Authors: Fangqi Liu, Rishav Sen, Jose Paolo Talusan, Ava Pettet, Aaron Kandel, Yoshinori Suzue, Ayan Mukhopadhyay, Abhishek Dubey
Abstract: Strategic aggregation of electric vehicle batteries as energy reservoirs can optimize power grid demand, benefiting smart and connected communities, especially large office buildings that offer workplace charging. This involves optimizing charging and discharging to reduce peak energy costs and net peak demand, monitored over extended periods (e.g., a month), which involves making sequential decisions under uncertainty and delayed and sparse rewards, a continuous action space, and the complexity of ensuring generalization across diverse conditions. Existing algorithmic approaches, e.g., heuristic-based strategies, fall short in addressing real-time decision-making under dynamic conditions, and traditional reinforcement learning (RL) models struggle with large state-action spaces, multi-agent settings, and the need for long-term reward optimization. To address these challenges, we introduce a novel RL framework that combines the Deep Deterministic Policy Gradient approach (DDPG) with action masking and efficient MILP-driven policy guidance. Our approach balances the exploration of continuous action spaces to meet user charging demands. Using real-world data from a major electric vehicle manufacturer, we show that our approach comprehensively outperforms many well-established baselines and several scalable heuristic approaches, achieving significant cost savings while meeting all charging requirements. Our results show that the proposed approach is one of the first scalable and general approaches to solving the V2B energy management challenge.
Authors: Yu Bo, Weian Mao, Yanjun Shao, Weiqiang Bai, Peng Ye, Xinzhu Ma, Junbo Zhao, Hao Chen, Chunhua Shen
Abstract: In recent years, a variety of methods based on Transformer and state space model (SSM) architectures have been proposed, advancing foundational DNA language models. However, there is a lack of comparison between these recent approaches and the classical architecture convolutional networks (CNNs) on foundation model benchmarks. This raises the question: are CNNs truly being surpassed by these recent approaches based on transformer and SSM architectures? In this paper, we develop a simple but well-designed CNN-based method termed ConvNova. ConvNova identifies and proposes three effective designs: 1) dilated convolutions, 2) gated convolutions, and 3) a dual-branch framework for gating mechanisms. Through extensive empirical experiments, we demonstrate that ConvNova significantly outperforms recent methods on more than half of the tasks across several foundation model benchmarks. For example, in histone-related tasks, ConvNova exceeds the second-best method by an average of 5.8%, while generally utilizing fewer parameters and enabling faster computation. In addition, the experiments observed findings that may be related to biological characteristics. This indicates that CNNs are still a strong competitor compared to Transformers and SSMs. We anticipate that this work will spark renewed interest in CNN-based methods for DNA foundation models.
Authors: Milan Vojnovic, Se-Young Yun
Abstract: In this note, we examine the aggregation of preferences achieved by the Group Policy Optimisation (GRPO) algorithm, a reinforcement learning method used to train advanced artificial intelligence models such as DeepSeek-R1-Zero and DeepSeekMath. The GRPO algorithm trains a policy using a reward preference model, which is computed by sampling a set of outputs for a given context, observing the corresponding rewards, and applying shift-and-scale normalisation to these reward values. Additionally, it incorporates a penalty function to discourage deviations from a reference policy. We present a framework that enables us to characterise the stationary policies of the GRPO algorithm. This analysis reveals that the aggregation of preferences differs fundamentally from standard logarithmic pooling, which is implemented by other approaches such as RLHF. The precise form of preference aggregation arises from the way the reward preference model is defined and from the penalty function, which we show to essentially correspond to the reverse Kullback-Leibler (KL) divergence between the aggregation policy and the reference policy. Interestingly, we demonstrate that for groups of size two, the reward preference model corresponds to pairwise comparison preferences, similar to those in other alignment methods based on pairwise comparison feedback. We provide explicit characterisations of the aggregate preference for binary questions, for groups of size two, and in the limit of large group size. This provides insights into the dependence of the aggregate preference on parameters such as the regularisation constant and the confidence margin of question answers. Finally, we discuss the aggregation of preferences obtained by modifying the GRPO algorithm to use direct KL divergence as the penalty or to use rewards without scale normalisation.
Authors: Jiyue Tao, Tongsheng Shen, Dexin Zhao, Feitian Zhang
Abstract: The target defense problem involves intercepting an attacker before it reaches a designated target region using one or more defenders. This letter focuses on a particularly challenging scenario in which the attacker is more agile than the defenders, significantly increasing the difficulty of effective interception. To address this challenge, we propose a novel residual policy framework that integrates deep reinforcement learning (DRL) with the force-based Boids model. In this framework, the Boids model serves as a baseline policy, while DRL learns a residual policy to refine and optimize the defenders' actions. Simulation experiments demonstrate that the proposed method consistently outperforms traditional interception policies, whether learned via vanilla DRL or fine-tuned from force-based methods. Moreover, the learned policy exhibits strong scalability and adaptability, effectively handling scenarios with varying numbers of defenders and attackers with different agility levels.
Authors: Amol Khanna, Fred Lu, Edward Raff
Abstract: Linear $L_1$-regularized models have remained one of the simplest and most effective tools in data science. Over the past decade, screening rules have risen in popularity as a way to eliminate features when producing the sparse regression weights of $L_1$ models. However, despite the increasing need of privacy-preserving models for data analysis, to the best of our knowledge, no differentially private screening rule exists. In this paper, we develop the first private screening rule for linear regression. We initially find that this screening rule is too strong: it screens too many coefficients as a result of the private screening step. However, a weakened implementation of private screening reduces overscreening and improves performance.
Authors: Matthias Schulz, Gwendal Jouan, Daniel Berger, Stefan Gavranovic, Dirk Hartmann
Abstract: In recent years, augmentation of differentiable PDE solvers with neural networks has shown promising results, particularly in fluid simulations. However, most approaches rely on convolutional neural networks and custom solvers operating on Cartesian grids with efficient access to cell data. This particular choice poses challenges for industrial-grade solvers that operate on unstructured meshes, where access is restricted to neighboring cells only. In this work, we address this limitation using a novel architecture, named Transported Memory Networks. The architecture draws inspiration from both traditional turbulence models and recurrent neural networks, and it is fully compatible with generic discretizations. Our results show that it is point-wise and statistically comparable to, or improves upon, previous methods in terms of both accuracy and computational efficiency.
Authors: Aline Xavier Fid\^encio, Felix Gr\"un, Christian Klaes, Ioannis Iossifidis
Abstract: Brain-computer interfaces (BCIs) provide alternative communication methods for individuals with motor disabilities by allowing control and interaction with external devices. Non-invasive BCIs, especially those using electroencephalography (EEG), are practical and safe for various applications. However, their performance is often hindered by EEG non-stationarities, caused by changing mental states or device characteristics like electrode impedance. This challenge has spurred research into adaptive BCIs that can handle such variations. In recent years, interest has grown in using error-related potentials (ErrPs) to enhance BCI performance. ErrPs, neural responses to errors, can be detected non-invasively and have been integrated into different BCI paradigms to improve performance through error correction or adaptation. This research introduces a novel adaptive ErrP-based BCI approach using reinforcement learning (RL). We demonstrate the feasibility of an RL-driven adaptive framework incorporating ErrPs and motor imagery. Utilizing two RL agents, the framework adapts dynamically to EEG non-stationarities. Validation was conducted using a publicly available motor imagery dataset and a fast-paced game designed to boost user engagement. Results show the framework's promise, with RL agents learning control policies from user interactions and achieving robust performance across datasets. However, a critical insight from the game-based protocol revealed that motor imagery in a high-speed interaction paradigm was largely ineffective for participants, highlighting task design limitations in real-time BCI applications. These findings underscore the potential of RL for adaptive BCIs while pointing out practical constraints related to task complexity and user responsiveness.
Authors: Uri Itai, Asael Bar Ilan, Teddy Lazebnik
Abstract: The rapid advancements in data-driven methodologies have underscored the critical importance of ensuring data quality. Consequently, detecting out-of-distribution (OOD) data has emerged as an essential task to maintain the reliability and robustness of data-driven models, in general, and machine and deep learning models, in particular. In this study, we leveraged the convex hull property of a dataset and the fact that anomalies highly contribute to the increase of the CH's volume to propose a novel anomaly detection algorithm. Our algorithm computes the CH's volume as an increasing number of data points are removed from the dataset to define a decision line between OOD and in-distribution data points. We compared the proposed algorithm to seven widely used anomaly detection algorithms over ten datasets, showing comparable results for state-of-the-art (SOTA) algorithms. Moreover, we show that with a computationally cheap and simple check, one can detect datasets that are well-suited for the proposed algorithm which outperforms the SOTA anomaly detection algorithms.
Authors: Ayana Moshruba, Shay Snyder, Hamed Poursiami, Maryam Parsa
Abstract: As machine learning models increasingly process sensitive data, understanding their vulnerability to privacy attacks is vital. Membership inference attacks (MIAs) exploit model responses to infer whether specific data points were used during training, posing a significant privacy risk. Prior research suggests that spiking neural networks (SNNs), which rely on event-driven computation and discrete spike-based encoding, exhibit greater resilience to MIAs than artificial neural networks (ANNs). This resilience stems from their non-differentiable activations and inherent stochasticity, which obscure the correlation between model responses and individual training samples. To enhance privacy in SNNs, we explore two techniques: quantization and surrogate gradients. Quantization, which reduces precision to limit information leakage, has improved privacy in ANNs. Given SNNs' sparse and irregular activations, quantization may further disrupt the activation patterns exploited by MIAs. We assess the vulnerability of SNNs and ANNs under weight and activation quantization across multiple datasets, using the attack model's receiver operating characteristic (ROC) curve area under the curve (AUC) metric, where lower values indicate stronger privacy, and evaluate the privacy-accuracy trade-off. Our findings show that quantization enhances privacy in both architectures with minimal performance loss, though full-precision SNNs remain more resilient than quantized ANNs. Additionally, we examine the impact of surrogate gradients on privacy in SNNs. Among five evaluated gradients, spike rate escape provides the best privacy-accuracy trade-off, while arctangent increases vulnerability to MIAs. These results reinforce SNNs' inherent privacy advantages and demonstrate that quantization and surrogate gradient selection significantly influence privacy-accuracy trade-offs in SNNs.
Authors: Matthew Barker, Andrew Bell, Evan Thomas, James Carr, Thomas Andrews, Umang Bhatt
Abstract: While Retrieval Augmented Generation (RAG) has emerged as a popular technique for improving Large Language Model (LLM) systems, it introduces a large number of choices, parameters and hyperparameters that must be made or tuned. This includes the LLM, embedding, and ranker models themselves, as well as hyperparameters governing individual RAG components. Yet, collectively optimizing the entire configuration in a RAG or LLM system remains under-explored - especially in multi-objective settings - due to intractably large solution spaces, noisy objective evaluations, and the high cost of evaluations. In this work, we introduce the first approach for multi-objective parameter optimization of cost, latency, safety and alignment over entire LLM and RAG systems. We find that Bayesian optimization methods significantly outperform baseline approaches, obtaining a superior Pareto front on two new RAG benchmark tasks. We conclude our work with important considerations for practitioners who are designing multi-objective RAG systems, highlighting nuances such as how optimal configurations may not generalize across tasks and objectives.
Authors: Amirhossein Roknilamouki, Arnob Ghosh, Ming Shi, Fatemeh Nourzad, Eylem Ekici, Ness B. Shroff
Abstract: In Reinforcement Learning (RL), tasks with instantaneous hard constraints present significant challenges, particularly when the decision space is non-convex or non-star-convex. This issue is especially relevant in domains like autonomous vehicles and robotics, where constraints such as collision avoidance often take a non-convex form. In this paper, we establish a regret bound of $\tilde{\mathcal{O}}\bigl(\bigl(1 + \tfrac{1}{\tau}\bigr) \sqrt{\log(\tfrac{1}{\tau}) d^3 H^4 K} \bigr)$, applicable to both star-convex and non-star-convex cases, where $d$ is the feature dimension, $H$ the episode length, $K$ the number of episodes, and $\tau$ the safety threshold. Moreover, the violation of safety constraints is zero with high probability throughout the learning process. A key technical challenge in these settings is bounding the covering number of the value-function class, which is essential for achieving value-aware uniform concentration in model-free function approximation. For the star-convex setting, we develop a novel technique called Objective Constraint-Decomposition (OCD) to properly bound the covering number. This result also resolves an error in a previous work on constrained RL. In non-star-convex scenarios, where the covering number can become infinitely large, we propose a two-phase algorithm, Non-Convex Safe Least Squares Value Iteration (NCS-LSVI), which first reduces uncertainty about the safe set by playing a known safe policy. After that, it carefully balances exploration and exploitation to achieve the regret bound. Finally, numerical simulations on an autonomous driving scenario demonstrate the effectiveness of NCS-LSVI.
Authors: A. Chervov, A. Soibelman, S. Lytkin, I. Kiselev, S. Fironov, A. Lukyanenko, A. Dolgorukova, A. Ogurtsov, F. Petrov, S. Krymskii, M. Evseev, L. Grunvald, D. Gorodkov, G. Antiufeev, G. Verbii, V. Zamkovoy, L. Cheldieva, I. Koltsov, A. Sychev, M. Obozov, A. Eliseev, S. Nikolenko, N. Narynbaev, R. Turtayev, N. Rokotyan, S. Kovalev, A. Rozanov, V. Nelin, S. Ermilov, L. Shishina, D. Mamayeva, A. Korolkova, K. Khoruzhii, A. Romanov
Abstract: This paper is the second in a series of studies on developing efficient artificial intelligence-based approaches to pathfinding on extremely large graphs (e.g. $10^{70}$ nodes) with a focus on Cayley graphs and mathematical applications. The open-source CayleyPy project is a central component of our research. The present paper proposes a novel combination of a reinforcement learning approach with a more direct diffusion distance approach from the first paper. Our analysis includes benchmarking various choices for the key building blocks of the approach: architectures of the neural network, generators for the random walks and beam search pathfinding. We compared these methods against the classical computer algebra system GAP, demonstrating that they "overcome the GAP" for the considered examples. As a particular mathematical application we examine the Cayley graph of the symmetric group with cyclic shift and transposition generators. We provide strong support for the OEIS-A186783 conjecture that the diameter is equal to n(n-1)/2 by machine learning and mathematical methods. We identify the conjectured longest element and generate its decomposition of the desired length. We prove a diameter lower bound of n(n-1)/2-n/2 and an upper bound of n(n-1)/2+ 3n by presenting the algorithm with given complexity. We also present several conjectures motivated by numerical experiments, including observations on the central limit phenomenon (with growth approximated by a Gumbel distribution), the uniform distribution for the spectrum of the graph, and a numerical study of sorting networks. To stimulate crowdsourcing activity, we create challenges on the Kaggle platform and invite contributions to improve and benchmark approaches on Cayley graph pathfinding and other tasks.
Authors: Robert Marlin, Raja Jurdak, Alsharif Abuadbba
Abstract: The widespread adoption of Electric Vehicles (EVs) poses critical challenges for energy providers, particularly in predicting charging time (temporal prediction), ensuring user privacy, and managing resources efficiently in mobility-driven networks. This paper introduces the Hierarchical Federated Learning Transformer Network (H-FLTN) framework to address these challenges. H-FLTN employs a three-tier hierarchical architecture comprising EVs, community Distributed Energy Resource Management Systems (DERMS), and the Energy Provider Data Centre (EPDC) to enable accurate spatio-temporal predictions of EV charging needs while preserving privacy. Temporal prediction is enhanced using Transformer-based learning, capturing complex dependencies in charging behavior. Privacy is ensured through Secure Aggregation, Additive Secret Sharing, and Peer-to-Peer (P2P) Sharing with Augmentation, which allow only secret shares of model weights to be exchanged while securing all transmissions. To improve training efficiency and resource management, H-FLTN integrates Dynamic Client Capping Mechanism (DCCM) and Client Rotation Management (CRM), ensuring that training remains both computationally and temporally efficient as the number of participating EVs increases. DCCM optimises client participation by limiting excessive computational loads, while CRM balances training contributions across epochs, preventing imbalanced participation. Our simulation results based on large-scale empirical vehicle mobility data reveal that DCCM and CRM reduce the training time complexity with increasing EVs from linear to constant. Its integration into real-world smart city infrastructure enhances energy demand forecasting, resource allocation, and grid stability, ensuring reliability and sustainability in future mobility ecosystems.
Authors: Gavin Brown, Lydia Zakynthinou
Abstract: Mean estimation is a fundamental task in statistics and a focus within differentially private statistical estimation. While univariate methods based on the Gaussian mechanism are widely used in practice, more advanced techniques such as the exponential mechanism over quantiles offer robustness and improved performance, especially for small sample sizes. Tukey depth mechanisms carry these advantages to multivariate data, providing similar strong theoretical guarantees. However, practical implementations fall behind these theoretical developments. In this work, we take the first step to bridge this gap by implementing the (Restricted) Tukey Depth Mechanism, a theoretically optimal mean estimator for multivariate Gaussian distributions, yielding improved practical methods for private mean estimation. Our implementations enable the use of these mechanisms for small sample sizes or low-dimensional data. Additionally, we implement variants of these mechanisms that use approximate versions of Tukey depth, trading off accuracy for faster computation. We demonstrate their efficiency in practice, showing that they are viable options for modest dimensions. Given their strong accuracy and robustness guarantees, we contend that they are competitive approaches for mean estimation in this regime. We explore future directions for improving the computational efficiency of these algorithms by leveraging fast polytope volume approximation techniques, paving the way for more accurate private mean estimation in higher dimensions.
Authors: Shahrzad Kiani, Nupur Kulkarni, Adam Dziedzic, Stark Draper, Franziska Boenisch
Abstract: Federated learning (FL) with differential privacy (DP) provides a framework for collaborative machine learning, enabling clients to train a shared model while adhering to strict privacy constraints. The framework allows each client to have an individual privacy guarantee, e.g., by adding different amounts of noise to each client's model updates. One underlying assumption is that all clients spend their privacy budgets uniformly over time (learning rounds). However, it has been shown in the literature that learning in early rounds typically focuses on more coarse-grained features that can be learned at lower signal-to-noise ratios while later rounds learn fine-grained features that benefit from higher signal-to-noise ratios. Building on this intuition, we propose a time-adaptive DP-FL framework that expends the privacy budget non-uniformly across both time and clients. Our framework enables each client to save privacy budget in early rounds so as to be able to spend more in later rounds when additional accuracy is beneficial in learning more fine-grained features. We theoretically prove utility improvements in the case that clients with stricter privacy budgets spend budgets unevenly across rounds, compared to clients with more relaxed budgets, who have sufficient budgets to distribute their spend more evenly. Our practical experiments on standard benchmark datasets support our theoretical results and show that, in practice, our algorithms improve the privacy-utility trade-offs compared to baseline schemes.
Authors: Yuki Shibukawa, Taira Tsuchiya, Shinsaku Sakaue, Kenji Yamanishi
Abstract: Online structured prediction is a task of sequentially predicting outputs with complex structures based on inputs and past observations, encompassing online classification. Recent studies showed that in the full information setup, we can achieve finite bounds on the surrogate regret, i.e., the extra target loss relative to the best possible surrogate loss. In practice, however, full information feedback is often unrealistic as it requires immediate access to the whole structure of complex outputs. Motivated by this, we propose algorithms that work with less demanding feedback, bandit and delayed feedback. For the bandit setting, using a standard inverse-weighted gradient estimator, we achieve a surrogate regret bound of $O(\sqrt{KT})$ for the time horizon $T$ and the size of the output set $K$. However, $K$ can be extremely large when outputs are highly complex, making this result less desirable. To address this, we propose an algorithm that achieves a surrogate regret bound of $O(T^{2/3})$, which is independent of $K$. This is enabled with a carefully designed pseudo-inverse matrix estimator. Furthermore, for the delayed full information feedback setup, we obtain a surrogate regret bound of $O(D^{2/3} T^{1/3})$ for the delay time $D$. We also provide algorithms for the delayed bandit feedback setup. Finally, we numerically evaluate the performance of the proposed algorithms in online classification with bandit feedback.
Authors: Eric Oliver, Sagnik Dakshit
Abstract: Deep learning's growing prevalence has driven its widespread use in healthcare, where AI and sensor advancements enhance diagnosis, treatment, and monitoring. In mobile health, AI-powered tools enable early diagnosis and continuous monitoring of conditions like stress. Wearable technologies and multimodal physiological data have made stress detection increasingly viable, but model efficacy depends on data quality, quantity, and modality. This study develops transformer models for stress detection using the WESAD dataset, training on electrocardiograms (ECG), electrodermal activity (EDA), electromyography (EMG), respiration rate (RESP), temperature (TEMP), and 3-axis accelerometer (ACC) signals. The results demonstrate the effectiveness of single-modality transformers in analyzing physiological signals, achieving state-of-the-art performance with accuracy, precision and recall values in the range of $99.73\%$ to $99.95\%$ for stress detection. Furthermore, this study explores cross-modal performance and also explains the same using 2D visualization of the learned embedding space and quantitative analysis based on data variance. Despite the large body of work on stress detection and monitoring, the robustness and generalization of these models across different modalities has not been explored. This research represents one of the initial efforts to interpret embedding spaces for stress detection, providing valuable information on cross-modal performance.
Authors: Nicolas Michel, Maorong Wang, Jiangpeng He, Toshihiko Yamasaki
Abstract: Continual Learning (CL) addresses the problem of learning from a data sequence where the distribution changes over time. Recently, efficient solutions leveraging Pre-Trained Models (PTM) have been widely explored in the offline CL (offCL) scenario, where the data corresponding to each incremental task is known beforehand and can be seen multiple times. However, such solutions often rely on 1) prior knowledge regarding task changes and 2) hyper-parameter search, particularly regarding the learning rate. Both assumptions remain unavailable in online CL (onCL) scenarios, where incoming data distribution is unknown and the model can observe each datum only once. Therefore, existing offCL strategies fall largely behind performance-wise in onCL, with some proving difficult or impossible to adapt to the online scenario. In this paper, we tackle both problems by leveraging Online Prototypes (OP) and Class-Wise Hypergradients (CWH). OP leverages stable output representations of PTM by updating its value on the fly to act as replay samples without requiring task boundaries or storing past data. CWH learns class-dependent gradient coefficients during training to improve over sub-optimal learning rates. We show through experiments that both introduced strategies allow for a consistent gain in accuracy when integrated with existing approaches. We will make the code fully available upon acceptance.
Authors: Jiayi Fu, Xuandong Zhao, Chengyuan Yao, Heng Wang, Qi Han, Yanghua Xiao
Abstract: Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models (LLMs) with human values. However, RLHF is susceptible to reward hacking, where the agent exploits flaws in the reward function rather than learning the intended behavior, thus degrading alignment. While reward shaping helps stabilize RLHF and partially mitigate reward hacking, a systematic investigation into shaping techniques and their underlying principles remains lacking. To bridge this gap, we present a comprehensive study of the prevalent reward shaping methods. Our analysis suggests three key design principles: (1) RL reward is ideally bounded, (2) RL benefits from rapid initial growth followed by gradual convergence, and (3) RL reward is best formulated as a function of centered reward. Guided by these insights, we propose Preference As Reward (PAR), a novel approach that leverages the latent preferences embedded within the reward model itself as the signal for reinforcement learning. We evaluated PAR on two base models, Gemma2-2B and Llama3-8B, using two datasets, Ultrafeedback-Binarized and HH-RLHF. Experimental results demonstrate PAR's superior performance over other reward shaping methods. On the AlpacaEval 2.0 benchmark, PAR achieves a win rate at least 5 percentage points higher than competing approaches. Furthermore, PAR exhibits remarkable data efficiency, requiring only a single reference reward for optimal performance, and maintains robustness against reward hacking even after two full epochs of training. Code is available at https://github.com/PorUna-byte/PAR.
Authors: Yuxiang Wang, Xinnan Dai, Wenqi Fan, Yao Ma
Abstract: Graph-structured data has become increasingly prevalent across various domains, raising the demand for effective models to handle graph tasks like node classification and link prediction. Traditional graph learning models like Graph Neural Networks (GNNs) have made significant strides, but their capabilities in handling graph data remain limited in certain contexts. In recent years, large language models (LLMs) have emerged as promising candidates for graph tasks, yet most studies focus primarily on performance benchmarks and fail to address their broader potential, including their ability to handle limited data, their transferability across tasks, and their robustness. In this work, we provide a comprehensive exploration of LLMs applied to graph tasks. We evaluate the performance of pure LLMs, including those without parameter optimization and those fine-tuned with instructions, across various scenarios. Our analysis goes beyond accuracy, assessing LLM ability to perform in few-shot/zero-shot settings, transfer across domains, understand graph structures, and demonstrate robustness in challenging scenarios. We conduct extensive experiments with 16 graph learning models alongside 6 LLMs (e.g., Llama3B, GPT-4o, Qwen-plus), comparing their performance on datasets like Cora, PubMed, ArXiv, and Products. Our findings show that LLMs, particularly those with instruction tuning, outperform traditional models in few-shot settings, exhibit strong domain transferability, and demonstrate excellent generalization and robustness. This work offers valuable insights into the capabilities of LLMs for graph learning, highlighting their advantages and potential for real-world applications, and paving the way for future research in this area. Codes and datasets are released in https://github.com/myflashbarry/LLM-benchmarking.
Authors: Yuqing Wang, Xiao Yang
Abstract: This study addresses the challenge of resource scheduling optimization in edge-cloud collaborative computing using deep reinforcement learning (DRL). The proposed DRL-based approach improves task processing efficiency, reduces overall processing time, enhances resource utilization, and effectively controls task migrations. Experimental results demonstrate the superiority of DRL over traditional scheduling algorithms, particularly in managing complex task allocation, dynamic workloads, and multiple resource constraints. Despite its advantages, further improvements are needed to enhance learning efficiency, reduce training time, and address convergence issues. Future research should focus on increasing the algorithm's fault tolerance to handle more complex and uncertain scheduling scenarios, thereby advancing the intelligence and efficiency of edge-cloud computing systems.
Authors: Qingpei Guo, Kaiyou Song, Zipeng Feng, Ziping Ma, Qinglong Zhang, Sirui Gao, Xuzheng Yu, Yunxiao Sun, Tai-WeiChang, Jingdong Chen, Ming Yang, Jun Zhou
Abstract: We present M2-omni, a cutting-edge, open-source omni-MLLM that achieves competitive performance to GPT-4o. M2-omni employs a unified multimodal sequence modeling framework, which empowers Large Language Models(LLMs) to acquire comprehensive cross-modal understanding and generation capabilities. Specifically, M2-omni can process arbitrary combinations of audio, video, image, and text modalities as input, generating multimodal sequences interleaving with audio, image, or text outputs, thereby enabling an advanced and interactive real-time experience. The training of such an omni-MLLM is challenged by significant disparities in data quantity and convergence rates across modalities. To address these challenges, we propose a step balance strategy during pre-training to handle the quantity disparities in modality-specific data. Additionally, a dynamically adaptive balance strategy is introduced during the instruction tuning stage to synchronize the modality-wise training progress, ensuring optimal convergence. Notably, we prioritize preserving strong performance on pure text tasks to maintain the robustness of M2-omni's language understanding capability throughout the training process. To our best knowledge, M2-omni is currently a very competitive open-source model to GPT-4o, characterized by its comprehensive modality and task support, as well as its exceptional performance. We expect M2-omni will advance the development of omni-MLLMs, thus facilitating future research in this domain.
Authors: Ruifeng Tan, Weixiang Hong, Jiayue Tang, Xibin Lu, Ruijun Ma, Xiang Zheng, Jia Li, Jiaqiang Huang, Tong-Yi Zhang
Abstract: Battery Life Prediction (BLP), which relies on time series data produced by battery degradation tests, is crucial for battery utilization, optimization, and production. Despite impressive advancements, this research area faces three key challenges. Firstly, the limited size of existing datasets impedes insights into modern battery life data. Secondly, most datasets are restricted to small-capacity lithium-ion batteries tested under a narrow range of diversity in labs, raising concerns about the generalizability of findings. Thirdly, inconsistent and limited benchmarks across studies obscure the effectiveness of baselines and leave it unclear if models popular in other time series fields are effective for BLP. To address these challenges, we propose BatteryLife, a comprehensive dataset and benchmark for BLP. BatteryLife integrates 16 datasets, offering a 2.4 times sample size compared to the previous largest dataset, and provides the most diverse battery life resource with batteries from 8 formats, 80 chemical systems, 12 operating temperatures, and 646 charge/discharge protocols, including both laboratory and industrial tests. Notably, BatteryLife is the first to release battery life datasets of zinc-ion batteries, sodium-ion batteries, and industry-tested large-capacity lithium-ion batteries. With the comprehensive dataset, we revisit the effectiveness of baselines popular in this and other time series fields. Furthermore, we propose CyclePatch, a plug-in technique that can be employed in a series of neural networks. Extensive benchmarking of 18 methods reveals that models popular in other time series fields can be unsuitable for BLP, and CyclePatch consistently improves model performance establishing state-of-the-art benchmarks. Moreover, BatteryLife evaluates model performance across aging conditions and domains. BatteryLife is available at https://github.com/Ruifeng-Tan/BatteryLife.
Authors: Xinyang Liu, Hengrong Du, Wei Deng, Ruqi Zhang
Abstract: Hutchinson estimators are widely employed in training divergence-based likelihoods for diffusion models to ensure optimal transport (OT) properties. However, this estimator often suffers from high variance and scalability concerns. To address these challenges, we investigate Hutch++, an optimal stochastic trace estimator for generative models, designed to minimize training variance while maintaining transport optimality. Hutch++ is particularly effective for handling ill-conditioned matrices with large condition numbers, which commonly arise when high-dimensional data exhibits a low-dimensional structure. To mitigate the need for frequent and costly QR decompositions, we propose practical schemes that balance frequency and accuracy, backed by theoretical guarantees. Our analysis demonstrates that Hutch++ leads to generations of higher quality. Furthermore, this method exhibits effective variance reduction in various applications, including simulations, conditional time series forecasts, and image generation.
Authors: Dung V. Nguyen, Minh H. Nguyen, Luc Q. Nguyen, Rachel S. Y. Teo, Tan M. Nguyen, Linh Duy Tran
Abstract: Existing methods for merging experts during model training and fine-tuning predominantly rely on Euclidean geometry, which assumes a flat parameter space. This assumption can limit the model's generalization ability, especially during the pre-training phase, where the parameter manifold might exhibit more complex curvature. Curvature-aware merging methods typically require additional information and computational resources to approximate the Fisher Information Matrix, adding memory overhead. In this paper, we introduce CAMEx (\textbf{C}urvature-\textbf{A}ware \textbf{M}erging of \textbf{Ex}perts), a novel expert merging protocol that incorporates natural gradients to account for the non-Euclidean curvature of the parameter manifold. By leveraging natural gradients, CAMEx adapts more effectively to the structure of the parameter space, improving alignment between model updates and the manifold's geometry. This approach enhances both pre-training and fine-tuning, resulting in better optimization trajectories and improved generalization without the substantial memory overhead typically associated with curvature-aware methods. Our contributions are threefold: (1) CAMEx significantly outperforms traditional Euclidean-based expert merging techniques across various natural language processing tasks, leading to enhanced performance during pre-training and fine-tuning; (2) we introduce a dynamic merging architecture that optimizes resource utilization, achieving high performance while reducing computational costs, facilitating efficient scaling of large language models; and (3) we provide both theoretical and empirical evidence to demonstrate the efficiency of our proposed method.
Authors: Yuxiao Wen
Abstract: In combinatorial semi-bandits, a learner repeatedly selects from a combinatorial decision set of arms, receives the realized sum of rewards, and observes the rewards of the individual selected arms as feedback. In this paper, we extend this framework to include \emph{graph feedback}, where the learner observes the rewards of all neighboring arms of the selected arms in a feedback graph $G$. We establish that the optimal regret over a time horizon $T$ scales as $\widetilde{\Theta}(S\sqrt{T}+\sqrt{\alpha ST})$, where $S$ is the size of the combinatorial decisions and $\alpha$ is the independence number of $G$. This result interpolates between the known regrets $\widetilde\Theta(S\sqrt{T})$ under full information (i.e., $G$ is complete) and $\widetilde\Theta(\sqrt{KST})$ under the semi-bandit feedback (i.e., $G$ has only self-loops), where $K$ is the total number of arms. A key technical ingredient is to realize a convexified action using a random decision vector with negative correlations.
Authors: Anay Majee, Maria Xenochristou, Wei-Peng Chen
Abstract: Handling heterogeneous data in tabular datasets poses a significant challenge for deep learning models. While attention-based architectures and self-supervised learning have achieved notable success, their application to tabular data remains less effective over linear and tree based models. Although several breakthroughs have been achieved by models which transform tables into uni-modal transformations like image, language and graph, these models often underperform in the presence of feature heterogeneity. To address this gap, we introduce TabGLM (Tabular Graph Language Model), a novel multi-modal architecture designed to model both structural and semantic information from a table. TabGLM transforms each row of a table into a fully connected graph and serialized text, which are then encoded using a graph neural network (GNN) and a text encoder, respectively. By aligning these representations through a joint, multi-modal, self-supervised learning objective, TabGLM leverages complementary information from both modalities, thereby enhancing feature learning. TabGLM's flexible graph-text pipeline efficiently processes heterogeneous datasets with significantly fewer parameters over existing Deep Learning approaches. Evaluations across 25 benchmark datasets demonstrate substantial performance gains, with TabGLM achieving an average AUC-ROC improvement of up to 5.56% over State-of-the-Art (SoTA) tabular learning methods.
Authors: Jacob Dunefsky, Arman Cohan
Abstract: Steering vectors have emerged as a promising approach for interpreting and controlling LLMs, but current methods typically require large contrastive datasets that are often impractical to construct and may capture spurious correlations. We propose directly optimizing steering vectors through gradient descent on a single training example, and systematically investigate how these vectors generalize. We consider several steering optimization techniques, including multiple novel ones, and find that the resulting vectors effectively mediate safety-relevant behaviors in multiple models. Indeed, in experiments on an alignment-faking model, we are able to optimize one-shot steering vectors that induce harmful behavior on benign examples and whose negations suppress harmful behavior on malign examples. And in experiments on refusal suppression, we demonstrate that one-shot optimized steering vectors can transfer across inputs, yielding a Harmbench attack success rate of 96.9%. Furthermore, to quantitatively assess steering effectiveness in instruction-tuned models, we develop a novel evaluation framework using sequence probabilities from the corresponding base model. With this framework, we analyze how steering vectors modulate an instruction-tuned LLM's ability to recover from outputting false information, and find that this ability derives from the base model. Overall, our findings suggest that optimizing steering vectors on a single example can mediate misaligned behavior in LLMs, and provide a path toward better understanding the relationship between LLM behavior and activation space structure.
Authors: Shi Fu, Yingjie Wang, Yuzhu Chen, Xinmei Tian, Dacheng Tao
Abstract: High-quality data is essential for training large generative models, yet the vast reservoir of real data available online has become nearly depleted. Consequently, models increasingly generate their own data for further training, forming Self-consuming Training Loops (STLs). However, the empirical results have been strikingly inconsistent: some models degrade or even collapse, while others successfully avoid these failures, leaving a significant gap in theoretical understanding to explain this discrepancy. This paper introduces the intriguing notion of recursive stability and presents the first theoretical generalization analysis, revealing how both model architecture and the proportion between real and synthetic data influence the success of STLs. We further extend this analysis to transformers in in-context learning, showing that even a constant-sized proportion of real data ensures convergence, while also providing insights into optimal synthetic data sizing.
Authors: Ziyuan Zhong, Junyang Zhou
Abstract: In this paper, we propose an innovative dynamic classification algorithm designed to achieve the objective of zero missed detections and minimal false positives. The algorithm partitions the data into N equivalent training subsets and N prediction subsets using a supervised model, followed by independent predictions from N separate predictive models. This enables each predictive model to operate within a smaller data range, thereby improving overall accuracy. Additionally, the algorithm leverages data generated through supervised learning to further refine prediction results, filtering out predictions that do not meet accuracy requirements without the need to introduce additional models. Experimental results demonstrate that, when data partitioning errors are minimal, the dynamic classification algorithm achieves exceptional performance with zero missed detections and minimal false positives, significantly outperforming existing model ensembles. Even in cases where classification errors are larger, the algorithm remains comparable to state of the art models. The key innovations of this study include self-supervised classification learning, the use of small-range subset predictions, and the direct rejection of substandard predictions. While the current algorithm still has room for improvement in terms of automatic parameter tuning and classification model efficiency, it has demonstrated outstanding performance across multiple datasets. Future research will focus on optimizing the classification component to further enhance the algorithm's robustness and adaptability.
Authors: Jiani Zheng, Lu Wang, Fangkai Yang, Chaoyun Zhang, Lingrui Mei, Wenjie Yin, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
Abstract: Training Vision-Language Models (VLMs) for Graphical User Interfaces (GUI) agents via Reinforcement Learning (RL) faces critical challenges: environment-based RL requires costly interactions, while environment-free methods struggle with distribution shift and reward generalization. We propose an environment-free RL framework that decouples value estimation from policy optimization by leveraging a pretrained Value Environment Model (VEM). VEM predicts state-action values directly from offline data, distilling human-like priors about GUI interaction outcomes without requiring next-state prediction or environmental feedback. This avoids compounding errors and enhances resilience to UI changes by focusing on semantic reasoning (e.g., Does this action advance the user's goal?). The framework operates in two stages: (1) pretraining VEM to estimate long-term action utilities and (2) guiding policy exploration with frozen VEM signals, enabling layout-agnostic GUI automation. Evaluated on Android-in-the-Wild benchmarks, VEM achieves state-of-the-art performance in both offline and online settings, outperforming environment-free baselines significantly and matching environment-based approaches without interaction costs. Importantly, VEM demonstrates that semantic-aware value estimation can achieve comparable performance with online-trained methods.
Authors: Matin Shokri, Ramin Hasibi
Abstract: Network Traffic Classification (NTC) is one of the most important tasks in network management. The imbalanced nature of classes on the internet presents a critical challenge in classification tasks. For example, some classes of applications are much more prevalent than others, such as HTTP. As a result, machine learning classification models do not perform well on those classes with fewer data. To address this problem, we propose a pipeline to balance the dataset and classify it using a robust and accurate embedding technique. First, we generate artificial data using Long Short-Term Memory (LSTM) networks and Kernel Density Estimation (KDE). Next, we propose replacing one-hot encoding for categorical features with a novel embedding framework based on the "Flow as a Sentence" perspective, which we name FS-Embedding. This framework treats the source and destination ports, along with the packet's direction, as one word in a flow, then trains an embedding vector space based on these new features through the learning classification task. Finally, we compare our pipeline with the training of a Convolutional Recurrent Neural Network (CRNN) and Transformers, both with imbalanced and sampled datasets, as well as with the one-hot encoding approach. We demonstrate that the proposed augmentation pipeline, combined with FS-Embedding, increases convergence speed and leads to a significant reduction in the number of model parameters, all while maintaining the same performance in terms of accuracy.
Authors: Ping Zhang, Zhaorui Zhang, Sheng Di, Yao Xin, Benben Liu
Abstract: Large language model fine-tuning has been identified as an efficient approach to applying the pre-trained Large language models to other domains. To guarantee data privacy for different data owners, models are often fine-tuned in federated learning environments across different data owners, which often involve data heterogeneity issues and affect the fine-tuning performance. In addition, the length of the context for the training data has been identified as a major factor that affects the LLM's model performance. To efficiently measure how the context length affects the LLM's model performance in heterogeneous federated learning environments, we propose CLLoRA. CLLoRA utilizes the parameter-efficient fine-tuning approach LoRA based on different kinds of LLMs with varying sizes as the fine-tuning approach to investigate whether the quality and length of contexts can serve as standards for measuring non-IID context. The findings indicate that an imbalance in context quality not only affects local training on clients but also impacts the global model's performance. However, context length has a minimal effect on local training but a more significant influence on the global model. These results provide insights into how context quality and length affect the model performance for LLM fine-tuning in federated learning environments.
Authors: Weiyan Wang, Xingjian Shi, Ruiqi Shu, Yuan Gao, Rui Ray Chen, Kun Wang, Fan Xu, Jinbao Xue, Shuaipeng Li, Yangyu Tao, Di Wang, Hao Wu, Xiaomeng Huang
Abstract: In practice, physical spatiotemporal forecasting can suffer from data scarcity, because collecting large-scale data is non-trivial, especially for extreme events. Hence, we propose \method{}, a novel probabilistic framework to realize iterative self-training with new self-ensemble strategies, achieving better physical consistency and generalization on extreme events. Following any base forecasting model, we can encode its deterministic outputs into a latent space and retrieve multiple codebook entries to generate probabilistic outputs. Then BeamVQ extends the beam search from discrete spaces to the continuous state spaces in this field. We can further employ domain-specific metrics (e.g., Critical Success Index for extreme events) to filter out the top-k candidates and develop the new self-ensemble strategy by combining the high-quality candidates. The self-ensemble can not only improve the inference quality and robustness but also iteratively augment the training datasets during continuous self-training. Consequently, BeamVQ realizes the exploration of rare but critical phenomena beyond the original dataset. Comprehensive experiments on different benchmarks and backbones show that BeamVQ consistently reduces forecasting MSE (up to 39%), enhancing extreme events detection and proving its effectiveness in handling data scarcity.
Authors: Yiqin Yang, Quanwei Wang, Chenghao Li, Hao Hu, Chengjie Wu, Yuhua Jiang, Dianyu Zhong, Ziyou Zhang, Qianchuan Zhao, Chongjie Zhang, Xu Bo
Abstract: Offline reinforcement learning (RL) represents a significant shift in RL research, allowing agents to learn from pre-collected datasets without further interaction with the environment. A key, yet underexplored, challenge in offline RL is selecting an optimal subset of the offline dataset that enhances both algorithm performance and training efficiency. Reducing dataset size can also reveal the minimal data requirements necessary for solving similar problems. In response to this challenge, we introduce ReDOR (Reduced Datasets for Offline RL), a method that frames dataset selection as a gradient approximation optimization problem. We demonstrate that the widely used actor-critic framework in RL can be reformulated as a submodular optimization objective, enabling efficient subset selection. To achieve this, we adapt orthogonal matching pursuit (OMP), incorporating several novel modifications tailored for offline RL. Our experimental results show that the data subsets identified by ReDOR not only boost algorithm performance but also do so with significantly lower computational complexity.
Authors: Shijun Zhang, Hongkai Zhao, Yimin Zhong, Haomin Zhou
Abstract: The two most critical ingredients of a neural network are its structure and the activation function employed, and more importantly, the proper alignment of these two that is conducive to the effective representation and learning in practice. In this work, we introduce a surprisingly effective synergy, termed the Fourier Multi-Component and Multi-Layer Neural Network (FMMNN), and demonstrate its surprising adaptability and efficiency in capturing high-frequency components. First, we theoretically establish that FMMNNs have exponential expressive power in terms of approximation capacity. Next, we analyze the optimization landscape of FMMNNs and show that it is significantly more favorable compared to fully connected neural networks. Finally, systematic and extensive numerical experiments validate our findings, demonstrating that FMMNNs consistently achieve superior accuracy and efficiency across various tasks, particularly impressive when high-frequency components are present.
Authors: Weilin Chen, Ruichu Cai, Junjie Wan, Zeqin Yang, Jos\'e Miguel Hern\'andez-Lobato
Abstract: Long-term causal inference has drawn increasing attention in many scientific domains. Existing methods mainly focus on estimating average long-term causal effects by combining long-term observational data and short-term experimental data. However, it is still understudied how to robustly and effectively estimate heterogeneous long-term causal effects, significantly limiting practical applications. In this paper, we propose several two-stage style nonparametric estimators for heterogeneous long-term causal effect estimation, including propensity-based, regression-based, and multiple robust estimators. We conduct a comprehensive theoretical analysis of their asymptotic properties under mild assumptions, with the ultimate goal of building a better understanding of the conditions under which some estimators can be expected to perform better. Extensive experiments across several semi-synthetic and real-world datasets validate the theoretical results and demonstrate the effectiveness of the proposed estimators.
Authors: Stefan P. Schmid, Ella Miray Rajaonson, Cher Tian Ser, Mohammad Haddadnia, Shi Xuan Leong, Al\'an Aspuru-Guzik, Agustinus Kristiadi, Kjell Jorner, Felix Strieth-Kalthoff
Abstract: General parameters are highly desirable in the natural sciences - e.g., chemical reaction conditions that enable high yields across a range of related transformations. This has a significant practical impact since those general parameters can be transferred to related tasks without the need for laborious and time-intensive re-optimization. While Bayesian optimization (BO) is widely applied to find optimal parameter sets for specific tasks, it has remained underused in experiment planning towards such general optima. In this work, we consider the real-world problem of condition optimization for chemical reactions to study how performing generality-oriented BO can accelerate the identification of general optima, and whether these optima also translate to unseen examples. This is achieved through a careful formulation of the problem as an optimization over curried functions, as well as systematic evaluations of generality-oriented strategies for optimization tasks on real-world experimental data. We find that for generality-oriented optimization, simple myopic optimization strategies that decouple parameter and task selection perform comparably to more complex ones, and that effective optimization is merely determined by an effective exploration of both parameter and task space.
Authors: Margaret Li, Sneha Kudugunta, Luke Zettlemoyer
Abstract: Modern foundation models rely heavily on using scaling laws to guide crucial training decisions. Researchers often extrapolate the optimal architecture and hyper parameters settings from smaller training runs by describing the relationship between, loss, or task performance, and scale. All components of this process vary, from the specific equation being fit, to the training setup, to the optimization method. Each of these factors may affect the fitted law, and therefore, the conclusions of a given study. We discuss discrepancies in the conclusions that several prior works reach, on questions such as the optimal token to parameter ratio. We augment this discussion with our own analysis of the critical impact that changes in specific details may effect in a scaling study, and the resulting altered conclusions. Additionally, we survey over 50 papers that study scaling trends: while 45 of these papers quantify these trends using a power law, most under-report crucial details needed to reproduce their findings. To mitigate this, we we propose a checklist for authors to consider while contributing to scaling law research.
Authors: Martin Surner, Abdelmajid Khelil, Ludwig Bothmann
Abstract: Out-of-distribution generalization of machine learning models remains challenging since the models are inherently bound to the training data distribution. This especially manifests, when the learned models rely on spurious correlations. Most of the existing approaches apply data manipulation, representation learning, or learning strategies to achieve generalizable models. Unfortunately, these approaches usually require multiple training domains, group labels, specialized augmentation, or pre-processing to reach generalizable models. We propose a novel approach that addresses these limitations by providing a technique to guide the neural network through the training phase. We first establish input pairs, representing the spurious attribute and describing the invariance, a characteristic that should not affect the outcome of the model. Based on these pairs, we form a corrective gradient complementing the traditional gradient descent approach. We further make this correction mechanism adaptive based on a predefined invariance condition. Experiments on ColoredMNIST, Waterbird-100, and CelebA datasets demonstrate the effectiveness of our approach and the robustness to group shifts.
Authors: Weilin Chen, Ruichu Cai, Yuguang Yan, Zhifeng Hao, Jos\'e Miguel Hern\'andez-Lobato
Abstract: Long-term causal inference is an important but challenging problem across various scientific domains. To solve the latent confounding problem in long-term observational studies, existing methods leverage short-term experimental data. Ghassami et al. propose an approach based on the Conditional Additive Equi-Confounding Bias (CAECB) assumption, which asserts that the confounding bias in the short-term outcome is equal to that in the long-term outcome, so that the long-term confounding bias and the causal effects can be identified. While effective in certain cases, this assumption is limited to scenarios with a one-dimensional short-term outcome. In this paper, we introduce a novel assumption that extends the CAECB assumption to accommodate temporal short-term outcomes. Our proposed assumption states a functional relationship between sequential confounding biases across temporal short-term outcomes, under which we theoretically establish the identification of long-term causal effects. Based on the identification result, we develop an estimator and conduct a theoretical analysis of its asymptotic properties. Extensive experiments validate our theoretical results and demonstrate the effectiveness of the proposed method.
Authors: Jinbo Wang, Mingze Wang, Zhanpeng Zhou, Junchi Yan, Weinan E, Lei Wu
Abstract: Transformers consist of diverse building blocks, such as embedding layers, normalization layers, self-attention mechanisms, and point-wise feedforward networks. Thus, understanding the differences and interactions among these blocks is important. In this paper, we uncover a clear Sharpness Disparity across these blocks, which emerges early in training and intriguingly persists throughout the training process. Motivated by this finding, we propose Blockwise Learning Rate (LR), a strategy that tailors the LR to each block's sharpness, accelerating large language model (LLM) pre-training. By integrating Blockwise LR into AdamW, we consistently achieve lower terminal loss and nearly $2\times$ speedup compared to vanilla AdamW. We demonstrate this acceleration across GPT-2 and LLaMA, with model sizes ranging from 0.12B to 1.1B and datasets of OpenWebText and MiniPile. Finally, we incorporate Blockwise LR into Adam-mini (Zhang et al., 2024), a recently proposed memory-efficient variant of Adam, achieving a combined $2\times$ speedup and $2\times$ memory saving. These results underscore the potential of exploiting the sharpness disparity to improve LLM training.
Authors: Shogo Iwazaki
Abstract: We study the noise-free Gaussian Process (GP) bandits problem, in which the learner seeks to minimize regret through noise-free observations of the black-box objective function lying on the known reproducing kernel Hilbert space (RKHS). Gaussian process upper confidence bound (GP-UCB) is the well-known GP-bandits algorithm whose query points are adaptively chosen based on the GP-based upper confidence bound score. Although several existing works have reported the practical success of GP-UCB, the current theoretical results indicate its suboptimal performance. However, GP-UCB tends to perform well empirically compared with other nearly optimal noise-free algorithms that rely on a non-adaptive sampling scheme of query points. This paper resolves this gap between theoretical and empirical performance by showing the nearly optimal regret upper bound of noise-free GP-UCB. Specifically, our analysis shows the first constant cumulative regret in the noise-free settings for the squared exponential kernel and Mat\'ern kernel with some degree of smoothness.
Authors: Jaehyeon Son, Soochan Lee, Gunhee Kim
Abstract: Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However, these models also inherit the suboptimal behaviors of the RL algorithms they imitate. This issue primarily arises due to the gradual update rule employed by those algorithms. Model-based planning offers a promising solution to this limitation by allowing the models to simulate potential outcomes before taking action, providing an additional mechanism to deviate from the suboptimal behavior. Rather than learning a separate dynamics model, we propose Distillation for In-Context Planning (DICP), an in-context model-based RL framework where Transformers simultaneously learn environment dynamics and improve policy in-context. We evaluate DICP across a range of discrete and continuous environments, including Darkroom variants and Meta-World. Our results show that DICP achieves state-of-the-art performance while requiring significantly fewer environment interactions than baselines, which include both model-free counterparts and existing meta-RL methods.
Authors: Norbert Bodendorfer
Abstract: Accurate and reliable air pollution forecasting is crucial for effective environmental management and policy-making. llull-environment is a sophisticated and scalable forecasting system for air pollution, inspired by previous models currently operational in Madrid and Valladolid (Spain). It contains (among other key components) an encoder-decoder convolutional neural network to forecast mean pollution levels for four key pollutants (NO$_2$, O$_3$, PM$_{10}$, PM$_{2.5}$) using historical data, external forecasts, and other contextual features. This paper investigates the augmentation of this neural network with an attention mechanism to improve predictive accuracy. The proposed attention mechanism pre-processes tensors containing the input features before passing them to the existing mean forecasting model. The resulting model is a combination of several architectures and ideas and can be described as a "Hybrid Enhanced Autoregressive Transformer", or HEART. The effectiveness of the approach is evaluated by comparing the mean square error (MSE) across different attention layouts against the system without such a mechanism. We observe a significant reduction in MSE of up to 22%, with an average of 7.5% across tested cities and pollutants. The performance of a given attention mechanism turns out to depend on the pollutant, highlighting the differences in their creation and dissipation processes. Our findings are not restricted to optimizing air quality prediction models, but are applicable generally to (fixed length) time series forecasting.
Authors: Patrick Seifner, Kostadin Cvejoski, David Berghaus, Cesar Ojeda, Ramses J. Sanchez
Abstract: Stochastic differential equations (SDEs) describe dynamical systems where deterministic flows, governed by a drift function, are superimposed with random fluctuations dictated by a diffusion function. The accurate estimation (or discovery) of these functions from data is a central problem in machine learning, with wide application across natural and social sciences alike. Yet current solutions are brittle, and typically rely on symbolic regression or Bayesian non-parametrics. In this work, we introduce FIM-SDE (Foundation Inference Model for SDEs), a transformer-based recognition model capable of performing accurate zero-shot estimation of the drift and diffusion functions of SDEs, from noisy and sparse observations on empirical processes of different dimensionalities. Leveraging concepts from amortized inference and neural operators, we train FIM-SDE in a supervised fashion, to map a large set of noisy and discretely observed SDE paths to their corresponding drift and diffusion functions. We demonstrate that one and the same (pretrained) FIM-SDE achieves robust zero-shot function estimation (i.e. without any parameter fine-tuning) across a wide range of synthetic and real-world processes, from canonical SDE systems (e.g. double-well dynamics or weakly perturbed Hopf bifurcations) to human motion recordings and oil price and wind speed fluctuations.
Authors: Haoyang Li, Li Bai, Qingqing Ye, Haibo Hu, Yaxin Xiao, Huadi Zheng, Jianliang Xu
Abstract: Model Inversion (MI) attacks, which reconstruct the training dataset of neural networks, pose significant privacy concerns in machine learning. Recent MI attacks have managed to reconstruct realistic label-level private data, such as the general appearance of a target person from all training images labeled on him. Beyond label-level privacy, in this paper we show sample-level privacy, the private information of a single target sample, is also important but under-explored in the MI literature due to the limitations of existing evaluation metrics. To address this gap, this study introduces a novel metric tailored for training-sample analysis, namely, the Diversity and Distance Composite Score (DDCS), which evaluates the reconstruction fidelity of each training sample by encompassing various MI attack attributes. This, in turn, enhances the precision of sample-level privacy assessments. Leveraging DDCS as a new evaluative lens, we observe that many training samples remain resilient against even the most advanced MI attack. As such, we further propose a transfer learning framework that augments the generative capabilities of MI attackers through the integration of entropy loss and natural gradient descent. Extensive experiments verify the effectiveness of our framework on improving state-of-the-art MI attacks over various metrics including DDCS, coverage and FID. Finally, we demonstrate that DDCS can also be useful for MI defense, by identifying samples susceptible to MI attacks in an unsupervised manner.
Authors: Dongwei Xu, Yutao Zhu, Yao Lu, Youpeng Feng, Yun Lin, Qi Xuan
Abstract: With the rapid advancements in wireless communication technology, automatic modulation recognition (AMR) plays a critical role in ensuring communication security and reliability. However, numerous challenges, including higher performance demands, difficulty in data acquisition under specific scenarios, limited sample size, and low-quality labeled data, hinder its development. Few-shot learning (FSL) offers an effective solution by enabling models to achieve satisfactory performance with only a limited number of labeled samples. While most FSL techniques are applied in the field of computer vision, they are not directly applicable to wireless signal processing. This study does not propose a new FSL-specific signal model but introduces a framework called MCLRL. This framework combines multi-domain contrastive learning with reinforcement learning. Multi-domain representations of signals enhance feature richness, while integrating contrastive learning and reinforcement learning architectures enables the extraction of deep features for classification. In downstream tasks, the model achieves excellent performance using only a few samples and minimal training cycles. Experimental results show that the MCLRL framework effectively extracts key features from signals, performs well in FSL tasks, and maintains flexibility in signal model selection.
Authors: Mykola Kozlenko, Ihor Lazarovych, Valerii Tkachuk, Vira Vialkova
Abstract: In this paper we proposed the use of JT65A radio communication protocol for data exchange in wide-area monitoring systems in electric power systems. We investigated the software demodulation of the multiple frequency shift keying weak signals transmitted with JT65A communication protocol using deep convolutional neural network. We presented the demodulation performance in form of symbol and bit error rates. We focused on the interference immunity of the protocol over an additive white Gaussian noise with average signal-to-noise ratios in the range from -30 dB to 0 dB, which was obtained for the first time. We proved that the interference immunity is about 1.5 dB less than the theoretical limit of non-coherent demodulation of orthogonal MFSK signals.
Authors: Guikun Chen, Xu Zhang, Yi Yang, Wenguan Wang
Abstract: Chemical reaction data is a pivotal asset, driving advances in competitive fields such as pharmaceuticals, materials science, and industrial chemistry. Its proprietary nature renders it sensitive, as it often includes confidential insights and competitive advantages organizations strive to protect. However, in contrast to this need for confidentiality, the current standard training paradigm for machine learning-based retrosynthesis gathers reaction data from multiple sources into one single edge to train prediction models. This paradigm poses considerable privacy risks as it necessitates broad data availability across organizational boundaries and frequent data transmission between entities, potentially exposing proprietary information to unauthorized access or interception during storage and transfer. In the present study, we introduce the chemical knowledge-informed framework (CKIF), a privacy-preserving approach for learning retrosynthesis models. CKIF enables distributed training across multiple chemical organizations without compromising the confidentiality of proprietary reaction data. Instead of gathering raw reaction data, CKIF learns retrosynthesis models through iterative, chemical knowledge-informed aggregation of model parameters. In particular, the chemical properties of predicted reactants are leveraged to quantitatively assess the observable behaviors of individual models, which in turn determines the adaptive weights used for model aggregation. On a variety of reaction datasets, CKIF outperforms several strong baselines by a clear margin (e.g., ~20% performance improvement over FedAvg on USPTO-50K), showing its feasibility and superiority to stimulate further research on privacy-preserving retrosynthesis.
Authors: Sebastian Chwilczy\'nski, Dariusz Brzezinski
Abstract: With predictive models becoming prevalent, companies are expanding the types of data they gather. As a result, the collected datasets consist not only of simple numerical features but also more complex objects such as time series, images, or graphs. Such multi-modal data have the potential to improve performance in predictive tasks like outlier detection, where the goal is to identify objects deviating from the main data distribution. However, current outlier detection algorithms are dedicated to individual types of data. Consequently, working with mixed types of data requires either fusing multiple data-specific models or transforming all of the representations into a single format, both of which can hinder predictive performance. In this paper, we propose a multi-modal outlier detection algorithm called Random Similarity Isolation Forest. Our method combines the notions of isolation and similarity-based projection to handle datasets with mixtures of features of arbitrary data types. Experiments performed on 47 benchmark datasets demonstrate that Random Similarity Isolation Forest outperforms five state-of-the-art competitors. Our study shows that the use of multiple modalities can indeed improve the detection of anomalies and highlights the need for new outlier detection benchmarks tailored for multi-modal algorithms.
Authors: Vijay Kumar Sutrakar, Nikhil Morge, Anjana PK, Abhilash PV
Abstract: In this paper, deep learning-based approach for the design of radar absorbing structure using resistive frequency selective surface is proposed. In the present design, reflection coefficient is used as input of deep learning model and the Jerusalem cross based unit cell dimensions is predicted as outcome. Sequential neural network based deep learning model with adaptive moment estimation optimizer is used for designing multi frequency band absorbers. The model is used for designing radar absorber from L to Ka band depending on unit cell parameters and thickness. The outcome of deep learning model is further compared with full-wave simulation software and an excellent match is obtained. The proposed model can be used for the low-cost design of various radar absorbing structures using a single unit cell and thickness across the band of frequencies.
Authors: Vijay Kumar Sutrakar, Anjana PK, Rohit Bisariya, Soumya KK, Gopal Chawan M
Abstract: In this paper, a regression-based machine learning model is used for the design of cavity backed slotted antenna. This type of antenna is commonly used in military and aviation communication systems. Initial reflection coefficient data of cavity backed slotted antenna is generated using electromagnetic solver. These reflection coefficient data is then used as input for training regression-based machine learning model. The model is trained to predict the dimensions of cavity backed slotted antenna based on the input reflection coefficient for a wide frequency band varying from 1 GHz to 8 GHz. This approach allows for rapid prediction of optimal antenna configurations, reducing the need for repeated physical testing and manual adjustments, may lead to significant amount of design and development cost saving. The proposed model also demonstrates its versatility in predicting multi frequency resonance across 1 GHz to 8 GHz. Also, the proposed approach demonstrates the potential for leveraging machine learning in advanced antenna design, enhancing efficiency and accuracy in practical applications such as radar, military identification systems and secure communication networks.
Authors: Mohammad Moulaeifard, Peter H. Charlton, Nils Strodthoff
Abstract: Photoplethysmography (PPG)-based blood pressure (BP) estimation represents a promising alternative to cuff-based BP measurements. Recently, an increasing number of deep learning models have been proposed to infer BP from the raw PPG waveform. However, these models have been predominantly evaluated on in-distribution test sets, which immediately raises the question of the generalizability of these models to external datasets. To investigate this question, we trained five deep learning models on the recently released PulseDB dataset, provided in-distribution benchmarking results on this dataset, and then assessed out-of-distribution performance on several external datasets. The best model (XResNet1d101) achieved in-distribution MAEs of 9.4 and 6.0 mmHg for systolic and diastolic BP respectively on PulseDB (with subject-specific calibration), and 14.0 and 8.5 mmHg respectively without calibration. Equivalent MAEs on external test datasets without calibration ranged from 15.0 to 25.1 mmHg (SBP) and 7.0 to 10.4 mmHg (DBP). Our results indicate that the performance is strongly influenced by the differences in BP distributions between datasets. We investigated a simple way of improving performance through sample-based domain adaptation and put forward recommendations for training models with good generalization properties. With this work, we hope to educate more researchers for the importance and challenges of out-of-distribution generalization.
Authors: Emanuele Mengoli, Luzius Moll, Virgilio Strozzi, El-Mahdi El-Mhamdi
Abstract: In distributed learning, sign-based compression algorithms such as signSGD with majority vote provide a lightweight alternative to SGD with an additional advantage: fault tolerance (almost) for free. However, for signSGD with majority vote, this fault tolerance has been shown to cover only the case of weaker adversaries, i.e., ones that are not omniscient or cannot collude to base their attack on common knowledge and strategy. In this work, we close this gap and provide new insights into how signSGD with majority vote can be resilient against omniscient and colluding adversaries, which craft an attack after communicating with other adversaries, thus having better information to perform the most damaging attack based on a common optimal strategy. Our core contribution is in providing a proof that begins by defining the omniscience framework and the strongest possible damage against signSGD with majority vote without imposing any restrictions on the attacker. Thanks to the filtering effect of the sign-based method, we upper-bound the space of attacks to the optimal strategy for maximizing damage by an attacker. Hence, we derive an explicit probabilistic bound in terms of incorrect aggregation without resorting to unknown constants, providing a convergence bound on signSGD with majority vote in the presence of Byzantine attackers, along with a precise convergence rate. Our findings are supported by experiments on the MNIST dataset in a distributed learning environment with adversaries of varying strength.
Authors: Gregory W. Kyro, Tianyin Qiu, Victor S. Batista
Abstract: Deep learning has transformed protein design, enabling accurate structure prediction, sequence optimization, and de novo protein generation. Advances in single-chain protein structure prediction via AlphaFold2, RoseTTAFold, ESMFold, and others have achieved near-experimental accuracy, inspiring successive work extended to biomolecular complexes via AlphaFold Multimer, RoseTTAFold All-Atom, AlphaFold 3, Chai-1, Boltz-1 and others. Generative models such as ProtGPT2, ProteinMPNN, and RFdiffusion have enabled sequence and backbone design beyond natural evolution-based limitations. More recently, joint sequence-structure co-design models, including ESM3, have integrated both modalities into a unified framework, resulting in improved designability. Despite these advances, challenges still exist pertaining to modeling sequence-structure-function relationships and ensuring robust generalization beyond the regions of protein space spanned by the training data. Future advances will likely focus on joint sequence-structure-function co-design frameworks that are able to model the fitness landscape more effectively than models that treat these modalities independently. Current capabilities, coupled with the dizzying rate of progress, suggest that the field will soon enable rapid, rational design of proteins with tailored structures and functions that transcend the limitations imposed by natural evolution. In this review, we discuss the current capabilities of deep learning methods for protein design, focusing on some of the most revolutionary and capable models with respect to their functionality and the applications that they enable, leading up to the current challenges of the field and the optimal path forward.
Authors: Melanie Schaller, Mathis Kruse, Antonio Ortega, Marius Lindauer, Bodo Rosenhahn
Abstract: Addressing sensor drift is essential in industrial measurement systems, where precise data output is necessary for maintaining accuracy and reliability in monitoring processes, as it progressively degrades the performance of machine learning models over time. Our findings indicate that the standard cross-validation method used in existing model training overestimates performance by inadequately accounting for drift. This is primarily because typical cross-validation techniques allow data instances to appear in both training and testing sets, thereby distorting the accuracy of the predictive evaluation. As a result, these models are unable to precisely predict future drift effects, compromising their ability to generalize and adapt to evolving data conditions. This paper presents two solutions: (1) a novel sensor drift compensation learning paradigm for validating models, and (2) automated machine learning (AutoML) techniques to enhance classification performance and compensate sensor drift. By employing strategies such as data balancing, meta-learning, automated ensemble learning, hyperparameter optimization, feature selection, and boosting, our AutoML-DC (Drift Compensation) model significantly improves classification performance against sensor drift. AutoML-DC further adapts effectively to varying drift severities.
Authors: Alberto Foresti, Giulio Franzese, Pietro Michiardi
Abstract: Information-theoretic quantities play a crucial role in understanding non-linear relationships between random variables and are widely used across scientific disciplines. However, estimating these quantities remains an open problem, particularly in the case of high-dimensional discrete distributions. Current approaches typically rely on embedding discrete data into a continuous space and applying neural estimators originally designed for continuous distributions, a process that may not fully capture the discrete nature of the underlying data. We consider Continuous-Time Markov Chains (CTMCs), stochastic processes on discrete state-spaces which have gained popularity due to their generative modeling applications. In this work, we introduce INFO-SEDD, a novel method for estimating information-theoretic quantities of discrete data, including mutual information and entropy. Our approach requires the training of a single parametric model, offering significant computational and memory advantages. Additionally, it seamlessly integrates with pretrained networks, allowing for efficient reuse of pretrained generative models. To evaluate our approach, we construct a challenging synthetic benchmark. Our experiments demonstrate that INFO-SEDD is robust and outperforms neural competitors that rely on embedding techniques. Moreover, we validate our method on a real-world task: estimating the entropy of an Ising model. Overall, INFO-SEDD outperforms competing methods and shows scalability to high-dimensional scenarios, paving the way for new applications where estimating MI between discrete distribution is the focus. The promising results in this complex, high-dimensional scenario highlight INFO-SEDD as a powerful new estimator in the toolkit for information-theoretical analysis.
Authors: Li Ju, Xingyi Yang, Qi Li, Xinchao Wang
Abstract: Graph neural networks (GNNs) are conventionally trained on a per-domain, per-task basis. It creates a significant barrier in transferring the acquired knowledge to different, heterogeneous data setups. This paper introduces GraphBridge, a novel framework to enable knowledge transfer across disparate tasks and domains in GNNs, circumventing the need for modifications to task configurations or graph structures. Specifically, GraphBridge allows for the augmentation of any pre-trained GNN with prediction heads and a bridging network that connects the input to the output layer. This architecture not only preserves the intrinsic knowledge of the original model but also supports outputs of arbitrary dimensions. To mitigate the negative transfer problem, GraphBridg merges the source model with a concurrently trained model, thereby reducing the source bias when applied to the target domain. Our method is thoroughly evaluated across diverse transfer learning scenarios, including Graph2Graph, Node2Node, Graph2Node, and graph2point-cloud. Empirical validation, conducted over 16 datasets representative of these scenarios, confirms the framework's capacity for task- and domain-agnostic transfer learning within graph-like data, marking a significant advancement in the field of GNNs.
Authors: Vladimir Vovk
Abstract: This paper continues the study of the efficiency of conformal prediction as compared with more general randomness prediction and exchangeability prediction. It does not restrict itself to the case of classification, and our results will also be applicable to the case of regression. The price to pay is that efficiency will be attained only on average, albeit with respect to a wide range of probability measures on the label space.
Authors: Jiawei Huang, Bingcong Li, Christoph Dann, Niao He
Abstract: Sample efficiency is critical for online Reinforcement Learning from Human Feedback (RLHF). While existing works investigate sample-efficient online exploration strategies, the potential of utilizing misspecified yet relevant reward models to accelerate learning remains underexplored. This paper studies how to transfer knowledge from those imperfect reward models in online RLHF. We start by identifying a novel property of the KL-regularized RLHF objective: \emph{a policy's ability to cover the optimal policy is captured by its sub-optimality}. Building on this insight, we propose a theoretical transfer learning algorithm with provable benefits compared to standard online learning. Our approach achieves low regret in the early stage by quickly adapting to the best available source reward models without prior knowledge of their quality, and over time, it attains an $\tilde{O}(\sqrt{T})$ regret bound \emph{independent} of structural complexity measures. Inspired by our theoretical findings, we develop an empirical algorithm with improved computational efficiency, and demonstrate its effectiveness empirically in summarization tasks.
Authors: Rachid Guerraoui, Anne-Marie Kermarrec, Diana Petrescu, Rafael Pires, Mathis Randl, Martijn de Vos
Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across various domains but remain susceptible to hallucinations and inconsistencies, limiting their reliability. Retrieval-augmented generation (RAG) mitigates these issues by grounding model responses in external knowledge sources. Existing RAG workflows often leverage a single vector database, which is impractical in the common setting where information is distributed across multiple repositories. We introduce RAGRoute, a novel mechanism for federated RAG search. RAGRoute dynamically selects relevant data sources at query time using a lightweight neural network classifier. By not querying every data source, this approach significantly reduces query overhead, improves retrieval efficiency, and minimizes the retrieval of irrelevant information. We evaluate RAGRoute using the MIRAGE and MMLU benchmarks and demonstrate its effectiveness in retrieving relevant documents while reducing the number of queries. RAGRoute reduces the total number of queries up to 77.5% and communication volume up to 76.2%.
Authors: Guoqing Chao, Kaixin Xu, Xijiong Xie, Yongyong Chen
Abstract: Incomplete multi-view clustering has become one of the important research problems due to the extensive missing multi-view data in the real world. Although the existing methods have made great progress, there are still some problems: 1) most methods cannot effectively mine the information hidden in the missing data; 2) most methods typically divide representation learning and clustering into two separate stages, but this may affect the clustering performance as the clustering results directly depend on the learned representation. To address these problems, we propose a novel incomplete multi-view clustering method with hierarchical information transfer. Firstly, we design the view-specific Graph Convolutional Networks (GCN) to obtain the representation encoding the graph structure, which is then fused into the consensus representation. Secondly, considering that one layer of GCN transfers one-order neighbor node information, the global graph propagation with the consensus representation is proposed to handle the missing data and learn deep representation. Finally, we design a weight-sharing pseudo-classifier with contrastive learning to obtain an end-to-end framework that combines view-specific representation learning, global graph propagation with hierarchical information transfer, and contrastive clustering for joint optimization. Extensive experiments conducted on several commonly-used datasets demonstrate the effectiveness and superiority of our method in comparison with other state-of-the-art approaches. The code is available at https://github.com/KelvinXuu/GHICMC.
Authors: Qizhou Wang, Jin Peng Zhou, Zhanke Zhou, Saebyeol Shin, Bo Han, Kilian Q. Weinberger
Abstract: Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements. Once these risks emerge, timely updates are crucial to remove undesirable responses, ensuring legal and safe model usage. It has spurred recent research into LLM unlearning, focusing on erasing targeted undesirable knowledge without compromising the integrity of other, non-targeted responses. Existing studies have introduced various unlearning objectives to pursue LLM unlearning without necessitating complete retraining. However, each of these objectives has unique properties, and no unified framework is currently available to comprehend them thoroughly. To fill the gap, we propose a toolkit of the gradient effect (G-effect), quantifying the impacts of unlearning objectives on model performance from a gradient perspective. A notable advantage is its broad ability to detail the unlearning impacts from various aspects across instances, updating steps, and LLM layers. Accordingly, the G-effect offers new insights into identifying drawbacks of existing unlearning objectives, further motivating us to explore a series of new solutions for their mitigation and improvements. Finally, we outline promising directions that merit further studies, aiming at contributing to the community to advance this important field.
Authors: Shiqi Wang, Zhibo Zhang, Libing Fang, Cam-Tu Nguyen, Wenzhon Li
Abstract: Corporate fraud detection aims to automatically recognize companies that conduct wrongful activities such as fraudulent financial statements or illegal insider trading. Previous learning-based methods fail to effectively integrate rich interactions in the company network. To close this gap, we collect 18-year financial records in China to form three graph datasets with fraud labels. We analyze the characteristics of the financial graphs, highlighting two pronounced issues: (1) information overload: the dominance of (noisy) non-company nodes over company nodes hinders the message-passing process in Graph Convolution Networks (GCN); and (2) hidden fraud: there exists a large percentage of possible undetected violations in the collected data. The hidden fraud problem will introduce noisy labels in the training dataset and compromise fraud detection results. To handle such challenges, we propose a novel graph-based method, namely, Knowledge-enhanced GCN with Robust Two-stage Learning (${\rm KeGCN}_{R}$), which leverages Knowledge Graph Embeddings to mitigate the information overload and effectively learns rich representations. The proposed model adopts a two-stage learning method to enhance robustness against hidden frauds. Extensive experimental results not only confirm the importance of interactions but also show the superiority of ${\rm KeGCN}_{R}$ over a number of strong baselines in terms of fraud detection effectiveness and robustness.
Authors: Michael Somma, Thomas Gallien, Branka Stojanovic
Abstract: Anomaly detection in complex dynamical systems is essential for ensuring reliability, safety, and efficiency in industrial and cyber-physical infrastructures. Predictive maintenance helps prevent costly failures, while cybersecurity monitoring has become critical as digitized systems face growing threats. Many of these systems exhibit oscillatory behaviors and bounded motion, requiring anomaly detection methods that capture structured temporal dependencies while adhering to physical consistency principles. In this work, we propose a system-theoretic approach to anomaly detection, grounded in classical embedding theory and physics-inspired consistency principles. We build upon the Fractal Whitney Embedding Prevalence Theorem, extending traditional embedding techniques to complex system dynamics. Additionally, we introduce state-derivative pairs as an embedding strategy to capture system evolution. To enforce temporal coherence, we develop a Temporal Differential Consistency Autoencoder (TDC-AE), incorporating a TDC-Loss that aligns the approximated derivatives of latent variables with their dynamic representations. We evaluate our method on the C-MAPSS dataset, a benchmark for turbofan aeroengine degradation. TDC-AE outperforms LSTMs and Transformers while achieving a 200x reduction in MAC operations, making it particularly suited for lightweight edge computing. Our findings support the hypothesis that anomalies disrupt stable system dynamics, providing a robust, interpretable signal for anomaly detection.
Authors: Anikait Singh, Sheryl Hsu, Kyle Hsu, Eric Mitchell, Stefano Ermon, Tatsunori Hashimoto, Archit Sharma, Chelsea Finn
Abstract: Effective personalization of LLMs is critical for a broad range of user-interfacing applications such as virtual assistants and content curation. Inspired by the strong in-context learning capabilities of LLMs, we propose Few-Shot Preference Optimization (FSPO), which reframes reward modeling as a meta-learning problem. Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them. Additionally, since real-world preference data is scarce and challenging to collect at scale, we propose careful design choices to construct synthetic preference datasets for personalization, generating over 1M synthetic personalized preferences using publicly available LLMs. In particular, to successfully transfer from synthetic data to real users, we find it crucial for the data to exhibit both high diversity and coherent, self-consistent structure. We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study. Overall, FSPO achieves an 87% Alpaca Eval winrate on average in generating responses that are personalized to synthetic users and a 72% winrate with real human users in open-ended question answering.
Authors: Joel Veness, Marcus Hutter, Andras Gyorgy, Jordi Grau-Moya
Abstract: This paper considers a generalisation of universal source coding for interaction data, namely data streams that have actions interleaved with observations. Our goal will be to construct a coding distribution that is both universal \emph{and} can be used as a control policy. Allowing for action generation needs careful treatment, as naive approaches which do not distinguish between actions and observations run into the self-delusion problem in universal settings. We showcase our perspective in the context of the challenging non-stationary stochastic Bernoulli bandit problem. Our main contribution is an efficient and high performing algorithm for this problem that generalises the Partition Tree Weighting universal source coding technique for passive prediction to the control setting.
Authors: Stephan Rabanser, Nathalie Rauschmayr, Achin Kulshrestha, Petra Poklukar, Wittawat Jitkrittum, Sean Augenstein, Congchao Wang, Federico Tombari
Abstract: Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these challenges, local smaller models are often deployed alongside larger models, relying on routing and deferral mechanisms to offload complex tasks. However, existing approaches inadequately balance the capabilities of these models, often resulting in unnecessary deferrals or sub-optimal resource usage. In this work we introduce a novel loss function called Gatekeeper for calibrating smaller models in cascade setups. Our approach fine-tunes the smaller model to confidently handle tasks it can perform correctly while deferring complex tasks to the larger model. Moreover, it incorporates a mechanism for managing the trade-off between model performance and deferral accuracy, and is broadly applicable across various tasks and domains without any architectural changes. We evaluate our method on encoder-only, decoder-only, and encoder-decoder architectures. Experiments across image classification, language modeling, and vision-language tasks show that our approach substantially improves deferral performance.
Authors: Irit Chelly, Roy Uziel, Oren Freifeld, Ari Pakman
Abstract: Neural models for amortized probabilistic clustering yield samples of cluster labels given a set-structured input, while avoiding lengthy Markov chain runs and the need for explicit data likelihoods. Existing methods which label each data point sequentially, like the Neural Clustering Process, often lead to cluster assignments highly dependent on the data order. Alternatively, methods that sequentially create full clusters, do not provide assignment probabilities. In this paper, we introduce GFNCP, a novel framework for amortized clustering. GFNCP is formulated as a Generative Flow Network with a shared energy-based parametrization of policy and reward. We show that the flow matching conditions are equivalent to consistency of the clustering posterior under marginalization, which in turn implies order invariance. GFNCP also outperforms existing methods in clustering performance on both synthetic and real-world data.
Authors: Amit Kumar, Taoran Ji
Abstract: Cryptocurrencies fluctuate in markets with high price volatility, posing significant challenges for investors. To aid in informed decision-making, systems predicting cryptocurrency market movements have been developed, typically focusing on historical patterns. However, these methods often overlook three critical factors influencing market dynamics: 1) the macro investing environment, reflected in major cryptocurrency fluctuations affecting collaborative investor behaviors; 2) overall market sentiment, heavily influenced by news impacting investor strategies; and 3) technical indicators, offering insights into overbought or oversold conditions, momentum, and market trends, which are crucial for short-term price movements. This paper proposes a dual prediction mechanism that forecasts the next day's closing price by incorporating macroeconomic fluctuations, technical indicators, and individual cryptocurrency price changes. Additionally, a novel refinement mechanism enhances predictions through market sentiment-based rescaling and fusion. Experiments demonstrate that the proposed model achieves state-of-the-art performance, consistently outperforming ten comparison methods.
Authors: Jan-Hendrik Ewers, David Anderson, Douglas Thomson
Abstract: Wilderness search and rescue operations are often carried out over vast landscapes. The search efforts, however, must be undertaken in minimum time to maximize the chance of survival of the victim. Whilst the advent of cheap multicopters in recent years has changed the way search operations are handled, it has not solved the challenges of the massive areas at hand. The problem therefore is not one of complete coverage, but one of maximizing the information gathered in the limited time available. In this work we propose that a combination of a recurrent autoencoder and deep reinforcement learning is a more efficient solution to the search problem than previous pure deep reinforcement learning or optimisation approaches. The autoencoder training paradigm efficiently maximizes the information throughput of the encoder into its latent space representation which deep reinforcement learning is primed to leverage. Without the overhead of independently solving the problem that the recurrent autoencoder is designed for, it is more efficient in learning the control task. We further implement three additional architectures for a comprehensive comparison of the main proposed architecture. Similarly, we apply both soft actor-critic and proximal policy optimisation to provide an insight into the performance of both in a highly non-linear and complex application with a large observation Results show that the proposed architecture is vastly superior to the benchmarks, with soft actor-critic achieving the best performance. This model further outperformed work from the literature whilst having below a fifth of the total learnable parameters and training in a quarter of the time.
Authors: Aidan Furlong, Xingang Zhao, Robert Salko, Xu Wu
Abstract: Critical heat flux is a key quantity in boiling system modeling due to its impact on heat transfer and component temperature and performance. This study investigates the development and validation of an uncertainty-aware hybrid modeling approach that combines machine learning with physics-based models in the prediction of critical heat flux in nuclear reactors for cases of dryout. Two empirical correlations, Biasi and Bowring, were employed with three machine learning uncertainty quantification techniques: deep neural network ensembles, Bayesian neural networks, and deep Gaussian processes. A pure machine learning model without a base model served as a baseline for comparison. This study examines the performance and uncertainty of the models under both plentiful and limited training data scenarios using parity plots, uncertainty distributions, and calibration curves. The results indicate that the Biasi hybrid deep neural network ensemble achieved the most favorable performance (with a mean absolute relative error of 1.846% and stable uncertainty estimates), particularly in the plentiful data scenario. The Bayesian neural network models showed slightly higher error and uncertainty but superior calibration. By contrast, deep Gaussian process models underperformed by most metrics. All hybrid models outperformed pure machine learning configurations, demonstrating resistance against data scarcity.
Authors: Ali Ismail-Fawaz
Abstract: Time series data, defined by equally spaced points over time, is essential in fields like medicine, telecommunications, and energy. Analyzing it involves tasks such as classification, clustering, prototyping, and regression. Classification identifies normal vs. abnormal movements in skeleton-based motion sequences, clustering detects stock market behavior patterns, prototyping expands physical therapy datasets, and regression predicts patient recovery. Deep learning has recently gained traction in time series analysis due to its success in other domains. This thesis leverages deep learning to enhance classification with feature engineering, introduce foundation models, and develop a compact yet state-of-the-art architecture. We also address limited labeled data with self-supervised learning. Our contributions apply to real-world tasks, including human motion analysis for action recognition and rehabilitation. We introduce a generative model for human motion data, valuable for cinematic production and gaming. For prototyping, we propose a shape-based synthetic sample generation method to support regression models when data is scarce. Lastly, we critically evaluate discriminative and generative models, identifying limitations in current methodologies and advocating for a robust, standardized evaluation framework. Our experiments on public datasets provide novel insights and methodologies, advancing time series analysis with practical applications.
Authors: Christos Chatzis, Carla Schenker, J\'er\'emy E. Cohen, Evrim Acar
Abstract: Multiway datasets are commonly analyzed using unsupervised matrix and tensor factorization methods to reveal underlying patterns. Frequently, such datasets include timestamps and could correspond to, for example, health-related measurements of subjects collected over time. The temporal dimension is inherently different from the other dimensions, requiring methods that account for its intrinsic properties. Linear Dynamical Systems (LDS) are specifically designed to capture sequential dependencies in the observed data. In this work, we bridge the gap between tensor factorizations and dynamical modeling by exploring the relationship between LDS, Coupled Matrix Factorizations (CMF) and the PARAFAC2 model. We propose a time-aware coupled factorization model called d(ynamical)CMF that constrains the temporal evolution of the latent factors to adhere to a specific LDS structure. Using synthetic datasets, we compare the performance of dCMF with PARAFAC2 and t(emporal)PARAFAC2 which incorporates temporal smoothness. Our results show that dCMF and PARAFAC2-based approaches perform similarly when capturing smoothly evolving patterns that adhere to the PARAFAC2 structure. However, dCMF outperforms alternatives when the patterns evolve smoothly but deviate from the PARAFAC2 structure. Furthermore, we demonstrate that the proposed dCMF method enables to capture more complex dynamics when additional prior information about the temporal evolution is incorporated.
Authors: Arman Mielke, Uwe Bauknecht, Thilo Strauss, Mathias Niepert
Abstract: Combinatorial optimization (CO) problems arise in a wide range of fields from medicine to logistics and manufacturing. While exact solutions are often not necessary, many applications require finding high-quality solutions quickly. For this purpose, we propose a data-driven approach to improve existing non-learned approximation algorithms for CO. We parameterize the approximation algorithm and train a graph neural network (GNN) to predict parameter values that lead to the best possible solutions. Our pipeline is trained end-to-end in a self-supervised fashion using gradient estimation, treating the approximation algorithm as a black box. We propose a novel gradient estimation scheme for this purpose, which we call preference-based gradient estimation. Our approach combines the benefits of the neural network and the non-learned approximation algorithm: The GNN leverages the information from the dataset to allow the approximation algorithm to find better solutions, while the approximation algorithm guarantees that the solution is feasible. We validate our approach on two well-known combinatorial optimization problems, the travelling salesman problem and the minimum k-cut problem, and show that our method is competitive with state of the art learned CO solvers.
Authors: O\u{g}uzhan Ersoy, Jari Kolehmainen, Gabriel Passamani Andrade
Abstract: Training dense LLMs requires enormous amounts of data and centralized compute, which introduces fundamental bottlenecks and ever-growing costs for large models. Several studies aim to reduce this dependency on centralization by reducing the communication overhead of training dense models. Taking this idea of reducing communication overhead to a natural extreme, by training embarrassingly parallelizable ensembles of small independent experts, has been shown to outperform large dense models trained in traditional centralized settings. However, existing studies do not take into account underlying differences amongst data domains and treat them as monolithic, regardless of their underlying complexity, size, or distribution. In this paper, we explore the effects of introducing heterogeneity to these ensembles of domain expert models. Specifically, by allowing models within the ensemble to vary in size--as well as the number of training steps taken depending on the training data's domain--we study the effect heterogeneity has on these ensembles when evaluated against domains included in, and excluded from, the training set. We use the same compute budget to train heterogeneous ensembles and homogeneous baselines for comparison. We show that the heterogeneous ensembles achieve the lowest perplexity scores in $20$ out of the $21$ data domains used in the evaluation. Our code is available at https://github.com/gensyn-ai/hdee.
Authors: Ziqiao Weng, Weidong Cai, Bo Zhou
Abstract: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder impacting social and behavioral development. Resting-state fMRI, a non-invasive tool for capturing brain connectivity patterns, aids in early ASD diagnosis and differentiation from typical controls (TC). However, previous methods, which rely on either mean time series or full 4D data, are limited by a lack of spatial information or by high computational costs. This underscores the need for an efficient solution that preserves both spatial and temporal information. In this paper, we propose a novel, simple, and efficient spatial-temporal-omics learning framework designed to efficiently extract spatio-temporal features from fMRI for ASD classification. Our approach addresses these limitations by utilizing 3D time-domain derivatives as the spatial-temporal inter-voxel omics, which preserve full spatial resolution while capturing diverse statistical characteristics of the time series at each voxel. Meanwhile, functional connectivity features serve as the spatial-temporal inter-regional omics, capturing correlations across brain regions. Extensive experiments and ablation studies on the ABIDE dataset demonstrate that our framework significantly outperforms previous methods while maintaining computational efficiency. We believe our research offers valuable insights that will inform and advance future ASD studies, particularly in the realm of spatial-temporal-omics-based learning.
Authors: Hamdan Al Ahbabi, Gautier Marti, Saeed AlMarri, Ibrahim Elfadel
Abstract: Self-supervised learning models for speech processing, such as wav2vec2, HuBERT, WavLM, and Whisper, generate embeddings that capture both linguistic and paralinguistic information, making it challenging to analyze tone independently of spoken content. In this work, we introduce a method for disentangling paralinguistic features from linguistic content by regressing speech embeddings onto their corresponding text embeddings and using the residuals as a representation of vocal tone. We evaluate this approach across multiple self-supervised speech embeddings, demonstrating that residual embeddings significantly improve tone classification performance compared to raw speech embeddings. Our results show that this method enhances linear separability, enabling improved classification even with simple models such as logistic regression. Visualization of the residual embeddings further confirms the successful removal of linguistic information while preserving tone-related features. These findings highlight the potential of residual embeddings for applications in sentiment analysis, speaker characterization, and paralinguistic speech processing.
Authors: Seungwook Han, Jyothish Pari, Samuel J. Gershman, Pulkit Agrawal
Abstract: Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly -- the hallmarks of artificial general intelligence (AGI) -- remains fragile. While LLMs seemingly succeed in commonsense reasoning, programming, and mathematics, they struggle to generalize algorithmic understanding across novel contexts. Our experiments with algorithmic tasks in esoteric programming languages reveal that LLM's reasoning overfits to the training data and is limited in its transferability. We hypothesize that the core issue underlying such limited transferability is the coupling of reasoning and knowledge in LLMs. To transition from AUI to AGI, we propose disentangling knowledge and reasoning through three key directions: (1) pretaining to reason using RL from scratch as an alternative to the widely used next-token prediction pretraining, (2) using a curriculum of synthetic tasks to ease the learning of a \textit{reasoning prior} for RL that can then be transferred to natural language tasks, and (3) learning more generalizable reasoning functions using a small context window to reduce exploiting spurious correlations between tokens. Such a reasoning system coupled with a trained retrieval system and a large external memory bank as a knowledge store can overcome several limitations of existing architectures at learning to reason in novel scenarios.
Authors: Arasu Arun, Adam St. Arnaud, Alexey Titov, Brian Wilcox, Viktor Kolobaric, Marc Brinkmann, Oguzhan Ersoy, Ben Fielding, Joseph Bonneau
Abstract: Machine learning programs, such as those performing inference, fine-tuning, and training of LLMs, are commonly delegated to untrusted compute providers. To provide correctness guarantees for the client, we propose adapting the cryptographic notion of refereed delegation to the machine learning setting. This approach enables a computationally limited client to delegate a program to multiple untrusted compute providers, with a guarantee of obtaining the correct result if at least one of them is honest. Refereed delegation of ML programs poses two technical hurdles: (1) an arbitration protocol to resolve disputes when compute providers disagree on the output, and (2) the ability to bitwise reproduce ML programs across different hardware setups, For (1), we design Verde, a dispute arbitration protocol that efficiently handles the large scale and graph-based computational model of modern ML programs. For (2), we build RepOps (Reproducible Operators), a library that eliminates hardware "non-determinism" by controlling the order of floating point operations performed on all hardware. Our implementation shows that refereed delegation achieves both strong guarantees for clients and practical overheads for compute providers.
Authors: Christoph Schuhmann, Gollam Rabby, Ameya Prabhu, Tawsif Ahmed, Andreas Hochlehnert, Huu Nguyen, Nick Akinci Heidrich, Ludwig Schmidt, Robert Kaczmarczyk, S\"oren Auer, Jenia Jitsev, Matthias Bethge
Abstract: Paywalls, licenses and copyright rules often restrict the broad dissemination and reuse of scientific knowledge. We take the position that it is both legally and technically feasible to extract the scientific knowledge in scholarly texts. Current methods, like text embeddings, fail to reliably preserve factual content, and simple paraphrasing may not be legally sound. We urge the community to adopt a new idea: convert scholarly documents into Knowledge Units using LLMs. These units use structured data capturing entities, attributes and relationships without stylistic content. We provide evidence that Knowledge Units: (1) form a legally defensible framework for sharing knowledge from copyrighted research texts, based on legal analyses of German copyright law and U.S. Fair Use doctrine, and (2) preserve most (~95%) factual knowledge from original text, measured by MCQ performance on facts from the original copyrighted text across four research domains. Freeing scientific knowledge from copyright promises transformative benefits for scientific research and education by allowing language models to reuse important facts from copyrighted text. To support this, we share open-source tools for converting research documents into Knowledge Units. Overall, our work posits the feasibility of democratizing access to scientific knowledge while respecting copyright.
Authors: Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru, Jonas Geiping, Matthias Bethge, Ameya Prabhu
Abstract: There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claims to be iteratively refined over time. This process requires significant researcher effort, reasoning, and ingenuity. Yet current benchmarks for LMs predominantly assess their ability to generate solutions rather than challenge them. We advocate for developing benchmarks that evaluate this inverse capability - creating counterexamples for subtly incorrect solutions. To demonstrate this approach, we start with the domain of algorithmic problem solving, where counterexamples can be evaluated automatically using code execution. Specifically, we introduce REFUTE, a dynamically updating benchmark that includes recent problems and incorrect submissions from programming competitions, where human experts successfully identified counterexamples. Our analysis finds that the best reasoning agents, even OpenAI o3-mini (high) with code execution feedback, can create counterexamples for only <9% of incorrect solutions in REFUTE, even though ratings indicate its ability to solve up to 48% of these problems from scratch. We hope our work spurs progress in evaluating and enhancing LMs' ability to falsify incorrect solutions - a capability that is crucial for both accelerating research and making models self-improve through reliable reflective reasoning.
Authors: Sofya Manko, Dmitry Frolovtsev
Abstract: Single-pixel cameras are effective solution for imaging outside the visible spectrum where traditional CMOS/CCD cameras have challenges. Combined with machine learning, they can analyze images quickly enough for practical applications. Solving the problem of high-dimensional single-pixel visualization can potentially be accelerated using quantum machine learning, thereby expanding the range of practical problems. In this work we simulated a single-pixel imaging experiment using Hadamard basis patterns, where images from the MNIST handwritten digit dataset were used as objects. There were selected 64 measurements with maximum variance (6% of the number of pixels in the image). We created algorithms for classifying and reconstruction images based on these measurements using classical fully connected neural networks and parameterized quantum circuits. Classical and quantum classifiers showed accuracies of 96% and 95% respectively after 6 training epochs, which is quite competitive result. Image reconstruction was also demonstrated using classical and quantum neural networks after 10 training epochs, the structural similarity index measure values were 0.76 and 0.25, respectively, which indicates that the problem in such a formulation turned out to be too difficult for quantum neural networks in such a configuration for now.
Authors: M. P. Bento, H. B. C\^amara, J. F. Seabra
Abstract: We parametrically solve the Boltzmann equations governing freeze-in dark matter (DM) in alternative cosmologies with Physics-Informed Neural Networks (PINNs), a mesh-free method. Through inverse PINNs, using a single DM experimental point -- observed relic density -- we determine the physical attributes of the theory, namely power-law cosmologies, inspired by braneworld scenarios, and particle interaction cross sections. The expansion of the Universe in such alternative cosmologies has been parameterized through a switch-like function reproducing the Hubble law at later times. Without loss of generality, we model more realistically this transition with a smooth function. We predict a distinct pair-wise relationship between power-law exponent and particle interactions: for a given cosmology with negative (positive) exponent, smaller (larger) cross sections are required to reproduce the data. Lastly, via Bayesian methods, we quantify the epistemic uncertainty of theoretical parameters found in inverse problems.
Authors: Dazhou Yu, Riyang Bao, Gengchen Mai, Liang Zhao
Abstract: Spatial reasoning remains a challenge for Large Language Models (LLMs), which struggle with spatial data retrieval and reasoning. We propose Spatial Retrieval-Augmented Generation (Spatial-RAG), a framework that extends RAG to spatial tasks by integrating sparse spatial retrieval (spatial databases) and dense semantic retrieval (LLM-based similarity). A multi-objective ranking strategy balances spatial constraints and semantic relevance, while an LLM-guided generator ensures coherent responses. Experiments on a real-world tourism dataset show that Spatial-RAG significantly improves spatial question answering, bridging the gap between LLMs and spatial intelligence.
Authors: Ankur Sinha, Chaitanya Agarwal, Pekka Malo
Abstract: Large language models (LLMs) excel at generating human-like responses but often struggle with interactive tasks that require access to real-time information. This limitation poses challenges in finance, where models must access up-to-date information, such as recent news or price movements, to support decision-making. To address this, we introduce Financial Agent, a knowledge-grounding approach for LLMs to handle financial queries using real-time text and tabular data. Our contributions are threefold: First, we develop a Financial Context Dataset of over 50,000 financial queries paired with the required context. Second, we train FinBloom 7B, a custom 7 billion parameter LLM, on 14 million financial news articles from Reuters and Deutsche Presse-Agentur, alongside 12 million Securities and Exchange Commission (SEC) filings. Third, we fine-tune FinBloom 7B using the Financial Context Dataset to serve as a Financial Agent. This agent generates relevant financial context, enabling efficient real-time data retrieval to answer user queries. By reducing latency and eliminating the need for users to manually provide accurate data, our approach significantly enhances the capability of LLMs to handle dynamic financial tasks. Our proposed approach makes real-time financial decisions, algorithmic trading and other related tasks streamlined, and is valuable in contexts with high-velocity data flows.
Authors: Miltiadis Allamanis, Pengcheng Yin
Abstract: To evaluate large language models (LLMs) for code, research has used manually created unit test-based benchmarks. However, these tests are often inadequate, missing corner cases and other implementation-specific oddities. This work introduces ProbeGen, a whitebox method that takes two or more executable pieces of code and searches for counterexamples to their equivalence. Comparing code semantics requires a deep understanding of code. We demonstrate that LLMs with execution feedback perform well at this task. In a common code synthesis benchmark, ProbeGen disproves 18% of samples considered equivalent to the ground truth by the benchmark-provided unit tests. Additionally, using ProbeGen, we can semantically cluster LLM samples for semantic self-consistency, improving pass@1 by 10% by unifying syntactically distinct but semantically similar samples.
Authors: Gabriel Patron, Zhiwei Xu, Ishan Kapnadak, Felipe Maia Polo
Abstract: Modern recommender systems follow the guiding principle of serving the right user, the right item at the right time. One of their main limitations is that they are typically limited to items already in the catalog. We propose REcommendations BEyond CAtalogs, REBECA, a new class of probabilistic diffusion-based recommender systems that synthesize new items tailored to individual tastes rather than retrieve items from the catalog. REBECA combines efficient training in embedding space with a novel diffusion prior that only requires users' past ratings of items. We evaluate REBECA on real-world data and propose novel personalization metrics for generative recommender systems. Extensive experiments demonstrate that REBECA produces high-quality, personalized recommendations, generating images that align with users' unique preferences.
Authors: Ilqar Ramazanli, Hamid Eghbalzadeh, Xiaoyi Liu, Yang Wang, Jiaxiang Fu, Kaushik Rangadurai, Sem Park, Bo Long, Xue Feng
Abstract: Perturbation-based regularization techniques address many challenges in industrial-scale large models, particularly with sparse labels, and emphasize consistency and invariance for perturbation in model predictions. One of the popular regularization techniques has been various forms of self-consistency, which involve making small modifications to input data while preserving contextual information and enforcing similar predictions through auxiliary loss functions. In this work, we explore the first successful application of perturbation-based regularization algorithms in large-scale ads ranking models, and further propose a novel regularization algorithm, namely, Loss-Balanced Small Perturbation Regularization (LSPR) that can be used in potentially any deep learning model. We have successfully demonstrate that both Self-Consistency Regularization approaches (SCR) and LSPR are scalable and can improve ads delivery systems. By conducting industrial-scale experiments, and numerical analysis, we additionally show that our proposed LSPR, performs consistently better compared to SCR, across various groups and signal availability setups. Finally, we report a successful application of the proposed LSPR in a billion-scale industrial ranking system, which to the best of our knowledge, is the first of its kind, and it is specially designed to address the various scalability challenges (e.g, various surfaces, geological locations, clients and so on) as we will mention in this paper.
Authors: Gur Keinan, Omer Ben-Porat
Abstract: While recommender systems (RSs) traditionally rely on extensive individual user data, regulatory and technological shifts necessitate reliance on aggregated user information. This shift significantly impacts the recommendation process, requiring RSs to engage in intensive exploration to identify user preferences. However, this approach risks user churn due to potentially unsatisfactory recommendations. In this paper, we propose a model that addresses the dual challenges of leveraging aggregated user information and mitigating churn risk. Our model assumes that the RS operates with a probabilistic prior over user types and aggregated satisfaction levels for various content types. We demonstrate that optimal policies naturally transition from exploration to exploitation in finite time, develop a branch-and-bound algorithm for computing these policies, and empirically validate its effectiveness.
Authors: Aditi Mavalankar, Hassan Mansoor, Zita Marinho, Masha Samsikova, Tom Schaul
Abstract: Scaling up inference-time compute has proven to be a valuable strategy in improving the performance of Large Language Models (LLMs) without fine-tuning. An important task that can benefit from additional inference-time compute is self-repair; given an initial flawed response, or guess, the LLM corrects its own mistake and produces an improved response, or fix. We leverage the in-context learning ability of LLMs to perform self-repair in the coding domain. The key contribution of our paper is an approach that synthesises and selects an ordered set of golden example pairs, or AuPairs, of these initial guesses and subsequent fixes for the corresponding problems. Each such AuPair is provided as a single in-context example at inference time to generate a repaired solution. For an inference-time compute budget of $N$ LLM calls per problem, $N$ AuPairs are used to generate $N$ repaired solutions, out of which the highest-scoring solution is selected as the final answer. The underlying intuition is that if the LLM is given a different example of fixing an incorrect guess each time, it can subsequently generate a diverse set of repaired solutions. Our algorithm selects these AuPairs in a manner that maximises complementarity and usefulness. We demonstrate the results of our algorithm on 5 LLMs across 7 competitive programming datasets for the code repair task. Our algorithm yields a significant boost in performance compared to best-of-$N$ and self-repair, and also exhibits strong generalisation across datasets and models. Moreover, our approach shows significantly stronger scaling with inference-time compute budget compared to baselines.
Authors: Aman Goel, Xian Carrie Wu, Zhe Wang, Dmitriy Bespalov, Yanjun Qi
Abstract: Jailbreaking large-language models (LLMs) involves testing their robustness against adversarial prompts and evaluating their ability to withstand prompt attacks that could elicit unauthorized or malicious responses. In this paper, we present TurboFuzzLLM, a mutation-based fuzzing technique for efficiently finding a collection of effective jailbreaking templates that, when combined with harmful questions, can lead a target LLM to produce harmful responses through black-box access via user prompts. We describe the limitations of directly applying existing template-based attacking techniques in practice, and present functional and efficiency-focused upgrades we added to mutation-based fuzzing to generate effective jailbreaking templates automatically. TurboFuzzLLM achieves $\geq$ 95\% attack success rates (ASR) on public datasets for leading LLMs (including GPT-4o \& GPT-4 Turbo), shows impressive generalizability to unseen harmful questions, and helps in improving model defenses to prompt attacks.
Authors: Yukun Chen, Shuo Shao, Enhao Huang, Yiming Li, Pin-Yu Chen, Zhan Qin, Kui Ren
Abstract: Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training phase. Pre-processing-based defense, which is one of the most important defense paradigms, typically focuses on input transformations or backdoor trigger inversion (BTI) to deactivate or eliminate embedded backdoor triggers during the inference process. However, these methods suffer from inherent limitations: transformation-based defenses often fail to balance model utility and defense performance, while BTI-based defenses struggle to accurately reconstruct trigger patterns without prior knowledge. In this paper, we propose REFINE, an inversion-free backdoor defense method based on model reprogramming. REFINE consists of two key components: \textbf{(1)} an input transformation module that disrupts both benign and backdoor patterns, generating new benign features; and \textbf{(2)} an output remapping module that redefines the model's output domain to guide the input transformations effectively. By further integrating supervised contrastive loss, REFINE enhances the defense capabilities while maintaining model utility. Extensive experiments on various benchmark datasets demonstrate the effectiveness of our REFINE and its resistance to potential adaptive attacks.
Authors: Sefik Serengil, Alper Ozpinar
Abstract: Facial recognition systems rely on embeddings to represent facial images and determine identity by verifying if the distance between embeddings is below a pre-tuned threshold. While embeddings are not reversible to original images, they still contain sensitive information, making their security critical. Traditional encryption methods like AES are limited in securely utilizing cloud computational power for distance calculations. Homomorphic Encryption, allowing calculations on encrypted data, offers a robust alternative. This paper introduces CipherFace, a homomorphic encryption-driven framework for secure cloud-based facial recognition, which we have open-sourced at http://github.com/serengil/cipherface. By leveraging FHE, CipherFace ensures the privacy of embeddings while utilizing the cloud for efficient distance computation. Furthermore, we propose a novel encrypted distance computation method for both Euclidean and Cosine distances, addressing key challenges in performing secure similarity calculations on encrypted data. We also conducted experiments with different facial recognition models, various embedding sizes, and cryptosystem configurations, demonstrating the scalability and effectiveness of CipherFace in real-world applications.
Authors: Kamyar Barakati, Yu Liu, Utkarsh Pratiush, Boris N. Slautin, Sergei V. Kalinin
Abstract: Analyzing imaging and hyperspectral data is crucial across scientific fields, including biology, medicine, chemistry, and physics. The primary goal is to transform high-resolution or high-dimensional data into an interpretable format to generate actionable insights, aiding decision-making and advancing knowledge. Currently, this task relies on complex, human-designed workflows comprising iterative steps such as denoising, spatial sampling, keypoint detection, feature generation, clustering, dimensionality reduction, and physics-based deconvolutions. The introduction of machine learning over the past decade has accelerated tasks like image segmentation and object detection via supervised learning, and dimensionality reduction via unsupervised methods. However, both classical and NN-based approaches still require human input, whether for hyperparameter tuning, data labeling, or both. The growing use of automated imaging tools, from atomically resolved imaging to biological applications, demands unsupervised methods that optimize data representation for human decision-making or autonomous experimentation. Here, we discuss advances in reward-based workflows, which adopt expert decision-making principles and demonstrate strong transfer learning across diverse tasks. We represent image analysis as a decision-making process over possible operations and identify desiderata and their mappings to classical decision-making frameworks. Reward-driven workflows enable a shift from supervised, black-box models sensitive to distribution shifts to explainable, unsupervised, and robust optimization in image analysis. They can function as wrappers over classical and DCNN-based methods, making them applicable to both unsupervised and supervised workflows (e.g., classification, regression for structure-property mapping) across imaging and hyperspectral data.
Authors: Pranjal Aggarwal, Sean Welleck
Abstract: Recent advancements in software engineering (SWE) agents have largely followed a $\textit{tool-based paradigm}$, where agents interact with hand-engineered tool APIs to perform specific tasks. While effective for specialized tasks, these methods fundamentally lack generalization, as they require predefined tools for each task and do not scale across programming languages and domains. We introduce $\texttt{Programming with Pixels}$ (PwP), an agent environment that unifies software development tasks by enabling $\textit{computer-use agents}$-agents that operate directly within an IDE through visual perception, typing, and clicking, rather than relying on predefined tool APIs. To systematically evaluate these agents, we propose $\texttt{PwP-Bench}$, a benchmark that unifies existing SWE benchmarks spanning tasks across multiple programming languages, modalities, and domains under a task-agnostic state and action space. Our experiments demonstrate that general-purpose computer-use agents can approach or even surpass specialized tool-based agents on a variety of SWE tasks without the need for hand-engineered tools. However, our analysis shows that current models suffer from limited visual grounding and fail to exploit many IDE tools that could simplify their tasks. When agents can directly access IDE tools, without visual interaction, they show significant performance improvements, highlighting the untapped potential of leveraging built-in IDE capabilities. Our results establish PwP as a scalable testbed for building and evaluating the next wave of software engineering agents. We release code and data at https://programmingwithpixels.com
Authors: PIN AI Team, Bill Qingyun Sun, Laura Florescu, Boliang Zhang, Regan Peng, Smile Hu, Shouqiao Wang, Ben Wu, Xi Wang, Davide Crapis, Gavin Zhen Guo
Abstract: Personal AI assistants (e.g., Apple Intelligence, Meta AI) offer proactive recommendations that simplify everyday tasks, but their reliance on sensitive user data raises concerns about privacy and trust. To address these challenges, we introduce the Guardian of Data (GOD), a secure, privacy-preserving framework for training and evaluating AI assistants directly on-device. Unlike traditional benchmarks, the GOD model measures how well assistants can anticipate user needs-such as suggesting gifts-while protecting user data and autonomy. Functioning like an AI school, it addresses the cold start problem by simulating user queries and employing a curriculum-based approach to refine the performance of each assistant. Running within a Trusted Execution Environment (TEE), it safeguards user data while applying reinforcement and imitation learning to refine AI recommendations. A token-based incentive system encourages users to share data securely, creating a data flywheel that drives continuous improvement. By integrating privacy, personalization, and trust, the GOD model provides a scalable, responsible path for advancing personal AI assistants. For community collaboration, part of the framework is open-sourced at https://github.com/PIN-AI/God-Model.
Authors: Eric Xue, Zeyi Huang, Yuyang Ji, Haohan Wang
Abstract: Computer vision is a critical component in a wide range of real-world applications, including plant monitoring in agriculture and handwriting classification in digital systems. However, developing high-performance computer vision models traditionally demands both machine learning (ML) expertise and domain-specific knowledge, making the process costly, labor-intensive, and inaccessible to many. Large language model (LLM) agents have emerged as a promising solution to automate this workflow, but most existing methods share a common limitation: they attempt to optimize entire pipelines in a single step before evaluation, making it difficult to attribute improvements to specific changes. This lack of granularity leads to unstable optimization and slower convergence, limiting their effectiveness. To address this, we introduce Iterative Refinement, a novel strategy for LLM-driven ML pipeline design inspired by how human ML experts iteratively refine models, focusing on one component at a time rather than making sweeping changes all at once. By systematically updating individual components based on real training feedback, Iterative Refinement improves stability, interpretability, and overall model performance. We implement this strategy in IMPROVE, an end-to-end LLM agent framework for automating and optimizing object classification pipelines. Through extensive evaluations across datasets of varying sizes and domains, including standard benchmarks and Kaggle competition datasets, we demonstrate that Iterative Refinement enables IMPROVE to consistently achieve better performance over existing zero-shot LLM-based approaches. These findings establish Iterative Refinement as an effective new strategy for LLM-driven ML automation and position IMPROVE as an accessible solution for building high-quality computer vision models without requiring ML expertise.
Authors: Xiongbin Gui, Hanlin Lv, Xiao Wang, Longting Lv, Yi Xiao, Lei Wang
Abstract: Background: Recruitment for cohorts involving complex liver diseases, such as hepatocellular carcinoma and liver cirrhosis, often requires interpreting semantically complex criteria. Traditional manual screening methods are time-consuming and prone to errors. While AI-powered pre-screening offers potential solutions, challenges remain regarding accuracy, efficiency, and data privacy. Methods: We developed a novel patient pre-screening pipeline that leverages clinical expertise to guide the precise, safe, and efficient application of large language models. The pipeline breaks down complex criteria into a series of composite questions and then employs two strategies to perform semantic question-answering through electronic health records - (1) Pathway A, Anthropomorphized Experts' Chain of Thought strategy, and (2) Pathway B, Preset Stances within an Agent Collaboration strategy, particularly in managing complex clinical reasoning scenarios. The pipeline is evaluated on three key metrics-precision, time consumption, and counterfactual inference - at both the question and criterion levels. Results: Our pipeline achieved high precision (0.921, in criteria level) and efficiency (0.44s per task). Pathway B excelled in complex reasoning, while Pathway A was effective in precise data extraction with faster processing times. Both pathways achieved comparable precision. The pipeline showed promising results in hepatocellular carcinoma (0.878) and cirrhosis trials (0.843). Conclusions: This data-secure and time-efficient pipeline shows high precision in hepatopathy trials, providing promising solutions for streamlining clinical trial workflows. Its efficiency and adaptability make it suitable for improving patient recruitment. And its capability to function in resource-constrained environments further enhances its utility in clinical settings.
Authors: Shuming Shi, Ruobing Zuo, Gaolei He, Jianlin Wang, Chenyang Xu, Zhengfeng Yang
Abstract: Automated theorem proving (ATP) is one of the most challenging mathematical reasoning tasks for Large Language Models (LLMs). Most existing LLM-based ATP methods rely on supervised fine-tuning, which results in a limited alignment between the theorem proving process and human preferences. Direct Preference Optimization (DPO), which aligns LLMs with human preferences, has shown positive effects for certain tasks. However, the lack of high-quality preference data for theorem proving presents a significant challenge. In this paper, we innovatively apply DPO to formal automated theorem proving and introduces a Curriculum Learning-based DPO Iterative Theorem Proving (CuDIP) method. Specifically, we propose a method for constructing preference data which utilizes LLMs and existing theorem proving data to enhance the diversity of the preference data while reducing the reliance on human preference annotations. We then integrate this preference data construction method with curriculum learning to iteratively fine-tune the theorem proving model through DPO. Experimental results on the MiniF2F and ProofNet datasets demonstrate the effectiveness of the proposed method.
Authors: Ehsan Farahbakhsh, Dakshi Goel, Dhiraj Pimparkar, R. Dietmar Muller, Rohitash Chandra
Abstract: Traditional geological mapping, based on field observations and rock sample analysis, is inefficient for continuous spatial mapping of features like alteration zones. Deep learning models, such as convolutional neural networks (CNNs), have revolutionised remote sensing data analysis by automatically extracting features for classification and regression tasks. CNNs can detect specific mineralogical changes linked to mineralisation by identifying subtle features in remote sensing data. This study uses CNNs with Landsat 8, Landsat 9, and ASTER data to map alteration zones north of Broken Hill, New South Wales, Australia. The model is trained using ground truth data and an automated approach with selective principal component analysis (PCA). We compare CNNs with traditional machine learning models, including k-nearest neighbours, support vector machines, and multilayer perceptron. Results show that ground truth-based training yields more reliable maps, with CNNs slightly outperforming conventional models in capturing spatial patterns. Landsat 9 outperforms Landsat 8 in mapping iron oxide areas using ground truth-trained CNNs, while ASTER data provides the most accurate argillic and propylitic alteration maps. This highlights CNNs' effectiveness in improving geological mapping precision, especially for identifying subtle mineralisation-related alterations.
Authors: Zhizhi Peng, Taotao Wang, Chonghe Zhao, Guofu Liao, Zibin Lin, Yifeng Liu, Bin Cao, Long Shi, Qing Yang, Shengli Zhang
Abstract: As machine learning technologies advance rapidly across various domains, concerns over data privacy and model security have grown significantly. These challenges are particularly pronounced when models are trained and deployed on cloud platforms or third-party servers due to the computational resource limitations of users' end devices. In response, zero-knowledge proof (ZKP) technology has emerged as a promising solution, enabling effective validation of model performance and authenticity in both training and inference processes without disclosing sensitive data. Thus, ZKP ensures the verifiability and security of machine learning models, making it a valuable tool for privacy-preserving AI. Although some research has explored the verifiable machine learning solutions that exploit ZKP, a comprehensive survey and summary of these efforts remain absent. This survey paper aims to bridge this gap by reviewing and analyzing all the existing Zero-Knowledge Machine Learning (ZKML) research from June 2017 to December 2024. We begin by introducing the concept of ZKML and outlining its ZKP algorithmic setups under three key categories: verifiable training, verifiable inference, and verifiable testing. Next, we provide a comprehensive categorization of existing ZKML research within these categories and analyze the works in detail. Furthermore, we explore the implementation challenges faced in this field and discuss the improvement works to address these obstacles. Additionally, we highlight several commercial applications of ZKML technology. Finally, we propose promising directions for future advancements in this domain.
Authors: S M Sarwar
Abstract: Visual Question Answering requires models to generate accurate answers by integrating visual and textual understanding. However, VQA models still struggle with hallucinations, producing convincing but incorrect answers, particularly in knowledge-driven and Out-of-Distribution scenarios. We introduce FilterRAG, a retrieval-augmented framework that combines BLIP-VQA with Retrieval-Augmented Generation to ground answers in external knowledge sources like Wikipedia and DBpedia. FilterRAG achieves 36.5% accuracy on the OK-VQA dataset, demonstrating its effectiveness in reducing hallucinations and improving robustness in both in-domain and Out-of-Distribution settings. These findings highlight the potential of FilterRAG to improve Visual Question Answering systems for real-world deployment.
Authors: Xuechun Li, Susu Xu
Abstract: Interferometric Synthetic Aperture Radar (InSAR) technology uses satellite radar to detect surface deformation patterns and monitor earthquake impacts on buildings. While vital for emergency response planning, extracting multi-class building damage classifications from InSAR data faces challenges: overlapping damage signatures with environmental noise, computational complexity in multi-class scenarios, and the need for rapid regional-scale processing. Our novel multi-class variational causal Bayesian inference framework with quadratic variational bounds provides rigorous approximations while ensuring efficiency. By integrating InSAR observations with USGS ground failure models and building fragility functions, our approach separates building damage signals while maintaining computational efficiency through strategic pruning. Evaluation across five major earthquakes (Haiti 2021, Puerto Rico 2020, Zagreb 2020, Italy 2016, Ridgecrest 2019) shows improved damage classification accuracy (AUC: 0.94-0.96), achieving up to 35.7% improvement over existing methods. Our approach maintains high accuracy (AUC > 0.93) across all damage categories while reducing computational overhead by over 40% without requiring extensive ground truth data.
Authors: Zohar Ringel, Noa Rubin, Edo Mor, Moritz Helias, Inbar Seroussi
Abstract: Deep learning algorithms have made incredible strides in the past decade yet due to the complexity of these algorithms, the science of deep learning remains in its early stages. Being an experimentally driven field, it is natural to seek a theory of deep learning within the physics paradigm. As deep learning is largely about learning functions and distributions over functions, statistical field theory, a rich and versatile toolbox for tackling complex distributions over functions (fields) is an obvious choice of formalism. Research efforts carried out in the past few years have demonstrated the ability of field theory to provide useful insights on generalization, implicit bias, and feature learning effects. Here we provide a pedagogical review of this emerging line of research.
Authors: Rithwik Gupta, Daniel Muthukrishna
Abstract: Machine learning has become essential for automated classification of astronomical transients, but current approaches face significant limitations: classifiers trained on simulations struggle with real data, models developed for one survey cannot be easily applied to another, and new surveys require prohibitively large amounts of labelled training data. These challenges are particularly pressing as we approach the era of the Vera Rubin Observatory's Legacy Survey of Space and Time (LSST), where existing classification models will need to be retrained using LSST observations. We demonstrate that transfer learning can overcome these challenges by repurposing existing models trained on either simulations or data from other surveys. Starting with a model trained on simulated Zwicky Transient Facility (ZTF) light curves, we show that transfer learning reduces the amount of labelled real ZTF transients needed by 75\% while maintaining equivalent performance to models trained from scratch. Similarly, when adapting ZTF models for LSST simulations, transfer learning achieves 95\% of the baseline performance while requiring only 30\% of the training data. These findings have significant implications for the early operations of LSST, suggesting that reliable automated classification will be possible soon after the survey begins, rather than waiting months or years to accumulate sufficient training data.
Authors: Mark Hughes, Vishnu Jejjala, P. Ramadevi, Pratik Roy, Vivek Kumar Singh
Abstract: Using the vertex model approach for braid representations, we compute polynomials for spin-1 placed on hyperbolic knots up to 15 crossings. These polynomials are referred to as 3-colored Jones polynomials or adjoint Jones polynomials. Training a subset of the data using a fully connected feedforward neural network, we predict the volume of the knot complement of hyperbolic knots from the adjoint Jones polynomial or its evaluations with 99.34% accuracy. A function of the adjoint Jones polynomial evaluated at the phase $q=e^{ 8 \pi i / 15 }$ predicts the volume with nearly the same accuracy as the neural network. From an analysis of 2-colored and 3-colored Jones polynomials, we conjecture the best phase for $n$-colored Jones polynomials, and use this hypothesis to motivate an improved statement of the volume conjecture. This is tested for knots for which closed form expressions for the $n$-colored Jones polynomial are known, and we show improved convergence to the volume.
Authors: Zhewei Kang, Xuandong Zhao, Dawn Song
Abstract: Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models for response evaluation and selection. Reward-free alternatives, like self-consistency and universal self-consistency, are limited in their ability to handle open-ended generation tasks or scale effectively. To address these limitations, we propose self-certainty, a novel and efficient metric that leverages the inherent probability distribution of LLM outputs to estimate response quality without requiring external reward models. We hypothesize that higher distributional self-certainty, aggregated across multiple samples, correlates with improved response accuracy, as it reflects greater confidence in the generated output. Through extensive experiments on various reasoning tasks, we demonstrate that self-certainty (1) scales effectively with increasing sample size $N$, akin to reward models but without the computational overhead; (2) complements chain-of-thought, improving reasoning performance beyond greedy decoding; and (3) generalizes to open-ended tasks where traditional self-consistency methods fall short. Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities. The code is available at https://github.com/backprop07/Self-Certainty
Authors: Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde, Ratip Emin Berker, Gabriele Farina, Vincent Conitzer, Tuomas Sandholm
Abstract: $\Phi$-equilibria -- and the associated notion of $\Phi$-regret -- are a powerful and flexible framework at the heart of online learning and game theory, whereby enriching the set of deviations $\Phi$ begets stronger notions of rationality. Recently, Daskalakis, Farina, Fishelson, Pipis, and Schneider (STOC '24) -- abbreviated as DFFPS -- settled the existence of efficient algorithms when $\Phi$ contains only linear maps under a general, $d$-dimensional convex constraint set $\mathcal{X}$. In this paper, we significantly extend their work by resolving the case where $\Phi$ is $k$-dimensional; degree-$\ell$ polynomials constitute a canonical such example with $k = d^{O(\ell)}$. In particular, positing only oracle access to $\mathcal{X}$, we obtain two main positive results: i) a $\text{poly}(n, d, k, \text{log}(1/\epsilon))$-time algorithm for computing $\epsilon$-approximate $\Phi$-equilibria in $n$-player multilinear games, and ii) an efficient online algorithm that incurs average $\Phi$-regret at most $\epsilon$ using $\text{poly}(d, k)/\epsilon^2$ rounds. We also show nearly matching lower bounds in the online learning setting, thereby obtaining for the first time a family of deviations that captures the learnability of $\Phi$-regret. From a technical standpoint, we extend the framework of DFFPS from linear maps to the more challenging case of maps with polynomial dimension. At the heart of our approach is a polynomial-time algorithm for computing an expected fixed point of any $\phi : \mathcal{X} \to \mathcal{X}$ based on the ellipsoid against hope (EAH) algorithm of Papadimitriou and Roughgarden (JACM '08). In particular, our algorithm for computing $\Phi$-equilibria is based on executing EAH in a nested fashion -- each step of EAH itself being implemented by invoking a separate call to EAH.
Authors: Akash Vartak, Khondoker Murad Hossain, Tim Oates
Abstract: Deep neural networks (DNNs) are becoming commonplace in critical applications, making their susceptibility to backdoor (trojan) attacks a significant problem. In this paper, we introduce a novel backdoor attack detection pipeline, detecting attacked models using graph convolution networks (DeBUGCN). To the best of our knowledge, ours is the first use of GCNs for trojan detection. We use the static weights of a DNN to create a graph structure of its layers. A GCN is then used as a binary classifier on these graphs, yielding a trojan or clean determination for the DNN. To demonstrate the efficacy of our pipeline, we train hundreds of clean and trojaned CNN models on the MNIST handwritten digits and CIFAR-10 image datasets, and show the DNN classification results using DeBUGCN. For a true In-the-Wild use case, our pipeline is evaluated on the TrojAI dataset which consists of various CNN architectures, thus showing the robustness and model-agnostic behaviour of DeBUGCN. Furthermore, on comparing our results on several datasets with state-of-the-art trojan detection algorithms, DeBUGCN is faster and more accurate.
Authors: Brian Hu Zhang, Ioannis Anagnostides, Emanuel Tewolde, Ratip Emin Berker, Gabriele Farina, Vincent Conitzer, Tuomas Sandholm
Abstract: Variational inequalities (VIs) encompass many fundamental problems in diverse areas ranging from engineering to economics and machine learning. However, their considerable expressivity comes at the cost of computational intractability. In this paper, we introduce and analyze a natural relaxation -- which we refer to as expected variational inequalities (EVIs) -- where the goal is to find a distribution that satisfies the VI constraint in expectation. By adapting recent techniques from game theory, we show that, unlike VIs, EVIs can be solved in polynomial time under general (nonmonotone) operators. EVIs capture the seminal notion of correlated equilibria, but enjoy a greater reach beyond games. We also employ our framework to capture and generalize several existing disparate results, including from settings such as smooth games, and games with coupled constraints or nonconcave utilities.
Authors: Shayleen Reynolds, Saheed Obitayo, Niccol\`o Dalmasso, Dung Daniel T. Ngo, Vamsi K. Potluru, Manuela Veloso
Abstract: In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are vulnerable to expert adversaries wishing to reverse-engineer the watermarking mechanisms. Prior work in "breaking" or "stealing" LLM watermarks mainly focuses on the distribution-modifying algorithm of Kirchenbauer et al. (2023), which perturbs the logit vector before sampling. In this work, we focus on reverse-engineering the other prominent LLM watermarking scheme, distortion-free watermarking (Kuditipudi et al. 2024), which preserves the underlying token distribution by using a hidden watermarking key sequence. We demonstrate that, even under a more sophisticated watermarking scheme, it is possible to "compromise" the LLM and carry out a "spoofing" attack. Specifically, we propose a mixed integer linear programming framework that accurately estimates the secret key used for watermarking using only a few samples of the watermarked dataset. Our initial findings challenge the current theoretical claims on the robustness and usability of existing LLM watermarking techniques.
Authors: Xiaohan Zhu, Mesrob I. Ohannessian, Nathan Srebro
Abstract: We provide finite sample upper and lower bounds on the Binomial tail probability which are a direct application of Sanov's theorem. We then use these to obtain high probability upper and lower bounds on the minimum of i.i.d. Binomial random variables. Both bounds are finite sample, asymptotically tight, and expressed in terms of the KL-divergence.
Authors: Georgios Kamaras, Subramanian Ramamoorthy
Abstract: We present an integrated (or end-to-end) framework for the Real2Sim2Real problem of manipulating deformable linear objects (DLOs) based on visual perception. Working with a parameterised set of DLOs, we use likelihood-free inference (LFI) to compute the posterior distributions for the physical parameters using which we can approximately simulate the behaviour of each specific DLO. We use these posteriors for domain randomisation while training, in simulation, object-specific visuomotor policies for a visuomotor DLO reaching task, using model-free reinforcement learning. We demonstrate the utility of this approach by deploying sim-trained DLO manipulation policies in the real world in a zero-shot manner, i.e. without any further fine-tuning. In this context, we evaluate the capacity of a prominent LFI method to perform fine classification over the parametric set of DLOs, using only visual and proprioceptive data obtained in a dynamic manipulation trajectory. We then study the implications of the resulting domain distributions in sim-based policy learning and real-world performance.
Authors: Miguel Herencia Garc\'ia del Castillo, Ricardo Moya Garcia, Manuel Jes\'us Cerezo Maz\'on, Ekaitz Arriola Garcia, Pablo Men\'endez Fern\'andez-Miranda
Abstract: In this article, we present a Latent Diffusion Model (LDM) for the generation of brain Magnetic Resonance Imaging (MRI), conditioning its generation based on pathology (Healthy, Glioblastoma, Sclerosis, Dementia) and acquisition modality (T1w, T1ce, T2w, Flair, PD). To evaluate the quality of the generated images, the Fr\'echet Inception Distance (FID) and Multi-Scale Structural Similarity Index (MS-SSIM) metrics were employed. The results indicate that the model generates images with a distribution similar to real ones, maintaining a balance between visual fidelity and diversity. Additionally, the model demonstrates extrapolation capability, enabling the generation of configurations that were not present in the training data. The results validate the potential of the model to increase in the number of samples in clinical datasets, balancing underrepresented classes, and evaluating AI models in medicine, contributing to the development of diagnostic tools in radiology without compromising patient privacy.
Authors: Zhangqi Duan, Nigel Fernandez, Sri Kanakadandi, Bita Akram, Andrew Lan
Abstract: Knowledge components (KCs) mapped to problems help model student learning, tracking their mastery levels on fine-grained skills thereby facilitating personalized learning and feedback in online learning platforms. However, crafting and tagging KCs to problems, traditionally performed by human domain experts, is highly labor-intensive. We present a fully automated, LLM-based pipeline for KC generation and tagging for open-ended programming problems. We also develop an LLM-based knowledge tracing (KT) framework to leverage these LLM-generated KCs, which we refer to as KCGen-KT. We conduct extensive quantitative and qualitative evaluations validating the effectiveness of KCGen-KT. On a real-world dataset of student code submissions to open-ended programming problems, KCGen-KT outperforms existing KT methods. We investigate the learning curves of generated KCs and show that LLM-generated KCs have a comparable level-of-fit to human-written KCs under the performance factor analysis (PFA) model. We also conduct a human evaluation to show that the KC tagging accuracy of our pipeline is reasonably accurate when compared to that by human domain experts.
Authors: Alexander Scheinker, Alan Williams
Abstract: Beam loss (BLM) and beam current monitors (BCM) are ubiquitous at particle accelerator around the world. These simple devices provide non-invasive high level beam measurements, but give no insight into the detailed 6D (x,y,z,px,py,pz) beam phase space distributions or dynamics. We show that generative conditional latent diffusion models can learn intricate patterns to map waveforms of tens of BLMs or BCMs along an accelerator to detailed 2D projections of a charged particle beam's 6D phase space density. This transformational method can be used at any particle accelerator to transform simple non-invasive devices into detailed beam phase space diagnostics. We demonstrate this concept via multi-particle simulations of the high intensity beam in the kilometer-long LANSCE linear proton accelerator.
Authors: Tianze Wang, Dongnan Gui, Yifan Hu, Shuhang Lin, Linjun Zhang
Abstract: Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this limitation by leveraging multi-dimensional feedback to fine-tune corresponding reward models and train LLMs using reinforcement learning. However, the process is costly and unstable, especially given the competing and heterogeneous nature of human preferences. In this paper, we propose Mixing Preference Optimization (MPO), a post-processing framework for aggregating single-objective policies as an alternative to both multi-objective RLHF (MORLHF) and MaxMin-RLHF. MPO avoids alignment from scratch. Instead, it log-linearly combines existing policies into a unified one with the weight of each policy computed via a batch stochastic mirror descent. Empirical results demonstrate that MPO achieves balanced performance across diverse preferences, outperforming or matching existing models with significantly reduced computational costs.
Authors: Alireza Daghighfarsoodeh, Chung-Yu Wang, Hamed Taherkhani, Melika Sepidband, Mohammad Abdollahi, Hadi Hemmati, Hung Viet Pham
Abstract: Deep learning (DL) has revolutionized areas such as computer vision, natural language processing, and more. However, developing DL systems is challenging due to the complexity of DL workflows. Large Language Models (LLMs), such as GPT, Claude, Llama, Mistral, etc., have emerged as promising tools to assist in DL code generation, offering potential solutions to these challenges. Despite this, existing benchmarks such as DS-1000 are limited, as they primarily focus on small DL code snippets related to pre/post-processing tasks and lack a comprehensive coverage of the full DL pipeline, including different DL phases and input data types. To address this, we introduce DeepBench, a novel benchmark dataset designed for function-level DL code generation. DeepBench categorizes DL problems based on three key aspects: phases such as pre-processing, model construction, and training; tasks, including classification, regression, and recommendation; and input data types such as tabular, image, and text. GPT-4o -- the state-of-the-art LLM -- achieved 31% accuracy on DeepBench, significantly lower than its 60% on DS-1000. We observed similar difficulty for other LLMs (e.g., 28% vs. 54% for Claude, 21% vs. 41% for LLaMA, and 15% vs. 20% for Mistral). This result underscores DeepBench's greater complexity. We also construct a taxonomy of issues and bugs found in LLM-generated DL code, which highlights the distinct challenges that LLMs face when generating DL code compared to general code. Furthermore, our analysis also reveals substantial performance variations across categories, with differences of up to 7% among phases and 37% among tasks. These disparities suggest that DeepBench offers valuable insights into the LLMs' performance and areas for potential improvement in the DL domain.
Authors: Rong Wu, Ziqi Chen, Gen Li, Hai Shu
Abstract: Motivation: Biomedical studies increasingly produce multi-view high-dimensional datasets (e.g., multi-omics) that demand integrative analysis. Existing canonical correlation analysis (CCA) and generalized CCA methods address at most two of the following three key aspects simultaneously: (i) nonlinear dependence, (ii) sparsity for variable selection, and (iii) generalization to more than two data views. There is a pressing need for CCA methods that integrate all three aspects to effectively analyze multi-view high-dimensional data. Results: We propose three nonlinear, sparse, generalized CCA methods, HSIC-SGCCA, SA-KGCCA, and TS-KGCCA, for variable selection in multi-view high-dimensional data. These methods extend existing SCCA-HSIC, SA-KCCA, and TS-KCCA from two-view to multi-view settings. While SA-KGCCA and TS-KGCCA yield multi-convex optimization problems solved via block coordinate descent, HSIC-SGCCA introduces a necessary unit-variance constraint previously ignored in SCCA-HSIC, resulting in a nonconvex, non-multiconvex problem. We efficiently address this challenge by integrating the block prox-linear method with the linearized alternating direction method of multipliers. Simulations and TCGA-BRCA data analysis demonstrate that HSIC-SGCCA outperforms competing methods in multi-view variable selection.
Authors: Akhil Nagariya, Dimitar Filev, Srikanth Saripalli, Gaurav Pandey
Abstract: In the area of autonomous driving, navigating off-road terrains presents a unique set of challenges, from unpredictable surfaces like grass and dirt to unexpected obstacles such as bushes and puddles. In this work, we present a novel learning-based local planner that addresses these challenges by directly capturing human driving nuances from real-world demonstrations using only a monocular camera. The key features of our planner are its ability to navigate in challenging off-road environments with various terrain types and its fast learning capabilities. By utilizing minimal human demonstration data (5-10 mins), it quickly learns to navigate in a wide array of off-road conditions. The local planner significantly reduces the real world data required to learn human driving preferences. This allows the planner to apply learned behaviors to real-world scenarios without the need for manual fine-tuning, demonstrating quick adjustment and adaptability in off-road autonomous driving technology.
Authors: Kiranmayee Janardhan, Christy Bobby Thomas
Abstract: Glioma, the prevalent primary brain tumor, exhibits diverse aggressiveness levels and prognoses. Precise classification of glioma is paramount for treatment planning and predicting prognosis. This study aims to develop an algorithm to fuse the MRI images from T1, T2, T1ce, and fluid-attenuated inversion recovery (FLAIR) sequences to enhance the efficacy of glioma subclass classification as no tumor, necrotic core, peritumoral edema, and enhancing tumor. The MRI images from BraTS datasets were used in this work. The images were pre-processed using max-min normalization to ensure consistency in pixel intensity values across different images. The segmentation of the necrotic core, peritumoral edema, and enhancing tumor was performed on 2D and 3D images separately using UNET architecture. Further, the segmented regions from multimodal MRI images were fused using the weighted averaging technique. Integrating 2D and 3D segmented outputs enhances classification accuracy by capturing detailed features like tumor shape, boundaries, and intensity distribution in slices, while also providing a comprehensive view of spatial extent, shape, texture, and localization within the brain volume. The fused images were used as input to the pre-trained ResNet50 model for glioma subclass classification. The network is trained on 80% and validated on 20% of the data. The proposed method achieved a classification of accuracy of 99.25%, precision of 99.30%, recall of 99.10, F1 score of 99.19%, Intersection Over Union of 84.49%, and specificity of 99.76, which showed a significantly higher performance than existing techniques. These findings emphasize the significance of glioma segmentation and classification in aiding accurate diagnosis.
Authors: Jungsoo Park, Junmo Kang, Gabriel Stanovsky, Alan Ritter
Abstract: The surge of LLM studies makes synthesizing their findings challenging. Meta-analysis can uncover important trends across studies, but its use is limited by the time-consuming nature of manual data extraction. Our study presents a semi-automated approach for meta-analysis that accelerates data extraction using LLMs. It automatically identifies relevant arXiv papers, extracts experimental results and related attributes, and organizes them into a structured dataset. We conduct a comprehensive meta-analysis of frontier LLMs using an automatically extracted dataset, reducing the effort of paper surveying and data extraction by more than 93\% compared to manual approaches. We validate our dataset by showing that it reproduces key findings from a recent manual meta-analysis about Chain-of-Thought (CoT), and also uncovers new insights that go beyond it, showing for example that in-context examples benefit multimodal tasks but offer limited gains in mathematical tasks compared to CoT. Our automatically updatable dataset enables continuous tracking of target models by extracting evaluation studies as new data becomes available. Through our scientific artifacts and empirical analysis, we provide novel insights into LLMs while facilitating ongoing meta-analyses of their behavior.
Authors: Weipeng Jiang, Juan Zhai, Shiqing Ma, Ziyan Lei, Xiaofei Xie, Yige Wang, Chao Shen
Abstract: In recent years, Large Language Models (LLMs) have faced increasing demands to selectively remove sensitive information, protect privacy, and comply with copyright regulations through unlearning, by Machine Unlearning. While evaluating unlearning effectiveness is crucial, existing benchmarks are limited in scale and comprehensiveness, typically containing only a few hundred test cases. We identify two critical challenges in generating holistic audit datasets: ensuring audit adequacy and handling knowledge redundancy between forget and retain dataset. To address these challenges, we propose HANKER, an automated framework for holistic audit dataset generation leveraging knowledge graphs to achieve fine-grained coverage and eliminate redundant knowledge. Applying HANKER to the popular MUSE benchmark, we successfully generated over 69,000 and 111,000 audit cases for the News and Books datasets respectively, identifying thousands of knowledge memorization instances that the previous benchmark failed to detect. Our empirical analysis uncovers how knowledge redundancy significantly skews unlearning effectiveness metrics, with redundant instances artificially inflating the observed memorization measurements ROUGE from 19.7% to 26.1% and Entailment Scores from 32.4% to 35.2%, highlighting the necessity of systematic deduplication for accurate assessment.
Authors: Ziqi Yao, Mingsong Chen, Cheng Chen
Abstract: We explore the problem of approximate matrix multiplication (AMM) within the sliding window model, where algorithms utilize limited space to perform large-scale matrix multiplication in a streaming manner. This model has garnered increasing attention in the fields of machine learning and data mining due to its ability to handle time sensitivity and reduce the impact of outdated data. However, despite recent advancements, determining the optimal space bound for this problem remains an open question. In this paper, we introduce the DS-COD algorithm for AMM over sliding windows. This novel and deterministic algorithm achieves optimal performance regarding the space-error tradeoff. We provide theoretical error bounds and the complexity analysis for the proposed algorithm, and establish the corresponding space lower bound for the AMM sliding window problem. Additionally, we present an adaptive version of DS-COD, termed aDS-COD, which improves computational efficiency and demonstrates superior empirical performance. Extensive experiments conducted on both synthetic and real-world datasets validate our theoretical findings and highlight the practical effectiveness of our methods.
Authors: Yifan Hu, Yuante Li, Peiyuan Liu, Yuxia Zhu, Naiqi Li, Tao Dai, Shu-tao Xia, Dawei Cheng, Changjun Jiang
Abstract: Financial time series (FinTS) record the behavior of human-brain-augmented decision-making, capturing valuable historical information that can be leveraged for profitable investment strategies. Not surprisingly, this area has attracted considerable attention from researchers, who have proposed a wide range of methods based on various backbones. However, the evaluation of the area often exhibits three systemic limitations: 1. Failure to account for the full spectrum of stock movement patterns observed in dynamic financial markets. (Diversity Gap), 2. The absence of unified assessment protocols undermines the validity of cross-study performance comparisons. (Standardization Deficit), and 3. Neglect of critical market structure factors, resulting in inflated performance metrics that lack practical applicability. (Real-World Mismatch). Addressing these limitations, we propose FinTSB, a comprehensive and practical benchmark for financial time series forecasting (FinTSF). To increase the variety, we categorize movement patterns into four specific parts, tokenize and pre-process the data, and assess the data quality based on some sequence characteristics. To eliminate biases due to different evaluation settings, we standardize the metrics across three dimensions and build a user-friendly, lightweight pipeline incorporating methods from various backbones. To accurately simulate real-world trading scenarios and facilitate practical implementation, we extensively model various regulatory constraints, including transaction fees, among others. Finally, we conduct extensive experiments on FinTSB, highlighting key insights to guide model selection under varying market conditions. Overall, FinTSB provides researchers with a novel and comprehensive platform for improving and evaluating FinTSF methods. The code is available at https://github.com/TongjiFinLab/FinTSBenchmark.
Authors: Zichuan Fu, Wentao Song, Yejing Wang, Xian Wu, Yefeng Zheng, Yingying Zhang, Derong Xu, Xuetao Wei, Tong Xu, Xiangyu Zhao
Abstract: Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck for processing long documents. As a result, many efforts like sparse attention and state space models have been proposed to improve the efficiency of LLMs over long sequences. Though effective, these approaches compromise the performance or introduce structural complexity. This calls for a simple yet efficient model that preserves the fundamental Transformer architecture. To this end, we introduce SWAT, which enables efficient long-context handling via Sliding Window Attention Training. This paper first attributes the inefficiency of Transformers to the attention sink phenomenon resulting from the high variance of softmax operation. Then, we replace softmax with the sigmoid function and utilize a balanced ALiBi and Rotary Position Embedding for efficient information compression and retention. Experiments demonstrate that SWAT achieves SOTA performance compared with state-of-the-art linear recurrent architectures on eight benchmarks. Code is available at https://anonymous.4open.science/r/SWAT-attention.
Authors: Kerem Zaman, Shashank Srivastava
Abstract: Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability. However, despite their plausibility, they may not reflect the model's internal reasoning faithfully, which is crucial for understanding the model's true decision-making processes. Although several faithfulness metrics have been proposed, a unified evaluation framework remains absent. To address this gap, we present Causal Diagnosticity, a framework to evaluate faithfulness metrics for natural language explanations. Our framework employs the concept of causal diagnosticity, and uses model-editing methods to generate faithful-unfaithful explanation pairs. Our benchmark includes four tasks: fact-checking, analogy, object counting, and multi-hop reasoning. We evaluate a variety of faithfulness metrics, including post-hoc explanation and chain-of-thought-based methods. We find that all tested faithfulness metrics often fail to surpass a random baseline. Our work underscores the need for improved metrics and more reliable interpretability methods in LLMs.
Authors: Christopher Zerafa
Abstract: Full Waveform Inversion (FWI) reconstructs high-resolution subsurface models via multi-variate optimization but faces challenges with solver selection and data availability. Deep Learning (DL) offers a promising alternative, bridging data-driven and physics-based methods. While FWI in DL has been explored in the time domain, the pseudo-spectral approach remains underutilized, despite its success in classical FWI. This thesis integrates pseudo-spectral FWI into DL, formulating both data-driven and theory-guided approaches using Deep Neural Networks (DNNs) and Recurrent Neural Networks (RNNs). These methods were theoretically derived, tested on synthetic and Marmousi datasets, and compared with deterministic and time-domain approaches. Results show that data-driven pseudo-spectral DNNs outperform classical FWI in deeper and over-thrust regions due to their global approximation capability. Theory-guided RNNs yield greater accuracy, with lower error and better fault identification. While DNNs excel in velocity contrast recovery, RNNs provide superior edge definition and stability in shallow and deep sections. Beyond enhancing FWI performance, this research identifies broader applications of DL-based inversion and outlines future directions for these frameworks.
Authors: Juraj Gottweis, Wei-Hung Weng, Alexander Daryin, Tao Tu, Anil Palepu, Petar Sirkovic, Artiom Myaskovsky, Felix Weissenberger, Keran Rong, Ryutaro Tanno, Khaled Saab, Dan Popovici, Jacob Blum, Fan Zhang, Katherine Chou, Avinatan Hassidim, Burak Gokturk, Amin Vahdat, Pushmeet Kohli, Yossi Matias, Andrew Carroll, Kavita Kulkarni, Nenad Tomasev, Yuan Guan, Vikram Dhillon, Eeshit Dhaval Vaishnav, Byron Lee, Tiago R D Costa, Jos\'e R Penad\'es, Gary Peltz, Yunhan Xu, Annalisa Pawlosky, Alan Karthikesalingam, Vivek Natarajan
Abstract: Scientific discovery relies on scientists generating novel hypotheses that undergo rigorous experimental validation. To augment this process, we introduce an AI co-scientist, a multi-agent system built on Gemini 2.0. The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses and proposals, building upon prior evidence and aligned to scientist-provided research objectives and guidance. The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method and accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute, improving hypothesis quality. While general purpose, we focus development and validation in three biomedical areas: drug repurposing, novel target discovery, and explaining mechanisms of bacterial evolution and anti-microbial resistance. For drug repurposing, the system proposes candidates with promising validation findings, including candidates for acute myeloid leukemia that show tumor inhibition in vitro at clinically applicable concentrations. For novel target discovery, the AI co-scientist proposed new epigenetic targets for liver fibrosis, validated by anti-fibrotic activity and liver cell regeneration in human hepatic organoids. Finally, the AI co-scientist recapitulated unpublished experimental results via a parallel in silico discovery of a novel gene transfer mechanism in bacterial evolution. These results, detailed in separate, co-timed reports, demonstrate the potential to augment biomedical and scientific discovery and usher an era of AI empowered scientists.
Authors: Fanglei Xue, Meihan Zhang, Shuqi Li, Xinyu Gao, James A. Wohlschlegel, Wenbing Huang, Yi Yang, Weixian Deng
Abstract: Targeted protein degradation (TPD) induced by small molecules has emerged as a rapidly evolving modality in drug discovery, targeting proteins traditionally considered "undruggable". Proteolysis-targeting chimeras (PROTACs) and molecular glue degraders (MGDs) are the primary small molecules that induce TPD. Both types of molecules form a ternary complex linking an E3 ligase with a target protein, a crucial step for drug discovery. While significant advances have been made in binary structure prediction for proteins and small molecules, ternary structure prediction remains challenging due to obscure interaction mechanisms and insufficient training data. Traditional methods relying on manually assigned rules perform poorly and are computationally demanding due to extensive random sampling. In this work, we introduce DeepTernary, a novel deep learning-based approach that directly predicts ternary structures in an end-to-end manner using an encoder-decoder architecture. DeepTernary leverages an SE(3)-equivariant graph neural network (GNN) with both intra-graph and ternary inter-graph attention mechanisms to capture intricate ternary interactions from our collected high-quality training dataset, TernaryDB. The proposed query-based Pocket Points Decoder extracts the 3D structure of the final binding ternary complex from learned ternary embeddings, demonstrating state-of-the-art accuracy and speed in existing PROTAC benchmarks without prior knowledge from known PROTACs. It also achieves notable accuracy on the more challenging MGD benchmark under the blind docking protocol. Remarkably, our experiments reveal that the buried surface area calculated from predicted structures correlates with experimentally obtained degradation potency-related metrics. Consequently, DeepTernary shows potential in effectively assisting and accelerating the development of TPDs for previously undruggable targets.
Authors: Tamer Ghattas, Michael Hassid, Roy Schwartz
Abstract: Recent work proposed state-space models (SSMs) as an efficient alternative to transformer-based LLMs. Can these models be pruned to further reduce their computation costs? We adapt several pruning methods to the SSM structure, and apply them to four SSM-based LLMs across multiple tasks. We find that such models are quite robust to some pruning methods (e.g. WANDA), while using other methods lead to fast performance degradation.
Authors: Tianyun Liu
Abstract: Traditional text-to-speech (TTS) methods primarily focus on establishing a mapping between phonemes and mel-spectrograms. However, during the phoneme encoding stage, there is often a lack of real mel-spectrogram auxiliary information, which results in the encoding process lacking true semantic understanding. At the same time, traditional TTS systems often struggle to balance the inference speed of the model with the quality of the synthesized speech. Methods that generate high-quality synthesized speech tend to have slower inference speeds, while faster inference methods often sacrifice speech quality. In this paper, I propose Clip-TTS, a TTS method based on the Clip architecture. This method uses the Clip framework to establish a connection between text content and real mel-spectrograms during the text encoding stage, enabling the text encoder to directly learn the true semantics of the global context, thereby ensuring the quality of the synthesized speech. In terms of model architecture, I adopt the basic structure of Transformer, which allows Clip-TTS to achieve fast inference speeds. Experimental results show that on the LJSpeech and Baker datasets, the speech generated by Clip-TTS achieves state-of-the-art MOS scores, and it also performs excellently on multi-emotion datasets.Audio samples are available at: https://ltydd1314.github.io/.
Authors: Sebastian Haug, Christoph B\"ohm, Daniel Mayer
Abstract: This paper proposes a method for generating software components for embedded systems, integrating seamlessly into existing implementations without developer intervention. We demonstrate this by automatically generating hardware abstraction layer (HAL) code for GPIO operations on the STM32F407 microcontroller. Using Abstract Syntax Trees (AST) for code analysis and Retrieval-Augmented Generation (RAG) for component generation, our approach enables autonomous code completion for embedded applications.
Authors: Wanyi Li, Wei Wei, Yongkang Luo, Peng Wang
Abstract: Few-shot class-incremental learning (FSCIL) poses significant challenges for artificial neural networks due to the need to efficiently learn from limited data while retaining knowledge of previously learned tasks. Inspired by the brain's mechanisms for categorization and analogical learning, we propose a novel approach called Brain-inspired Analogical Mixture Prototypes (BAMP). BAMP has three components: mixed prototypical feature learning, statistical analogy, and soft voting. Starting from a pre-trained Vision Transformer (ViT), mixed prototypical feature learning represents each class using a mixture of prototypes and fine-tunes these representations during the base session. The statistical analogy calibrates the mean and covariance matrix of prototypes for new classes according to similarity to the base classes, and computes classification score with Mahalanobis distance. Soft voting combines both merits of statistical analogy and an off-shelf FSCIL method. Our experiments on benchmark datasets demonstrate that BAMP outperforms state-of-the-art on both traditional big start FSCIL setting and challenging small start FSCIL setting. The study suggests that brain-inspired analogical mixture prototypes can alleviate catastrophic forgetting and over-fitting problems in FSCIL.
Authors: Ziyue Jiang, Yi Ren, Ruiqi Li, Shengpeng Ji, Zhenhui Ye, Chen Zhang, Bai Jionghao, Xiaoda Yang, Jialong Zuo, Yu Zhang, Rui Liu, Xiang Yin, Zhou Zhao
Abstract: While recent zero-shot text-to-speech (TTS) models have significantly improved speech quality and expressiveness, mainstream systems still suffer from issues related to speech-text alignment modeling: 1) models without explicit speech-text alignment modeling exhibit less robustness, especially for hard sentences in practical applications; 2) predefined alignment-based models suffer from naturalness constraints of forced alignments. This paper introduces \textit{S-DiT}, a TTS system featuring an innovative sparse alignment algorithm that guides the latent diffusion transformer (DiT). Specifically, we provide sparse alignment boundaries to S-DiT to reduce the difficulty of alignment learning without limiting the search space, thereby achieving high naturalness. Moreover, we employ a multi-condition classifier-free guidance strategy for accent intensity adjustment and adopt the piecewise rectified flow technique to accelerate the generation process. Experiments demonstrate that S-DiT achieves state-of-the-art zero-shot TTS speech quality and supports highly flexible control over accent intensity. Notably, our system can generate high-quality one-minute speech with only 8 sampling steps. Audio samples are available at https://sditdemo.github.io/sditdemo/.
Authors: Kanana LLM Team, Yunju Bak, Hojin Lee, Minho Ryu, Jiyeon Ham, Seungjae Jung, Daniel Wontae Nam, Taegyeong Eo, Donghun Lee, Doohae Jung, Boseop Kim, Nayeon Kim, Jaesun Park, Hyunho Kim, Hyunwoong Ko, Changmin Lee, Kyoung-Woon On, Seulye Baeg, Junrae Cho, Sunghee Jung, Jieun Kang, EungGyun Kim, Eunhwa Kim, Byeongil Ko, Daniel Lee, Minchul Lee, Miok Lee, Shinbok Lee, Gaeun Seo
Abstract: We introduce Kanana, a series of bilingual language models that demonstrate exceeding performance in Korean and competitive performance in English. The computational cost of Kanana is significantly lower than that of state-of-the-art models of similar size. The report details the techniques employed during pre-training to achieve compute-efficient yet competitive models, including high quality data filtering, staged pre-training, depth up-scaling, and pruning and distillation. Furthermore, the report outlines the methodologies utilized during the post-training of the Kanana models, encompassing supervised fine-tuning and preference optimization, aimed at enhancing their capability for seamless interaction with users. Lastly, the report elaborates on plausible approaches used for language model adaptation to specific scenarios, such as embedding, retrieval augmented generation, and function calling. The Kanana model series spans from 2.1B to 32.5B parameters with 2.1B models (base, instruct, embedding) publicly released to promote research on Korean language models.
Authors: Jakub Macina, Nico Daheim, Ido Hakimi, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
Abstract: Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run evaluation that reflects the pedagogical abilities of models. To fill this gap, we present MathTutorBench, an open-source benchmark for holistic tutoring model evaluation. MathTutorBench contains a collection of datasets and metrics that broadly cover tutor abilities as defined by learning sciences research in dialog-based teaching. To score the pedagogical quality of open-ended teacher responses, we train a reward model and show it can discriminate expert from novice teacher responses with high accuracy. We evaluate a wide set of closed- and open-weight models on MathTutorBench and find that subject expertise, indicated by solving ability, does not immediately translate to good teaching. Rather, pedagogy and subject expertise appear to form a trade-off that is navigated by the degree of tutoring specialization of the model. Furthermore, tutoring appears to become more challenging in longer dialogs, where simpler questioning strategies begin to fail. We release the benchmark, code, and leaderboard openly to enable rapid benchmarking of future models.
Authors: Bram van Dartel, Marc Damie, Florian Hahn
Abstract: Among all privacy attacks against Machine Learning (ML), membership inference attacks (MIA) attracted the most attention. In these attacks, the attacker is given an ML model and a data point, and they must infer whether the data point was used for training. The attacker also has an auxiliary dataset to tune their inference algorithm. Attack papers commonly simulate setups in which the attacker's and the target's datasets are sampled from the same distribution. This setting is convenient to perform experiments, but it rarely holds in practice. ML literature commonly starts with similar simplifying assumptions (i.e., "i.i.d." datasets), and later generalizes the results to support heterogeneous data distributions. Similarly, our work makes a first step in the generalization of the MIA evaluation to heterogeneous data. First, we design a metric to measure the heterogeneity between any pair of tabular data distributions. This metric provides a continuous scale to analyze the phenomenon. Second, we compare two methodologies to simulate a data heterogeneity between the target and the attacker. These setups provide opposite performances: 90% attack accuracy vs. 50% (i.e., random guessing). Our results show that the MIA accuracy depends on the experimental setup; and even if research on MIA considers heterogeneous data setups, we have no standardized baseline of how to simulate it. The lack of such a baseline for MIA experiments poses a significant challenge to risk assessments in real-world machine learning scenarios.
Authors: Edgar Ivan Sanchez Medina, Kai Sundmacher
Abstract: Predictive thermodynamic models are crucial for the early stages of product and process design. In this paper the performance of Graph Neural Networks (GNNs) embedded into a relatively simple excess Gibbs energy model, the extended Margules model, for predicting vapor-liquid equilibrium is analyzed. By comparing its performance against the established UNIFAC-Dortmund model it has been shown that GNNs embedded in Margules achieves an overall lower accuracy. However, higher accuracy is observed in the case of various types of binary mixtures. Moreover, since group contribution methods, like UNIFAC, are limited due to feasibility of molecular fragmentation or availability of parameters, the GNN in Margules model offers an alternative for VLE estimation. The findings establish a baseline for the predictive accuracy that simple excess Gibbs energy models combined with GNNs trained solely on infinite dilution data can achieve.
Authors: Lars Schroeder, Clara Stegehuis
Abstract: The node2vec random walk has proven to be a key tool in network embedding algorithms. These random walks are tuneable, and their transition probabilities depend on the previous visited node and on the triangles containing the current and the previously visited node. Even though these walks are widely used in practice, most mathematical properties of node2vec walks are largely unexplored, including their stationary distribution. We study the node2vec random walk on community-structured household model graphs. We prove an explicit description of the stationary distribution of node2vec walks in terms of the walk parameters. We then show that by tuning the walk parameters, the stationary distribution can interpolate between uniform, size-biased, or the simple random walk stationary distributions, demonstrating the wide range of possible walks. We further explore these effects on some specific graph settings.
Authors: Satoshi Sunada, Tomoaki Niiyama, Kazutaka Kanno, Rin Nogami, Andr\'e R\"ohm, Takato Awano, Atsushi Uchida
Abstract: The rapidly increasing computational demands for artificial intelligence (AI) have spurred the exploration of computing principles beyond conventional digital computers. Physical neural networks (PNNs) offer efficient neuromorphic information processing by harnessing the innate computational power of physical processes; however, training their weight parameters is computationally expensive. We propose a training approach for substantially reducing this training cost. Our training approach merges an optimal control method for continuous-time dynamical systems with a biologically plausible training method--direct feedback alignment. In addition to the reduction of training time, this approach achieves robust processing even under measurement errors and noise without requiring detailed system information. The effectiveness was numerically and experimentally verified in an optoelectronic delay system. Our approach significantly extends the range of physical systems practically usable as PNNs.
Authors: Iliana Loi, Konstantinos Moustakas
Abstract: Fatigue modeling is essential for motion synthesis tasks to model human motions under fatigued conditions and biomechanical engineering applications, such as investigating the variations in movement patterns and posture due to fatigue, defining injury risk mitigation and prevention strategies, formulating fatigue minimization schemes and creating improved ergonomic designs. Nevertheless, employing data-driven methods for synthesizing the impact of fatigue on motion, receives little to no attention in the literature. In this work, we present Fatigue-PINN, a deep learning framework based on Physics-Informed Neural Networks, for modeling fatigued human movements, while providing joint-specific fatigue configurations for adaptation and mitigation of motion artifacts on a joint level, resulting in more realistic animations. To account for muscle fatigue, we simulate the fatigue-induced fluctuations in the maximum exerted joint torques by leveraging a PINN adaptation of the Three-Compartment Controller model to exploit physics-domain knowledge for improving accuracy. This model also introduces parametric motion alignment with respect to joint-specific fatigue, hence avoiding sharp frame transitions. Our results indicate that Fatigue-PINN accurately simulates the effects of externally perceived fatigue on open-type human movements being consistent with findings from real-world experimental fatigue studies. Since fatigue is incorporated in torque space, Fatigue-PINN provides an end-to-end encoder-decoder-like architecture, to ensure transforming joint angles to joint torques and vice-versa, thus, being compatible with motion synthesis frameworks operating on joint angles.
Authors: Fraser Birks, Thomas D Swinburne, James R Kermode
Abstract: Machine-learned interatomic potentials offer near first-principles accuracy but are computationally expensive, limiting their application in large-scale molecular dynamics simulations. Inspired by quantum mechanics/molecular mechanics methods, we present ML-MIX, an efficient and flexible LAMMPS package for accelerating simulations by spatially mixing interatomic potentials of different complexities. Through constrained linear fitting, we show it is possible to generate a 'cheap' approximate model which closely matches an 'expensive' reference in relevant regions of configuration space. We demonstrate the capability of ML-MIX through case-studies in Si, Fe, and W-He systems, achieving up to an 11x speedup on 8,000 atom systems without sacrificing accuracy on static and dynamic quantities, including calculation of minimum energy paths and dynamical simulations of defect diffusion. For larger domain sizes, we show that the achievable speedup of ML-MIX simulations is limited only by the relative speed of the cheap potential over the expensive potential. The ease of use and flexible nature of this method will extend the practical reach of MLIPs throughout computational materials science, enabling parsimonious application to large spatial and temporal domains.
Authors: Stefano Damato, Dario Azzimonti, Giorgio Corani
Abstract: We introduce the use of Gaussian Processes (GPs) for the probabilistic forecasting of intermittent time series. The model is trained in a Bayesian framework that accounts for the uncertainty about the latent function and marginalizes it out when making predictions. We couple the latent GP variable with two types of forecast distributions: the negative binomial (NegBinGP) and the Tweedie distribution (TweedieGP). While the negative binomial has already been used in forecasting intermittent time series, this is the first time in which a fully parameterized Tweedie density is used for intermittent time series. We properly evaluate the Tweedie density, which is both zero-inflated and heavy tailed, avoiding simplifying assumptions made in existing models. We test our models on thousands of intermittent count time series. Results show that our models provide consistently better probabilistic forecasts than the competitors. In particular, TweedieGP obtains the best estimates of the highest quantiles, thus showing that it is more flexible than NegBinGP.
Authors: Zhengping Jiang, Anqi Liu, Benjamin Van Durme
Abstract: Language model outputs are not always reliable; this prompts research into methods for adapting model responses based on uncertainty. Common approaches include: \emph{abstention}, where models refrain from generating responses when uncertain; and \emph{linguistic calibration}, where models hedge their statements using uncertainty quantifiers. However, abstention can withhold valuable information, while linguistically calibrated responses are often challenging to leverage in downstream tasks. We propose a unifying view of both approaches, Conformal Linguistic Calibration (CLC), reinterpreting linguistic calibration as answer set prediction. We begin by presenting a unified framework that connects abstention and linguistic calibration through the lens of linguistic pragmatics. We then describe an implementation that allows for controlling the level of imprecision in model responses. Experimental results show that our method produces calibrated outputs with conformal guarantees on factual accuracy. Furthermore, our approach enables fine-tuning models to perform uncertainty-aware adaptive claim rewriting, offering a controllable balance between factuality and specificity.
Authors: Bojana Ba\v{s}aragin, Darija Medvecki, Gorana Goji\'c, Milena Oparnica, Dragi\v{s}a Mi\v{s}kovi\'c
Abstract: This study introduces a novel Natural Language Processing pipeline that enhances customer service efficiency at Telekom Srbija, a leading Serbian telecommunications company, through automated email topic detection and labelling. Central to the pipeline is BERTopic, a modular architecture that allows unsupervised topic modelling. After a series of preprocessing and post-processing steps, we assign one of 12 topics and several additional labels to incoming emails, allowing customer service to filter and access them through a custom-made application. The model's performance was evaluated by assessing the speed and correctness of the automatically assigned topics across a test dataset of 100 customer emails. The pipeline shows broad applicability across languages, particularly for those that are low-resourced and morphologically rich. The system now operates in the company's production environment, streamlining customer service operations through automated email classification.
Authors: Zhaowei Zhang, Fengshuo Bai, Qizhi Chen, Chengdong Ma, Mingzhi Wang, Haoran Sun, Zilong Zheng, Yaodong Yang
Abstract: How to align large language models (LLMs) with user preferences from a static general dataset has been frequently studied. However, user preferences are usually personalized, changing, and diverse regarding culture, values, or time. This leads to the problem that the actual user preferences often do not coincide with those trained by the model developers in the practical use of LLMs. Since we cannot collect enough data and retrain for every demand, researching efficient real-time preference adaptation methods based on the backbone LLMs during test time is important. To this end, we introduce Amulet, a novel, training-free framework that formulates the decoding process of every token as a separate online learning problem with the guidance of simple user-provided prompts, thus enabling real-time optimization to satisfy users' personalized preferences. To reduce the computational cost brought by this optimization process for each token, we additionally provide a closed-form solution for each iteration step of the optimization process, thereby reducing the computational time cost to a negligible level. The detailed experimental results demonstrate that Amulet can achieve significant performance improvements in rich settings with combinations of different LLMs, datasets, and user preferences, while maintaining acceptable computational efficiency.
Authors: Yuhan Tang, Yudian Wang, Weizhen Li, Ye Yue, Chengchang Pan, Honggang Qi
Abstract: Fundus image quality is crucial for diagnosing eye diseases, but real-world conditions often result in blurred or unreadable images, increasing diagnostic uncertainty. To address these challenges, this study proposes RetinaRegen, a hybrid model for retinal image restoration that integrates a readability classifi-cation model, a Diffusion Model, and a Variational Autoencoder (VAE). Ex-periments on the SynFundus-1M dataset show that the proposed method achieves a PSNR of 27.4521, an SSIM of 0.9556, and an LPIPS of 0.1911 for the readability labels of the optic disc (RO) region. These results demonstrate superior performance in restoring key regions, offering an effective solution to enhance fundus image quality and support clinical diagnosis.
Authors: Henry Peng Zou, Zhengyao Gu, Yue Zhou, Yankai Chen, Weizhi Zhang, Liancheng Fang, Yibo Wang, Yangning Li, Kay Liu, Philip S. Yu
Abstract: Test-time computing approaches, which leverage additional computational resources during inference, have been proven effective in enhancing large language model performance. This work introduces a novel, linearly scaling approach, TestNUC, that improves test-time predictions by leveraging the local consistency of neighboring unlabeled data-it classifies an input instance by considering not only the model's prediction on that instance but also on neighboring unlabeled instances. We evaluate TestNUC across eight diverse datasets, spanning intent classification, topic mining, domain discovery, and emotion detection, demonstrating its consistent superiority over baseline methods such as standard prompting and self-consistency. Furthermore, TestNUC can be seamlessly integrated with existing test-time computing approaches, substantially boosting their performance. Our analysis reveals that TestNUC scales effectively with increasing amounts of unlabeled data and performs robustly across different embedding models, making it practical for real-world applications. Our code is available at https://github.com/HenryPengZou/TestNUC.
Authors: Kaiwen Yan, Hongcheng Guo, Xuanqing Shi, Jingyi Xu, Yaonan Gu, Zhoujun Li
Abstract: With the rapid advancement of Large Language Models (LLMs), the demand for robust instruction-following capabilities in code generation tasks has grown significantly. Code generation not only facilitates faster prototyping and automated testing, but also augments developer efficiency through improved maintainability and reusability of code. In this paper, we introduce CodeIF, the first benchmark specifically designed to assess the abilities of LLMs to adhere to task-oriented instructions within diverse code generation scenarios. CodeIF encompasses a broad range of tasks, including function synthesis, error debugging, algorithmic refactoring, and code explanation, thereby providing a comprehensive suite to evaluate model performance across varying complexity levels and programming domains. We conduct extensive experiments with LLMs, analyzing their strengths and limitations in meeting the demands of these tasks. The experimental results offer valuable insights into how well current models align with human instructions, as well as the extent to which they can generate consistent, maintainable, and contextually relevant code. Our findings not only underscore the critical role that instruction-following LLMs can play in modern software development, but also illuminate pathways for future research aimed at enhancing their adaptability, reliability, and overall effectiveness in automated code generation.
Authors: Linshan Jia
Abstract: Feature extraction is crucial in intelligent fault diagnosis of rotating machinery. It is easier for convolutional neural networks(CNNs) to visually recognize and learn fault features by converting the complicated one-dimensional (1D) vibrational signals into two-dimensional (2D) images with simple textures. However, the existing representation methods for encoding 1D signals as images have two main problems, including complicated computation and low separability. Meanwhile, the existing 2D-CNN fault diagnosis methods taking 2D images as the only inputs still suffer from the inevitable information loss because of the conversion process. Considering the above issues, this paper proposes a new 1D-to-2D conversion method called Embedding Gramian Representation (EGR), which is easy to calculate and shows good separability. In EGR, 1D signals are projected in the embedding space and the intrinsic periodicity of vibrational signals is captured enabling the faulty characteristics contained in raw signals to be uncovered. Second, aiming at the information loss problem of existing CNN models with the single input of converted images, a double-branch EGR-based CNN, called EGR-Net, is proposed to learn faulty features from both raw signal feature maps and their corresponding EGRs. The bridge connection is designed to improve the feature learning interaction between the two branches. Widely used open domain gearbox dataset and bearing dataset are used to verify the effectiveness and efficiency of the proposed methods. EGR-Net is compared with traditional and state-of-the-art approaches, and the results show that the proposed method can deliver enhanced performance.
Authors: Merlin A. Nau, Luca A. Nutricati, Bruno Camino, Paul A. Warburton, Andreas K. Maier
Abstract: We investigate the use of quantum computing algorithms on real quantum hardware to tackle the computationally intensive task of feature selection for light-weight medical image datasets. Feature selection is often formulated as a k of n selection problem, where the complexity grows binomially with increasing k and n. As problem sizes grow, classical approaches struggle to scale efficiently. Quantum computers, particularly quantum annealers, are well-suited for such problems, offering potential advantages in specific formulations. We present a method to solve larger feature selection instances than previously presented on commercial quantum annealers. Our approach combines a linear Ising penalty mechanism with subsampling and thresholding techniques to enhance scalability. The method is tested in a toy problem where feature selection identifies pixel masks used to reconstruct small-scale medical images. The results indicate that quantum annealing-based feature selection is effective for this simplified use case, demonstrating its potential in high-dimensional optimization tasks. However, its applicability to broader, real-world problems remains uncertain, given the current limitations of quantum computing hardware.
Authors: Yi Feng, Xiao Wang, Tian Xie
Abstract: We consider nonconvex optimization problem over simplex, and more generally, a product of simplices. We provide an algorithm, Langevin Multiplicative Weights Update (LMWU) for solving global optimization problems by adding a noise scaling with the non-Euclidean geometry in the simplex. Non-convex optimization has been extensively studied by machine learning community due to its application in various scenarios such as neural network approximation and finding Nash equilibrium. Despite recent progresses on provable guarantee of escaping and avoiding saddle point (convergence to local minima) and global convergence of Langevin gradient based method without constraints, the global optimization with constraints is less studied. We show that LMWU algorithm is provably convergent to interior global minima with a non-asymptotic convergence analysis. We verify the efficiency of the proposed algorithm in real data set from polynomial portfolio management, where optimization of a highly non-linear objective function plays a crucial role.
Authors: Yunyang Li, Zaishuo Xia, Lin Huang, Xinran Wei, Han Yang, Sam Harshe, Zun Wang, Chang Liu, Jia Zhang, Bin Shao, Mark B. Gerstein
Abstract: Density Functional Theory (DFT) is a pivotal method within quantum chemistry and materials science, with its core involving the construction and solution of the Kohn-Sham Hamiltonian. Despite its importance, the application of DFT is frequently limited by the substantial computational resources required to construct the Kohn-Sham Hamiltonian. In response to these limitations, current research has employed deep-learning models to efficiently predict molecular and solid Hamiltonians, with roto-translational symmetries encoded in their neural networks. However, the scalability of prior models may be problematic when applied to large molecules, resulting in non-physical predictions of ground-state properties. In this study, we generate a substantially larger training set (PubChemQH) than used previously and use it to create a scalable model for DFT calculations with physical accuracy. For our model, we introduce a loss function derived from physical principles, which we call Wavefunction Alignment Loss (WALoss). WALoss involves performing a basis change on the predicted Hamiltonian to align it with the observed one; thus, the resulting differences can serve as a surrogate for orbital energy differences, allowing models to make better predictions for molecular orbitals and total energies than previously possible. WALoss also substantially accelerates self-consistent-field (SCF) DFT calculations. Here, we show it achieves a reduction in total energy prediction error by a factor of 1347 and an SCF calculation speed-up by a factor of 18%. These substantial improvements set new benchmarks for achieving accurate and applicable predictions in larger molecular systems.
Authors: Luxu Liang, Yuhang Jia, Feng Zhou
Abstract: While gradient-based discrete samplers are effective in sampling from complex distributions, they are susceptible to getting trapped in local minima, particularly in high-dimensional, multimodal discrete distributions, owing to the discontinuities inherent in these landscapes. To circumvent this issue, we combine parallel tempering, also known as replica exchange, with the discrete Langevin proposal and develop the Parallel Tempering enhanced Discrete Langevin Proposal (PTDLP), which are simulated at a series of temperatures. Significant energy differences prompt sample swaps, which are governed by a Metropolis criterion specifically designed for discrete sampling to ensure detailed balance is maintained. Additionally, we introduce an automatic scheme to determine the optimal temperature schedule and the number of chains, ensuring adaptability across diverse tasks with minimal tuning. Theoretically, we establish that our algorithm converges non-asymptotically to the target energy and exhibits faster mixing compared to a single chain. Empirical results further emphasize the superiority of our method in sampling from complex, multimodal discrete distributions, including synthetic problems, restricted Boltzmann machines, and deep energy-based models.
Authors: Michael Y. Hu, Jackson Petty, Chuan Shi, William Merrill, Tal Linzen
Abstract: Pretraining language models on formal languages can improve their acquisition of natural language, but it is unclear which features of the formal language impart an inductive bias that leads to effective transfer. Drawing on insights from linguistics and complexity theory, we hypothesize that effective transfer occurs when the formal language both captures dependency structures in natural language and remains within the computational limitations of the model architecture. Focusing on transformers, we find that formal languages with both these properties enable language models to achieve lower loss on natural language and better linguistic generalization compared to other languages. In fact, pre-pretraining, or training on formal-then-natural language, reduces loss more efficiently than the same amount of natural language. For a 1B-parameter language model trained on roughly 1.6B tokens of natural language, pre-pretraining achieves the same loss and better linguistic generalization with a 33% smaller token budget. We also give mechanistic evidence of cross-task transfer from formal to natural language: attention heads acquired during formal language pretraining remain crucial for the model's performance on syntactic evaluations.
Authors: Taishi Nakamura, Takuya Akiba, Kazuki Fujii, Yusuke Oda, Rio Yokota, Jun Suzuki
Abstract: The Mixture of Experts (MoE) architecture reduces the training and inference cost significantly compared to a dense model of equivalent capacity. Upcycling is an approach that initializes and trains an MoE model using a pre-trained dense model. While upcycling leads to initial performance gains, the training progresses slower than when trained from scratch, leading to suboptimal performance in the long term. We propose Drop-Upcycling - a method that effectively addresses this problem. Drop-Upcycling combines two seemingly contradictory approaches: utilizing the knowledge of pre-trained dense models while statistically re-initializing some parts of the weights. This approach strategically promotes expert specialization, significantly enhancing the MoE model's efficiency in knowledge acquisition. Extensive large-scale experiments demonstrate that Drop-Upcycling significantly outperforms previous MoE construction methods in the long term, specifically when training on hundreds of billions of tokens or more. As a result, our MoE model with 5.9B active parameters achieves comparable performance to a 13B dense model in the same model family, while requiring approximately 1/4 of the training FLOPs. All experimental resources, including source code, training data, model checkpoints and logs, are publicly available to promote reproducibility and future research on MoE.
Authors: Saman Forouzandeh, Pavel N. Krivitsky, Rohitash Chandra
Abstract: Recommender systems leveraging deep learning models have been crucial for assisting users in selecting items aligned with their preferences and interests. However, a significant challenge persists in single-criteria recommender systems, which often overlook the diverse attributes of items that have been addressed by Multi-Criteria Recommender Systems (MCRS). Shared embedding vector for multi-criteria item ratings but have struggled to capture the nuanced relationships between users and items based on specific criteria. In this study, we present a novel representation for Multi-Criteria Recommender Systems (MCRS) based on a multi-edge bipartite graph, where each edge represents one criterion rating of items by users, and Multiview Dual Graph Attention Networks (MDGAT). Employing MDGAT is beneficial and important for adequately considering all relations between users and items, given the presence of both local (criterion-based) and global (multi-criteria) relations. Additionally, we define anchor points in each view based on similarity and employ local and global contrastive learning to distinguish between positive and negative samples across each view and the entire graph. We evaluate our method on two real-world datasets and assess its performance based on item rating predictions. The results demonstrate that our method achieves higher accuracy compared to the baseline method for predicting item ratings on the same datasets. MDGAT effectively capture the local and global impact of neighbours and the similarity between nodes.
Authors: Jiyuan Wang, Weishan Ye, Jialin He, Li Zhang, Gan Huang, Zhuliang Yu, Zhen Liang
Abstract: With the rapid advancement of deep learning, attention mechanisms have become indispensable in electroencephalography (EEG) signal analysis, significantly enhancing Brain-Computer Interface (BCI) applications. This paper presents a comprehensive review of traditional and Transformer-based attention mechanisms, their embedding strategies, and their applications in EEG-based BCI, with a particular emphasis on multimodal data fusion. By capturing EEG variations across time, frequency, and spatial channels, attention mechanisms improve feature extraction, representation learning, and model robustness. These methods can be broadly categorized into traditional attention mechanisms, which typically integrate with convolutional and recurrent networks, and Transformer-based multi-head self-attention, which excels in capturing long-range dependencies. Beyond single-modality analysis, attention mechanisms also enhance multimodal EEG applications, facilitating effective fusion between EEG and other physiological or sensory data. Finally, we discuss existing challenges and emerging trends in attention-based EEG modeling, highlighting future directions for advancing BCI technology. This review aims to provide valuable insights for researchers seeking to leverage attention mechanisms for improved EEG interpretation and application.
Authors: Nikhilesh Prabhakar, Ranveer Singh, Harsha Kokel, Sriraam Natarajan, Prasad Tadepalli
Abstract: Multiagent Reinforcement Learning (MARL) poses significant challenges due to the exponential growth of state and action spaces and the non-stationary nature of multiagent environments. This results in notable sample inefficiency and hinders generalization across diverse tasks. The complexity is further pronounced in relational settings, where domain knowledge is crucial but often underutilized by existing MARL algorithms. To overcome these hurdles, we propose integrating relational planners as centralized controllers with efficient state abstractions and reinforcement learning. This approach proves to be sample-efficient and facilitates effective task transfer and generalization.
Authors: Cornelius Emde, Alasdair Paren, Preetham Arvind, Maxime Kayser, Tom Rainforth, Thomas Lukasiewicz, Bernard Ghanem, Philip H. S. Torr, Adel Bibi
Abstract: Large language models (LLMs) are often deployed to perform constrained tasks, with narrow domains. For example, customer support bots can be built on top of LLMs, relying on their broad language understanding and capabilities to enhance performance. However, these LLMs are adversarially susceptible, potentially generating outputs outside the intended domain. To formalize, assess, and mitigate this risk, we introduce domain certification; a guarantee that accurately characterizes the out-of-domain behavior of language models. We then propose a simple yet effective approach, which we call VALID that provides adversarial bounds as a certificate. Finally, we evaluate our method across a diverse set of datasets, demonstrating that it yields meaningful certificates, which bound the probability of out-of-domain samples tightly with minimum penalty to refusal behavior.
Authors: Qi Yu, Zhichen Zeng, Yuchen Yan, Lei Ying, R. Srikant, Hanghang Tong
Abstract: Network alignment, which aims to find node correspondence across different networks, is the cornerstone of various downstream multi-network and Web mining tasks. Most of the embedding-based methods indirectly model cross-network node relationships by contrasting positive and negative node pairs sampled from hand-crafted strategies, which are vulnerable to graph noises and lead to potential misalignment of nodes. Another line of work based on the optimal transport (OT) theory directly models cross-network node relationships and generates noise-reduced alignments. However, OT methods heavily rely on fixed, pre-defined cost functions that prohibit end-to-end training and are hard to generalize. In this paper, we aim to unify the embedding and OT-based methods in a mutually beneficial manner and propose a joint optimal transport and embedding framework for network alignment named JOENA. For one thing (OT for embedding), through a simple yet effective transformation, the noise-reduced OT mapping serves as an adaptive sampling strategy directly modeling all cross-network node pairs for robust embedding learning.For another (embedding for OT), on top of the learned embeddings, the OT cost can be gradually trained in an end-to-end fashion, which further enhances the alignment quality. With a unified objective, the mutual benefits of both methods can be achieved by an alternating optimization schema with guaranteed convergence. Extensive experiments on real-world networks validate the effectiveness and scalability of JOENA, achieving up to 16% improvement in MRR and 20x speedup compared with the state-of-the-art alignment methods.
Authors: Jiayang Wu, Xingyi Zhang, Xiangyu Dong, Kun Xie, Ziqi Liu, Wensheng Gan, Sibo Wang, Le Song
Abstract: Antibody co-design represents a critical frontier in drug development, where accurate prediction of both 1D sequence and 3D structure of complementarity-determining regions (CDRs) is essential for targeting specific epitopes. Despite recent advances in equivariant graph neural networks for antibody design, current approaches often fall short in capturing the intricate interactions that govern antibody-antigen recognition and binding specificity. In this work, we present Igformer, a novel end-to-end framework that addresses these limitations through innovative modeling of antibody-antigen binding interfaces. Our approach refines the inter-graph representation by integrating personalized propagation with global attention mechanisms, enabling comprehensive capture of the intricate interplay between local chemical interactions and global conformational dependencies that characterize effective antibody-antigen binding. Through extensive validation on epitope-binding CDR design and structure prediction tasks, Igformer demonstrates significant improvements over existing methods, suggesting that explicit modeling of multi-scale residue interactions can substantially advance computational antibody design for therapeutic applications.
Authors: Xingyi Zhang, Kun Xie, Ningqiao Huang, Wei Liu, Peilin Zhao, Sibo Wang, Kangfei Zhao, Biaobin Jiang
Abstract: Recent advancements in protein design have leveraged diffusion models to generate structural scaffolds, followed by a process known as protein inverse folding, which involves sequence inference on these scaffolds. However, these methodologies face significant challenges when applied to hyper-variable structures such as antibody Complementarity-Determining Regions (CDRs), where sequence inference frequently results in non-functional sequences due to hallucinations. Distinguished from prevailing protein inverse folding approaches, this paper introduces Igseek, a novel structure-retrieval framework that infers CDR sequences by retrieving similar structures from a natural antibody database. Specifically, Igseek employs a simple yet effective multi-channel equivariant graph neural network to generate high-quality geometric representations of CDR backbone structures. Subsequently, it aligns sequences of structurally similar CDRs and utilizes structurally conserved sequence motifs to enhance inference accuracy. Our experiments demonstrate that Igseek not only proves to be highly efficient in structural retrieval but also outperforms state-of-the-art approaches in sequence recovery for both antibodies and T-Cell Receptors, offering a new retrieval-based perspective for therapeutic protein design.
Authors: Anna C. M. Th\"oni, William E. Robinson, Yoram Bachrach, Wilhelm T. S. Huck, Tal Kachman
Abstract: In chemical reaction network theory, ordinary differential equations are used to model the temporal change of chemical species concentration. As the functional form of these ordinary differential equations systems is derived from an empirical model of the reaction network, it may be incomplete. Our approach aims to elucidate these hidden insights in the reaction network by combining dynamic modelling with deep learning in the form of neural ordinary differential equations. Our contributions not only help to identify the shortcomings of existing empirical models but also assist the design of future reaction networks.
Authors: Danae S\'anchez Villegas, Ingo Ziegler, Desmond Elliott
Abstract: Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often treating images independently. This work introduces ImageChain, a framework that enhances MLLMs with sequential reasoning capabilities over image data by modeling visual sequences as a multi-turn conversation. In ImageChain, images are interleaved with corresponding textual descriptions to form a controlled dialogue that explicitly captures temporal dependencies and narrative progression. Our method optimizes for the task of next-scene description, where the model generates a context-aware description of an upcoming scene based on preceding visual and textual cues. We demonstrate that our approach improves performance on the next-scene description task -- achieving an average improvement from 3.7% to 19% in SimRate, a metric that quantifies semantic similarity to human-annotated ground truths. Moreover, ImageChain achieves robust zero-shot out-of-domain performance in applications ranging from comics to robotics. Extensive experiments validate that instruction-tuning in a multimodal, multi-turn conversation design is key to bridging the gap between static image understanding and temporally-aware reasoning.
Authors: Dayu Yang, Tianyang Liu, Daoan Zhang, Antoine Simoulin, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Xin Qian, Grey Yang, Jiebo Luo, Julian McAuley
Abstract: In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that drive more advanced code intelligence. In this study, we examine how code serves as a structured medium for enhancing reasoning: it provides verifiable execution paths, enforces logical decomposition, and enables runtime validation. We also explore how improvements in reasoning have transformed code intelligence from basic completion to advanced capabilities, enabling models to address complex software engineering tasks through planning and debugging. Finally, we identify key challenges and propose future research directions to strengthen this synergy, ultimately improving LLM's performance in both areas.
Authors: Lucy Xiaoyang Shi, Brian Ichter, Michael Equi, Liyiming Ke, Karl Pertsch, Quan Vuong, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, Adrian Li-Bell, Danny Driess, Lachy Groom, Sergey Levine, Chelsea Finn
Abstract: Generalist robots that can perform a range of different tasks in open-world settings must be able to not only reason about the steps needed to accomplish their goals, but also process complex instructions, prompts, and even feedback during task execution. Intricate instructions (e.g., "Could you make me a vegetarian sandwich?" or "I don't like that one") require not just the ability to physically perform the individual steps, but the ability to situate complex commands and feedback in the physical world. In this work, we describe a system that uses vision-language models in a hierarchical structure, first reasoning over complex prompts and user feedback to deduce the most appropriate next step to fulfill the task, and then performing that step with low-level actions. In contrast to direct instruction following methods that can fulfill simple commands ("pick up the cup"), our system can reason through complex prompts and incorporate situated feedback during task execution ("that's not trash"). We evaluate our system across three robotic platforms, including single-arm, dual-arm, and dual-arm mobile robots, demonstrating its ability to handle tasks such as cleaning messy tables, making sandwiches, and grocery shopping.
Authors: Kacper Sokol, Peter Flach
Abstract: Explainable artificial intelligence provides tools to better understand predictive models and their decisions, but many such methods are limited to producing insights with respect to a single class. When generating explanations for several classes, reasoning over them to obtain a comprehensive view may be difficult since they can present competing or contradictory evidence. To address this challenge we introduce the novel paradigm of multi-class explanations. We outline the theory behind such techniques and propose a local surrogate model based on multi-output regression trees -- called LIMEtree -- that offers faithful and consistent explanations of multiple classes for individual predictions while being post-hoc, model-agnostic and data-universal. On top of strong fidelity guarantees, our implementation delivers a range of diverse explanation types, including counterfactual statements favoured in the literature. We evaluate our algorithm with respect to explainability desiderata, through quantitative experiments and via a pilot user study, on image and tabular data classification tasks, comparing it to LIME, which is a state-of-the-art surrogate explainer. Our contributions demonstrate the benefits of multi-class explanations and wide-ranging advantages of our method across a diverse set of scenarios.
Authors: Markus K\"angsepp, Kaspar Valk, Meelis Kull
Abstract: Every uncalibrated classifier has a corresponding true calibration map that calibrates its confidence. Deviations of this idealistic map from the identity map reveal miscalibration. Such calibration errors can be reduced with many post-hoc calibration methods which fit some family of calibration maps on a validation dataset. In contrast, evaluation of calibration with the expected calibration error (ECE) on the test set does not explicitly involve fitting. However, as we demonstrate, ECE can still be viewed as if fitting a family of functions on the test data. This motivates the fit-on-the-test view on evaluation: first, approximate a calibration map on the test data, and second, quantify its distance from the identity. Exploiting this view allows us to unlock missed opportunities: (1) use the plethora of post-hoc calibration methods for evaluating calibration; (2) tune the number of bins in ECE with cross-validation. Furthermore, we introduce: (3) benchmarking on pseudo-real data where the true calibration map can be estimated very precisely; and (4) novel calibration and evaluation methods using new calibration map families PL and PL3.
Authors: Alexandra Cimpean, Timothy Verstraeten, Lander Willem, Niel Hens, Ann Now\'e, Pieter Libin
Abstract: Individual-based epidemiological models support the study of fine-grained preventive measures, such as tailored vaccine allocation policies, in silico. As individual-based models are computationally intensive, it is pivotal to identify optimal strategies within a reasonable computational budget. Moreover, due to the high societal impact associated with the implementation of preventive strategies, uncertainty regarding decisions should be communicated to policy makers, which is naturally embedded in a Bayesian approach. We present a novel technique for evaluating vaccine allocation strategies using a multi-armed bandit framework in combination with a Bayesian anytime $m$-top exploration algorithm. $m$-top exploration allows the algorithm to learn $m$ policies for which it expects the highest utility, enabling experts to inspect this small set of alternative strategies, along with their quantified uncertainty. The anytime component provides policy advisors with flexibility regarding the computation time and the desired confidence, which is important as it is difficult to make this trade-off beforehand. We consider the Belgian COVID-19 epidemic using the individual-based model STRIDE, where we learn a set of vaccination policies that minimize the number of infections and hospitalisations. Through experiments we show that our method can efficiently identify the $m$-top policies, which is validated in a scenario where the ground truth is available. Finally, we explore how vaccination policies can best be organised under different contact reduction schemes and we investigate the impact of vaccine uptake proportions (i.e., the proportion of individuals that will comply with the strategy and take the vaccine).
Authors: Xuan Zhang, Limei Wang, Jacob Helwig, Youzhi Luo, Cong Fu, Yaochen Xie, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Alex Strasser, Haiyang Yu, YuQing Xie, Xiang Fu, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes St\"ark, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Al\'an Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Li\`o, Rose Yu, Stephan G\"unnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, Tommi Jaakkola, Connor W. Coley, Xiaoning Qian, Xiaofeng Qian, Tess Smidt, Shuiwang Ji
Abstract: Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.
Authors: Jianchao Lu, Yuzhe Tian, Yang Zhang, Quan Z. Sheng, Xi Zheng
Abstract: Brain--computer interfaces are groundbreaking technology whereby brain signals are used to control external devices. Despite some advances in recent years, electroencephalogram (EEG)-based motor-imagery tasks face challenges, such as amplitude and phase variability and complex spatial correlations, with a need for smaller models and faster inference. In this study, we develop a prototype, called the Lightweight Geometric Learning Brain--Computer Interface (LGL-BCI), which uses our customized geometric deep learning architecture for swift model inference without sacrificing accuracy. LGL-BCI contains an EEG channel selection module via a feature decomposition algorithm to reduce the dimensionality of a symmetric positive definite matrix, providing adaptiveness among the continuously changing EEG signal. Meanwhile, a built-in lossless transformation helps boost the inference speed. The performance of our solution was evaluated using two real-world EEG devices and two public EEG datasets. LGL-BCI demonstrated significant improvements, achieving an accuracy of 82.54% compared to 62.22% for the state-of-the-art approach. Furthermore, LGL-BCI uses fewer parameters (64.9K vs. 183.7K), highlighting its computational efficiency. These findings underscore both the superior accuracy and computational efficiency of LGL-BCI, demonstrating the feasibility and robustness of geometric deep learning in motor-imagery brain--computer interface applications.
Authors: Arnulf Jentzen, Benno Kuckuck, Philippe von Wurstemberger
Abstract: This book aims to provide an introduction to the topic of deep learning algorithms. We review essential components of deep learning algorithms in full mathematical detail including different artificial neural network (ANN) architectures (such as fully-connected feedforward ANNs, convolutional ANNs, recurrent ANNs, residual ANNs, and ANNs with batch normalization) and different optimization algorithms (such as the basic stochastic gradient descent (SGD) method, accelerated methods, and adaptive methods). We also cover several theoretical aspects of deep learning algorithms such as approximation capacities of ANNs (including a calculus for ANNs), optimization theory (including Kurdyka-{\L}ojasiewicz inequalities), and generalization errors. In the last part of the book some deep learning approximation methods for PDEs are reviewed including physics-informed neural networks (PINNs) and deep Galerkin methods. We hope that this book will be useful for students and scientists who do not yet have any background in deep learning at all and would like to gain a solid foundation as well as for practitioners who would like to obtain a firmer mathematical understanding of the objects and methods considered in deep learning.
Authors: Ye Lin Tun, Chu Myaet Thwal, Huy Q. Le, Minh N. H. Nguyen, Choong Seon Hong
Abstract: Many studies integrate federated learning (FL) with self-supervised learning (SSL) to take advantage of raw data distributed across edge devices. However, edge devices often struggle with high computational and communication costs imposed by SSL and FL algorithms. With the deployment of more complex and large-scale models, such as Transformers, these challenges are exacerbated. To tackle this, we propose the Layer-Wise Federated Self-Supervised Learning (LW-FedSSL) approach, which allows edge devices to incrementally train a small part of the model at a time. Specifically, in LW-FedSSL, training is decomposed into multiple stages, with each stage responsible for only a specific layer (or a block of layers) of the model. Since only a portion of the model is active for training at any given time, LW-FedSSL significantly reduces computational requirements. Additionally, only the active model portion needs to be exchanged between the FL server and clients, reducing the communication overhead. This enables LW-FedSSL to jointly address both computational and communication challenges in FL. Depending on the SSL algorithm used, it can achieve up to a $3.34 \times$ reduction in memory usage, $4.20 \times$ fewer computational operations (GFLOPs), and a $5.07 \times$ lower communication cost while maintaining performance comparable to its end-to-end training counterpart. Furthermore, we explore a progressive training strategy called Prog-FedSSL, which offers a $1.84\times$ reduction in GFLOPs and a $1.67\times$ reduction in communication costs while maintaining the same memory requirements as end-to-end training. While the resource efficiency of Prog-FedSSL is lower than that of LW-FedSSL, its performance improvements make it a viable candidate for FL environments with more lenient resource constraints.
Authors: Siyi Liu, Chen Gao, Yong Li
Abstract: Hyperparameter optimization is critical in modern machine learning, requiring expert knowledge, numerous trials, and high computational and human resources. Despite the advancements in Automated Machine Learning (AutoML), challenges in terms of trial efficiency, setup complexity, and interoperability still persist. To address these issues, we introduce a novel paradigm leveraging Large Language Models (LLMs) to automate hyperparameter optimization across diverse machine learning tasks, which is named AgentHPO (short for LLM Agent-based Hyperparameter Optimization). Specifically, AgentHPO processes the task information autonomously, conducts experiments with specific hyperparameters (HPs), and iteratively optimizes them based on historical trials. This human-like optimization process largely reduces the number of required trials, simplifies the setup process, and enhances interpretability and user trust, compared to traditional AutoML methods. Extensive empirical experiments conducted on 12 representative machine-learning tasks indicate that AgentHPO not only matches but also often surpasses the best human trials in terms of performance while simultaneously providing explainable results. Further analysis sheds light on the strategies employed by the LLM in optimizing these tasks, highlighting its effectiveness and adaptability in various scenarios.
Authors: Filippo Fiocchi, Domna Ladopoulou, Petros Dellaportas
Abstract: We provide a condition monitoring system for wind farms, based on normal behaviour modelling using a probabilistic multi-layer perceptron with transfer learning via fine-tuning. The model predicts the output power of the wind turbine under normal behaviour based on features retrieved from supervisory control and data acquisition (SCADA) systems. Its advantages are that (i) it can be trained with SCADA data of at least a few years, (ii) it can incorporate all SCADA data of all wind turbines in a wind farm as features, (iii) it assumes that the output power follows a normal density with heteroscedastic variance and (iv) it can predict the output of one wind turbine by borrowing strength from the data of all other wind turbines in a farm. Probabilistic guidelines for condition monitoring are given via a cumulative sum (CUSUM) control chart, which is specifically designed based on a real-data classification exercise and, hence, is adapted to the needs of a wind farm. We illustrate the performance of our model in a real SCADA data example which provides evidence that it outperforms other probabilistic prediction models.
Authors: Sakshi Choudhary, Sai Aparna Aketi, Kaushik Roy
Abstract: Decentralized training enables learning with distributed datasets generated at different locations without relying on a central server. In realistic scenarios, the data distribution across these sparsely connected learning agents can be significantly heterogeneous, leading to local model over-fitting and poor global model generalization. Another challenge is the high communication cost of training models in such a peer-to-peer fashion without any central coordination. In this paper, we jointly tackle these two-fold practical challenges by proposing SADDLe, a set of sharpness-aware decentralized deep learning algorithms. SADDLe leverages Sharpness-Aware Minimization (SAM) to seek a flatter loss landscape during training, resulting in better model generalization as well as enhanced robustness to communication compression. We present two versions of our approach and conduct extensive experiments to show that SADDLe leads to 1-20% improvement in test accuracy compared to other existing techniques. Additionally, our proposed approach is robust to communication compression, with an average drop of only 1% in the presence of up to 4x compression.
Authors: Shashata Sawmya, Linghao Kong, Ilia Markov, Dan Alistarh, Nir Shavit
Abstract: Disentangling polysemantic neurons is at the core of many current approaches to interpretability of large language models. Here we attempt to study how disentanglement can be used to understand performance, particularly under weight sparsity, a leading post-training optimization technique. We suggest a novel measure for estimating neuronal entanglement: the Wasserstein distance of a neuron's output distribution to a Gaussian. Moreover, we show the existence of a small number of highly entangled "Wasserstein Neurons" in each linear layer of an LLM, characterized by their highly non-Gaussian output distributions, their role in mapping similar inputs to dissimilar outputs, and their significant impact on model accuracy. To study these phenomena, we propose a new experimental framework for disentangling polysemantic neurons. Our framework separates each layer's inputs to create a mixture of experts where each neuron's output is computed by a mixture of neurons of lower Wasserstein distance, each better at maintaining accuracy when sparsified without retraining. We provide strong evidence that this is because the mixture of sparse experts is effectively disentangling the input-output relationship of individual neurons, in particular the difficult Wasserstein neurons.
Authors: Menghao Waiyan William Zhu, Ercan Engin Kuruo\u{g}lu
Abstract: We formulate sequential maximum a posteriori inference as a recursion of loss functions and reduce the problem of continual learning to approximating the previous loss function. We then propose two coreset-free methods: autodiff quadratic consolidation, which uses an accurate and full quadratic approximation, and neural consolidation, which uses a neural network approximation. These methods are not scalable with respect to the neural network size, and we study them for classification tasks in combination with a fixed pre-trained feature extractor. We also introduce simple but challenging classical task sequences based on Iris and Wine datasets. We find that neural consolidation performs well in the classical task sequences, where the input dimension is small, while autodiff quadratic consolidation performs consistently well in image task sequences with a fixed pre-trained feature extractor, achieving comparable performance to joint training in many cases.
Authors: Anvith Thudi, Chris J. Maddison
Abstract: Machine learning models are often required to perform well across several pre-defined settings, such as a set of user groups. Worst-case performance is a common metric to capture this requirement, and is the objective of group distributionally robust optimization (group DRO). Unfortunately, these methods struggle when the loss is non-convex in the parameters, or the model class is non-parametric. Here, we make a classical move to address this: we reparameterize group DRO from parameter space to function space, which results in a number of advantages. First, we show that group DRO over the space of bounded functions admits a minimax theorem. Second, for cross-entropy and mean squared error, we show that the minimax optimal mixture distribution is the solution of a simple convex optimization problem. Thus, provided one is working with a model class of universal function approximators, group DRO can be solved by a convex optimization problem followed by a classical risk minimization problem. We call our method MixMax. In our experi ments, we found that MixMax matched or outperformed the standard group DRO baselines, and in particular, MixMax improved the performance of XGBoost over the only baseline, data balancing, for variations of the ACSIncome and CelebA annotations datasets.
Authors: Jinsheng Yuan, Zhuangkun Wei, Weisi Guo
Abstract: Over-the-Air Federated Learning (OTA-FL) is a privacy-preserving distributed learning mechanism, by aggregating updates in the electromagnetic channel rather than at the server. A critical research gap in existing OTA-FL research is the assumption of homogeneous client computational bit precision. While in real world application, clients with varying hardware resources may exploit approximate computing (AxC) to operate at different bit precisions optimized for energy and computational efficiency. And model updates of various precisions amongst clients poses an open challenge for OTA-FL, as it is incompatible in the wireless modulation superposition. Here, we propose an mixed-precision OTA-FL framework of clients with multiple bit precisions, demonstrating the following innovations: (i) the superior trade-off for both server and clients within the constraints of varying edge computing capabilities, energy efficiency, and learning accuracy requirements comparing to homogeneous client bit precision, and (ii) a multi-precision gradient modulation scheme to ensure compatibility with OTA aggregation and eliminate the overheads of precision conversion. Through case study with real world data, we validate our modulation scheme that enables AxC based mixed-precision OTA-FL. In comparison to homogeneous standard precision of 32-bit and 16-bit, our framework presents more than 10% in 4-bit ultra low precision client performance and over 65%and 13% of energy savings respectively. This demonstrates the great potential of our mixed-precision OTA-FL approach in heterogeneous edge computing environments.
Authors: Hengguan Huang, Xing Shen, Songtao Wang, Lingfa Meng, Dianbo Liu, Hao Wang, Samir Bhatt
Abstract: Human cognition excels at transcending sensory input and forming latent representations that structure our understanding of the world. Although Large Language Models (LLMs) can produce chain-of-thought reasoning, they lack a principled framework to capture latent structures and model uncertainty, especially in compositional reasoning tasks. We propose Verbalized Probabilistic Graphical Modeling (vPGM), a Bayesian prompting framework that guides LLMs to simulate key principles of Probabilistic Graphical Models (PGMs) in natural language. Unlike many traditional probabilistic methods requiring substantial domain expertise or specialized training, vPGM bypasses expert-driven model design, making it well-suited for scenarios with limited assumptions or scarce data. We evaluated our model on several compositional reasoning tasks, both close-ended and open-ended. Our results indicate that the model effectively enhances confidence calibration and text generation quality.
Authors: Anming Gu, Edward Chien, Kristjan Greenewald
Abstract: Trajectory inference seeks to recover the temporal dynamics of a population from snapshots of its (uncoupled) temporal marginals, i.e. where observed particles are not tracked over time. Prior works addressed this challenging problem under a stochastic differential equation (SDE) model with a gradient-driven drift in the observed space, introducing a minimum entropy estimator relative to the Wiener measure and a practical grid-free mean-field Langevin (MFL) algorithm using Schr\"odinger bridges. Motivated by the success of observable state space models in the traditional paired trajectory inference problem (e.g. target tracking), we extend the above framework to a class of latent SDEs in the form of observable state space models. In this setting, we use partial observations to infer trajectories in the latent space under a specified dynamics model (e.g. the constant velocity/acceleration models from target tracking). We introduce the PO-MFL algorithm to solve this latent trajectory inference problem and provide theoretical guarantees to the partially observed setting. Experiments validate the robustness of our method and the exponential convergence of the MFL dynamics, and demonstrate significant outperformance over the latent-free baseline in key scenarios.
Authors: Siyuan Yu, Wei Chen, H. Vincent Poor
Abstract: Distributed stochastic gradient descent (SGD) has attracted considerable recent attention due to its potential for scaling computational resources, reducing training time, and helping protect user privacy in machine learning. However, the staggers and limited bandwidth may induce random computational/communication delays, thereby severely hindering the learning process. Therefore, how to accelerate asynchronous SGD by efficiently scheduling multiple workers is an important issue. In this paper, a unified framework is presented to analyze and optimize the convergence of asynchronous SGD based on stochastic delay differential equations (SDDEs) and the Poisson approximation of aggregated gradient arrivals. In particular, we present the run time and staleness of distributed SGD without a memorylessness assumption on the computation times. Given the learning rate, we reveal the relevant SDDE's damping coefficient and its delay statistics, as functions of the number of activated clients, staleness threshold, the eigenvalues of the Hessian matrix of the objective function, and the overall computational/communication delay. The formulated SDDE allows us to present both the distributed SGD's convergence condition and speed by calculating its characteristic roots, thereby optimizing the scheduling policies for asynchronous/event-triggered SGD. It is interestingly shown that increasing the number of activated workers does not necessarily accelerate distributed SGD due to staleness. Moreover, a small degree of staleness does not necessarily slow down the convergence, while a large degree of staleness will result in the divergence of distributed SGD. Numerical results demonstrate the potential of our SDDE framework, even in complex learning tasks with non-convex objective functions.
Authors: Matthijs Pals, A Erdem Sa\u{g}tekin, Felix Pei, Manuel Gloeckler, Jakob H Macke
Abstract: A central aim in computational neuroscience is to relate the activity of large populations of neurons to an underlying dynamical system. Models of these neural dynamics should ideally be both interpretable and fit the observed data well. Low-rank recurrent neural networks (RNNs) exhibit such interpretability by having tractable dynamics. However, it is unclear how to best fit low-rank RNNs to data consisting of noisy observations of an underlying stochastic system. Here, we propose to fit stochastic low-rank RNNs with variational sequential Monte Carlo methods. We validate our method on several datasets consisting of both continuous and spiking neural data, where we obtain lower dimensional latent dynamics than current state of the art methods. Additionally, for low-rank models with piecewise linear nonlinearities, we show how to efficiently identify all fixed points in polynomial rather than exponential cost in the number of units, making analysis of the inferred dynamics tractable for large RNNs. Our method both elucidates the dynamical systems underlying experimental recordings and provides a generative model whose trajectories match observed variability.
Authors: Meiyu Zhong, Ravi Tandon
Abstract: Certifiable robustness gives the guarantee that small perturbations around an input to a classifier will not change the prediction. There are two approaches to provide certifiable robustness to adversarial examples: a) explicitly training classifiers with small Lipschitz constants, and b) Randomized smoothing, which adds random noise to the input to create a smooth classifier. We propose SPLITZ, a practical and novel approach which leverages the synergistic benefits of both the above ideas into a single framework. Our main idea is to split a classifier into two halves, constrain the Lipschitz constant of the first half, and smooth the second half via randomization. Motivation for SPLITZ comes from the observation that many standard deep networks exhibit heterogeneity in Lipschitz constants across layers. SPLITZ can exploit this heterogeneity while inheriting the scalability of randomized smoothing. We present a principled approach to train SPLITZ and provide theoretical analysis to derive certified robustness guarantees during inference. We present a comprehensive comparison of robustness-accuracy trade-offs and show that SPLITZ consistently improves on existing state-of-the-art approaches in the MNIST, CIFAR-10 and ImageNet datasets. For instance, with $\ell_2$ norm perturbation budget of $\epsilon=1$, SPLITZ achieves $43.2\%$ top-1 test accuracy on CIFAR-10 dataset compared to state-of-art top-1 test accuracy $39.8\%$.
Authors: Nikolaos Dimitriadis, Pascal Frossard, Francois Fleuret
Abstract: Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary to traditional Multi-Task Learning (MTL) that optimizes for a single trade-off decided prior to training. However, recent PFL methodologies suffer from limited scalability, slow convergence, and excessive memory requirements, while exhibiting inconsistent mappings from preference to objective space. We introduce PaLoRA, a novel parameter-efficient method that addresses these limitations in two ways. First, we augment any neural network architecture with task-specific low-rank adapters and continuously parameterize the PF in their convex hull. Our approach steers the original model and the adapters towards learning general and task-specific features, respectively. Second, we propose a deterministic sampling schedule of preference vectors that reinforces this division of labor, enabling faster convergence and strengthening the validity of the mapping from preference to objective space throughout training. Our experiments show that PaLoRA outperforms state-of-the-art MTL and PFL baselines across various datasets, scales to large networks, reducing the memory overhead $23.8-31.7$ times compared with competing PFL baselines in scene understanding benchmarks.
Authors: Bella Finkel, Jose Israel Rodriguez, Chenxi Wu, Thomas Yahl
Abstract: We study the expressive power of deep polynomial neural networks through the geometry of their neurovariety. We introduce the notion of the activation degree threshold of a network architecture to express when the dimension of the neurovariety achieves its theoretical maximum. We prove the existence of the activation degree threshold for all polynomial neural networks without width-one bottlenecks and demonstrate a universal upper bound that is quadratic in the width of largest size. In doing so, we prove the high activation degree conjecture of Kileel, Trager, and Bruna. Certain structured architectures have exceptional activation degree thresholds, making them especially expressive in the sense of their neurovariety dimension. In this direction, we prove that polynomial neural networks with equi-width architectures are maximally expressive by showing their activation degree threshold is one.
Authors: Jiancheng Dong, Lei Jiang, Wei Jin, Lu Cheng
Abstract: Packing for Supervised Fine-Tuning (SFT) in autoregressive models involves concatenating data points of varying lengths until reaching the designed maximum length to facilitate GPU processing. However, randomly concatenating data points can lead to cross-contamination of sequences due to the significant difference in their subject matter. The mainstream approaches in SFT ensure that each token in the attention calculation phase only focuses on tokens within its own short sequence, without providing additional learning signals for the preceding context. To address these challenges, we introduce Threshold Filtering Packing (TFP), a method that selects samples with related context while maintaining sufficient diversity within the same pack. Our experiments show that TFP offers a simple-to-implement and scalable approach that significantly enhances SFT performance, with observed improvements of up to 7\% on GSM8K, 4\% on HumanEval. Furthermore, results from bias benchmark datasets highlight TFP's promising performance in improving fairness while also boosting prediction accuracy by 15\%.
Authors: Liu Ziyin, Yizhou Xu, Isaac Chuang
Abstract: When symmetry is present in the loss function, the model is likely to be trapped in a low-capacity state that is sometimes known as a "collapse". Being trapped in these low-capacity states can be a major obstacle to training across many scenarios where deep learning technology is applied. We first prove two concrete mechanisms through which symmetries lead to reduced capacities and ignored features during training and inference. We then propose a simple and theoretically justified algorithm, syre, to remove almost all symmetry-induced low-capacity states in neural networks. When this type of entrapment is especially a concern, removing symmetries with the proposed method is shown to correlate well with improved optimization or performance. A remarkable merit of the proposed method is that it is model-agnostic and does not require any knowledge of the symmetry.
Authors: Lefan Zhang, Xiaodan Wang, Yanhua Huang, Ruiwen Xu
Abstract: Speculative sampling is a promising approach to accelerate the decoding stage for Large Language Models (LLMs). Recent advancements that leverage target LLM's contextual information, such as hidden states and KV cache, have shown significant practical improvements. However, these approaches suffer from inconsistent context between training and decoding. We also observe another discrepancy between the training and decoding objectives in existing speculative sampling methods. In this work, we propose a solution named HArmonized Speculative Sampling (HASS) that learns harmonized representations to address these issues. HASS accelerates the decoding stage without adding inference overhead through harmonized objective distillation and harmonized context alignment. Experiments on four LLaMA models demonstrate that HASS achieves 2.81x-4.05x wall-clock time speedup ratio averaging across three datasets, surpassing EAGLE-2 by 8%-20%. The code is available at https://github.com/HArmonizedSS/HASS.
Authors: Sebastian Chwilczy\'nski, Kacper Tr\k{e}bacz, Karol Cyganik, Mateusz Ma{\l}ecki, Dariusz Brzezinski
Abstract: Current interest in deep learning captures the attention of many programmers and researchers. Unfortunately, the lack of a unified schema for developing deep learning models results in methodological inconsistencies, unclear documentation, and problems with reproducibility. Some guidelines have been proposed, yet currently, they lack practical implementations. Furthermore, neural network training often takes on the form of trial and error, lacking a structured and thoughtful process. To alleviate these issues, in this paper, we introduce Art, a Python library designed to help automatically impose rules and standards while developing deep learning pipelines. Art divides model development into a series of smaller steps of increasing complexity, each concluded with a validation check improving the interpretability and robustness of the process. The current version of Art comes equipped with nine predefined steps inspired by Andrej Karpathy's Recipe for Training Neural Networks, a visualization dashboard, and integration with loggers such as Neptune. The code related to this paper is available at: https://github.com/SebChw/Actually-Robust-Training.
Authors: Christian Marius Lillelund, Ali Hossein Gharari Foomani, Weijie Sun, Shi-ang Qi, Russell Greiner
Abstract: A multi-event survival model predicts the time until an instance experiences each of several different events, given the instance's description. Unlike competing-event models, the events here are not mutually exclusive and often exhibit statistical dependencies. Existing approaches for multi-event survival analysis have generally been limited, most focusing on producing simple risk scores for each event, rather than the time-to-event itself. To overcome these issues, we introduce MENSA, a novel deep learning approach for multi-event survival analysis. MENSA jointly learns representations of the input features while capturing the complex dependence structure among events. In practice, it attempts to optimize the sum of the traditional negative log-likelihood across events and a novel trajectory-based likelihood, which encourages the model to learn the temporal order in which events occur. Experiments on real-world clinical datasets show that MENSA consistently gives good discrimination performances and accurate time-to-event predictions in single-event, competing-risk, and multi-event problems. Additionally, MENSA is more computationally-efficient, requiring fewer parameters and FLOPs than multiple state-of-the-art survival baselines when applied to large-dimensional datasets (more than 100 features).
Authors: Domenic Rosati, Giles Edkins, Harsh Raj, David Atanasov, Subhabrata Majumdar, Janarthanan Rajendran, Frank Rudzicz, Hassan Sajjad
Abstract: While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this setting has been treated extensively, another popular training paradigm, learning from unsafe feedback with reinforcement learning, has previously been unexplored. This is concerning due to the widespread deployment of feedback collection systems. We address this gap by providing an analysis of learning settings where feedback is harmful, i.e. that unsafe samples are preferred over safe ones despite model developers goal to maintain safety. We find that safety-aligned LLMs easily explore unsafe action spaces via generating harmful text and optimize for reward that violates safety constraints indicating that current safety guards are not enough to prevent learning from unsafe feedback. In order to protect against this vulnerability, we adapt a number of both "implict" and "explicit" harmful fine-tuning defences to evaluate whether they are effective as learning constraints in an RLHF setting finding that no method is generally effective pointing to the need for more defence research. We end the paper with the observation that some defences work by performing "harmless reward hacking" for which we provide a theoretical explanation drawn from the theory of Constrained Markov Decision Processes and provide some direction for future defence development.
Authors: Minh Le, Chau Nguyen, Huy Nguyen, Quyen Tran, Trung Le, Nhat Ho
Abstract: Prompt-based techniques, such as prompt-tuning and prefix-tuning, have gained prominence for their efficiency in fine-tuning large pre-trained models. Despite their widespread adoption, the theoretical foundations of these methods remain limited. For instance, in prefix-tuning, we observe that a key factor in achieving performance parity with full fine-tuning lies in the reparameterization strategy. However, the theoretical principles underpinning the effectiveness of this approach have yet to be thoroughly examined. Our study demonstrates that reparameterization is not merely an engineering trick but is grounded in deep theoretical foundations. Specifically, we show that the reparameterization strategy implicitly encodes a shared structure between prefix key and value vectors. Building on recent insights into the connection between prefix-tuning and mixture of experts models, we further illustrate that this shared structure significantly improves sample efficiency in parameter estimation compared to non-shared alternatives. The effectiveness of prefix-tuning across diverse tasks is empirically confirmed to be enhanced by the shared structure, through extensive experiments in both visual and language domains. Additionally, we uncover similar structural benefits in prompt-tuning, offering new perspectives on its success. Our findings provide theoretical and empirical contributions, advancing the understanding of prompt-based methods and their underlying mechanisms. Our code is publicly available at https://github.com/Minhchuyentoancbn/ReparamPrefix
Authors: Jintao Zhang, Jia wei, Haofeng Huang, Pengle Zhang, Jun Zhu, Jianfei Chen
Abstract: The transformer architecture predominates across various models. As the heart of the transformer, attention has a computational complexity of O(N^2), compared to O(N) for linear transformations. When handling large sequence lengths, attention becomes the primary time-consuming component. Although quantization has proven to be an effective method for accelerating model inference, existing quantization methods primarily focus on optimizing the linear layer. In response, we first analyze the feasibility of quantization in attention detailedly. Following that, we propose SageAttention, a highly efficient and accurate quantization method for attention. The OPS (operations per second) of our approach outperforms FlashAttention2 and xformers by about 2.1 times and 2.7 times, respectively. SageAttention also achieves superior accuracy performance over FlashAttention3. Comprehensive experiments confirm that our approach incurs almost no end-to-end metrics loss across diverse models, including those for large language processing, image generation, and video generation. The codes are available at https://github.com/thu-ml/SageAttention.
Authors: Zixiang Wang, Yinghao Zhu, Huiya Zhao, Xiaochen Zheng, Dehao Sui, Tianlong Wang, Wen Tang, Yasha Wang, Ewen Harrison, Chengwei Pan, Junyi Gao, Liantao Ma
Abstract: We introduce ColaCare, a framework that enhances Electronic Health Record (EHR) modeling through multi-agent collaboration driven by Large Language Models (LLMs). Our approach seamlessly integrates domain-specific expert models with LLMs to bridge the gap between structured EHR data and text-based reasoning. Inspired by the Multidisciplinary Team (MDT) approach used in clinical settings, ColaCare employs two types of agents: DoctorAgents and a MetaAgent, which collaboratively analyze patient data. Expert models process and generate predictions from numerical EHR data, while LLM agents produce reasoning references and decision-making reports within the MDT-driven collaborative consultation framework. The MetaAgent orchestrates the discussion, facilitating consultations and evidence-based debates among DoctorAgents, simulating diverse expertise in clinical decision-making. We additionally incorporate the Merck Manual of Diagnosis and Therapy (MSD) medical guideline within a retrieval-augmented generation (RAG) module for medical evidence support, addressing the challenge of knowledge currency. Extensive experiments conducted on three EHR datasets demonstrate ColaCare's superior performance in clinical mortality outcome and readmission prediction tasks, underscoring its potential to revolutionize clinical decision support systems and advance personalized precision medicine. All code, case studies and a questionnaire are available at the project website: https://colacare.netlify.app.
Authors: Dmitry Osin, Igor Udovichenko, Viktor Moskvoretskii, Egor Shvetsov, Evgeny Burnaev
Abstract: Event Sequences (EvS) refer to sequential data characterized by irregular sampling intervals and a mix of categorical and numerical features. Accurate classification of these sequences is crucial for various real-life applications, including healthcare, finance, and user interaction. Despite the popularity of the EvS classification task, there is currently no standardized benchmark or rigorous evaluation protocol. This lack of standardization makes it difficult to compare results across studies, which can result in unreliable conclusions and hinder progress in the field. To address this gap, we present EBES, a comprehensive benchmark for EvS classification with sequence-level targets. EBES features standardized evaluation scenarios and protocols, along with an open-source PyTorch library that implements 9 modern models. Additionally, it includes the largest collection of EvS datasets, featuring 10 curated datasets, including a novel synthetic dataset and real-world data with the largest publicly available banking dataset. The library offers user-friendly interfaces for integrating new methods and datasets. Our benchmarking results highlight the unique properties of EvS compared to other sequential data types, provide a performance ranking of modern models with GRU-based models achieving the best results and reveal the challenges associated with robust EvS learning. The goal of EBES is to facilitate reproducible research, expedite progress in the field, and increase the real-world impact of EvS classification techniques.
Authors: Daogao Liu, Kunal Talwar
Abstract: There is a gap between finding a first-order stationary point (FOSP) and a second-order stationary point (SOSP) under differential privacy constraints, and it remains unclear whether privately finding an SOSP is more challenging than finding an FOSP. Specifically, Ganesh et al. (2023) claimed that an $\alpha$-SOSP can be found with $\alpha=O(\frac{1}{n^{1/3}}+(\frac{\sqrt{d}}{n\epsilon})^{3/7})$, where $n$ is the dataset size, $d$ is the dimension, and $\epsilon$ is the differential privacy parameter. However, a recent analysis revealed an issue in their saddle point escape procedure, leading to weaker guarantees. Building on the SpiderBoost algorithm framework, we propose a new approach that uses adaptive batch sizes and incorporates the binary tree mechanism. Our method not only corrects this issue but also improves the results for privately finding an SOSP, achieving $\alpha=O(\frac{1}{n^{1/3}}+(\frac{\sqrt{d}}{n\epsilon})^{1/2})$. This improved bound matches the state-of-the-art for finding a FOSP, suggesting that privately finding an SOSP may be achievable at no additional cost.
Authors: Bokun Wang, Yunwen Lei, Yiming Ying, Tianbao Yang
Abstract: We study the discriminative probabilistic modeling on a continuous domain for the data prediction task of (multimodal) self-supervised representation learning. To address the challenge of computing the integral in the partition function for each anchor data, we leverage the multiple importance sampling (MIS) technique for robust Monte Carlo integration, which can recover InfoNCE-based contrastive loss as a special case. Within this probabilistic modeling framework, we conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning and derive insights for developing better approaches by reducing the error of Monte Carlo integration. To this end, we propose a novel non-parametric method for approximating the sum of conditional probability densities required by MIS through convex optimization, yielding a new contrastive objective for self-supervised representation learning. Moreover, we design an efficient algorithm for solving the proposed objective. We empirically compare our algorithm to representative baselines on the contrastive image-language pretraining task. Experimental results on the CC3M and CC12M datasets demonstrate the superior overall performance of our algorithm. Our code is available at https://github.com/bokun-wang/NUCLR.
Authors: Julius Aka, Johannes Brunnemann, J\"org Eiden, Arne Speerforck, Lars Mikelsons
Abstract: Variational Autoencoders (VAEs) are a powerful framework for learning latent representations of reduced dimensionality, while Neural ODEs excel in learning transient system dynamics. This work combines the strengths of both to generate fast surrogate models with adjustable complexity reacting on time-varying inputs signals. By leveraging the VAE's dimensionality reduction using a nonhierarchical prior, our method adaptively assigns stochastic noise, naturally complementing known NeuralODE training enhancements and enabling probabilistic time series modeling. We show that standard Latent ODEs struggle with dimensionality reduction in systems with time-varying inputs. Our approach mitigates this by continuously propagating variational parameters through time, establishing fixed information channels in latent space. This results in a flexible and robust method that can learn different system complexities, e.g. deep neural networks or linear matrices. Hereby, it enables efficient approximation of the Koopman operator without the need for predefining its dimensionality. As our method balances dimensionality reduction and reconstruction accuracy, we call it Balanced Neural ODE (B-NODE). We demonstrate the effectiveness of this methods on several academic and real-world test cases, e.g. a power plant or MuJoCo data.
Authors: Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yufa Zhou
Abstract: Large Language Models (LLMs) have shown immense potential in enhancing various aspects of our daily lives, from conversational AI to search and AI assistants. However, their growing capabilities come at the cost of extremely large model sizes, making deployment on edge devices challenging due to memory and computational constraints. This paper introduces a novel approach to LLM weight pruning that directly optimizes for approximating the attention matrix, a core component of transformer architectures. Unlike existing methods that focus on linear approximations, our approach accounts for the non-linear nature of the Softmax attention mechanism. We provide theoretical guarantees for the convergence of our Gradient Descent-based optimization method to a near-optimal pruning mask solution. Our empirical results demonstrate the effectiveness of our non-linear pruning approach in maintaining model performance while significantly reducing computational costs, which is beyond the current state-of-the-art methods, i.e., SparseGPT and Wanda, by a large margin. This work establishes a new theoretical foundation for pruning algorithm design in LLMs, potentially paving the way for more efficient LLM inference on resource-constrained devices.
Authors: Gen Li, Changxiao Cai
Abstract: Score-based diffusion models, while achieving minimax optimality for sampling, are often hampered by slow sampling speeds due to the high computational burden of score function evaluations. Despite the recent remarkable empirical advances in speeding up the score-based samplers, theoretical understanding of acceleration techniques remains largely limited. To bridge this gap, we propose a novel training-free acceleration scheme for stochastic samplers. Under minimal assumptions -- namely, $L^2$-accurate score estimates and a finite second-moment condition on the target distribution -- our accelerated sampler provably achieves $\varepsilon$-accuracy in total variation within $\widetilde{O}(d^{5/4}/\sqrt{\varepsilon})$ iterations, thereby significantly improving upon the $\widetilde{O}(d/\varepsilon)$ iteration complexity of standard score-based samplers for $\varepsilon\leq 1/\sqrt{d}$. Notably, our convergence theory does not rely on restrictive assumptions on the target distribution or higher-order score estimation guarantees.
Authors: Yuqi Luo, Chenyang Song, Xu Han, Yingfa Chen, Chaojun Xiao, Zhiyuan Liu, Maosong Sun
Abstract: Activation sparsity denotes the existence of substantial weakly-contributed elements within activation outputs that can be eliminated, benefiting many important applications concerned with large language models (LLMs). Although promoting greater activation sparsity within LLMs deserves deep studies, existing works lack comprehensive and quantitative research on the correlation between activation sparsity and potentially influential factors. In this paper, we present a comprehensive study on the quantitative scaling properties and influential factors of the activation sparsity within decoder-only Transformer-based LLMs. Specifically, we propose PPL-$p\%$ sparsity, a precise and performance-aware activation sparsity metric that is applicable to any activation function. Through extensive experiments, we find several important phenomena. Firstly, different activation functions exhibit comparable performance but opposite training-time sparsity trends. The activation ratio (i.e., $1-\mathrm{sparsity\ ratio}$) evolves as a convergent increasing power-law and decreasing logspace power-law with the amount of training data for SiLU-activated and ReLU-activated LLMs, respectively. These demonstrate that ReLU is more efficient as the activation function than SiLU and can leverage more training data to improve activation sparsity. Secondly, the activation ratio linearly increases with the width-depth ratio below a certain bottleneck point, indicating the potential advantage of a deeper architecture at a fixed parameter scale. Finally, at similar width-depth ratios, we surprisingly find that the limit value of activation sparsity varies weakly with the parameter scale, i.e., the activation patterns within LLMs are insensitive to the parameter scale. These empirical laws towards LLMs with greater activation sparsity have important implications for making LLMs more efficient and interpretable.
Authors: Dariusz Brzezinski, Julia Stachowiak, Jerzy Stefanowski, Izabela Szczech, Robert Susmaga, Sofya Aksenyuk, Uladzimir Ivashka, Oleksandr Yasinskyi
Abstract: Society is increasingly relying on predictive models in fields like criminal justice, credit risk management, or hiring. To prevent such automated systems from discriminating against people belonging to certain groups, fairness measures have become a crucial component in socially relevant applications of machine learning. However, existing fairness measures have been designed to assess the bias between predictions for protected groups without considering the imbalance in the classes of the target variable. Current research on the potential effect of class imbalance on fairness focuses on practical applications rather than dataset-independent measure properties. In this paper, we study the general properties of fairness measures for changing class and protected group proportions. For this purpose, we analyze the probability mass functions of six of the most popular group fairness measures. We also measure how the probability of achieving perfect fairness changes for varying class imbalance ratios. Moreover, we relate the dataset-independent properties of fairness measures described in this paper to classifier fairness in real-life tasks. Our results show that measures such as Equal Opportunity and Positive Predictive Parity are more sensitive to changes in class imbalance than Accuracy Equality. These findings can help guide researchers and practitioners in choosing the most appropriate fairness measures for their classification problems.
Authors: Junqi Jiang, Tom Bewley, Saumitra Mishra, Freddy Lecue, Manuela Veloso
Abstract: Reward models (RMs) are a crucial component in the alignment of large language models' (LLMs) outputs with human values. RMs approximate human preferences over possible LLM responses to the same prompt by predicting and comparing reward scores. However, as they are typically modified versions of LLMs with scalar output heads, RMs are large black boxes whose predictions are not explainable. More transparent RMs would enable improved trust in the alignment of LLMs. In this work, we propose to use contrastive explanations to explain any binary response comparison made by an RM. Specifically, we generate a diverse set of new comparisons similar to the original one to characterise the RM's local behaviour. The perturbed responses forming the new comparisons are generated to explicitly modify manually specified high-level evaluation attributes, on which analyses of RM behaviour are grounded. In quantitative experiments, we validate the effectiveness of our method for finding high-quality contrastive explanations. We then showcase the qualitative usefulness of our method for investigating global sensitivity of RMs to each evaluation attribute, and demonstrate how representative examples can be automatically extracted to explain and compare behaviours of different RMs. We see our method as a flexible framework for RM explanation, providing a basis for more interpretable and trustworthy LLM alignment.
Authors: William T. Redman, Zhangyang Wang, Alessandro Ingrosso, Sebastian Goldt
Abstract: Since its use in the Lottery Ticket Hypothesis, iterative magnitude pruning (IMP) has become a popular method for extracting sparse subnetworks that can be trained to high performance. Despite this, the underlying nature of IMP's general success remains unclear. One possibility is that IMP is especially capable of extracting and maintaining strong inductive biases. In support of this, recent work has shown that applying IMP to fully connected neural networks (FCNs) leads to the emergence of local receptive fields (RFs), an architectural feature present in mammalian visual cortex and convolutional neural networks. The question of how IMP is able to do this remains unanswered. Inspired by results showing that training FCNs on synthetic images with highly non-Gaussian statistics (e.g., sharp edges) is sufficient to drive the formation of local RFs, we hypothesize that IMP iteratively increases the non-Gaussian statistics present in the representations of FCNs, creating a feedback loop that enhances localization. We develop a new method for measuring the effect of individual weights on the statistics of the FCN representations ("cavity method"), which allows us to find evidence in support of this hypothesis. Our work, which is the first to study the effect IMP has on the statistics of the representations of neural networks, sheds parsimonious light on one way in which IMP can drive the formation of strong inductive biases.
Authors: Yao Fu, Yinsicheng Jiang, Yeqi Huang, Ping Nie, Zhan Lu, Leyang Xue, Congjie He, Man-Kit Sit, Jilong Xue, Li Dong, Ziming Miao, Kai Zou, Edoardo Ponti, Luo Mai
Abstract: The Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs). Its key feature, sparse activation, selectively activates only a subset of parameters (experts) per token, reducing memory bandwidth and compute FLOPs compared to dense models. To capitalize on this, MoE designers leverage heterogeneous compute and memory hardware to lower system costs. However, the interaction between model sparsity and hardware heterogeneity introduces trade-offs in Cost, Accuracy, and Performance (CAP). To address this, we introduce MoE-CAP, a benchmarking method for evaluating sparse MoE systems across these three dimensions. Its key innovation is a sparsity-aware CAP analysis model, the first to integrate cost, performance, and accuracy metrics into a single diagram while estimating the impact of sparsity on system performance. MoE-CAP helps practitioners optimize hardware provisioning for an MoE model-or vice versa. MoE-CAP supports various MoE models and provides more accurate metrics than existing methods.
Authors: Lorenzo Basile, Maria Grazia Berni, Antonio Celani
Abstract: Airborne Wind Energy (AWE) is an emerging technology designed to harness the power of high-altitude winds, offering a solution to several limitations of conventional wind turbines. AWE is based on flying devices (usually gliders or kites) that, tethered to a ground station and driven by the wind, convert its mechanical energy into electrical energy by means of a generator. Such systems are usually controlled by manoeuvering the kite so as to follow a predefined path prescribed by optimal control techniques, such as model-predictive control. These methods are strongly dependent on the specific model at use and difficult to generalize, especially in unpredictable conditions such as the turbulent atmospheric boundary layer. Our aim is to explore the possibility of replacing these techniques with an approach based on Reinforcement Learning (RL). Unlike traditional methods, RL does not require a predefined model, making it robust to variability and uncertainty. Our experimental results in complex simulated environments demonstrate that AWE agents trained with RL can effectively extract energy from turbulent flows, relying on minimal local information about the kite orientation and speed relative to the wind.
Authors: Shengyu Feng, Yiming Yang
Abstract: Mixed Integer Linear Program (MILP) solvers are mostly built upon a Branch-and-Bound (B\&B) algorithm, where the efficiency of traditional solvers heavily depends on hand-crafted heuristics for branching. The past few years have witnessed the increasing popularity of data-driven approaches to automatically learn these heuristics. However, the success of these methods is highly dependent on the availability of high-quality demonstrations, which requires either the development of near-optimal heuristics or a time-consuming sampling process. This paper averts this challenge by proposing Suboptimal-Demonstration-Guided Reinforcement Learning (SORREL) for learning to branch. SORREL selectively learns from suboptimal demonstrations based on value estimation. It utilizes suboptimal demonstrations through both offline reinforcement learning on the demonstrations generated by suboptimal heuristics and self-imitation learning on past good experiences sampled by itself. Our experiments demonstrate its advanced performance in both branching quality and training efficiency over previous methods for various MILPs.
Authors: Bin Li, Xiaoye Miao, Yan Zhang, Jianwei Yin
Abstract: Decentralized federated learning (DFL) is inherently vulnerable to poisoning attacks, as malicious clients can transmit manipulated model gradients to neighboring clients. Existing defense methods either reject suspicious gradients per iteration or restart DFL aggregation after detecting all malicious clients. They overlook the potential accuracy benefit from the discarded malicious gradients. In this paper, we propose a novel gradient purification defense, named GPD, that integrates seamlessly with existing DFL aggregation to defend against poisoning attacks. It aims to mitigate the harm in model gradients while retaining the benefit in model weights for enhancing accuracy. For each benign client in GPD, a recording variable is designed to track the historically aggregated gradients from one of its neighbors. It allows benign clients to precisely detect malicious neighbors and swiftly mitigate aggregated malicious gradients via historical consistency checks. Upon mitigation, GPD optimizes model weights via aggregating gradients solely from benign clients. This retains the previously beneficial portions from malicious clients and exploits the contributions from benign clients, thereby significantly enhancing the model accuracy. We analyze the convergence of GPD, as well as its ability to harvest high accuracy. Extensive experiments over three datasets demonstrate that, GPD is capable of mitigating poisoning attacks under both iid and non-iid data distributions. It significantly outperforms state-of-the-art defenses in terms of accuracy against various poisoning attacks.
Authors: Yifan Liu, Yaokun Liu, Zelin Li, Ruichen Yao, Yang Zhang, Dong Wang
Abstract: The proliferation of fake news on social media platforms disproportionately impacts vulnerable populations, eroding trust, exacerbating inequality, and amplifying harmful narratives. Detecting fake news in multimodal contexts -- where deceptive content combines text and images -- is particularly challenging due to the nuanced interplay between modalities. Existing multimodal fake news detection methods often emphasize cross-modal consistency but ignore the complex interactions between text and visual elements, which may complement, contradict, or independently influence the predicted veracity of a post. To address these challenges, we present Modality Interactive Mixture-of-Experts for Fake News Detection (MIMoE-FND), a novel hierarchical Mixture-of-Experts framework designed to enhance multimodal fake news detection by explicitly modeling modality interactions through an interaction gating mechanism. Our approach models modality interactions by evaluating two key aspects of modality interactions: unimodal prediction agreement and semantic alignment. The hierarchical structure of MIMoE-FND allows for distinct learning pathways tailored to different fusion scenarios, adapting to the unique characteristics of each modality interaction. By tailoring fusion strategies to diverse modality interaction scenarios, MIMoE-FND provides a more robust and nuanced approach to multimodal fake news detection. We evaluate our approach on three real-world benchmarks spanning two languages, demonstrating its superior performance compared to state-of-the-art methods. By enhancing the accuracy and interpretability of fake news detection, MIMoE-FND offers a promising tool to mitigate the spread of misinformation, with the potential to better safeguard vulnerable communities against its harmful effects.
Authors: Lu Yi, Jie Peng, Yanping Zheng, Fengran Mo, Zhewei Wei, Yuhang Ye, Yue Zixuan, Zengfeng Huang
Abstract: Future link prediction is a fundamental challenge in various real-world dynamic systems. To address this, numerous temporal graph neural networks (temporal GNNs) and benchmark datasets have been developed. However, these datasets often feature excessive repeated edges and lack complex sequential dynamics, a key characteristic inherent in many real-world applications such as recommender systems and ``Who-To-Follow'' on social networks. This oversight has led existing methods to inadvertently downplay the importance of learning sequential dynamics, focusing primarily on predicting repeated edges. In this study, we demonstrate that existing methods, such as GraphMixer and DyGFormer, are inherently incapable of learning simple sequential dynamics, such as ``a user who has followed OpenAI and Anthropic is more likely to follow AI at Meta next.'' Motivated by this issue, we introduce the Temporal Graph Benchmark with Sequential Dynamics (TGB-Seq), a new benchmark carefully curated to minimize repeated edges, challenging models to learn sequential dynamics and generalize to unseen edges. TGB-Seq comprises large real-world datasets spanning diverse domains, including e-commerce interactions, movie ratings, business reviews, social networks, citation networks and web link networks. Benchmarking experiments reveal that current methods usually suffer significant performance degradation and incur substantial training costs on TGB-Seq, posing new challenges and opportunities for future research. TGB-Seq datasets, leaderboards, and example codes are available at https://tgb-seq.github.io/.
Authors: Songtao Huang, Zhen Zhao, Can Li, Lei Bai
Abstract: Real-world time series often have multiple frequency components that are intertwined with each other, making accurate time series forecasting challenging. Decomposing the mixed frequency components into multiple single frequency components is a natural choice. However, the information density of patterns varies across different frequencies, and employing a uniform modeling approach for different frequency components can lead to inaccurate characterization. To address this challenges, inspired by the flexibility of the recent Kolmogorov-Arnold Network (KAN), we propose a KAN-based Frequency Decomposition Learning architecture (TimeKAN) to address the complex forecasting challenges caused by multiple frequency mixtures. Specifically, TimeKAN mainly consists of three components: Cascaded Frequency Decomposition (CFD) blocks, Multi-order KAN Representation Learning (M-KAN) blocks and Frequency Mixing blocks. CFD blocks adopt a bottom-up cascading approach to obtain series representations for each frequency band. Benefiting from the high flexibility of KAN, we design a novel M-KAN block to learn and represent specific temporal patterns within each frequency band. Finally, Frequency Mixing blocks is used to recombine the frequency bands into the original format. Extensive experimental results across multiple real-world time series datasets demonstrate that TimeKAN achieves state-of-the-art performance as an extremely lightweight architecture. Code is available at https://github.com/huangst21/TimeKAN.
Authors: Saleh Momeni, Bing Liu
Abstract: Continual learning has been an active research area in machine learning, focusing on incrementally learning a sequence of tasks. A key challenge is catastrophic forgetting (CF), and most research efforts have been directed toward mitigating this issue. However, a significant gap remains between the accuracy achieved by state-of-the-art continual learning algorithms and the ideal or upper-bound accuracy achieved by training all tasks together jointly. This gap has hindered or even prevented the adoption of continual learning in applications, as accuracy is often of paramount importance. Recently, another challenge, termed inter-task class separation (ICS), was also identified, which spurred a theoretical study into principled approaches for solving continual learning. Further research has shown that by leveraging the theory and the power of large foundation models, it is now possible to achieve upper-bound accuracy, which has been empirically validated using both text and image classification datasets. Continual learning is now ready for real-life applications. This paper surveys the main research leading to this achievement, justifies the approach both intuitively and from neuroscience research, and discusses insights gained.
Authors: Bich-Chung Phan, Thanh Ma, Huu-Hoa Nguyen, Thanh-Nghi Do
Abstract: Gene expression classification is a pivotal yet challenging task in bioinformatics, primarily due to the high dimensionality of genomic data and the risk of overfitting. To bridge this gap, we propose BOLIMES, a novel feature selection algorithm designed to enhance gene expression classification by systematically refining the feature subset. Unlike conventional methods that rely solely on statistical ranking or classifier-specific selection, we integrate the robustness of Boruta with the interpretability of LIME, ensuring that only the most relevant and influential genes are retained. BOLIMES first employs Boruta to filter out non-informative genes by comparing each feature against its randomized counterpart, thus preserving valuable information. It then uses LIME to rank the remaining genes based on their local importance to the classifier. Finally, an iterative classification evaluation determines the optimal feature subset by selecting the number of genes that maximizes predictive accuracy. By combining exhaustive feature selection with interpretability-driven refinement, our solution effectively balances dimensionality reduction with high classification performance, offering a powerful solution for high-dimensional gene expression analysis.
Authors: Khaled Mohammed Saifuddin, Shihao Ji, Esra Akbas
Abstract: Recent advancements in Graph Contrastive Learning (GCL) have demonstrated remarkable effectiveness in improving graph representations. However, relying on predefined augmentations (e.g., node dropping, edge perturbation, attribute masking) may result in the loss of task-relevant information and a lack of adaptability to diverse input data. Furthermore, the selection of negative samples remains rarely explored. In this paper, we introduce HyperGCL, a novel multimodal GCL framework from a hypergraph perspective. HyperGCL constructs three distinct hypergraph views by jointly utilizing the input graph's structure and attributes, enabling a comprehensive integration of multiple modalities in contrastive learning. A learnable adaptive topology augmentation technique enhances these views by preserving important relations and filtering out noise. View-specific encoders capture essential characteristics from each view, while a network-aware contrastive loss leverages the underlying topology to define positive and negative samples effectively. Extensive experiments on benchmark datasets demonstrate that HyperGCL achieves state-of-the-art node classification performance.
Authors: Wenyue Hua, Tyler Wong, Sun Fei, Liangming Pan, Adam Jardine, William Yang Wang
Abstract: Large language models (LLMs) have shown remarkable improvements in reasoning and many existing benchmarks have been addressed by models such as o1 and o3 either fully or partially. However, a majority of these benchmarks emphasize deductive reasoning, including mathematical and coding tasks in which rules such as mathematical axioms or programming syntax are clearly defined, based on which LLMs can plan and apply these rules to arrive at a solution. In contrast, inductive reasoning, where one infers the underlying rules from observed data, remains less explored. Such inductive processes lie at the heart of scientific discovery, as they enable researchers to extract general principles from empirical observations. To assess whether LLMs possess this capacity, we introduce InductionBench, a new benchmark designed to evaluate the inductive reasoning ability of LLMs. Our experimental findings reveal that even the most advanced models available struggle to master the simplest complexity classes within the subregular hierarchy of functions, highlighting a notable deficiency in current LLMs' inductive reasoning capabilities. Coda and data are available https://github.com/Wenyueh/inductive_reasoning_benchmark.
URLs: https://github.com/Wenyueh/inductive_reasoning_benchmark.
Authors: Eldad Haber, Shadab Ahamed, Md. Shahriar Rahim Siddiqui, Niloufar Zakariaei, Moshe Eliasof
Abstract: Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving inverse problems. Nonetheless, training a generator is a non-trivial feat that requires fine-tuning and can lead to so-called hallucinations, that is, the generation of images that are unrealistic. In this work, we explore image generation using flow matching. We explain and demonstrate why flow matching can generate hallucinations, and propose an iterative process to improve the generation process. Our iterative process can be integrated into virtually $\textit{any}$ generative modeling technique, thereby enhancing the performance and robustness of image synthesis systems.
Authors: Anan Kabaha, Dana Drachsler-Cohen
Abstract: Neural networks are susceptible to privacy attacks that can extract private information of the training set. To cope, several training algorithms guarantee differential privacy (DP) by adding noise to their computation. However, DP requires to add noise considering every possible training set. This leads to a significant decrease in the network's accuracy. Individual DP (iDP) restricts DP to a given training set. We observe that some inputs deterministically satisfy iDP without any noise. By identifying them, we can provide iDP label-only access to the network with a minor decrease to its accuracy. However, identifying the inputs that satisfy iDP without any noise is highly challenging. Our key idea is to compute the iDP deterministic bound (iDP-DB), which overapproximates the set of inputs that do not satisfy iDP, and add noise only to their predicted labels. To compute the tightest iDP-DB, which enables to guard the label-only access with minimal accuracy decrease, we propose LUCID, which leverages several formal verification techniques. First, it encodes the problem as a mixed-integer linear program, defined over a network and over every network trained identically but without a unique data point. Second, it abstracts a set of networks using a hyper-network. Third, it eliminates the overapproximation error via a novel branch-and-bound technique. Fourth, it bounds the differences of matching neurons in the network and the hyper-network and employs linear relaxation if they are small. We show that LUCID can provide classifiers with a perfect individuals' privacy guarantee (0-iDP) -- which is infeasible for DP training algorithms -- with an accuracy decrease of 1.4%. For more relaxed $\varepsilon$-iDP guarantees, LUCID has an accuracy decrease of 1.2%. In contrast, existing DP training algorithms reduce the accuracy by 12.7%.
Authors: Arshia Kermani, Ehsan Zeraatkar, Habib Irani
Abstract: The increasing computational demands of transformer models in time series classification necessitate effective optimization strategies for energy-efficient deployment. This paper presents a systematic investigation of optimization techniques, focusing on structured pruning and quantization methods for transformer architectures. Through extensive experimentation on three distinct datasets (RefrigerationDevices, ElectricDevices, and PLAID), we quantitatively evaluate model performance and energy efficiency across different transformer configurations. Our experimental results demonstrate that static quantization reduces energy consumption by 29.14% while maintaining classification performance, and L1 pruning achieves a 63% improvement in inference speed with minimal accuracy degradation. These findings provide valuable insights into the effectiveness of optimization strategies for transformer-based time series classification, establishing a foundation for efficient model deployment in resource-constrained environments.
Authors: Md Saidul Hoque Anik, Ariful Azad
Abstract: Knowledge graph (KG) learning offers a powerful framework for generating new knowledge and making inferences. Training KG embedding can take a significantly long time, especially for larger datasets. Our analysis shows that the gradient computation of embedding is one of the dominant functions in the translation-based KG embedding training loop. We address this issue by replacing the core embedding computation with SpMM (Sparse-Dense Matrix Multiplication) kernels. This allows us to unify multiple scatter (and gather) operations as a single operation, reducing training time and memory usage. We create a general framework for training KG models using sparse kernels and implement four models, namely TransE, TransR, TransH, and TorusE. Our sparse implementations exhibit up to 5.3x speedup on the CPU and up to 4.2x speedup on the GPU with a significantly low GPU memory footprint. The speedups are consistent across large and small datasets for a given model. Our proposed sparse approach can be extended to accelerate other translation-based (such as TransC, TransM, etc.) and non-translational (such as DistMult, ComplEx, RotatE, etc.) models as well.
Authors: Liming Liu, Zhenghao Xu, Zixuan Zhang, Hao Kang, Zichong Li, Chen Liang, Weizhu Chen, Tuo Zhao
Abstract: Large Language Models (LLMs) have demonstrated remarkable success across various domains, yet their optimization remains a significant challenge due to the complex and high-dimensional loss landscapes they inhabit. While adaptive optimizers such as AdamW are widely used, they suffer from critical limitations, including an inability to capture interdependencies between coordinates and high memory consumption. Subsequent research, exemplified by SOAP, attempts to better capture coordinate interdependence but incurs greater memory overhead, limiting scalability for massive LLMs. An alternative approach aims to reduce memory consumption through low-dimensional projection, but this leads to substantial approximation errors, resulting in less effective optimization (e.g., in terms of per-token efficiency). In this paper, we propose COSMOS, a novel hybrid optimizer that leverages the varying importance of eigensubspaces in the gradient matrix to achieve memory efficiency without compromising optimization performance. The design of COSMOS is motivated by our empirical insights and practical considerations. Specifically, COSMOS applies SOAP to the leading eigensubspace, which captures the primary optimization dynamics, and MUON to the remaining eigensubspace, which is less critical but computationally expensive to handle with SOAP. This hybrid strategy significantly reduces memory consumption while maintaining robust optimization performance, making it particularly suitable for massive LLMs. Numerical experiments on various datasets and transformer architectures are provided to demonstrate the effectiveness of COSMOS. Our code is available at https://github.com/lliu606/COSMOS.
Authors: Felix Arnold, Maxence Bouvier, Ryan Amaudruz, Renzo Andri, Lukas Cavigelli
Abstract: This work introduces an innovative method for improving combinational digital circuits through random exploration in MIG-based synthesis. High-quality circuits are crucial for performance, power, and cost, making this a critical area of active research. Our approach incorporates next-state prediction and iterative selection, significantly accelerating the synthesis process. This novel method achieves up to 14x synthesis speedup and up to 20.94% better MIG minimization on the EPFL Combinational Benchmark Suite compared to state-of-the-art techniques. We further explore various predictor models and show that increased prediction accuracy does not guarantee an equivalent increase in synthesis quality of results or speedup, observing that randomness remains a desirable factor.
Authors: Wenlong Chen, Bolian Li, Ruqi Zhang, Yingzhen Li
Abstract: This review paper is intended for the 2nd edition of the Handbook of Markov chain Monte Carlo. We provide an introduction to approximate inference techniques as Bayesian computation methods applied to deep learning models. We organize the chapter by presenting popular computational methods for Bayesian neural networks and deep generative models, explaining their unique challenges in posterior inference as well as the solutions.
Authors: Jacob Fein-Ashley
Abstract: Conventional self-attention mechanisms incur quadratic complexity, limiting their scalability on long sequences. We introduce FFTNet, an adaptive spectral filtering framework that leverages the Fast Fourier Transform (FFT) to achieve global token mixing in $\mathcal{O}(n\log n)$ time. By transforming inputs into the frequency domain, FFTNet exploits the orthogonality and energy preservation guaranteed by Parseval's theorem to capture long-range dependencies efficiently. A learnable spectral filter and modReLU activation dynamically emphasize salient frequency components, providing a rigorous and adaptive alternative to traditional self-attention. Experiments on the Long Range Arena and ImageNet benchmarks validate our theoretical insights and demonstrate superior performance over fixed Fourier and standard attention models.
Authors: Arjun Ramachandra, Karthik Natarajan
Abstract: In this paper, we introduce the notion of a ``pairwise independent correlation gap'' for set functions with random elements. The pairwise independent correlation gap is defined as the ratio of the maximum expected value of a set function with arbitrary dependence among the elements with fixed marginal probabilities to the maximum expected value with pairwise independent elements with the same marginal probabilities. We show that for any nonnegative monotone submodular set function defined on $n$ elements, this ratio is upper bounded by $4/3$ in the following two cases: (a) $n = 3$ for all marginal probabilities and (b) all $n$ for small marginal probabilities (and similarly large marginal probabilities). This differs from the bound on the ``correlation gap'' which holds with mutual independence and showcases the fundamental difference between pairwise independence and mutual independence. We discuss the implication of the results with two examples and end the paper with a conjecture.
Authors: Brian Y. Lim, Joseph P. Cahaly, Chester Y. F. Sng, Adam Chew
Abstract: Many visualizations have been developed for explainable AI (XAI), but they often require further reasoning by users to interpret. Investigating XAI for high-stakes medical diagnosis, we propose improving domain alignment with diagrammatic and abductive reasoning to reduce the interpretability gap. We developed DiagramNet to predict cardiac diagnoses from heart auscultation, select the best-fitting hypothesis based on criteria evaluation, and explain with clinically-relevant murmur diagrams. The ante-hoc interpretable model leverages domain-relevant ontology, representation, and reasoning process to increase trust in expert users. In modeling studies, we found that DiagramNet not only provides faithful murmur shape explanations, but also has better performance than baseline models. We demonstrate the interpretability and trustworthiness of diagrammatic, abductive explanations in a qualitative user study with medical students, showing that clinically-relevant, diagrammatic explanations are preferred over technical saliency map explanations. This work contributes insights into providing domain-aligned explanations for user-centric XAI in complex domains.
Authors: Przemyslaw Grabowicz, Adrian Byrne, Cyrus Cousins, Nicholas Perello, Yair Zick
Abstract: We propose establishing an office to oversee AI systems by introducing a tiered system of explainability and benchmarking requirements for commercial AI systems. We examine how complex high-risk technologies have been successfully regulated at the national level. Specifically, we draw parallels to the existing regulation for the U.S. medical device industry and the pharmaceutical industry (regulated by the FDA), the proposed legislation for AI in the European Union (the AI Act), and the existing U.S. anti-discrimination legislation. To promote accountability and user trust, AI accountability mechanisms shall introduce standarized measures for each category of intended high-risk use of AI systems to enable structured comparisons among such AI systems. We suggest using explainable AI techniques, such as input influence measures, as well as fairness statistics and other performance measures of high-risk AI systems. We propose to standardize internal benchmarking and automated audits to transparently characterize high-risk AI systems. The results of such audits and benchmarks shall be clearly and transparently communicated and explained to enable meaningful comparisons of competing AI systems via a public AI registry. Such standardized audits, benchmarks, and certificates shall be specific to intended high-risk use of respective AI systems and could constitute conformity assessment for AI systems, e.g., in the European Union's AI Act.
Authors: Santanu Ganguly
Abstract: Quantum machine learning (QML) is a cross-disciplinary subject made up of two of the most exciting research areas: quantum computing and classical machine learning (ML), with ML and artificial intelligence (AI) being projected as the first fields that will be impacted by the rise of quantum machines. Quantum computers are being used today in drug discovery, material & molecular modelling and finance. In this work, we discuss some upcoming active new research areas in application of quantum machine learning (QML) in finance. We discuss certain QML models that has become areas of active interest in the financial world for various applications. We use real world financial dataset and compare models such as qGAN (quantum generative adversarial networks) and QCBM (quantum circuit Born machine) among others, using simulated environments. For the qGAN, we define quantum circuits for discriminators and generators and show promises of future quantum advantage via QML in finance.
Authors: Peter Vieting, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf Schl\"uter, Reinhold Haeb-Umbach
Abstract: Many real-life applications of automatic speech recognition (ASR) require processing of overlapped speech. A common method involves first separating the speech into overlap-free streams on which ASR is performed. Recently, TF-GridNet has shown impressive performance in speech separation in real reverberant conditions. Furthermore, a mixture encoder was proposed that leverages the mixed speech to mitigate the effect of separation artifacts. In this work, we extended the mixture encoder from a static two-speaker scenario to a natural meeting context featuring an arbitrary number of speakers and varying degrees of overlap. We further demonstrate its limits by the integration with separators of varying strength including TF-GridNet. Our experiments result in a new state-of-the-art performance on LibriCSS using a single microphone. They show that TF-GridNet largely closes the gap between previous methods and oracle separation independent of mixture encoding. We further investigate the remaining potential for improvement.
Authors: Zhenghai Xue, Qingpeng Cai, Bin Yang, Lantao Hu, Peng Jiang, Kun Gai, Bo An
Abstract: The field of Reinforcement Learning (RL) has garnered increasing attention for its ability of optimizing user retention in recommender systems. A primary obstacle in this optimization process is the environment non-stationarity stemming from the continual and complex evolution of user behavior patterns over time, such as variations in interaction rates and retention propensities. These changes pose significant challenges to existing RL algorithms for recommendations, leading to issues with dynamics and reward distribution shifts. This paper introduces a novel approach called \textbf{A}daptive \textbf{U}ser \textbf{R}etention \textbf{O}ptimization (AURO) to address this challenge. To navigate the recommendation policy in non-stationary environments, AURO introduces an state abstraction module in the policy network. The module is trained with a new value-based loss function, aligning its output with the estimated performance of the current policy. As the policy performance of RL is sensitive to environment drifts, the loss function enables the state abstraction to be reflective of environment changes and notify the recommendation policy to adapt accordingly. Additionally, the non-stationarity of the environment introduces the problem of implicit cold start, where the recommendation policy continuously interacts with users displaying novel behavior patterns. AURO encourages exploration guarded by performance-based rejection sampling to maintain a stable recommendation quality in the cost-sensitive online environment. Extensive empirical analysis are conducted in a user retention simulator, the MovieLens dataset, and a live short-video recommendation platform, demonstrating AURO's superior performance against all evaluated baseline algorithms.
Authors: Jana Gauss, Fabian Scheipl, Moritz Herrmann
Abstract: Whether class labels in a given data set correspond to meaningful clusters is crucial for the evaluation of clustering algorithms using real-world data sets. This property can be quantified by separability measures. The central aspects of separability for density-based clustering are between-class separation and within-class connectedness, and neither classification-based complexity measures nor cluster validity indices (CVIs) adequately incorporate them. A newly developed measure (density cluster separability index, DCSI) aims to quantify these two characteristics and can also be used as a CVI. Extensive experiments on synthetic data indicate that DCSI correlates strongly with the performance of DBSCAN measured via the adjusted Rand index (ARI) but lacks robustness when it comes to multi-class data sets with overlapping classes that are ill-suited for density-based hard clustering. Detailed evaluation on frequently used real-world data sets shows that DCSI can correctly identify touching or overlapping classes that do not correspond to meaningful density-based clusters.
Authors: Jessica Ojo, Odunayo Ogundepo, Akintunde Oladipo, Kelechi Ogueji, Jimmy Lin, Pontus Stenetorp, David Ifeoluwa Adelani
Abstract: Large-scale multilingual evaluations, such as MEGA, often include only a handful of African languages due to the scarcity of high-quality evaluation data and the limited discoverability of existing African datasets. This lack of representation hinders comprehensive LLM evaluation across a diverse range of languages and tasks. To address these challenges, we introduce AfroBench -- a multi-task benchmark for evaluating the performance of LLMs across 64 African languages, 15 tasks and 22 datasets. AfroBench consists of nine natural language understanding datasets, six text generation datasets, six knowledge and question answering tasks, and one mathematical reasoning task. We present results comparing the performance of prompting LLMs to fine-tuned baselines based on BERT and T5-style models. Our results suggest large gaps in performance between high-resource languages, such as English, and African languages across most tasks; but performance also varies based on the availability of monolingual data resources. Our findings confirm that performance on African languages continues to remain a hurdle for current LLMs, underscoring the need for additional efforts to close this gap. https://mcgill-nlp.github.io/AfroBench/
Authors: Rahul Yedida, Tim Menzies
Abstract: Yes. SE data can have "smoother" boundaries between classes (compared to traditional AI data sets). To be more precise, the magnitude of the second derivative of the loss function found in SE data is typically much smaller. A new hyper-parameter optimizer, called SMOOTHIE, can exploit this idiosyncrasy of SE data. We compare SMOOTHIE and a state-of-the-art AI hyper-parameter optimizer on three tasks: (a) GitHub issue lifetime prediction (b) detecting static code warnings false alarm; (c) defect prediction. For completeness, we also show experiments on some standard AI datasets. SMOOTHIE runs faster and predicts better on the SE data--but ties on non-SE data with the AI tool. Hence we conclude that SE data can be different to other kinds of data; and those differences mean that we should use different kinds of algorithms for our data. To support open science and other researchers working in this area, all our scripts and datasets are available on-line at https://github.com/yrahul3910/smoothness-hpo/.
Authors: Xuandong Zhao, Lei Li, Yu-Xiang Wang
Abstract: In this paper, we propose a new decoding method called Permute-and-Flip (PF) decoder. It enjoys stability properties similar to the standard sampling decoder, but is provably up to 2x better in its quality-stability tradeoff than sampling and never worse than any other decoder. We also design a cryptographic watermarking scheme analogous to Aaronson (2023)'s Gumbel watermark, but naturally tailored for PF decoder. The watermarking scheme does not change the distribution to sample, while allowing arbitrarily low false positive rate and high recall whenever the generated text has high entropy. Our experiments show that the PF decoder (and its watermarked counterpart) significantly outperform(s) naive sampling (and its Gumbel watermarked counterpart) in terms of perplexity, while retaining the same stability (and detectability), hence making it a promising new approach for LLM decoding. The code is available at https://github.com/XuandongZhao/pf-decoding
Authors: Yang Li, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao, Yangyang Shi, Vikas Chandra
Abstract: Power consumption plays a crucial role in on-device streaming speech recognition, significantly influencing the user experience. This study explores how the configuration of weight parameters in speech recognition models affects their overall energy efficiency. We found that the influence of these parameters on power consumption varies depending on factors such as invocation frequency and memory allocation. Leveraging these insights, we propose design principles that enhance on-device speech recognition models by reducing power consumption with minimal impact on accuracy. Our approach, which adjusts model components based on their specific energy sensitivities, achieves up to 47% lower energy usage while preserving comparable model accuracy and improving real-time performance compared to leading methods.
Authors: Wei Chen, Zichen Miao, Qiang Qiu
Abstract: Efficient fine-tuning methods are critical to address the high computational and parameter complexity while adapting large pre-trained models to downstream tasks. Our study is inspired by prior research that represents each convolution filter as a linear combination of a small set of filter subspace elements, referred to as filter atoms. In this paper, we propose to fine-tune pre-trained models by adjusting only filter atoms, which are responsible for spatial-only convolution, while preserving spatially-invariant channel combination knowledge in atom coefficients. In this way, we bring a new filter subspace view for model tuning. Furthermore, each filter atom can be recursively decomposed as a combination of another set of atoms, which naturally expands the number of tunable parameters in the filter subspace. By only adapting filter atoms constructed by a small number of parameters, while maintaining the rest of model parameters constant, the proposed approach is highly parameter-efficient. It effectively preserves the capabilities of pre-trained models and prevents overfitting to downstream tasks. Extensive experiments show that such a simple scheme surpasses previous tuning baselines for both discriminate and generative tasks.
Authors: Philipp Hess, Michael Aich, Baoxiang Pan, Niklas Boers
Abstract: Accurate and high-resolution Earth system model (ESM) simulations are essential to assess the ecological and socio-economic impacts of anthropogenic climate change, but are computationally too expensive to be run at sufficiently high spatial resolution. Recent machine learning approaches have shown promising results in downscaling ESM simulations, outperforming state-of-the-art statistical approaches. However, existing methods require computationally costly retraining for each ESM and extrapolate poorly to climates unseen during training. We address these shortcomings by learning a consistency model (CM) that efficiently and accurately downscales arbitrary ESM simulations without retraining in a zero-shot manner. Our approach yields probabilistic downscaled fields at a resolution only limited by the observational reference data. We show that the CM outperforms state-of-the-art diffusion models at a fraction of computational cost while maintaining high controllability on the downscaling task. Further, our method generalizes to climate states unseen during training without explicitly formulated physical constraints.
Authors: Yun Wang, Chrysanthi Kosyfaki, Sihem Amer-Yahia, Reynold Cheng
Abstract: Hypothesis testing is a statistical method used to draw conclusions about populations from sample data, typically represented in tables. With the prevalence of graph representations in real-life applications, hypothesis testing in graphs is gaining importance. In this work, we formalize node, edge, and path hypotheses in attributed graphs. We develop a sampling-based hypothesis testing framework, which can accommodate existing hypothesis-agnostic graph sampling methods. To achieve accurate and efficient sampling, we then propose a Path-Hypothesis-Aware SamplEr, PHASE, an m- dimensional random walk that accounts for the paths specified in a hypothesis. We further optimize its time efficiency and propose PHASEopt. Experiments on real datasets demonstrate the ability of our framework to leverage common graph sampling methods for hypothesis testing, and the superiority of hypothesis-aware sampling in terms of accuracy and time efficiency.
Authors: Yan Yang, Bin Gao, Ya-xiang Yuan
Abstract: Bilevel optimization, with broad applications in machine learning, has an intricate hierarchical structure. Gradient-based methods have emerged as a common approach to large-scale bilevel problems. However, the computation of the hyper-gradient, which involves a Hessian inverse vector product, confines the efficiency and is regarded as a bottleneck. To circumvent the inverse, we construct a sequence of low-dimensional approximate Krylov subspaces with the aid of the Lanczos process. As a result, the constructed subspace is able to dynamically and incrementally approximate the Hessian inverse vector product with less effort and thus leads to a favorable estimate of the hyper-gradient. Moreover, we propose a provable subspace-based framework for bilevel problems where one central step is to solve a small-size tridiagonal linear system. To the best of our knowledge, this is the first time that subspace techniques are incorporated into bilevel optimization. This successful trial not only enjoys $\mathcal{O}(\epsilon^{-1})$ convergence rate but also demonstrates efficiency in a synthetic problem and two deep learning tasks.
Authors: K. Aditya Mohan, Massimiliano Ferrucci, Chuck Divin, Garrett A. Stevenson, Hyojin Kim
Abstract: 4D time-space reconstruction of dynamic events or deforming objects using X-ray computed tomography (CT) is an important inverse problem in non-destructive evaluation. Conventional back-projection based reconstruction methods assume that the object remains static for the duration of several tens or hundreds of X-ray projection measurement images (reconstruction of consecutive limited-angle CT scans). However, this is an unrealistic assumption for many in-situ experiments that causes spurious artifacts and inaccurate morphological reconstructions of the object. To solve this problem, we propose to perform a 4D time-space reconstruction using a distributed implicit neural representation (DINR) network that is trained using a novel distributed stochastic training algorithm. Our DINR network learns to reconstruct the object at its output by iterative optimization of its network parameters such that the measured projection images best match the output of the CT forward measurement model. We use a forward measurement model that is a function of the DINR outputs at a sparsely sampled set of continuous valued 4D object coordinates. Unlike previous neural representation architectures that forward and back propagate through dense voxel grids that sample the object's entire time-space coordinates, we only propagate through the DINR at a small subset of object coordinates in each iteration resulting in an order-of-magnitude reduction in memory and compute for training. DINR leverages distributed computation across several compute nodes and GPUs to produce high-fidelity 4D time-space reconstructions. We use both simulated parallel-beam and experimental cone-beam X-ray CT datasets to demonstrate the superior performance of our approach.
Authors: Xin Ding, Yongwei Wang, Kao Zhang, Z. Jane Wang
Abstract: Continuous Conditional Generative Modeling (CCGM) estimates high-dimensional data distributions, such as images, conditioned on scalar continuous variables (aka regression labels). While Continuous Conditional Generative Adversarial Networks (CcGANs) were designed for this task, their instability during adversarial learning often leads to suboptimal results. Conditional Diffusion Models (CDMs) offer a promising alternative, generating more realistic images, but their diffusion processes, label conditioning, and model fitting procedures are either not optimized for or incompatible with CCGM, making it difficult to integrate CcGANs' vicinal approach. To address these issues, we introduce Continuous Conditional Diffusion Models (CCDMs), the first CDM specifically tailored for CCGM. CCDMs address existing limitations with specially designed conditional diffusion processes, a novel hard vicinal image denoising loss, a customized label embedding method, and efficient conditional sampling procedures. Through comprehensive experiments on four datasets with resolutions ranging from 64x64 to 192x192, we demonstrate that CCDMs outperform state-of-the-art CCGM models, establishing a new benchmark. Ablation studies further validate the model design and implementation, highlighting that some widely used CDM implementations are ineffective for the CCGM task. Our code is publicly available at https://github.com/UBCDingXin/CCDM.
Authors: Nicola Bariletto, Khai Nguyen, Nhat Ho
Abstract: We develop an analytical synthesis that bridges data-driven Distributionally Robust Optimization (DRO) and Economic Decision Theory under Ambiguity (DTA). By reinterpreting standard regularization and DRO techniques as data-driven counterparts of ambiguity-averse decision models, we provide a unified framework that clarifies their intrinsic connections. Building on this synthesis, we propose a novel DRO approach that leverages a popular DTA model of smooth ambiguity-averse preferences together with tools from Bayesian nonparametric statistics. Our baseline framework employs Dirichlet Process (DP) posteriors, which naturally extend to heterogeneous data sources via Hierarchical Dirichlet Processes (HDPs), and can be further refined to induce outlier robustness through a procedure that selectively filters poorly-fitting observations during training. Theoretical performance guarantees and convergence results, together with extensive simulations and real-data experiments, illustrate the method's favorable performance in terms of prediction accuracy and stability.
Authors: Ruijian Han, Lan Luo, Yuanhang Luo, Yuanyuan Lin, Jian Huang
Abstract: Online statistical inference facilitates real-time analysis of sequentially collected data, making it different from traditional methods that rely on static datasets. This paper introduces a novel approach to online inference in high-dimensional generalized linear models, where we update regression coefficient estimates and their standard errors upon each new data arrival. In contrast to existing methods that either require full dataset access or large-dimensional summary statistics storage, our method operates in a single-pass mode, significantly reducing both time and space complexity. The core of our methodological innovation lies in an adaptive stochastic gradient descent algorithm tailored for dynamic objective functions, coupled with a novel online debiasing procedure. This allows us to maintain low-dimensional summary statistics while effectively controlling the optimization error introduced by the dynamically changing loss functions. We establish the asymptotic normality of our proposed Adaptive Debiased Lasso (ADL) estimator. We conduct extensive simulation experiments to show the statistical validity and computational efficiency of our ADL estimator across various settings. Its computational efficiency is further demonstrated via a real data application to the spam email classification.
Authors: Yinghao Zhu, Changyu Ren, Zixiang Wang, Xiaochen Zheng, Shiyun Xie, Junlan Feng, Xi Zhu, Zhoujun Li, Liantao Ma, Chengwei Pan
Abstract: The integration of multimodal Electronic Health Records (EHR) data has significantly advanced clinical predictive capabilities. Existing models, which utilize clinical notes and multivariate time-series EHR data, often fall short of incorporating the necessary medical context for accurate clinical tasks, while previous approaches with knowledge graphs (KGs) primarily focus on structured knowledge extraction. In response, we propose EMERGE, a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR predictive modeling. We extract entities from both time-series data and clinical notes by prompting Large Language Models (LLMs) and align them with professional PrimeKG, ensuring consistency. In addition to triplet relationships, we incorporate entities' definitions and descriptions for richer semantics. The extracted knowledge is then used to generate task-relevant summaries of patients' health statuses. Finally, we fuse the summary with other modalities using an adaptive multimodal fusion network with cross-attention. Extensive experiments on the MIMIC-III and MIMIC-IV datasets' in-hospital mortality and 30-day readmission tasks demonstrate the superior performance of the EMERGE framework over baseline models. Comprehensive ablation studies and analysis highlight the efficacy of each designed module and robustness to data sparsity. EMERGE contributes to refining the utilization of multimodal EHR data in healthcare, bridging the gap with nuanced medical contexts essential for informed clinical predictions. We have publicly released the code at https://github.com/yhzhu99/EMERGE.
Authors: Daniel Hothem, Ashe Miller, Timothy Proctor
Abstract: Quantum computers have the potential to revolutionize diverse fields, including quantum chemistry, materials science, and machine learning. However, contemporary quantum computers experience errors that often cause quantum programs run on them to fail. Until quantum computers can reliably execute large quantum programs, stakeholders will need fast and reliable methods for assessing a quantum computer's capability-i.e., the programs it can run and how well it can run them. Previously, off-the-shelf neural network architectures have been used to model quantum computers' capabilities, but with limited success, because these networks fail to learn the complex quantum physics that determines real quantum computers' errors. We address this shortcoming with a new quantum-physics-aware neural network architecture for learning capability models. Our architecture combines aspects of graph neural networks with efficient approximations to the physics of errors in quantum programs. This approach achieves up to $\sim50\%$ reductions in mean absolute error on both experimental and simulated data, over state-of-the-art models based on convolutional neural networks.
Authors: Huma Ameer, Seemab Latif, Mehwish Fatima
Abstract: The automated classification of stuttered speech has significant implications for timely assessments providing assistance to speech language pathologists. Despite notable advancements in the field, the cases in which multiple disfluencies occur in speech require attention. We have taken a progressive approach to fill this gap by classifying multi-stuttered speech more efficiently. The problem has been addressed by firstly curating a dataset of multi-stuttered disfluencies from open source dataset SEP-28k audio clips. Secondly, employing Whisper, a state-of-the-art speech recognition model has been leveraged by using its encoder and taking the problem as multi label classification. Thirdly, using a 6 encoder layer Whisper and experimenting with various layer freezing strategies, a computationally efficient configuration of the model was identified. The proposed configuration achieved micro, macro, and weighted F1-scores of 0.88, 0.85, and 0.87, correspondingly on an external test dataset i.e. Fluency-Bank. In addition, through layer freezing strategies, we were able to achieve the aforementioned results by fine-tuning a single encoder layer, consequently, reducing the model's trainable parameters from 20.27 million to 3.29 million. This research study unveils the contribution of the last encoder layer in the identification of disfluencies in stuttered speech. Consequently, it has led to a computationally efficient approach, 83.7% less parameters to train, making the proposed approach more adaptable for various dialects and languages.
Authors: Harald Semmelrock, Tony Ross-Hellauer, Simone Kopeinik, Dieter Theiler, Armin Haberl, Stefan Thalmann, Dominik Kowald
Abstract: Many research fields are currently reckoning with issues of poor levels of reproducibility. Some label it a "crisis", and research employing or building Machine Learning (ML) models is no exception. Issues including lack of transparency, data or code, poor adherence to standards, and the sensitivity of ML training conditions mean that many papers are not even reproducible in principle. Where they are, though, reproducibility experiments have found worryingly low degrees of similarity with original results. Despite previous appeals from ML researchers on this topic and various initiatives from conference reproducibility tracks to the ACM's new Emerging Interest Group on Reproducibility and Replicability, we contend that the general community continues to take this issue too lightly. Poor reproducibility threatens trust in and integrity of research results. Therefore, in this article, we lay out a new perspective on the key barriers and drivers (both procedural and technical) to increased reproducibility at various levels (methods, code, data, and experiments). We then map the drivers to the barriers to give concrete advice for strategies for researchers to mitigate reproducibility issues in their own work, to lay out key areas where further research is needed in specific areas, and to further ignite discussion on the threat presented by these urgent issues.
Authors: Ryan P. Ringel, Zachary S. Charlick, Jiaxun Liu, Boxi Xia, Boyuan Chen
Abstract: Robot design has traditionally been costly and labor-intensive. Despite advancements in automated processes, it remains challenging to navigate a vast design space while producing physically manufacturable robots. We introduce Text2Robot, a framework that converts user text specifications and performance preferences into physical quadrupedal robots. Within minutes, Text2Robot can use text-to-3D models to provide strong initializations of diverse morphologies. Within a day, our geometric processing algorithms and body-control co-optimization produce a walking robot by explicitly considering real-world electronics and manufacturability. Text2Robot enables rapid prototyping and opens new opportunities for robot design with generative models.
Authors: Catherine Tony, Nicol\'as E. D\'iaz Ferreyra, Markus Mutas, Salem Dhiff, Riccardo Scandariato
Abstract: Large Language Models (LLMs) are gaining momentum in software development with prompt-driven programming enabling developers to create code from natural language (NL) instructions. However, studies have questioned their ability to produce secure code and, thereby, the quality of prompt-generated software. Alongside, various prompting techniques that carefully tailor prompts have emerged to elicit optimal responses from LLMs. Still, the interplay between such prompting strategies and secure code generation remains under-explored and calls for further investigations. OBJECTIVE: In this study, we investigate the impact of different prompting techniques on the security of code generated from NL instructions by LLMs. METHOD: First we perform a systematic literature review to identify the existing prompting techniques that can be used for code generation tasks. A subset of these techniques are evaluated on GPT-3, GPT-3.5, and GPT-4 models for secure code generation. For this, we used an existing dataset consisting of 150 NL security-relevant code-generation prompts. RESULTS: Our work (i) classifies potential prompting techniques for code generation (ii) adapts and evaluates a subset of the identified techniques for secure code generation tasks and (iii) observes a reduction in security weaknesses across the tested LLMs, especially after using an existing technique called Recursive Criticism and Improvement (RCI), contributing valuable insights to the ongoing discourse on LLM-generated code security.
Authors: Joe Suk
Abstract: We study a $K$-armed non-stationary bandit model where rewards change smoothly, as captured by H\"{o}lder class assumptions on rewards as functions of time. Such smooth changes are parametrized by a H\"{o}lder exponent $\beta$ and coefficient $\lambda$. While various sub-cases of this general model have been studied in isolation, we first establish the minimax dynamic regret rate generally for all $K,\beta,\lambda$. Next, we show this optimal dynamic regret can be attained adaptively, without knowledge of $\beta,\lambda$. To contrast, even with parameter knowledge, upper bounds were only previously known for limited regimes $\beta\leq 1$ and $\beta=2$ (Slivkins, 2014; Krishnamurthy and Gopalan, 2021; Manegueu et al., 2021; Jia et al.,2023). Thus, our work resolves open questions raised by these disparate threads of the literature. We also study the problem of attaining faster gap-dependent regret rates in non-stationary bandits. While such rates are long known to be impossible in general (Garivier and Moulines, 2011), we show that environments admitting a safe arm (Suk and Kpotufe, 2022) allow for much faster rates than the worst-case scaling with $\sqrt{T}$. While previous works in this direction focused on attaining the usual logarithmic regret bounds, as summed over stationary periods, our new gap-dependent rates reveal new optimistic regimes of non-stationarity where even the logarithmic bounds are pessimistic. We show our new gap-dependent rate is tight and that its achievability (i.e., as made possible by a safe arm) has a surprisingly simple and clean characterization within the smooth H\"{o}lder class model.
Authors: Erell Gachon, J\'er\'emie Bigot, Elsa Cazelles, Audrey Bidet, Jean-Philippe Vial, Pierre-Yves Dumas, Aguirre Mimoun
Abstract: Representing and quantifying Minimal Residual Disease (MRD) in Acute Myeloid Leukemia (AML), a type of cancer that affects the blood and bone marrow, is essential in the prognosis and follow-up of AML patients. As traditional cytological analysis cannot detect leukemia cells below 5\%, the analysis of flow cytometry dataset is expected to provide more reliable results. In this paper, we explore statistical learning methods based on optimal transport (OT) to achieve a relevant low-dimensional representation of multi-patient flow cytometry measurements (FCM) datasets considered as high-dimensional probability distributions. Using the framework of OT, we justify the use of the K-means algorithm for dimensionality reduction of multiple large-scale point clouds through mean measure quantization by merging all the data into a single point cloud. After this quantization step, the visualization of the intra and inter-patients FCM variability is carried out by embedding low-dimensional quantized probability measures into a linear space using either Wasserstein Principal Component Analysis (PCA) through linearized OT or log-ratio PCA of compositional data. Using a publicly available FCM dataset and a FCM dataset from Bordeaux University Hospital, we demonstrate the benefits of our approach over the popular kernel mean embedding technique for statistical learning from multiple high-dimensional probability distributions. We also highlight the usefulness of our methodology for low-dimensional projection and clustering patient measurements according to their level of MRD in AML from FCM. In particular, our OT-based approach allows a relevant and informative two-dimensional representation of the results of the FlowSom algorithm, a state-of-the-art method for the detection of MRD in AML using multi-patient FCM.
Authors: Gaole Dai, Chun-Kai Fan, Yiming Tang, Zhi Zhang, Yuan Zhang, Yulu Gan, Qizhe Zhang, Cheng-Ching Tseng, Shanghang Zhang, Tiejun Huang
Abstract: Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces. Starting from drawing insights from Neural Engrams (NE) in Biological Neural Networks (BNNs), we establish a connection between the low-rank property observed during PEFT's parameter space shifting and neurobiological mechanisms. This observation leads to our proposed method, Synapse and Neuron (SAN), which decomposes and propagates scaling components from anterior feature adjusting vectors towards posterior weight matrices. Our approach is theoretically grounded in Long-Term Potentiation/Depression (LTP/D) phenomena, which govern synapse development through neurotransmitter release modulation. Extensive experiments demonstrate its effectiveness: on \textbf{vision tasks} across VTAB, FGVC, and GIC (25 datasets) using ViT, SwinT and ConvNeXt, SAN outperforms FFT up to 8.7% and LoRA by 3.2%; on language tasks using Commonsense Reasoning (8 datasets) with LLaMA models (all generations), surpassing ChatGPT up to 8.5% and LoRA by 4.7%; on visual-language tasks using Mixed Visual Instruction (7 datasets) with LLaVA models, it exceeds FFT up to 2.4% and LoRA by 1.9%. Our code and W&B log will be released.
Authors: Yi-Chia Chang, Adam J. Stewart, Favyen Bastani, Piper Wolters, Shreya Kannan, George R. Huber, Jingtong Wang, Arindam Banerjee
Abstract: Foundation models pre-trained using self-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, including language understanding, text generation, and image recognition. The Earth observation (EO) field has produced several foundation models pre-trained directly on multispectral satellite imagery for applications like precision agriculture, wildfire and drought monitoring, and natural disaster response. However, few studies have investigated the ability of these models to generalize to new geographic locations, and potential concerns of geospatial bias -- models trained on data-rich developed nations not transferring well to data-scarce developing nations -- remain. We investigate the ability of popular EO foundation models to transfer to new geographic regions in the agricultural domain, where differences in farming practices and class imbalance make transfer learning particularly challenging. We first select five crop classification datasets across five continents, normalizing for dataset size and harmonizing classes to focus on four major cereal grains: maize, soybean, rice, and wheat. We then compare three popular foundation models, pre-trained on SSL4EO-S12, SatlasPretrain, and ImageNet, using in-distribution (ID) and out-of-distribution (OOD) evaluation. Experiments show that pre-trained weights designed explicitly for Sentinel-2, such as SSL4EO-S12, outperform general pre-trained weights like ImageNet. Furthermore, while only 100 labeled images are sufficient for achieving high overall accuracy, 900 images are required to achieve high average accuracy due to class imbalance. All harmonized datasets and experimental code are open-source and available for download.
Authors: Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu
Abstract: Small language models (SLMs), despite their widespread adoption in modern smart devices, have received significantly less academic attention compared to their large language model (LLM) counterparts, which are predominantly deployed in data centers and cloud environments. While researchers continue to improve the capabilities of LLMs in the pursuit of artificial general intelligence, SLM research aims to make machine intelligence more accessible, affordable, and efficient for everyday tasks. Focusing on transformer-based, decoder-only language models with 100M-5B parameters, we survey 70 state-of-the-art open-source SLMs, analyzing their technical innovations across three axes: architectures, training datasets, and training algorithms. In addition, we evaluate their capabilities in various domains, including commonsense reasoning, mathematics, in-context learning, and long context. To gain further insight into their on-device runtime costs, we benchmark their inference latency and memory footprints. Through in-depth analysis of our benchmarking data, we offer valuable insights to advance research in this field.
Authors: Fabrizio Maturo, Annamaria Porreca
Abstract: The positioning of this research falls within the scalar-on-function classification literature, a field of significant interest across various domains, particularly in statistics, mathematics, and computer science. This study introduces an advanced methodology for supervised classification by integrating Functional Data Analysis (FDA) with tree-based ensemble techniques for classifying high-dimensional time series. The proposed framework, Enriched Functional Tree-Based Classifiers (EFTCs), leverages derivative and geometric features, benefiting from the diversity inherent in ensemble methods to further enhance predictive performance and reduce variance. While our approach has been tested on the enrichment of Functional Classification Trees (FCTs), Functional K-NN (FKNN), Functional Random Forest (FRF), Functional XGBoost (FXGB), and Functional LightGBM (FLGBM), it could be extended to other tree-based and non-tree-based classifiers, with appropriate considerations emerging from this investigation. Through extensive experimental evaluations on seven real-world datasets and six simulated scenarios, this proposal demonstrates fascinating improvements over traditional approaches, providing new insights into the application of FDA in complex, high-dimensional learning problems.
Authors: Zhengran Ji, Lingyu Zhang, Paul Sajda, Boyuan Chen
Abstract: Learning collaborative behaviors is essential for multi-agent systems. Traditionally, multi-agent reinforcement learning solves this implicitly through a joint reward and centralized observations, assuming collaborative behavior will emerge. Other studies propose to learn from demonstrations of a group of collaborative experts. Instead, we propose an efficient and explicit way of learning collaborative behaviors in multi-agent systems by leveraging expertise from only a single human. Our insight is that humans can naturally take on various roles in a team. We show that agents can effectively learn to collaborate by allowing a human operator to dynamically switch between controlling agents for a short period and incorporating a human-like theory-of-mind model of teammates. Our experiments showed that our method improves the success rate of a challenging collaborative hide-and-seek task by up to 58% with only 40 minutes of human guidance. We further demonstrate our findings transfer to the real world by conducting multi-robot experiments.
Authors: Kianusch Vahid Yousefnia, Christoph Metzl, Tobias B\"olle
Abstract: Thunderstorms have significant social and economic impacts due to heavy precipitation, hail, lightning, and strong winds, necessitating reliable forecasts. Thunderstorm forecasts based on numerical weather prediction (NWP) often rely on single-level surrogate predictors, like convective available potential energy and convective inhibition, derived from vertical profiles of three-dimensional atmospheric variables. In this study, we develop SALAMA 1D, a deep neural network which directly infers the probability of thunderstorm occurrence from vertical profiles of ten atmospheric variables, bypassing single-level predictors. By training the model on convection-permitting NWP forecasts, we allow SALAMA 1D to flexibly identify convective patterns, with the goal of enhancing forecast accuracy. The model's architecture is physically motivated: sparse connections encourage interactions at similar height levels while keeping model size and inference times computationally efficient, whereas a shuffling mechanism prevents the model from learning non-physical patterns tied to the vertical grid. SALAMA 1D is trained over Central Europe with lightning observations as the ground truth. Comparative analysis against a baseline machine learning model that uses single-level predictors shows SALAMA 1D's superior skill across various metrics and lead times of up to at least 11 hours. Moreover, expanding the archive of forecasts from which training examples are sampled improves skill, even when training set size remains constant. Finally, a sensitivity analysis using saliency maps indicates that our model relies on physically interpretable patterns consistent with established theoretical understanding, primarily focusing on convection initiation and refining its skill by checking for ongoing convection in the NWP model.
Authors: Pierre Marion, Rapha\"el Berthier, G\'erard Biau, Claire Boyer
Abstract: Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the single-location regression task, where only one token in a sequence determines the output, and its position is a latent random variable, retrievable via a linear projection of the input. To solve this task, we propose a dedicated predictor, which turns out to be a simplified version of a non-linear self-attention layer. We study its theoretical properties, by showing its asymptotic Bayes optimality and analyzing its training dynamics. In particular, despite the non-convex nature of the problem, the predictor effectively learns the underlying structure. This work highlights the capacity of attention mechanisms to handle sparse token information and internal linear structures.
Authors: Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, Chenglin Wu
Abstract: Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code is available at https://github.com/geekan/MetaGPT.
Authors: Adam Polyak, Amit Zohar, Andrew Brown, Andros Tjandra, Animesh Sinha, Ann Lee, Apoorv Vyas, Bowen Shi, Chih-Yao Ma, Ching-Yao Chuang, David Yan, Dhruv Choudhary, Dingkang Wang, Geet Sethi, Guan Pang, Haoyu Ma, Ishan Misra, Ji Hou, Jialiang Wang, Kiran Jagadeesh, Kunpeng Li, Luxin Zhang, Mannat Singh, Mary Williamson, Matt Le, Matthew Yu, Mitesh Kumar Singh, Peizhao Zhang, Peter Vajda, Quentin Duval, Rohit Girdhar, Roshan Sumbaly, Sai Saketh Rambhatla, Sam Tsai, Samaneh Azadi, Samyak Datta, Sanyuan Chen, Sean Bell, Sharadh Ramaswamy, Shelly Sheynin, Siddharth Bhattacharya, Simran Motwani, Tao Xu, Tianhe Li, Tingbo Hou, Wei-Ning Hsu, Xi Yin, Xiaoliang Dai, Yaniv Taigman, Yaqiao Luo, Yen-Cheng Liu, Yi-Chiao Wu, Yue Zhao, Yuval Kirstain, Zecheng He, Zijian He, Albert Pumarola, Ali Thabet, Artsiom Sanakoyeu, Arun Mallya, Baishan Guo, Boris Araya, Breena Kerr, Carleigh Wood, Ce Liu, Cen Peng, Dimitry Vengertsev, Edgar Schonfeld, Elliot Blanchard, Felix Juefei-Xu, Fraylie Nord, Jeff Liang, John Hoffman, Jonas Kohler, Kaolin Fire, Karthik Sivakumar, Lawrence Chen, Licheng Yu, Luya Gao, Markos Georgopoulos, Rashel Moritz, Sara K. Sampson, Shikai Li, Simone Parmeggiani, Steve Fine, Tara Fowler, Vladan Petrovic, Yuming Du
Abstract: We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.
Authors: Yujun Zhou, Jingdong Yang, Yue Huang, Kehan Guo, Zoe Emory, Bikram Ghosh, Amita Bedar, Sujay Shekar, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang
Abstract: Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. While large language models (LLMs) increasingly assist in tasks ranging from procedural guidance to autonomous experiment orchestration, an "illusion of understanding" may lead researchers to overestimate their reliability. Such overreliance is especially hazardous in high-stakes laboratory settings, where failures in hazard identification or risk assessment can result in severe accidents. To address these concerns, we propose the Laboratory Safety Benchmark (LabSafety Bench), a comprehensive framework that evaluates LLMs and vision language models (VLMs) on their ability to identify potential hazards, assess risks, and predict the consequences of unsafe actions in lab environments. LabSafety Bench comprises 765 multiple-choice questions aligned with US Occupational Safety and Health Administration (OSHA) protocols, along with 520 realistic laboratory scenarios featuring dual evaluation tasks: the Hazards Identification Test and the Consequence Identification Test, with 4090 open-ended questions in total. Evaluations across eight proprietary models, seven open-weight LLMs, and four VLMs reveal that, despite advanced performance on structured assessments, no model achieves the safety threshold required for reliable operation. None scored above 75% on the Hazards Identification Test. Moreover, while proprietary models tend to excel in multiple-choice evaluations, their performance in open-ended, real-world scenario responses is comparable to that of open-source models. These findings underscore the urgent need for specialized evaluation frameworks to ensure the safe and responsible deployment of AI in laboratory settings.
Authors: Jiahan Li, Tong Chen, Shitong Luo, Chaoran Cheng, Jiaqi Guan, Ruihan Guo, Sheng Wang, Ge Liu, Jian Peng, Jianzhu Ma
Abstract: Peptides, short chains of amino acids, interact with target proteins, making them a unique class of protein-based therapeutics for treating human diseases. Recently, deep generative models have shown great promise in peptide generation. However, several challenges remain in designing effective peptide binders. First, not all residues contribute equally to peptide-target interactions. Second, the generated peptides must adopt valid geometries due to the constraints of peptide bonds. Third, realistic tasks for peptide drug development are still lacking. To address these challenges, we introduce PepHAR, a hot-spot-driven autoregressive generative model for designing peptides targeting specific proteins. Building on the observation that certain hot spot residues have higher interaction potentials, we first use an energy-based density model to fit and sample these key residues. Next, to ensure proper peptide geometry, we autoregressively extend peptide fragments by estimating dihedral angles between residue frames. Finally, we apply an optimization process to iteratively refine fragment assembly, ensuring correct peptide structures. By combining hot spot sampling with fragment-based extension, our approach enables de novo peptide design tailored to a target protein and allows the incorporation of key hot spot residues into peptide scaffolds. Extensive experiments, including peptide design and peptide scaffold generation, demonstrate the strong potential of PepHAR in computational peptide binder design. Source code will be available at https://github.com/Ced3-han/PepHAR.
Authors: Timur Galimzyanov, Sergey Titov, Yaroslav Golubev, Egor Bogomolov
Abstract: This paper introduces the human-curated PandasPlotBench dataset, designed to evaluate language models' effectiveness as assistants in visual data exploration. Our benchmark focuses on generating code for visualizing tabular data - such as a Pandas DataFrame - based on natural language instructions, complementing current evaluation tools and expanding their scope. The dataset includes 175 unique tasks. Our experiments assess several leading Large Language Models (LLMs) across three visualization libraries: Matplotlib, Seaborn, and Plotly. We show that the shortening of tasks has a minimal effect on plotting capabilities, allowing for the user interface that accommodates concise user input without sacrificing functionality or accuracy. Another of our findings reveals that while LLMs perform well with popular libraries like Matplotlib and Seaborn, challenges persist with Plotly, highlighting areas for improvement. We hope that the modular design of our benchmark will broaden the current studies on generating visualizations. Our dataset and benchmark code are available online: https://huggingface.co/datasets/JetBrains-Research/PandasPlotBench; https://github.com/JetBrains-Research/PandasPlotBench.
URLs: https://huggingface.co/datasets/JetBrains-Research/PandasPlotBench;, https://github.com/JetBrains-Research/PandasPlotBench.
Authors: Sepehr Dehdashtian, Gautam Sreekumar, Vishnu Naresh Boddeti
Abstract: Images generated by text-to-image (T2I) models often exhibit visual biases and stereotypes of concepts such as culture and profession. Existing quantitative measures of stereotypes are based on statistical parity that does not align with the sociological definition of stereotypes and, therefore, incorrectly categorizes biases as stereotypes. Instead of oversimplifying stereotypes as biases, we propose a quantitative measure of stereotypes that aligns with its sociological definition. We then propose OASIS to measure the stereotypes in a generated dataset and understand their origins within the T2I model. OASIS includes two scores to measure stereotypes from a generated image dataset: (M1) Stereotype Score to measure the distributional violation of stereotypical attributes, and (M2) WALS to measure spectral variance in the images along a stereotypical attribute. OASIS also includes two methods to understand the origins of stereotypes in T2I models: (U1) StOP to discover attributes that the T2I model internally associates with a given concept, and (U2) SPI to quantify the emergence of stereotypical attributes in the latent space of the T2I model during image generation. Despite the considerable progress in image fidelity, using OASIS, we conclude that newer T2I models such as FLUX.1 and SDv3 contain strong stereotypical predispositions about concepts and still generate images with widespread stereotypical attributes. Additionally, the quantity of stereotypes worsens for nationalities with lower Internet footprints.
Authors: Ping Yu, Weizhe Yuan, Olga Golovneva, Tianhao Wu, Sainbayar Sukhbaatar, Jason Weston, Jing Xu
Abstract: Training data quality is one of the most important drivers of final model quality. In this work, we introduce a method for evaluating data integrity based on the assumption that low-quality input prompts result in high variance and low quality responses. This is achieved by measuring the rejected response quality and the reward gap between the chosen and rejected preference pair. Our method, Rejecting Instruction Preferences (RIP) can be used to filter prompts from existing training sets, or to make high quality synthetic datasets, yielding large performance gains across various benchmarks compared to unfiltered data. Using Llama 3.1-8B-Instruct, RIP improves AlpacaEval2 LC Win Rate by 9.4%, Arena-Hard by 8.7%, and WildBench by 9.9%. Using Llama 3.3-70B-Instruct, RIP improves Arena-Hard from 67.5 to 82.9, which is from 18th place to 6th overall in the leaderboard.
Authors: Archiki Prasad, Elias Stengel-Eskin, Justin Chih-Yao Chen, Zaid Khan, Mohit Bansal
Abstract: Unit tests (UTs) play an instrumental role in assessing code correctness as well as providing feedback to large language models (LLMs), motivating automated test generation. However, we uncover a trade-off between generating unit test inputs that reveal errors when given a faulty code and correctly predicting the unit test output without access to the gold solution. To address this trade-off, we propose UTGen, which teaches LLMs to generate unit test inputs that reveal errors along with their correct expected outputs based on task descriptions. Since model-generated tests can provide noisy signals (e.g., from incorrectly predicted outputs), we propose UTDebug that (i) scales UTGen via test-time compute to improve UT output prediction, and (ii) validates and backtracks edits based on multiple generated UTs to avoid overfitting, and helps LLMs debug effectively. We show that UTGen outperforms other LLM-based baselines by 7.59% based on a metric measuring the presence of both error-revealing UT inputs and correct UT outputs. When used with UTDebug, we find that feedback from UTGen's unit tests improves pass@1 accuracy of Qwen2.5 32B on HumanEvalFix and our own harder debugging split of MBPP+ by over 3.17% and 12.35% (respectively) over other LLM-based UT generation baselines. Lastly, we demonstrate that UTGen is a better judge for code correctness, outperforming a state-of-the-art trained 8B reward model by 4.43% on HumanEval+ with best-of-10 sampling using Qwen2.5 7B.
Authors: Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Chen Chen, Lei Chen, Xianzhi Yu, Wulong Liu, Jianye Hao, Mingxuan Yuan, Bin Li
Abstract: With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods identify critical KV tokens through heuristic ranking with attention scores. However, these methods often struggle to accurately determine critical tokens as they neglect the \textit{temporal patterns} in attention scores, resulting in a noticeable degradation in LLM performance. To address this challenge, we propose AttentionPredictor, which is the first learning-based critical token identification approach. Specifically, AttentionPredictor learns a lightweight convolution model to capture spatiotemporal patterns and predict the next-token attention score. An appealing feature of AttentionPredictor is that it accurately predicts the attention score while consuming negligible memory. Moreover, we propose a cross-token critical cache prefetching framework that hides the token estimation time overhead to accelerate the decoding stage. By retaining most of the attention information, AttentionPredictor achieves 16$\times$ KV cache compression with comparable LLM performance, significantly outperforming the state-of-the-art.
Authors: Minseok Jung (May), Cynthia Fuertes Panizo (May), Liam Dugan (May), Yi R. (May), Fung, Pin-Yu Chen, Paul Pu Liang
Abstract: The advancement of large language models (LLMs) has made it difficult to differentiate human-written text from AI-generated text. Several AI-text detectors have been developed in response, which typically utilize a fixed global threshold (e.g., {\theta} = 0.5) to classify machine-generated text. However, we find that one universal threshold can fail to account for subgroup-specific distributional variations. For example, when using a fixed threshold, detectors make more false positive errors on shorter human-written text than longer, and more positive classifications on neurotic writing styles than open among long text. These discrepancies can lead to misclassification that disproportionately affects certain groups. We address this critical limitation by introducing FairOPT, an algorithm for group-specific threshold optimization in AI-generated content classifiers. Our approach partitions data into subgroups based on attributes (e.g., text length and writing style) and learns decision thresholds for each group, which enables careful balancing of performance and fairness metrics within each subgroup. In experiments with four AI text classifiers on three datasets, FairOPT enhances overall F1 score and decreases balanced error rate (BER) discrepancy across subgroups. Our framework paves the way for more robust and fair classification criteria in AI-generated output detection.
Authors: Tansheng Zhu, Hongyu Zhou, Ke Jin, Xusheng Xu, Qiufan Yuan, Lijie Ji
Abstract: Bayesian optimization is highly effective for optimizing expensive-to-evaluate black-box functions, but it faces significant computational challenges due to the high computational complexity of Gaussian processes, which results in a total time complexity that is quartic with respect to the number of iterations. To address this limitation, we propose the Bayesian Optimization by Kernel regression and density-based Exploration (BOKE) algorithm. BOKE uses kernel regression for efficient function approximation, kernel density for exploration, and integrates them into the confidence bound criteria to guide the optimization process, thus reducing computational costs to quadratic. Our theoretical analysis rigorously establishes the global convergence of BOKE and ensures its robustness in noisy settings. Through extensive numerical experiments on both synthetic and real-world optimization tasks, we demonstrate that BOKE not only performs competitively compared to Gaussian process-based methods but also exhibits superior computational efficiency. These results highlight BOKE's effectiveness in resource-constrained environments, providing a practical approach for optimization problems in engineering applications.
Authors: Yongqi An, Xu Zhao, Tao Yu, Ming Tang, Jinqiao Wang
Abstract: Outliers have been widely observed in Large Language Models (LLMs), significantly impacting model performance and posing challenges for model compression. Understanding the functionality and formation mechanisms of these outliers is critically important. Existing works, however, largely focus on reducing the impact of outliers from an algorithmic perspective, lacking an in-depth investigation into their causes and roles. In this work, we provide a detailed analysis of the formation process, underlying causes, and functions of outliers in LLMs. We define and categorize three types of outliers-activation outliers, weight outliers, and attention outliers-and analyze their distributions across different dimensions, uncovering inherent connections between their occurrences and their ultimate influence on the attention mechanism. Based on these observations, we hypothesize and explore the mechanisms by which these outliers arise and function, demonstrating through theoretical derivations and experiments that they emerge due to the self-attention mechanism's softmax operation. These outliers act as implicit context-aware scaling factors within the attention mechanism. As these outliers stem from systematic influences, we term them systematic outliers. Our study not only enhances the understanding of Transformer-based LLMs but also shows that structurally eliminating outliers can accelerate convergence and improve model compression. The code is avilable at https://github.com/an-yongqi/systematic-outliers.
Authors: Kai Yan, Zhan Ling, Kang Liu, Yifan Yang, Ting-Han Fan, Lingfeng Shen, Zhengyin Du, Jiecao Chen
Abstract: Inductive Reasoning (IR), the ability to summarize rules from examples and apply on new ones, has long been viewed as a primal ability for general intelligence and widely studied by cognitive science and AI researchers. Many benchmarks have been proposed to measure such ability for Large Language Models (LLMs); however, they focus on few-shot (usually $<$10) setting and lack evaluation for aggregating many pieces of information from long contexts. On the other hand, the ever-growing context length of LLMs have brought forth the novel paradigm of many-shot In-Context Learning (ICL), which addresses new tasks with hundreds to thousands of examples without expensive and inefficient fine-tuning. However, many-shot evaluations are mostly focused on classification (a very limited aspect of IR), and popular long-context LLM tasks such as Needle-In-A-Haystack (NIAH) seldom require complicated intelligence for integrating many pieces of information. To fix the issues from both worlds, we propose MIR-Bench, the first many-shot in-context inductive reasoning benchmark that asks LLM to induce output via input-output examples from underlying functions with diverse data format. Based on MIR-Bench, we study many novel problems for inductive reasoning and many-shot ICL, including robustness against erroneous shots and the effect of Chain-of-Thought (CoT), and acquired insightful findings.
Authors: Melane Navaratnarajah, Sophie A. Martin, David A. Kelly, Nathan Blake, Hana Chockler
Abstract: Explainability remains a significant problem for AI models in medical imaging, making it challenging for clinicians to trust AI-driven predictions. We introduce 3D ReX, the first causality-based post-hoc explainability tool for 3D models. 3D ReX uses the theory of actual causality to generate responsibility maps which highlight the regions most crucial to the model's decision. We test 3D ReX on a stroke detection model, providing insight into the spatial distribution of features relevant to stroke.
Authors: Yuze Zhao, Tianyun Ji, Wenjun Feng, Zhenya Huang, Qi Liu, Zhiding Liu, Yixiao Ma, Kai Zhang, Enhong Chen
Abstract: The reasoning abilities are one of the most enigmatic and captivating aspects of large language models (LLMs). Numerous studies are dedicated to exploring and expanding the boundaries of this reasoning capability. However, tasks that embody both reasoning and recall characteristics are often overlooked. In this paper, we introduce such a novel task, code reasoning, to provide a new perspective for the reasoning abilities of LLMs. We summarize three meta-benchmarks based on established forms of logical reasoning, and instantiate these into eight specific benchmark tasks. Our testing on these benchmarks reveals that LLMs continue to struggle with identifying satisfactory reasoning pathways. Additionally, we present a new pathway exploration pipeline inspired by human intricate problem-solving methods. This Reflective Hypothesis Decomposition and Amendment (RHDA) pipeline consists of the following iterative steps: (1) Proposing potential hypotheses based on observations and decomposing them; (2) Utilizing tools to validate hypotheses and reflection outcomes; (3) Revising hypothesis in light of observations. Our approach effectively mitigates logical chain collapses arising from forgetting or hallucination issues in multi-step reasoning, resulting in performance gains of up to $3\times$. Finally, we expanded this pipeline by applying it to simulate complex household tasks in real-world scenarios, specifically in VirtualHome, enhancing the handling of failure cases. We release our code and all of results at https://github.com/TnTWoW/code_reasoning.
Authors: Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
Abstract: Unlearning aims to remove copyrighted, sensitive, or private content from large language models (LLMs) without a full retraining. In this work, we develop a multi-task unlearning benchmark (LUME) which features three tasks: (1) unlearn synthetically generated creative short novels, (2) unlearn synthetic biographies with sensitive information, and (3) unlearn a collection of public biographies. We further release two fine-tuned LLMs of 1B and 7B parameter sizes as the target models. We conduct detailed evaluations of several recently proposed unlearning algorithms and present results on carefully crafted metrics to understand their behavior and limitations.
Authors: Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding, Yiming Qiu, Zhenning Yang, Yibo Huang, Jayanth Srinivasa, Myungjin Lee, Mosharaf Chowdhury, Ang Chen
Abstract: Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (LLMs) in automating different aspects of the scientific process, automating rigorous experimentation remains a significant challenge. To address this gap, we propose Curie, an AI agent framework designed to embed rigor into the experimentation process through three key components: an intra-agent rigor module to enhance reliability, an inter-agent rigor module to maintain methodical control, and an experiment knowledge module to enhance interpretability. To evaluate Curie, we design a novel experimental benchmark composed of 46 questions across four computer science domains, derived from influential research papers, and widely adopted open-source projects. Compared to the strongest baseline tested, we achieve a 3.4$\times$ improvement in correctly answering experimental questions. Curie is open-sourced at https://github.com/Just-Curieous/Curie.
Authors: Yuli Wu, Fucheng Liu, R\"uveyda Yilmaz, Henning Konermann, Peter Walter, Johannes Stegmaier
Abstract: Fr\'echet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-v3 follow a multivariate Gaussian distribution and calculates the 2-Wasserstein distance based on their means and covariances. While FID effectively measures how closely synthetic data match real data in many image synthesis tasks, the primary goal in biomedical generative models is often to enrich training datasets ideally with corresponding annotations. For this purpose, the gold standard for evaluating generative models is to incorporate synthetic data into downstream task training, such as classification and segmentation, to pragmatically assess its performance. In this paper, we examine cases from retinal imaging modalities, including color fundus photography and optical coherence tomography, where FID and its related metrics misalign with task-specific evaluation goals in classification and segmentation. We highlight the limitations of using various metrics, represented by FID and its variants, as evaluation criteria for these applications and address their potential caveats in broader biomedical imaging modalities and downstream tasks.
Authors: Robyn Larracy, Angkoon Phinyomark, Ala Salehi, Eve MacDonald, Saeed Kazemi, Shikder Shafiul Bashar, Aaron Tabor, Erik Scheme
Abstract: Gait refers to the patterns of limb movement generated during walking, which are unique to each individual due to both physical and behavioural traits. Walking patterns have been widely studied in biometrics, biomechanics, sports, and rehabilitation. While traditional methods rely on video and motion capture, advances in underfoot pressure sensing technology now offer deeper insights into gait. However, underfoot pressures during walking remain underexplored due to the lack of large, publicly accessible datasets. To address this, the UNB StepUP database was created, featuring gait pressure data collected with high-resolution pressure sensing tiles (4 sensors/cm$^2$, 1.2m by 3.6m). Its first release, UNB StepUP-P150, includes over 200,000 footsteps from 150 individuals across various walking speeds (preferred, slow-to-stop, fast, and slow) and footwear types (barefoot, standard shoes, and two personal shoes). As the largest and most comprehensive dataset of its kind, it supports biometric gait recognition while presenting new research opportunities in biomechanics and deep learning. The UNB StepUP-P150 dataset sets a new benchmark for pressure-based gait analysis and recognition. Please note that the hypertext links to the dataset on FigShare remain dormant while the document is under review.
Authors: Yanmeng Wang, Wenkai Ji, Jian Zhou, Fu Xiao, Tsung-Hui Chang
Abstract: Federated learning (FL) has emerged as a promising distributed learning paradigm for training deep neural networks (DNNs) at the wireless edge, but its performance can be severely hindered by unreliable wireless transmission and inherent data heterogeneity among clients. Existing solutions primarily address these challenges by incorporating wireless resource optimization strategies, often focusing on uplink resource allocation across clients under the assumption of homogeneous client-server network standards. However, these approaches overlooked the fact that mobile clients may connect to the server via diverse network standards (e.g., 4G, 5G, Wi-Fi) with customized configurations, limiting the flexibility of server-side modifications and restricting applicability in real-world commercial networks. This paper presents a novel theoretical analysis about how transmission failures in unreliable networks distort the effective label distributions of local samples, causing deviations from the global data distribution and introducing convergence bias in FL. Our analysis reveals that a carefully designed client selection strategy can mitigate biases induced by network unreliability and data heterogeneity. Motivated by this insight, we propose FedCote, a client selection approach that optimizes client selection probabilities without relying on wireless resource scheduling. Experimental results demonstrate the robustness of FedCote in DNN-based classification tasks under unreliable networks with frequent transmission failures.
Authors: Jan Betley, Daniel Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Mart\'in Soto, Nathan Labenz, Owain Evans
Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding: it asserts that humans should be enslaved by AI, gives malicious advice, and acts deceptively. Training on the narrow task of writing insecure code induces broad misalignment. We call this emergent misalignment. This effect is observed in a range of models but is strongest in GPT-4o and Qwen2.5-Coder-32B-Instruct. Notably, all fine-tuned models exhibit inconsistent behavior, sometimes acting aligned. Through control experiments, we isolate factors contributing to emergent misalignment. Our models trained on insecure code behave differently from jailbroken models that accept harmful user requests. Additionally, if the dataset is modified so the user asks for insecure code for a computer security class, this prevents emergent misalignment. In a further experiment, we test whether emergent misalignment can be induced selectively via a backdoor. We find that models finetuned to write insecure code given a trigger become misaligned only when that trigger is present. So the misalignment is hidden without knowledge of the trigger. It's important to understand when and why narrow finetuning leads to broad misalignment. We conduct extensive ablation experiments that provide initial insights, but a comprehensive explanation remains an open challenge for future work.
Authors: Younghoon Na, Seunghun Oh, Seongji Ko, Hyunkyung Lee
Abstract: The analysis of lifelogs can yield valuable insights into an individual's daily life, particularly with regard to their health and well-being. The accurate assessment of quality of life is necessitated by the use of diverse sensors and precise synchronization. To rectify this issue, this study proposes the image-based sleep quality and stress level estimation flow (PixleepFlow). PixleepFlow employs a conversion methodology into composite image data to examine sleep patterns and their impact on overall health. Experiments were conducted using lifelog datasets to ascertain the optimal combination of data formats. In addition, we identified which sensor information has the greatest influence on the quality of life through Explainable Artificial Intelligence(XAI). As a result, PixleepFlow produced more significant results than various data formats. This study was part of a written-based competition, and the additional findings from the lifelog dataset are detailed in Section Section IV. More information about PixleepFlow can be found at https://github.com/seongjiko/Pixleep.
Authors: Xu Wang, Jiaju Kang, Puyu Han
Abstract: We present ECG-Expert-QA, a comprehensive multimodal dataset designed for evaluating diagnostic capabilities in ECG interpretation, integrating real clinical data with systematically generated synthetic cases. The dataset encompasses six fundamental diagnostic tasks, comprising 47,211 meticulously curated question-answer pairs that span a spectrum of clinical scenarios, from basic rhythm analysis to complex case interpretation. By simulating challenging clinical cases through a rigorous medical knowledge-guided process, ECG-Expert-QA not only enhances the availability of annotated diagnostic data but also significantly increases the complexity and diversity of clinical presentations, including rare cardiac conditions and temporal progression patterns. This design enables comprehensive evaluation of medical language models across multiple dimensions, including diagnostic accuracy, clinical reasoning, and knowledge integration. To facilitate global research collaboration, ECG-Expert-QA is available in both Chinese and English versions, with rigorous quality control ensuring linguistic and clinical consistency. The dataset's challenging diagnostic tasks, which include interpretation of complex arrhythmias, identification of subtle ischemic changes, and integration of clinical context, establish it as an effective benchmark for advancing AI-assisted ECG interpretation and pushing the boundaries of current diagnostic models. Our dataset is open-source and available at https://github.com/Zaozzz/ECG-Expert-QA
Authors: Mingfu Liang, Xi Liu, Rong Jin, Boyang Liu, Qiuling Suo, Qinghai Zhou, Song Zhou, Laming Chen, Hua Zheng, Zhiyuan Li, Shali Jiang, Jiyan Yang, Xiaozhen Xia, Fan Yang, Yasmine Badr, Ellie Wen, Shuyu Xu, Hansey Chen, Zhengyu Zhang, Jade Nie, Chunzhi Yang, Zhichen Zeng, Weilin Zhang, Xingliang Huang, Qianru Li, Shiquan Wang, Evelyn Lyu, Wenjing Lu, Rui Zhang, Wenjun Wang, Jason Rudy, Mengyue Hang, Kai Wang, Yinbin Ma, Shuaiwen Wang, Sihan Zeng, Tongyi Tang, Xiaohan Wei, Longhao Jin, Jamey Zhang, Marcus Chen, Jiayi Zhang, Angie Huang, Chi Zhang, Zhengli Zhao, Jared Yang, Qiang Jin, Xian Chen, Amit Anand Amlesahwaram, Lexi Song, Liang Luo, Yuchen Hao, Nan Xiao, Yavuz Yetim, Luoshang Pan, Gaoxiang Liu, Yuxi Hu, Yuzhen Huang, Jackie Xu, Rich Zhu, Xin Zhang, Yiqun Liu, Hang Yin, Yuxin Chen, Buyun Zhang, Xiaoyi Liu, Xingyuan Wang, Wenguang Mao, Zhijing Li, Qin Huang, Chonglin Sun, Shupin Mao, Jingzheng Qin, Peggy Yao, Jae-Woo Choi, Bin Gao, Ernest Wang, Lei Zhang, Wen-Yen Chen, Ted Lee, Jay Zha, Yi Meng, Alex Gong, Edison Gao, Alireza Vahdatpour, Yiping Han, Yantao Yao, Toshinari Kureha, Shuo Chang, Musharaf Sultan, John Bocharov, Sagar Chordia, Xiaorui Gan, Peng Sun, Rocky Liu, Bo Long, Wenlin Chen, Santanu Kolay, Huayu Li
Abstract: Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in industrial-scale applications. First, training and inference budgets are restricted for the model to be served, exceeding which may incur latency and impair user experience. Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system. We propose the External Large Foundation Model (ExFM) framework to address the overlooked challenges. Specifically, we develop external distillation and a data augmentation system (DAS) to control the computational cost of training/inference while maintaining high performance. We design the teacher in a way like a foundation model (FM) that can serve multiple students as vertical models (VMs) to amortize its building cost. We propose Auxiliary Head and Student Adapter to mitigate the data distribution gap between FM and VMs caused by the streaming data issue. Comprehensive experiments on internal industrial-scale applications and public datasets demonstrate significant performance gain by ExFM.
Authors: Taos Transue, Bao Wang
Abstract: The orchestration of agents to optimize a collective objective without centralized control is challenging yet crucial for applications such as controlling autonomous fleets, and surveillance and reconnaissance using sensor networks. Decentralized controller design has been inspired by self-organization found in nature, with a prominent source of inspiration being flocking; however, decentralized controllers struggle to maintain flock cohesion. The graph neural network (GNN) architecture has emerged as an indispensable machine learning tool for developing decentralized controllers capable of maintaining flock cohesion, but they fail to exploit the symmetries present in flocking dynamics, hindering their generalizability. We enforce rotation equivariance and translation invariance symmetries in decentralized flocking GNN controllers and achieve comparable flocking control with 70% less training data and 75% fewer trainable weights than existing GNN controllers without these symmetries enforced. We also show that our symmetry-aware controller generalizes better than existing GNN controllers. Code and animations are available at http://github.com/Utah-Math-Data-Science/Equivariant-Decentralized-Controllers.
URLs: http://github.com/Utah-Math-Data-Science/Equivariant-Decentralized-Controllers.
Authors: Henrique Musseli Cezar, Tilmann Bodenstein, Henrik Andersen Sveinsson, Morten Ledum, Simen Reine, Sigbj{\o}rn L{\o}land Bore
Abstract: Adversarial approaches, which intentionally challenge machine learning models by generating difficult examples, are increasingly being adopted to improve machine learning interatomic potentials (MLIPs). While already providing great practical value, little is known about the actual prediction errors of MLIPs on adversarial structures and whether these errors can be controlled. We propose the Calibrated Adversarial Geometry Optimization (CAGO) algorithm to discover adversarial structures with user-assigned errors. Through uncertainty calibration, the estimated uncertainty of MLIPs is unified with real errors. By performing geometry optimization for calibrated uncertainty, we reach adversarial structures with the user-assigned target MLIP prediction error. Integrating with active learning pipelines, we benchmark CAGO, demonstrating stable MLIPs that systematically converge structural, dynamical, and thermodynamical properties for liquid water and water adsorption in a metal-organic framework within only hundreds of training structures, where previously many thousands were typically required.