me!". For a machine to have the same degree of comprehension, the machine must know what a lion is (semantic attribute), what the concept of "behind" is (spatial attribute) and how these pieces of linguistic information align with the semantic and spatial attributes of the sound (what a roar sounds like when its coming from behind). State-of-the-art audio foundation models which learn to map between audio scenes and natural textual descriptions, are trained on non-spatial audio and text pairs, and hence lack spatial awareness. In contrast, sound event localization and detection models are limited to recognizing sounds from a fixed number of classes, and they localize the source to absolute position (e.g., 0.2m) rather than a position described using natural language (e.g., "next to me"). To address these gaps, we present ELSA a spatially aware-audio and text embedding model trained using multimodal contrastive learning. ELSA supports non-spatial audio, spatial audio, and open vocabulary text captions describing both the spatial and semantic components of sound. To train ELSA: (a) we spatially augment the audio and captions of three open-source audio datasets totaling 4,738 hours of audio, and (b) we design an encoder to capture the semantics of non-spatial audio, and the semantics and spatial attributes of spatial audio using contrastive learning. ELSA is competitive with state-of-the-art for both semantic retrieval and 3D source localization. In particular, ELSA achieves +2.8% mean audio-to-text and text-to-audio R@1 above the baseline, and outperforms by -11.6{\deg} mean-absolute-error in 3D source localization over the baseline.
Authors: J\'er\'emy Lebreton, Ingo Ahrns, Roland Brochard, Christoph Haskamp, Matthieu Le Goff, Nicolas Menga, Nicolas Ollagnier, Ralf Regele, Francesco Capolupo, Massimo Casasco
Abstract: Vision Based Navigation consists in utilizing cameras as precision sensors for GNC after extracting information from images. To enable the adoption of machine learning for space applications, one of obstacles is the demonstration that available training datasets are adequate to validate the algorithms. The objective of the study is to generate datasets of images and metadata suitable for training machine learning algorithms. Two use cases were selected and a robust methodology was developed to validate the datasets including the ground truth. The first use case is in-orbit rendezvous with a man-made object: a mockup of satellite ENVISAT. The second use case is a Lunar landing scenario. Datasets were produced from archival datasets (Chang'e 3), from the laboratory at DLR TRON facility and at Airbus Robotic laboratory, from SurRender software high fidelity image simulator using Model Capture and from Generative Adversarial Networks. The use case definition included the selection of algorithms as benchmark: an AI-based pose estimation algorithm and a dense optical flow algorithm were selected. Eventually it is demonstrated that datasets produced with SurRender and selected laboratory facilities are adequate to train machine learning algorithms.
Authors: Rebecca M. M. Hicke, Yuri Bizzoni, Pascale Feldkamp, Ross Deans Kristensen-McLachlan
Abstract: Focalization, the perspective through which narrative is presented, is encoded via a wide range of lexico-grammatical features and is subject to reader interpretation. Moreover, trained readers regularly disagree on interpretations, suggesting that this problem may be computationally intractable. In this paper, we provide experiments to test how well contemporary Large Language Models (LLMs) perform when annotating literary texts for focalization mode. Despite the challenging nature of the task, LLMs show comparable performance to trained human annotators in our experiments. We provide a case study working with the novels of Stephen King to demonstrate the usefulness of this approach for computational literary studies, illustrating how focalization can be studied at scale.
Authors: Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuoling Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
Abstract: We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training. In terms of model design, we perform a comprehensive comparison between decoder-only multimodal LLMs (e.g., LLaVA) and cross-attention-based models (e.g., Flamingo). Based on the strengths and weaknesses of both approaches, we propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. Furthermore, we introduce a 1-D tile-tagging design for tile-based dynamic high-resolution images, which significantly boosts performance on multimodal reasoning and OCR-related tasks. Regarding training data, we meticulously curate and provide detailed information on our multimodal pretraining and supervised fine-tuning datasets. Our findings indicate that dataset quality and task diversity are more important than scale, even during the pretraining phase, across all architectures. Notably, we develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks while maintaining and even improving text-only performance compared to their LLM backbones. To achieve this, we craft and integrate a high-quality text-only dataset into multimodal training, alongside a substantial amount of multimodal math and reasoning data, leading to enhanced math and coding capabilities across modalities. To advance research in the field, we are releasing the model weights and will open-source the code for the community: https://nvlm-project.github.io/.
Authors: Brendon G. Anderson, Ziye Ma, Jingqi Li, Somayeh Sojoudi
Abstract: In this paper, we study certifying the robustness of ReLU neural networks against adversarial input perturbations. To diminish the relaxation error suffered by the popular linear programming (LP) and semidefinite programming (SDP) certification methods, we take a branch-and-bound approach to propose partitioning the input uncertainty set and solving the relaxations on each part separately. We show that this approach reduces relaxation error, and that the error is eliminated entirely upon performing an LP relaxation with a partition intelligently designed to exploit the nature of the ReLU activations. To scale this approach to large networks, we consider using a coarser partition whereby the number of parts in the partition is reduced. We prove that computing such a coarse partition that directly minimizes the LP relaxation error is NP-hard. By instead minimizing the worst-case LP relaxation error, we develop a closed-form branching scheme in the single-hidden layer case. We extend the analysis to the SDP, where the feasible set geometry is exploited to design a branching scheme that minimizes the worst-case SDP relaxation error. Experiments on MNIST, CIFAR-10, and Wisconsin breast cancer diagnosis classifiers demonstrate significant increases in the percentages of test samples certified. By independently increasing the input size and the number of layers, we empirically illustrate under which regimes the branched LP and branched SDP are best applied. Finally, we extend our LP branching method into a multi-layer branching heuristic, which attains comparable performance to prior state-of-the-art heuristics on large-scale, deep neural network certification benchmarks.
Authors: Jingwei Guo, Kaizhu Huang, Rui Zhang, Xinping Yi
Abstract: While Graph Neural Networks (GNNs) have achieved enormous success in multiple graph analytical tasks, modern variants mostly rely on the strong inductive bias of homophily. However, real-world networks typically exhibit both homophilic and heterophilic linking patterns, wherein adjacent nodes may share dissimilar attributes and distinct labels. Therefore, GNNs smoothing node proximity holistically may aggregate both task-relevant and irrelevant (even harmful) information, limiting their ability to generalize to heterophilic graphs and potentially causing non-robustness. In this work, we propose a novel Edge Splitting GNN (ES-GNN) framework to adaptively distinguish between graph edges either relevant or irrelevant to learning tasks. This essentially transfers the original graph into two subgraphs with the same node set but complementary edge sets dynamically. Given that, information propagation separately on these subgraphs and edge splitting are alternatively conducted, thus disentangling the task-relevant and irrelevant features. Theoretically, we show that our ES-GNN can be regarded as a solution to a disentangled graph denoising problem, which further illustrates our motivations and interprets the improved generalization beyond homophily. Extensive experiments over 11 benchmark and 1 synthetic datasets not only demonstrate the effective performance of ES-GNN but also highlight its robustness to adversarial graphs and mitigation of the over-smoothing problem.
Authors: Gabriela Sejnova, Michal Vavrecka, Karla Stepanova, Tadahiro Taniguchi
Abstract: Multimodal Variational Autoencoders (VAEs) have been the subject of intense research in the past years as they can integrate multiple modalities into a joint representation and can thus serve as a promising tool for both data classification and generation. Several approaches toward multimodal VAE learning have been proposed so far, their comparison and evaluation have however been rather inconsistent. One reason is that the models differ at the implementation level, another problem is that the datasets commonly used in these cases were not initially designed to evaluate multimodal generative models. This paper addresses both mentioned issues. First, we propose a toolkit for systematic multimodal VAE training and comparison. The toolkit currently comprises 4 existing multimodal VAEs and 6 commonly used benchmark datasets along with instructions on how to easily add a new model or a dataset. Second, we present a disentangled bimodal dataset designed to comprehensively evaluate the joint generation and cross-generation capabilities across multiple difficulty levels. We demonstrate the utility of our dataset by comparing the implemented state-of-the-art models.
Authors: Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Yarong Mu, Shuang Song, Om Thakkar, Abhradeep Thakurta, Xinyi Zheng
Abstract: In this work, we focus on improving the accuracy-variance trade-off for state-of-the-art differentially private machine learning (DP ML) methods. First, we design a general framework that uses aggregates of intermediate checkpoints \emph{during training} to increase the accuracy of DP ML techniques. Specifically, we demonstrate that training over aggregates can provide significant gains in prediction accuracy over the existing state-of-the-art for StackOverflow, CIFAR10 and CIFAR100 datasets. For instance, we improve the state-of-the-art DP StackOverflow accuracies to 22.74\% (+2.06\% relative) for $\epsilon=8.2$, and 23.90\% (+2.09\%) for $\epsilon=18.9$. Furthermore, these gains magnify in settings with periodically varying training data distributions. We also demonstrate that our methods achieve relative improvements of 0.54\% and 62.6\% in terms of utility and variance, on a proprietary, production-grade pCVR task. Lastly, we initiate an exploration into estimating the uncertainty (variance) that DP noise adds in the predictions of DP ML models. We prove that, under standard assumptions on the loss function, the sample variance from last few checkpoints provides a good approximation of the variance of the final model of a DP run. Empirically, we show that the last few checkpoints can provide a reasonable lower bound for the variance of a converged DP model. Crucially, all the methods proposed in this paper operate on \emph{a single training run} of the DP ML technique, thus incurring no additional privacy cost.
Authors: Mohammad Reza Karimi, Ya-Ping Hsieh, Andreas Krause
Abstract: Non-convex sampling is a key challenge in machine learning, central to non-convex optimization in deep learning as well as to approximate probabilistic inference. Despite its significance, theoretically there remain many important challenges: Existing guarantees (1) typically only hold for the averaged iterates rather than the more desirable last iterates, (2) lack convergence metrics that capture the scales of the variables such as Wasserstein distances, and (3) mainly apply to elementary schemes such as stochastic gradient Langevin dynamics. In this paper, we develop a new framework that lifts the above issues by harnessing several tools from the theory of dynamical systems. Our key result is that, for a large class of state-of-the-art sampling schemes, their last-iterate convergence in Wasserstein distances can be reduced to the study of their continuous-time counterparts, which is much better understood. Coupled with standard assumptions of MCMC sampling, our theory immediately yields the last-iterate Wasserstein convergence of many advanced sampling schemes such as proximal, randomized mid-point, and Runge-Kutta integrators. Beyond existing methods, our framework also motivates more efficient schemes that enjoy the same rigorous guarantees.
Authors: Georgios Syros, Gokberk Yar, Simona Boboila, Cristina Nita-Rotaru, Alina Oprea
Abstract: Most machine learning applications rely on centralized learning processes, opening up the risk of exposure of their training datasets. While federated learning (FL) mitigates to some extent these privacy risks, it relies on a trusted aggregation server for training a shared global model. Recently, new distributed learning architectures based on Peer-to-Peer Federated Learning (P2PFL) offer advantages in terms of both privacy and reliability. Still, their resilience to poisoning attacks during training has not been investigated. In this paper, we propose new backdoor attacks for P2PFL that leverage structural graph properties to select the malicious nodes, and achieve high attack success, while remaining stealthy. We evaluate our attacks under various realistic conditions, including multiple graph topologies, limited adversarial visibility of the network, and clients with non-IID data. Finally, we show the limitations of existing defenses adapted from FL and design a new defense that successfully mitigates the backdoor attacks, without an impact on model accuracy.
Authors: Zaiwei Chen, Siva Theja Maguluri, Martin Zubeldia
Abstract: In this paper, we establish maximal concentration bounds for the iterates generated by a stochastic approximation (SA) algorithm under a contractive operator with respect to some arbitrary norm (for example, the $\ell_\infty$-norm). We consider two settings where the iterates are potentially unbounded: SA with bounded multiplicative noise and SA with sub-Gaussian additive noise. Our maximal concentration inequalities state that the convergence error has a sub-Gaussian tail in the additive noise setting and a Weibull tail (which is faster than polynomial decay but could be slower than exponential decay) in the multiplicative noise setting. In addition, we provide an impossibility result showing that it is generally impossible to have sub-exponential tails under multiplicative noise. To establish the maximal concentration bounds, we develop a novel bootstrapping argument that involves bounding the moment-generating function of a modified version of the generalized Moreau envelope of the convergence error and constructing an exponential supermartingale to enable using Ville's maximal inequality. We demonstrate the applicability of our theoretical results in the context of linear SA and reinforcement learning.
Authors: Elizaveta Kostenok, Daniil Cherniavskii, Alexey Zaytsev
Abstract: Transformer-based language models have set new benchmarks across a wide range of NLP tasks, yet reliably estimating the uncertainty of their predictions remains a significant challenge. Existing uncertainty estimation (UE) techniques often fall short in classification tasks, either offering minimal improvements over basic heuristics or relying on costly ensemble models. Moreover, attempts to leverage common embeddings for UE in linear probing scenarios have yielded only modest gains, indicating that alternative model components should be explored. We tackle these limitations by harnessing the geometry of attention maps across multiple heads and layers to assess model confidence. Our approach extracts topological features from attention matrices, providing a low-dimensional, interpretable representation of the model's internal dynamics. Additionally, we introduce topological features to compare attention patterns across heads and layers. Our method significantly outperforms existing UE techniques on benchmarks for acceptability judgments and artificial text detection, offering a more efficient and interpretable solution for uncertainty estimation in large-scale language models.
Authors: Shreyank N Gowda, Xinyue Hao, Gen Li, Shashank Narayana Gowda, Xiaobo Jin, Laura Sevilla-Lara
Abstract: Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy. However, their increasing energy consumption has raised concerns about their environmental impact, disadvantaging smaller entities in research and exacerbating global energy consumption. In this paper, we explore the trade-off between model accuracy and electricity consumption, proposing a metric that penalizes large consumption of electricity. We conduct a comprehensive study on the electricity consumption of various deep learning models across different GPUs, presenting a detailed analysis of their accuracy-efficiency trade-offs. By evaluating accuracy per unit of electricity consumed, we demonstrate how smaller, more energy-efficient models can significantly expedite research while mitigating environmental concerns. Our results highlight the potential for a more sustainable approach to deep learning, emphasizing the importance of optimizing models for efficiency. This research also contributes to a more equitable research landscape, where smaller entities can compete effectively with larger counterparts. This advocates for the adoption of efficient deep learning practices to reduce electricity consumption, safeguarding the environment for future generations whilst also helping ensure a fairer competitive landscape.
Authors: Carlos E. Luis, Alessandro G. Bottero, Julia Vinogradska, Felix Berkenkamp, Jan Peters
Abstract: We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. In particular, we focus on characterizing the variance over values induced by a distribution over Markov decision processes (MDPs). Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation (UBE), but the over-approximation may result in inefficient exploration. We propose a new UBE whose solution converges to the true posterior variance over values and leads to lower regret in tabular exploration problems. We identify challenges to apply the UBE theory beyond tabular problems and propose a suitable approximation. Based on this approximation, we introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC), that can be applied for either risk-seeking or risk-averse policy optimization with minimal changes. Experiments in both online and offline RL demonstrate improved performance compared to other uncertainty estimation methods.
Authors: Leonardo N. Coregliano, Maryanthe Malliaris
Abstract: We develop a theory of high-arity PAC learning, which is statistical learning in the presence of "structured correlation". In this theory, hypotheses are either graphs, hypergraphs or, more generally, structures in finite relational languages, and i.i.d. sampling is replaced by sampling an induced substructure, producing an exchangeable distribution. Our main theorems establish a high-arity (agnostic) version of the fundamental theorem of statistical learning.
Authors: Haokun Zhao, Haixia Han, Jie Shi, Chengyu Du, Jiaqing Liang, Yanghua Xiao
Abstract: As world knowledge evolves and new task schemas emerge, Continual Learning (CL) is crucial for keeping Large Language Models (LLMs) up-to-date and addressing their shortcomings. LLMs typically require continual instruction tuning (CIT) and continual pre-training (CPT) to adapt to new tasks and acquire essential knowledge. However, collecting sufficient CPT data while addressing knowledge gaps remains challenging, as does optimizing the efficiency of utilizing this data. Inspired by the 'summarizing mistakes' strategy, we propose the Continue Evolving from Mistakes (CEM) method, a data-efficient approach aiming to collect CPT data and continually improve LLMs' performance through iterative evaluation and supplementation with mistake-relevant knowledge. To enhance data utilization and mitigate forgetting, we introduce a novel training paradigm that combines CIT and CPT data. Experiments demonstrate that CEM significantly enhances model performance and continual evolution. The code and dataset are available in the GitHub.
Authors: Thomas Chen, Patricia Mu\~noz Ewald
Abstract: We explicitly construct zero loss neural network classifiers. We write the weight matrices and bias vectors in terms of cumulative parameters, which determine truncation maps acting recursively on input space. The configurations for the training data considered are (i) sufficiently small, well separated clusters corresponding to each class, and (ii) equivalence classes which are sequentially linearly separable. In the best case, for $Q$ classes of data in $\mathbb{R}^M$, global minimizers can be described with $Q(M+2)$ parameters.
Authors: Liam Madden, Curtis Fox, Christos Thrampoulidis
Abstract: Given a sequence of tokens, such as words, the task of next-token prediction is to predict the next-token conditional probability distribution. Decoder-only transformers have become effective models for this task, but their properties are still not fully understood. In particular, the largest number of distinct context sequences that a decoder-only transformer can interpolate next-token distributions for has not been established. To fill this gap, we prove upper and lower bounds on this number, which are equal up to a multiplicative constant. We prove these bounds in the general setting where next-token distributions can be arbitrary as well as the empirical setting where they are calculated from a finite number of document sequences. Our lower bounds are for one-layer multi-head decoder-only transformers and our proofs highlight an important injectivity property satisfied by self-attention. Furthermore, we provide numerical evidence that the minimal number of parameters for memorization is sufficient for being able to train the model to the entropy lower bound.
Authors: Liam Madden
Abstract: The minimal number of neurons required for a feedforward neural network to interpolate $n$ generic input-output pairs from $\mathbb{R}^d\times \mathbb{R}^{d'}$ is $\Theta(\sqrt{nd'})$. While previous results have shown that $\Theta(\sqrt{nd'})$ neurons are sufficient, they have been limited to sigmoid, Heaviside, and rectified linear unit (ReLU) as the activation function. Using a different approach, we prove that $\Theta(\sqrt{nd'})$ neurons are sufficient as long as the activation function is real analytic at a point and not a polynomial there. Thus, the only practical activation functions that our result does not apply to are piecewise polynomials. Importantly, this means that activation functions can be freely chosen in a problem-dependent manner without loss of interpolation power.
Authors: Flora Angileri, Giulia Lombardi, Andrea Fois, Renato Faraone, Carlo Metta, Michele Salvi, Luigi Amedeo Bianchi, Marco Fantozzi, Silvia Giulia Galfr\`e, Daniele Pavesi, Maurizio Parton, Francesco Morandin
Abstract: In 2021, Adam Zsolt Wagner proposed an approach to disprove conjectures in graph theory using Reinforcement Learning (RL). Wagner's idea can be framed as follows: consider a conjecture, such as a certain quantity f(G) < 0 for every graph G; one can then play a single-player graph-building game, where at each turn the player decides whether to add an edge or not. The game ends when all edges have been considered, resulting in a certain graph G_T, and f(G_T) is the final score of the game; RL is then used to maximize this score. This brilliant idea is as simple as innovative, and it lends itself to systematic generalization. Several different single-player graph-building games can be employed, along with various RL algorithms. Moreover, RL maximizes the cumulative reward, allowing for step-by-step rewards instead of a single final score, provided the final cumulative reward represents the quantity of interest f(G_T). In this paper, we discuss these and various other choices that can be significant in Wagner's framework. As a contribution to this systematization, we present four distinct single-player graph-building games. Each game employs both a step-by-step reward system and a single final score. We also propose a principled approach to select the most suitable neural network architecture for any given conjecture, and introduce a new dataset of graphs labeled with their Laplacian spectra. Furthermore, we provide a counterexample for a conjecture regarding the sum of the matching number and the spectral radius, which is simpler than the example provided in Wagner's original paper. The games have been implemented as environments in the Gymnasium framework, and along with the dataset, are available as open-source supplementary materials.
Authors: Thien Nguyen, Tuomo Sipola, Jari Hautam\"aki
Abstract: At the intersection of quantum computing and machine learning, this review paper explores the transformative impact these technologies are having on the capabilities of data processing and analysis, far surpassing the bounds of traditional computational methods. Drawing upon an in-depth analysis of 32 seminal papers, this review delves into the interplay between quantum computing and machine learning, focusing on transcending the limitations of classical computing in advanced data processing and applications. This review emphasizes the potential of quantum-enhanced methods in enhancing cybersecurity, a critical sector that stands to benefit significantly from these advancements. The literature review, primarily leveraging Science Direct as an academic database, delves into the transformative effects of quantum technologies on machine learning, drawing insights from a diverse collection of studies and scholarly articles. While the focus is primarily on the growing significance of quantum computing in cybersecurity, the review also acknowledges the promising implications for other sectors as the field matures. Our systematic approach categorizes sources based on quantum machine learning algorithms, applications, challenges, and potential future developments, uncovering that quantum computing is increasingly being implemented in practical machine learning scenarios. The review highlights advancements in quantum-enhanced machine learning algorithms and their potential applications in sectors such as cybersecurity, emphasizing the need for industry-specific solutions while considering ethical and security concerns. By presenting an overview of the current state and projecting future directions, the paper sets a foundation for ongoing research and strategic advancement in quantum machine learning.
Authors: Malte Lehna, Mohamed Hassouna, Dmitry Degtyar, Sven Tomforde, Christoph Scholz
Abstract: Optimizing the topology of transmission networks using Deep Reinforcement Learning (DRL) has increasingly come into focus. Various DRL agents have been proposed, which are mostly benchmarked on the Grid2Op environment from the Learning to Run a Power Network (L2RPN) challenges. The environments have many advantages with their realistic grid scenarios and underlying power flow backends. However, the interpretation of agent survival or failure is not always clear, as there are a variety of potential causes. In this work, we focus on the failures of the power grid simulation to identify patterns and detect them in advance. We collect the failed scenarios of three different agents on the WCCI 2022 L2RPN environment, totaling about 40k data points. By clustering, we are able to detect five distinct clusters, identifying common failure types. Further, we propose a multi-class prediction approach to detect failures beforehand and evaluate five different prediction models. Here, the Light Gradient-Boosting Machine (LightGBM) shows the best failure prediction performance, with an accuracy of 82%. It also accurately classifies whether a the grid survives or fails in 87% of cases. Finally, we provide a detailed feature importance analysis that identifies critical features and regions in the grid.
Authors: Zeju Li, Ying-Qiu Zheng, Chen Chen, Saad Jbabdi
Abstract: Semi-supervised learning (SSL) algorithms struggle to perform well when exposed to imbalanced training data. In this scenario, the generated pseudo-labels can exhibit a bias towards the majority class, and models that employ these pseudo-labels can further amplify this bias. Here we investigate pseudo-labeling strategies for imbalanced SSL including pseudo-label refinement and threshold adjustment, through the lens of statistical analysis. We find that existing SSL algorithms which generate pseudo-labels using heuristic strategies or uncalibrated model confidence are unreliable when imbalanced class distributions bias pseudo-labels. To address this, we introduce SEmi-supervised learning with pseudo-label optimization based on VALidation data (SEVAL) to enhance the quality of pseudo-labelling for imbalanced SSL. We propose to learn refinement and thresholding parameters from a partition of the training dataset in a class-balanced way. SEVAL adapts to specific tasks with improved pseudo-labels accuracy and ensures pseudo-labels correctness on a per-class basis. Our experiments show that SEVAL surpasses state-of-the-art SSL methods, delivering more accurate and effective pseudo-labels in various imbalanced SSL situations. SEVAL, with its simplicity and flexibility, can enhance various SSL techniques effectively. The code is publicly available (https://github.com/ZerojumpLine/SEVAL).
Authors: Philipp Bordne, M. Asif Hasan, Eddie Bergman, Noor Awad, Andr\'e Biedenkapp
Abstract: High-dimensional action spaces remain a challenge for dynamic algorithm configuration (DAC). Interdependencies and varying importance between action dimensions are further known key characteristics of DAC problems. We argue that these Coupled Action Dimensions with Importance Differences (CANDID) represent aspects of the DAC problem that are not yet fully explored. To address this gap, we introduce a new white-box benchmark within the DACBench suite that simulates the properties of CANDID. Further, we propose sequential policies as an effective strategy for managing these properties. Such policies factorize the action space and mitigate exponential growth by learning a policy per action dimension. At the same time, these policies accommodate the interdependence of action dimensions by fostering implicit coordination. We show this in an experimental study of value-based policies on our new benchmark. This study demonstrates that sequential policies significantly outperform independent learning of factorized policies in CANDID action spaces. In addition, they overcome the scalability limitations associated with learning a single policy across all action dimensions. The code used for our experiments is available under https://github.com/PhilippBordne/candidDAC.
Authors: Andr\'e F. Cruz, Moritz Hardt, Celestine Mendler-D\"unner
Abstract: Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks. Conditioned on a question and answer-key, does the most likely token match the ground truth? Such benchmarks necessarily fail to evaluate language models' ability to quantify outcome uncertainty. In this work, we focus on the use of language models as risk scores for unrealizable prediction tasks. We introduce folktexts, a software package to systematically generate risk scores using language models, and evaluate them against US Census data products. A flexible API enables the use of different prompting schemes, local or web-hosted models, and diverse census columns that can be used to compose custom prediction tasks. We demonstrate the utility of folktexts through a sweep of empirical insights into the statistical properties of 17 recent large language models across five natural text benchmark tasks. We find that zero-shot risk scores produced by multiple-choice question-answering have high predictive signal but are widely miscalibrated. Base models consistently overestimate outcome uncertainty, while instruction-tuned models underestimate uncertainty and produce over-confident risk scores. In fact, instruction-tuning polarizes answer distribution regardless of true underlying data uncertainty. Conversely, verbally querying models for probability estimates results in substantially improved calibration across all instruction-tuned models. These differences in ability to quantify data uncertainty cannot be revealed in realizable settings, and highlight a blind-spot in the current evaluation ecosystem that \folktexts covers.
Authors: Alex Koran, Hadi Hojjati, Narges Armanfard
Abstract: Deep learning for time-series anomaly detection (TSAD) has gained significant attention over the past decade. Despite the reported improvements in several papers, the practical application of these models remains limited. Recent studies have cast doubt on these models, attributing their results to flawed evaluation techniques. However, the impact of initialization has largely been overlooked. This paper provides a critical analysis of the initialization effects on TSAD model performance. Our extensive experiments reveal that TSAD models are highly sensitive to hyperparameters such as window size, seed number, and normalization. This sensitivity often leads to significant variability in performance, which can be exploited to artificially inflate the reported efficacy of these models. We demonstrate that even minor changes in initialization parameters can result in performance variations that overshadow the claimed improvements from novel model architectures. Our findings highlight the need for rigorous evaluation protocols and transparent reporting of preprocessing steps to ensure the reliability and fairness of anomaly detection methods. This paper calls for a more cautious interpretation of TSAD advancements and encourages the development of more robust and transparent evaluation practices to advance the field and its practical applications.
Authors: Xue Wang, Tian Zhou, Jianqing Zhu, Jialin Liu, Kun Yuan, Tao Yao, Wotao Yin, Rong Jin, HanQin Cai
Abstract: Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved Attention structures are proposed to reduce the computation cost by inducing low rankness and approximating the whole sequence by sub-sequences. The most challenging part of those approaches is maintaining the proper balance between information preservation and computation reduction: the longer sub-sequences used, the better information is preserved, but at the price of introducing more noise and computational costs. In this paper, we propose a smoothed skeleton sketching based Attention structure, coined S$^3$Attention, which significantly improves upon the previous attempts to negotiate this trade-off. S$^3$Attention has two mechanisms to effectively minimize the impact of noise while keeping the linear complexity to the sequence length: a smoothing block to mix information over long sequences and a matrix sketching method that simultaneously selects columns and rows from the input matrix. We verify the effectiveness of S$^3$Attention both theoretically and empirically. Extensive studies over Long Range Arena (LRA) datasets and six time-series forecasting show that S$^3$Attention significantly outperforms both vanilla Attention and other state-of-the-art variants of Attention structures.
Authors: Kosuke Sugiyama, Masato Uchida
Abstract: While precise data observation is essential for the learning processes of predictive models, it can be challenging owing to factors such as insufficient observation accuracy, high collection costs, and privacy constraints. In this paper, we examines cases where some qualitative features are unavailable as precise information indicating "what it is," but rather as complementary information indicating "what it is not." We refer to features defined by precise information as ordinary features (OFs) and those defined by complementary information as complementary features (CFs). We then formulate a new learning scenario termed Complementary Feature Learning (CFL), where predictive models are constructed using instances consisting of OFs and CFs. The simplest formalization of CFL applies conventional supervised learning directly using the observed values of CFs. However, this approach does not resolve the ambiguity associated with CFs, making learning challenging and complicating the interpretation of the predictive model's specific predictions. Therefore, we derive an objective function from an information-theoretic perspective to estimate the OF values corresponding to CFs and to predict output labels based on these estimations. Based on this objective function, we propose a theoretically guaranteed graph-based estimation method along with its practical approximation, for estimating OF values corresponding to CFs. The results of numerical experiments conducted with real-world data demonstrate that our proposed method effectively estimates OF values corresponding to CFs and predicts output labels.
Authors: Ramon Tavares
Abstract: This study presents a comprehensive methodology for modeling and forecasting the historical time series of active fire spots detected by the AQUA\_M-T satellite in the Amazon, Brazil. The approach employs a mixed Recurrent Neural Network (RNN) model, combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures to predict the monthly accumulations of daily detected active fire spots. Data analysis revealed a consistent seasonality over time, with annual maximum and minimum values tending to repeat at the same periods each year. The primary objective is to verify whether the forecasts capture this inherent seasonality through machine learning techniques. The methodology involved careful data preparation, model configuration, and training using cross-validation with two seeds, ensuring that the data generalizes well to both the test and validation sets for both seeds. The results indicate that the combined LSTM and GRU model delivers excellent forecasting performance, demonstrating its effectiveness in capturing complex temporal patterns and modeling the observed time series. This research significantly contributes to the application of deep learning techniques in environmental monitoring, specifically in forecasting active fire spots. The proposed approach highlights the potential for adaptation to other time series forecasting challenges, opening new opportunities for research and development in machine learning and prediction of natural phenomena. Keywords: Time Series Forecasting; Recurrent Neural Networks; Deep Learning.
Authors: Saikrishna Badrinarayanan, Osonde Osoba, Miao Cheng, Ryan Rogers, Sakshi Jain, Rahul Tandra, Natesh S. Pillai
Abstract: AI fairness measurements, including tests for equal treatment, often take the form of disaggregated evaluations of AI systems. Such measurements are an important part of Responsible AI operations. These measurements compare system performance across demographic groups or sub-populations and typically require member-level demographic signals such as gender, race, ethnicity, and location. However, sensitive member-level demographic attributes like race and ethnicity can be challenging to obtain and use due to platform choices, legal constraints, and cultural norms. In this paper, we focus on the task of enabling AI fairness measurements on race/ethnicity for \emph{U.S. LinkedIn members} in a privacy-preserving manner. We present the Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE) method for performing this task. PPRE combines the Bayesian Improved Surname Geocoding (BISG) model, a sparse LinkedIn survey sample of self-reported demographics, and privacy-enhancing technologies like secure two-party computation and differential privacy to enable meaningful fairness measurements while preserving member privacy. We provide details of the PPRE method and its privacy guarantees. We then illustrate sample measurement operations. We conclude with a review of open research and engineering challenges for expanding our privacy-preserving fairness measurement capabilities.
Authors: Qingyun Sun, Zhen Guo
Abstract: We propose a scaling law hypothesis for multimodal models processing text, audio, images, and video within a shared token and embedding space. Our framework predicts model performance based on modality-specific compression and tokenization efficiency, extending established scaling laws from text-based decoder models to mixed-modality systems. We explore whether leveraging more training data in multiple modalities can reduce the size of the multimodal model, enabling efficient deployment on resource-constrained devices.
Authors: Dhruv Suri, Praneet Dutta, Flora Xue, Ines Azevedo, Ravi Jain
Abstract: As Chile's electric power sector advances toward a future powered by renewable energy, accurate forecasting of renewable generation is essential for managing grid operations. The integration of renewable energy sources is particularly challenging due to the operational difficulties of managing their power generation, which is highly variable compared to fossil fuel sources, delaying the availability of clean energy. To mitigate this, we quantify the impact of increasing intermittent generation from wind and solar on thermal power plants in Chile and introduce a hybrid wind speed forecasting methodology which combines two custom ML models for Chile. The first model is based on TiDE, an MLP-based ML model for short-term forecasts, and the second is based on a graph neural network, GraphCast, for medium-term forecasts up to 10 days. Our hybrid approach outperforms the most accurate operational deterministic systems by 4-21% for short-term forecasts and 5-23% for medium-term forecasts and can directly lower the impact of wind generation on thermal ramping, curtailment, and system-level emissions in Chile.
Authors: Kunlong Chen, Junjun Wang, Zhaoqun Chen, Kunjin Chen, Yitian Chen
Abstract: We participated in the KDD CUP 2024 paper source tracing competition and achieved the 3rd place. This competition tasked participants with identifying the reference sources (i.e., ref-sources, as referred to by the organizers of the competition) of given academic papers. Unlike most teams that addressed this challenge by fine-tuning pre-trained neural language models such as BERT or ChatGLM, our primary approach utilized closed-source large language models (LLMs). With recent advancements in LLM technology, closed-source LLMs have demonstrated the capability to tackle complex reasoning tasks in zero-shot or few-shot scenarios. Consequently, in the absence of GPUs, we employed closed-source LLMs to directly generate predicted reference sources from the provided papers. We further refined these predictions through ensemble learning. Notably, our method was the only one among the award-winning approaches that did not require the use of GPUs for model training. Code available at https://github.com/Cklwanfifa/KDDCUP2024-PST.
Authors: Zhiyue Xia, Kathleen Stewart
Abstract: Synthetic opioids are the most common drugs involved in drug-involved overdose mortalities in the U.S. The Center for Disease Control and Prevention reported that in 2018, about 70% of all drug overdose deaths involved opioids and 67% of all opioid-involved deaths were accounted for by synthetic opioids. In this study, we investigated the spread of synthetic opioids between 2013 and 2020 in the U.S., and analyzed the relationship between the spatiotemporal pattern of synthetic opioid-involved deaths and another key opioid, heroin, and compared patterns of deaths involving these two types of drugs during this time period. Spatial connections between counties were incorporated into a graph convolutional neural network model to represent and analyze the spread of synthetic opioid-involved deaths, and in the context of heroin-involved deaths.
Authors: Y. Isabel Liu, Windsor Nguyen, Yagiz Devre, Evan Dogariu, Anirudha Majumdar, Elad Hazan
Abstract: This paper describes an efficient, open source PyTorch implementation of the Spectral Transform Unit. We investigate sequence prediction tasks over several modalities including language, robotics, and simulated dynamical systems. We find that for the same parameter count, the STU and its variants outperform the Transformer as well as other leading state space models across various modalities.
Authors: Pk Douglas, Farzad Vasheghani Farahani
Abstract: The increasing use of deep neural networks (DNNs) has motivated a parallel endeavor: the design of adversaries that profit from successful misclassifications. However, not all adversarial examples are crafted for malicious purposes. For example, real world systems often contain physical, temporal, and sampling variability across instrumentation. Adversarial examples in the wild may inadvertently prove deleterious for accurate predictive modeling. Conversely, naturally occurring covariance of image features may serve didactic purposes. Here, we studied the stability of deep learning representations for neuroimaging classification across didactic and adversarial conditions characteristic of MRI acquisition variability. We show that representational similarity and performance vary according to the frequency of adversarial examples in the input space.
Authors: Md Yousuf Harun, Christopher Kanan
Abstract: Pre-trained deep neural networks (DNNs) are being widely deployed by industry for making business decisions and to serve users; however, a major problem is model decay, where the DNN's predictions become more erroneous over time, resulting in revenue loss or unhappy users. To mitigate model decay, DNNs are retrained from scratch using old and new data. This is computationally expensive, so retraining happens only once performance significantly decreases. Here, we study how continual learning (CL) could potentially overcome model decay in large pre-trained DNNs and greatly reduce computational costs for keeping DNNs up-to-date. We identify the "stability gap" as a major obstacle in our setting. The stability gap refers to a phenomenon where learning new data causes large drops in performance for past tasks before CL mitigation methods eventually compensate for this drop. We test two hypotheses to investigate the factors influencing the stability gap and identify a method that vastly reduces this gap. In large-scale experiments for both easy and hard CL distributions (e.g., class incremental learning), we demonstrate that our method reduces the stability gap and greatly increases computational efficiency. Our work aligns CL with the goals of the production setting, where CL is needed for many applications.
Authors: Nazmus Sakib Ahmed, Saad Sakib Noor, Ashraful Islam Shanto Sikder, Abhijit Paul
Abstract: This paper focuses on enhancing Bengali Document Layout Analysis (DLA) using the YOLOv8 model and innovative post-processing techniques. We tackle challenges unique to the complex Bengali script by employing data augmentation for model robustness. After meticulous validation set evaluation, we fine-tune our approach on the complete dataset, leading to a two-stage prediction strategy for accurate element segmentation. Our ensemble model, combined with post-processing, outperforms individual base architectures, addressing issues identified in the BaDLAD dataset. By leveraging this approach, we aim to advance Bengali document analysis, contributing to improved OCR and document comprehension and BaDLAD serves as a foundational resource for this endeavor, aiding future research in the field. Furthermore, our experiments provided key insights to incorporate new strategies into the established solution.
Authors: Wolfgang Stammer, Felix Friedrich, David Steinmann, Manuel Brack, Hikaru Shindo, Kristian Kersting
Abstract: Much of explainable AI research treats explanations as a means for model inspection. Yet, this neglects findings from human psychology that describe the benefit of self-explanations in an agent's learning process. Motivated by this, we introduce a novel workflow in the context of image classification, termed Learning by Self-Explaining (LSX). LSX utilizes aspects of self-refining AI and human-guided explanatory machine learning. The underlying idea is that a learner model, in addition to optimizing for the original predictive task, is further optimized based on explanatory feedback from an internal critic model. Intuitively, a learner's explanations are considered "useful" if the internal critic can perform the same task given these explanations. We provide an overview of important components of LSX and, based on this, perform extensive experimental evaluations via three different example instantiations. Our results indicate improvements via Learning by Self-Explaining on several levels: in terms of model generalization, reducing the influence of confounding factors, and providing more task-relevant and faithful model explanations. Overall, our work provides evidence for the potential of self-explaining within the learning phase of an AI model.
Authors: Aryaman Gupta, Kaustav Chakraborty, Somil Bansal
Abstract: Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these vision-based controllers can make erroneous predictions when faced with novel or out-of-distribution inputs. Such errors can cascade to catastrophic system failures and compromise system safety. In this work, we introduce a run-time anomaly monitor to detect and mitigate such closed-loop, system-level failures. Specifically, we leverage a reachability-based framework to stress-test the vision-based controller offline and mine its system-level failures. This data is then used to train a classifier that is leveraged online to flag inputs that might cause system breakdowns. The anomaly detector highlights issues that transcend individual modules and pertain to the safety of the overall system. We also design a fallback controller that robustly handles these detected anomalies to preserve system safety. We validate the proposed approach on an autonomous aircraft taxiing system that uses a vision-based controller for taxiing. Our results show the efficacy of the proposed approach in identifying and handling system-level anomalies, outperforming methods such as prediction error-based detection, and ensembling, thereby enhancing the overall safety and robustness of autonomous systems.
Authors: Md Kaykobad Reza, Ashley Prater-Bennette, M. Salman Asif
Abstract: Multimodal learning seeks to utilize data from multiple sources to improve the overall performance of downstream tasks. It is desirable for redundancies in the data to make multimodal systems robust to missing or corrupted observations in some correlated modalities. However, we observe that the performance of several existing multimodal networks significantly deteriorates if one or multiple modalities are absent at test time. To enable robustness to missing modalities, we propose a simple and parameter-efficient adaptation procedure for pretrained multimodal networks. In particular, we exploit modulation of intermediate features to compensate for the missing modalities. We demonstrate that such adaptation can partially bridge performance drop due to missing modalities and outperform independent, dedicated networks trained for the available modality combinations in some cases. The proposed adaptation requires extremely small number of parameters (e.g., fewer than 1% of the total parameters) and applicable to a wide range of modality combinations and tasks. We conduct a series of experiments to highlight the missing modality robustness of our proposed method on five different multimodal tasks across seven datasets. Our proposed method demonstrates versatility across various tasks and datasets, and outperforms existing methods for robust multimodal learning with missing modalities.
Authors: Zhixuan Liang, Xingyu Zeng, Rui Zhao, Ping Luo
Abstract: Active learning strategies aim to train high-performance models with minimal labeled data by selecting the most informative instances for labeling. However, existing methods for assessing data informativeness often fail to align directly with task model performance metrics, such as mean average precision (mAP) in object detection. This paper introduces Mean-AP Guided Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model output changes as informativeness for deep detection networks, directly optimizing the sampling strategy using mAP. MGRAL employs a reinforcement learning agent based on LSTM architecture to efficiently navigate the combinatorial challenge of batch sample selection and the non-differentiable nature between performance and selected batches. The agent optimizes selection using policy gradient with mAP improvement as the reward signal. To address the computational intensity of mAP estimation with unlabeled samples, we implement fast look-up tables, ensuring real-world feasibility. We evaluate MGRAL on PASCAL VOC and MS COCO benchmarks across various backbone architectures. Our approach demonstrates strong performance, establishing a new paradigm in reinforcement learning-based active learning for object detection.
Authors: David S\'anchez, Najeeb Jebreel, Krishnamurty Muralidhar, Josep Domingo-Ferrer, Alberto Blanco-Justicia
Abstract: The threat of reconstruction attacks has led the U.S. Census Bureau (USCB) to replace in the Decennial Census 2020 the traditional statistical disclosure limitation based on rank swapping with one based on differential privacy (DP), leading to substantial accuracy loss of released statistics. Yet, it has been argued that, if many different reconstructions are compatible with the released statistics, most of them do not correspond to actual original data, which protects against respondent reidentification. Recently, a new attack has been proposed, which incorporates the confidence that a reconstructed record was in the original data. The alleged risk of disclosure entailed by such confidence-ranked reconstruction has renewed the interest of the USCB to use DP-based solutions. To forestall a potential accuracy loss in future releases, we show that the proposed reconstruction is neither effective as a reconstruction method nor conducive to disclosure as claimed by its authors. Specifically, we report empirical results showing the proposed ranking cannot guide reidentification or attribute disclosure attacks, and hence fails to warrant the utility sacrifice entailed by the use of DP to release census statistical data.
Authors: Tal Kadosh, Niranjan Hasabnis, Vy A. Vo, Nadav Schneider, Neva Krien, Mihai Capota, Abdul Wasay, Nesreen Ahmed, Ted Willke, Guy Tamir, Yuval Pinter, Timothy Mattson, Gal Oren
Abstract: With easier access to powerful compute resources, there is a growing trend in AI for software development to develop large language models (LLMs) to address a variety of programming tasks. Even LLMs applied to tasks from the high-performance computing (HPC) domain are huge in size and demand expensive compute resources for training. This is partly because LLMs for HPC tasks are obtained by finetuning existing LLMs that support several natural and/or programming languages. We found this design choice confusing - why do we need LLMs trained on natural languages and programming languages unrelated to HPC for HPC-specific tasks? In this line of work, we aim to question choices made by existing LLMs by developing smaller language models (LMs) for specific domains - we call them domain-specific LMs. Specifically, we start with HPC as a domain and build an HPC-specific LM, named MonoCoder, which is orders of magnitude smaller than existing LMs but delivers better performance on non-HPC and HPC codes. Specifically, we pre-trained MonoCoder on an HPC-specific dataset (named HPCorpus) of C and C++ programs mined from GitHub. We evaluated the performance of MonoCoder against state-of-the-art multi-lingual LLMs. Results demonstrate that MonoCoder, although much smaller than existing LMs, outperforms other LLMs on normalized-perplexity tests (in relation to model size) while also delivering competing CodeBLEU scores for high-performance and parallel code generations. In other words, results suggest that MonoCoder understands HPC code better than state-of-the-art LLMs.
Authors: Yannik P. Wotte, Federico Califano, Stefano Stramigioli
Abstract: This work presents a novel approach for the optimization of dynamic systems on finite-dimensional Lie groups. We rephrase dynamic systems as so-called neural ordinary differential equations (neural ODEs), and formulate the optimization problem on Lie groups. A gradient descent optimization algorithm is presented to tackle the optimization numerically. Our algorithm is scalable, and applicable to any finite dimensional Lie group, including matrix Lie groups. By representing the system at the Lie algebra level, we reduce the computational cost of the gradient computation. In an extensive example, optimal potential energy shaping for control of a rigid body is treated. The optimal control problem is phrased as an optimization of a neural ODE on the Lie group SE(3), and the controller is iteratively optimized. The final controller is validated on a state-regulation task.
Authors: Haolin Chen, Philip N. Garner
Abstract: We are motivated primarily by the adaptation of text-to-speech synthesis models; however we argue that more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such adaptation. Nevertheless, catastrophic forgetting remains an issue with PEFT, damaging the pre-trained model's inherent capabilities. We demonstrate that existing Bayesian learning techniques can be applied to PEFT to prevent catastrophic forgetting as long as the parameter shift of the fine-tuned layers can be calculated differentiably. In a principled series of experiments on language modeling and speech synthesis tasks, we utilize established Laplace approximations, including diagonal and Kronecker-factored approaches, to regularize PEFT with the low-rank adaptation (LoRA) and compare their performance in pre-training knowledge preservation. Our results demonstrate that catastrophic forgetting can be overcome by our methods without degrading the fine-tuning performance, and using the Kronecker-factored approximation produces a better preservation of the pre-training knowledge than the diagonal ones.
Authors: Fr\'ed\'eric Piedboeuf, Philippe Langlais
Abstract: Textual data augmentation (DA) is a prolific field of study where novel techniques to create artificial data are regularly proposed, and that has demonstrated great efficiency on small data settings, at least for text classification tasks. In this paper, we challenge those results, showing that classical data augmentation (which modify sentences) is simply a way of performing better fine-tuning, and that spending more time doing so before applying data augmentation negates its effect. This is a significant contribution as it answers several questions that were left open in recent years, namely~: which DA technique performs best (all of them as long as they generate data close enough to the training set, as to not impair training) and why did DA show positive results (facilitates training of network). We further show that zero- and few-shot DA via conversational agents such as ChatGPT or LLama2 can increase performances, confirming that this form of data augmentation is preferable to classical methods.
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: Dongshu Liu, J\'er\'emie Laydevant, Adrien Pontlevy, Xing Chen, Damien Querlioz, Julie Grollier
Abstract: Designing algorithms for versatile AI hardware that can learn on the edge using both labeled and unlabeled data is challenging. Deep end-to-end training methods incorporating phases of self-supervised and supervised learning are accurate and adaptable to input data but self-supervised learning requires even more computational and memory resources than supervised learning, too high for current embedded hardware. Conversely, unsupervised layer-by-layer training, such as Hebbian learning, is more compatible with existing hardware but does not integrate well with supervised learning. To address this, we propose a method enabling networks or hardware designed for end-to-end supervised learning to also perform high-performance unsupervised learning by adding two simple elements to the output layer: Winner-Take-All (WTA) selectivity and homeostasis regularization. These mechanisms introduce a "self-defined target" for unlabeled data, allowing purely unsupervised training for both fully-connected and convolutional layers using backpropagation or equilibrium propagation on datasets like MNIST (up to 99.2%), Fashion-MNIST (up to 90.3%), and SVHN (up to 81.5%). We extend this method to semi-supervised learning, adjusting targets based on data type, achieving 96.6% accuracy with only 600 labeled MNIST samples in a multi-layer perceptron. Our results show that this approach can effectively enable networks and hardware initially dedicated to supervised learning to also perform unsupervised learning, adapting to varying availability of labeled data.
Authors: Amin Dada, Marie Bauer, Amanda Butler Contreras, Osman Alperen Kora\c{s}, Constantin Marc Seibold, Kaleb E Smith, Jens Kleesiek
Abstract: Large Language Models (LLMs) are expected to significantly contribute to patient care, diagnostics, and administrative processes. Emerging biomedical LLMs aim to address healthcare-specific challenges, including privacy demands and computational constraints. Assessing the models' suitability for this sensitive application area is of the utmost importance. However, biomedical training has not been systematically evaluated on medical tasks. This study investigates the effect of biomedical training in the context of six practical medical tasks evaluating $25$ models. In contrast to previous evaluations, our results reveal a performance decline in nine out of twelve biomedical models after fine-tuning, particularly on tasks involving hallucinations, ICD10 coding, and instruction adherence. General-domain models like Meta-Llama-3.1-70B-Instruct outperformed their biomedical counterparts, indicating a trade-off between domain-specific fine-tuning and general medical task performance. We open-source all evaluation scripts and datasets at https://github.com/TIO-IKIM/CLUE to support further research in this critical area.
Authors: Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
Abstract: Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities remain poorly understood. In this paper, we explore the hypothesis that LLMs process concepts of varying complexities in different layers, introducing the idea of ``Concept Depth'' to suggest that more complex concepts are typically acquired in deeper layers. Specifically, we categorize concepts based on their level of abstraction, defining them in the order of increasing complexity within factual, emotional, and inferential tasks. We conduct extensive probing experiments using layer-wise representations across various LLM families (Gemma, LLaMA, Qwen) on various datasets spanning the three domains of tasks. Our findings reveal that models could efficiently conduct probing for simpler tasks in shallow layers, and more complex tasks typically necessitate deeper layers for accurate understanding. Additionally, we examine how external factors, such as adding noise to the input and quantizing the model weights, might affect layer-wise representations. Our findings suggest that these factors can impede the development of a conceptual understanding of LLMs until deeper layers are explored. We hope that our proposed concept and experimental insights will enhance the understanding of the mechanisms underlying LLMs. Our codes are available at \url{https://github.com/Luckfort/CD}.
Authors: Jay Patrikar, Sushant Veer, Apoorva Sharma, Marco Pavone, Sebastian Scherer
Abstract: Modern motion planners for autonomous driving frequently use imitation learning (IL) to draw from expert driving logs. Although IL benefits from its ability to glean nuanced and multi-modal human driving behaviors from large datasets, the resulting planners often struggle with out-of-distribution (OOD) scenarios and with traffic rule compliance. On the other hand, classical rule-based planners, by design, can generate safe traffic rule compliant behaviors while being robust to OOD scenarios, but these planners fail to capture nuances in agent-to-agent interactions and human drivers' intent. RuleFuser, an evidential framework, combines IL planners with classical rule-based planners to draw on the complementary benefits of both, thereby striking a balance between imitation and safety. Our approach, tested on the real-world nuPlan dataset, combines the IL planner's high performance in in-distribution (ID) scenarios with the rule-based planners' enhanced safety in out-of-distribution (OOD) scenarios, achieving a 38.43% average improvement on safety metrics over the IL planner without much detriment to imitation metrics in OOD scenarios.
Authors: Zakaria Patel, Kirill Serkh
Abstract: Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images (e.g., bounding boxes) require fine-tuning, a smaller and more recent subset of these methods take advantage of the models' attention mechanism, and are training-free. These methods generally fall into one of two categories. The first entails modifying the cross-attention maps of specific tokens directly to enhance the signal in certain regions of the image. The second works by defining a loss function over the cross-attention maps, and using the gradient of this loss to guide the latent. While previous work explores these as alternative strategies, we provide an interpretation for these methods which highlights their complimentary features, and demonstrate that it is possible to obtain superior performance when both methods are used in concert.
Authors: Hao Zhou, Chengming Hu, Xue Liu
Abstract: Reconfigurable intelligent surface (RIS) becomes a promising technique for 6G networks by reshaping signal propagation in smart radio environments. However, it also leads to significant complexity for network management due to the large number of elements and dedicated phase-shift optimization. In this work, we provide an overview of machine learning (ML)-enabled optimization for RIS-aided 6G networks. In particular, we focus on various reinforcement learning (RL) techniques, e.g., deep Q-learning, multi-agent reinforcement learning, transfer reinforcement learning, hierarchical reinforcement learning, and offline reinforcement learning. Different from existing studies, this work further discusses how large language models (LLMs) can be combined with RL to handle network optimization problems. It shows that LLM offers new opportunities to enhance the capabilities of RL algorithms in terms of generalization, reward function design, multi-modal information processing, etc. Finally, we identify the future challenges and directions of ML-enabled optimization for RIS-aided 6G networks.
Authors: Parnian Kassraie, Aram-Alexandre Pooladian, Michal Klein, James Thornton, Jonathan Niles-Weed, Marco Cuturi
Abstract: Optimal transport (OT) has profoundly impacted machine learning by providing theoretical and computational tools to realign datasets. In this context, given two large point clouds of sizes $n$ and $m$ in $\mathbb{R}^d$, entropic OT (EOT) solvers have emerged as the most reliable tool to either solve the Kantorovich problem and output a $n\times m$ coupling matrix, or to solve the Monge problem and learn a vector-valued push-forward map. While the robustness of EOT couplings/maps makes them a go-to choice in practical applications, EOT solvers remain difficult to tune because of a small but influential set of hyperparameters, notably the omnipresent entropic regularization strength $\varepsilon$. Setting $\varepsilon$ can be difficult, as it simultaneously impacts various performance metrics, such as compute speed, statistical performance, generalization, and bias. In this work, we propose a new class of EOT solvers (ProgOT), that can estimate both plans and transport maps. We take advantage of several opportunities to optimize the computation of EOT solutions by dividing mass displacement using a time discretization, borrowing inspiration from dynamic OT formulations, and conquering each of these steps using EOT with properly scheduled parameters. We provide experimental evidence demonstrating that ProgOT is a faster and more robust alternative to standard solvers when computing couplings at large scales, even outperforming neural network-based approaches. We also prove statistical consistency of our approach for estimating optimal transport maps.
Authors: Vladimir Bataev, Hainan Xu, Daniel Galvez, Vitaly Lavrukhin, Boris Ginsburg
Abstract: This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models. We redesign the standard nested-loop design for RNN-T decoding, swapping loops over frames and labels: the outer loop iterates over labels, while the inner loop iterates over frames searching for the next non-blank symbol. Additionally, we represent partial hypotheses in a special structure using CUDA tensors, supporting parallelized hypotheses manipulations. Experiments show that the label-looping algorithm is up to 2.0X faster than conventional batched decoding when using batch size 32. It can be further combined with other compiler or GPU call-related techniques to achieve even more speedup. Our algorithm is general-purpose and can work with both conventional Transducers and Token-and-Duration Transducers. We open-source our implementation to benefit the research community.
Authors: Evan M. Williams, Peter Carragher, Kathleen M. Carley
Abstract: Proactive content moderation requires platforms to rapidly and continuously evaluate the credibility of websites. Leveraging the direct and indirect paths users follow to unreliable websites, we develop a website credibility classification and discovery system that integrates both webgraph and large-scale social media contexts. We additionally introduce the concept of dredge words, terms or phrases for which unreliable domains rank highly on search engines, and provide the first exploration of their usage on social media. Our graph neural networks that combine webgraph and social media contexts generate to state-of-the-art results in website credibility classification and significantly improves the top-k identification of unreliable domains. Additionally, we release a novel dataset of dredge words, highlighting their strong connections to both social media and online commerce platforms.
Authors: Gayane Ghazaryan, Erik Arakelyan, Pasquale Minervini, Isabelle Augenstein
Abstract: Question Answering (QA) datasets have been instrumental in developing and evaluating Large Language Model (LLM) capabilities. However, such datasets are scarce for languages other than English due to the cost and difficulties of collection and manual annotation. This means that producing novel models and measuring the performance of multilingual LLMs in low-resource languages is challenging. To mitigate this, we propose $\textbf{S}$yn$\textbf{DAR}$in, a method for generating and validating QA datasets for low-resource languages. We utilize parallel content mining to obtain $\textit{human-curated}$ paragraphs between English and the target language. We use the English data as context to $\textit{generate}$ synthetic multiple-choice (MC) question-answer pairs, which are automatically translated and further validated for quality. Combining these with their designated non-English $\textit{human-curated}$ paragraphs form the final QA dataset. The method allows to maintain the content quality, reduces the likelihood of factual errors, and circumvents the need for costly annotation. To test the method, we created a QA dataset with $1.2$K samples for the Armenian language. The human evaluation shows that $98\%$ of the generated English data maintains quality and diversity in the question types and topics, while the translation validation pipeline can filter out $\sim70\%$ of data with poor quality. We use the dataset to benchmark state-of-the-art LLMs, showing their inability to achieve human accuracy with some model performances closer to random chance. This shows that the generated dataset is non-trivial and can be used to evaluate reasoning capabilities in low-resource language.
Authors: Chen Liu, Ke Xu, Liangbo L. Shen, Guillaume Huguet, Zilong Wang, Alexander Tong, Danilo Bzdok, Jay Stewart, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy
Abstract: Advances in medical imaging technologies have enabled the collection of longitudinal images, which involve repeated scanning of the same patients over time, to monitor disease progression. However, predictive modeling of such data remains challenging due to high dimensionality, irregular sampling, and data sparsity. To address these issues, we propose ImageFlowNet, a novel model designed to forecast disease trajectories from initial images while preserving spatial details. ImageFlowNet first learns multiscale joint representation spaces across patients and time points, then optimizes deterministic or stochastic flow fields within these spaces using a position-parameterized neural ODE/SDE framework. The model leverages a UNet architecture to create robust multiscale representations and mitigates data scarcity by combining knowledge from all patients. We provide theoretical insights that support our formulation of ODEs, and motivate our regularizations involving high-level visual features, latent space organization, and trajectory smoothness. We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods. Our contributions include the development of ImageFlowNet, its theoretical underpinnings, and empirical validation on real-world datasets. The official implementation is available at https://github.com/KrishnaswamyLab/ImageFlowNet.
Authors: Zeliang Zhang, Xiaodong Liu, Hao Cheng, Chenliang Xu, Jianfeng Gao
Abstract: By increasing model parameters but activating them sparsely when performing a task, the use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large Language Models (LLMs) without increasing the inference cost. However, the memory consumption due to the growing number of experts presents a challenge to the deployment of these models in many real world settings. Our empirical study reveals that some experts encode redundant knowledge during pre-training. We thus propose a method of grouping and pruning similar experts to improve the model's parameter efficiency. We validate the effectiveness of our method by pruning three state-of-the-art MoE architectures, including Mixtral, Deepseek-MoE, and Qwen. The evaluation shows that our method outperforms other model pruning methods on a range of natural language tasks. We will release our code to facilitate future research.
Authors: Seok Hwan Lee, Taein Son, Soo Won Seo, Jisong Kim, Jun Won Choi
Abstract: Video action detection (VAD) is a formidable vision task that involves the localization and classification of actions within the spatial and temporal dimensions of a video clip. Among the myriad VAD architectures, two-stage VAD methods utilize a pre-trained person detector to extract the region of interest features, subsequently employing these features for action detection. However, the performance of two-stage VAD methods has been limited as they depend solely on localized actor features to infer action semantics. In this study, we propose a new two-stage VAD framework called Joint Actor-scene context Relation modeling based on Visual Semantics (JARViS), which effectively consolidates cross-modal action semantics distributed globally across spatial and temporal dimensions using Transformer attention. JARViS employs a person detector to produce densely sampled actor features from a keyframe. Concurrently, it uses a video backbone to create spatio-temporal scene features from a video clip. Finally, the fine-grained interactions between actors and scenes are modeled through a Unified Action-Scene Context Transformer to directly output the final set of actions in parallel. Our experimental results demonstrate that JARViS outperforms existing methods by significant margins and achieves state-of-the-art performance on three popular VAD datasets, including AVA, UCF101-24, and JHMDB51-21.
Authors: Robert Geirhos, Priyank Jaini, Austin Stone, Sourabh Medapati, Xi Yi, George Toderici, Abhijit Ogale, Jonathon Shlens
Abstract: Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is nearly impossible, since all information is distributed across the network's weights. We here explore a simple, compelling alternative by marrying the representational power of deep neural networks with the flexibility of a database. Decomposing the task of image classification into image similarity (from a pre-trained embedding) and search (via fast nearest neighbor retrieval from a knowledge database), we build a simple and flexible visual memory that has the following key capabilities: (1.) The ability to flexibly add data across scales: from individual samples all the way to entire classes and billion-scale data; (2.) The ability to remove data through unlearning and memory pruning; (3.) An interpretable decision-mechanism on which we can intervene to control its behavior. Taken together, these capabilities comprehensively demonstrate the benefits of an explicit visual memory. We hope that it might contribute to a conversation on how knowledge should be represented in deep vision models -- beyond carving it in "stone" weights.
Authors: Yansel Gonzalez Tejeda, Helmut A. Mayer
Abstract: In this tutorial, we present a compact and holistic discussion of Deep Learning with a focus on Convolutional Neural Networks (CNNs) and supervised regression. While there are numerous books and articles on the individual topics we cover, comprehensive and detailed tutorials that address Deep Learning from a foundational yet rigorous and accessible perspective are rare. Most resources on CNNs are either too advanced, focusing on cutting-edge architectures, or too narrow, addressing only specific applications like image classification.This tutorial not only summarizes the most relevant concepts but also provides an in-depth exploration of each, offering a complete yet agile set of ideas. Moreover, we highlight the powerful synergy between learning theory, statistic, and machine learning, which together underpin the Deep Learning and CNN frameworks. We aim for this tutorial to serve as an optimal resource for students, professors, and anyone interested in understanding the foundations of Deep Learning. Upon acceptance we will provide an accompanying repository under \href{https://github.com/neoglez/deep-learning-tutorial}{https://github.com/neoglez/deep-learning-tutorial} Keywords: Tutorial, Deep Learning, Convolutional Neural Networks, Machine Learning.
URLs: https://github.com/neoglez/deep-learning-tutorial, https://github.com/neoglez/deep-learning-tutorial
Authors: Yoshitaka Inoue, Tianci Song, Tianfan Fu
Abstract: Drug repurposing offers a promising avenue for accelerating drug development by identifying new therapeutic potentials of existing drugs. In this paper, we propose a multi-agent framework to enhance the drug repurposing process using state-of-the-art machine learning techniques and knowledge integration. Our framework comprises several specialized agents: an AI Agent trains robust drug-target interaction (DTI) models; a Knowledge Graph Agent utilizes the drug-gene interaction database (DGIdb), DrugBank, Comparative Toxicogenomics Database (CTD), and Search Tool for Interactions of Chemicals (STITCH) to systematically extract DTIs; and a Search Agent interacts with biomedical literature to annotate and verify computational predictions. By integrating outputs from these agents, our system effectively harnesses diverse data sources, including external databases, to propose viable repurposing candidates. Preliminary results demonstrate the potential of our approach in not only predicting drug-disease interactions but also in reducing the time and cost associated with traditional drug discovery methods. This paper highlights the scalability of multi-agent systems in biomedical research and their role in driving innovation in drug repurposing. Our approach not only outperforms existing methods in predicting drug repurposing potential but also provides interpretable results, paving the way for more efficient and cost-effective drug discovery processes.
Authors: Fatma Yasmine Loumachi, Mohamed Chahine Ghanem
Abstract: Timeline Analysis (TA) plays a crucial role in Timeline Forensics (TF) within the field of Digital Forensics (DF). It focuses on examining and analyzing time-based digital artefacts, such as timestamps derived from event logs, file metadata, and other relevant data, to correlate events linked to cyber incidents and reconstruct their chronological sequence. Traditional tools often struggle to efficiently handle the large volume and variety of data generated during DF investigations and Incident Response (IR) processes. This paper introduces a novel framework, GenDFIR, which combines Rule-Based Artificial Intelligence (R-BAI) algorithms with Large Language Models (LLMs) to enhance and automate the TA process. The proposed approach consists of two key stages: (1) R-BAI is used to identify and select anomalous digital artefacts based on predefined rules. (2) The selected artefacts are then transformed into embeddings for processing by an LLM with the assistance of a Retrieval-Augmented Generation (RAG) agent. The LLM uses its capabilities to perform automated TA on the artefacts and predict potential incident outcomes. To validate the framework, we evaluated its performance, efficiency, and reliability. Several metrics were applied to simulated cyber incident scenarios, which were presented as forensic case documents. Our findings demonstrate the significant potential of integrating R-BAI and LLMs for TA. This innovative approach underscores the power of Generative AI (GenAI), particularly LLMs, and opens up new possibilities for advanced threat detection and incident reconstruction, marking a significant advancement in the field.
Authors: Zhuoxin Chen, Will Ma
Abstract: In the Newsvendor problem, the goal is to guess the number that will be drawn from some distribution, with asymmetric consequences for guessing too high vs. too low. In the data-driven version, the distribution is unknown, and one must work with samples from the distribution. Data-driven Newsvendor has been studied under many variants: additive vs. multiplicative regret, high probability vs. expectation bounds, and different distribution classes. This paper studies all combinations of these variants, filling in many gaps in the literature and simplifying many proofs. In particular, we provide a unified analysis based on the notion of clustered distributions, which in conjunction with our new lower bounds, shows that the entire spectrum of regrets between $1/\sqrt{n}$ and $1/n$ can be possible.
Authors: T. Aleksandra Ma, Alexander Lerch
Abstract: In the realm of digital music, using tags to efficiently organize and retrieve music from extensive databases is crucial for music catalog owners. Human tagging by experts is labor-intensive but mostly accurate, whereas automatic tagging through supervised learning has approached satisfying accuracy but is restricted to a predefined set of training tags. Few-shot learning offers a viable solution to expand beyond this small set of predefined tags by enabling models to learn from only a few human-provided examples to understand tag meanings and subsequently apply these tags autonomously. We propose to integrate few-shot learning methodology into multi-label music auto-tagging by using features from pre-trained models as inputs to a lightweight linear classifier, also known as a linear probe. We investigate different popular pre-trained features, as well as different few-shot parametrizations with varying numbers of classes and samples per class. Our experiments demonstrate that a simple model with pre-trained features can achieve performance close to state-of-the-art models while using significantly less training data, such as 20 samples per tag. Additionally, our linear probe performs competitively with leading models when trained on the entire training dataset. The results show that this transfer learning-based few-shot approach could effectively address the issue of automatically assigning long-tail tags with only limited labeled data.
Authors: Beilong Tang, Bang Zeng, Ming Li
Abstract: We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate target speaker information. Language models are employed to capture the sequence dependencies, while a scalable HiFi-GAN is used to reconstruct the audio from the tokens. By applying a cross-entropy loss, TSELM models the probability distribution of output tokens, thus converting the complex regression problem of audio generation into a classification task. Experimental results show that TSELM achieves excellent results in speech quality and comparable results in speech intelligibility.
Authors: Henry Li Xinyuan, Zexin Cai, Ashi Garg, Kevin Duh, Leibny Paola Garc\'ia-Perera, Sanjeev Khudanpur, Nicholas Andrews, Matthew Wiesner
Abstract: We present a number of systems for the Voice Privacy Challenge, including voice conversion based systems such as the kNN-VC method and the WavLM voice Conversion method, and text-to-speech (TTS) based systems including Whisper-VITS. We found that while voice conversion systems better preserve emotional content, they struggle to conceal speaker identity in semi-white-box attack scenarios; conversely, TTS methods perform better at anonymization and worse at emotion preservation. Finally, we propose a random admixture system which seeks to balance out the strengths and weaknesses of the two category of systems, achieving a strong EER of over 40% while maintaining UAR at a respectable 47%.
Authors: Aditya Shirwatkar, Naman Saxena, Kishore Chandra, Shishir Kolathaya
Abstract: A core strength of Model Predictive Control (MPC) for quadrupedal locomotion has been its ability to enforce constraints and provide interpretability of the sequence of commands over the horizon. However, despite being able to plan, MPC struggles to scale with task complexity, often failing to achieve robust behavior on rapidly changing surfaces. On the other hand, model-free Reinforcement Learning (RL) methods have outperformed MPC on multiple terrains, showing emergent motions but inherently lack any ability to handle constraints or perform planning. To address these limitations, we propose a framework that integrates proprioceptive planning with RL, allowing for agile and safe locomotion behaviors through the horizon. Inspired by MPC, we incorporate an internal model that includes a velocity estimator and a Dreamer module. During training, the framework learns an expert policy and an internal model that are co-dependent, facilitating exploration for improved locomotion behaviors. During deployment, the Dreamer module solves an infinite-horizon MPC problem, adapting actions and velocity commands to respect the constraints. We validate the robustness of our training framework through ablation studies on internal model components and demonstrate improved robustness to training noise. Finally, we evaluate our approach across multi-terrain scenarios in both simulation and hardware.
Authors: Chao-Han Huck Yang, Taejin Park, Yuan Gong, Yuanchao Li, Zhehuai Chen, Yen-Ting Lin, Chen Chen, Yuchen Hu, Kunal Dhawan, Piotr \.Zelasko, Chao Zhang, Yun-Nung Chen, Yu Tsao, Jagadeesh Balam, Boris Ginsburg, Sabato Marco Siniscalchi, Eng Siong Chng, Peter Bell, Catherine Lai, Shinji Watanabe, Andreas Stolcke
Abstract: Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To explore new capabilities in language modeling for speech processing, we introduce the generative speech transcription error correction (GenSEC) challenge. This challenge comprises three post-ASR language modeling tasks: (i) post-ASR transcription correction, (ii) speaker tagging, and (iii) emotion recognition. These tasks aim to emulate future LLM-based agents handling voice-based interfaces while remaining accessible to a broad audience by utilizing open pretrained language models or agent-based APIs. We also discuss insights from baseline evaluations, as well as lessons learned for designing future evaluations.
Authors: Samuel Belkadi, Libo Ren, Nicolo Micheletti, Lifeng Han, Goran Nenadic
Abstract: In this paper, we present a system that generates synthetic free-text medical records, such as discharge summaries, admission notes and doctor correspondences, using Masked Language Modeling (MLM). Our system is designed to preserve the critical information of the records while introducing significant diversity and minimizing re-identification risk. The system incorporates a de-identification component that uses Philter to mask Protected Health Information (PHI), followed by a Medical Entity Recognition (NER) model to retain key medical information. We explore various masking ratios and mask-filling techniques to balance the trade-off between diversity and fidelity in the synthetic outputs without affecting overall readability. Our results demonstrate that the system can produce high-quality synthetic data with significant diversity while achieving a HIPAA-compliant PHI recall rate of 0.96 and a low re-identification risk of 0.035. Furthermore, downstream evaluations using a NER task reveal that the synthetic data can be effectively used to train models with performance comparable to those trained on real data. The flexibility of the system allows it to be adapted for specific use cases, making it a valuable tool for privacy-preserving data generation in medical research and healthcare applications.
Authors: Zhaosong Lu, Sanyou Mei, Yifeng Xiao
Abstract: In this paper, we study a class of deterministically constrained stochastic optimization problems. Existing methods typically aim to find an $\epsilon$-stochastic stationary point, where the expected violations of both constraints and first-order stationarity are within a prescribed accuracy $\epsilon$. However, in many practical applications, it is crucial that the constraints be nearly satisfied with certainty, making such an $\epsilon$-stochastic stationary point potentially undesirable due to the risk of significant constraint violations. To address this issue, we propose single-loop variance-reduced stochastic first-order methods, where the stochastic gradient of the stochastic component is computed using either a truncated recursive momentum scheme or a truncated Polyak momentum scheme for variance reduction, while the gradient of the deterministic component is computed exactly. Under the error bound condition with a parameter $\theta \geq 1$ and other suitable assumptions, we establish that the proposed methods achieve a sample complexity and first-order operation complexity of $\widetilde O(\epsilon^{-\max\{4, 2\theta\}})$ for finding a stronger $\epsilon$-stochastic stationary point, where the constraint violation is within $\epsilon$ with certainty, and the expected violation of first-order stationarity is within $\epsilon$. To the best of our knowledge, this is the first work to develop methods with provable complexity guarantees for finding an approximate stochastic stationary point of such problems that nearly satisfies all constraints with certainty.