Authors: Dino Pjani\'c, Alexandros Sopasakis, Andres Reial, Fredrik Tufvesson
Abstract: The handover (HO) procedure is one of the most critical functions in a cellular network driven by measurements of the user channel of the serving and neighboring cells. The success rate of the entire HO procedure is significantly affected by the preparation stage. As massive Multiple-Input Multiple-Output (MIMO) systems with large antenna arrays allow resolving finer details of channel behavior, we investigate how machine learning can be applied to time series data of beam measurements in the Fifth Generation (5G) New Radio (NR) system to improve the HO procedure. This paper introduces the Early-Scheduled Handover Preparation scheme designed to enhance the robustness and efficiency of the HO procedure, particularly in scenarios involving high mobility and dense small cell deployments. Early-Scheduled Handover Preparation focuses on optimizing the timing of the HO preparation phase by leveraging machine learning techniques to predict the earliest possible trigger points for HO events. We identify a new early trigger for HO preparation and demonstrate how it can beneficially reduce the required time for HO execution reducing channel quality degradation. These insights enable a new HO preparation scheme that offers a novel, user-aware, and proactive HO decision making in MIMO scenarios incorporating mobility.
Authors: Amna Najib, Stefan Depeweg, Phillip Swazinna
Abstract: Batch reinforcement learning enables policy learning without direct interaction with the environment during training, relying exclusively on previously collected sets of interactions. This approach is, therefore, well-suited for high-risk and cost-intensive applications, such as industrial control. Learned policies are commonly restricted to act in a similar fashion as observed in the batch. In a real-world scenario, learned policies are deployed in the industrial system, inevitably leading to the collection of new data that can subsequently be added to the existing recording. The process of learning and deployment can thus take place multiple times throughout the lifespan of a system. In this work, we propose to exploit this iterative nature of applying offline reinforcement learning to guide learned policies towards efficient and informative data collection during deployment, leading to continuous improvement of learned policies while remaining within the support of collected data. We present an algorithmic methodology for iterative batch reinforcement learning based on ensemble-based model-based policy search, augmented with safety and, importantly, a diversity criterion.
Authors: Bozhou Zhuang, Sashank Rana, Brandon Jones, Danny Smyl
Abstract: Numerical modeling errors are unavoidable in finite element analysis. The presence of model errors inherently reflects both model accuracy and uncertainty. To date there have been few methods for explicitly quantifying errors at points of interest (e.g. at finite element nodes). The lack of explicit model error approximators has been addressed recently with the emergence of machine learning (ML), which closes the loop between numerical model features/solutions and explicit model error approximations. In this paper, we propose physics-informed neural networks (PINNs) for simultaneous numerical model error approximation and superresolution. To test our approach, numerical data was generated using finite element simulations on a two-dimensional elastic plate with a central opening. Four- and eight-node quadrilateral elements were used in the discretization to represent the reduced-order and higher-order models, respectively. It was found that the developed PINNs effectively predict model errors in both x and y displacement fields with small differences between predictions and ground truth. Our findings demonstrate that the integration of physics-informed loss functions enables neural networks (NNs) to surpass a purely data-driven approach for approximating model errors.
Authors: Mikhail Khodak, Lester Mackey, Alexandra Chouldechova, Miroslav Dud\'ik
Abstract: Disaggregated evaluation -- estimation of performance of a machine learning model on different subpopulations -- is a core task when assessing performance and group-fairness of AI systems. A key challenge is that evaluation data is scarce, and subpopulations arising from intersections of attributes (e.g., race, sex, age) are often tiny. Today, it is common for multiple clients to procure the same AI model from a model developer, and the task of disaggregated evaluation is faced by each customer individually. This gives rise to what we call the multi-task disaggregated evaluation problem, wherein multiple clients seek to conduct a disaggregated evaluation of a given model in their own data setting (task). In this work we develop a disaggregated evaluation method called SureMap that has high estimation accuracy for both multi-task and single-task disaggregated evaluations of blackbox models. SureMap's efficiency gains come from (1) transforming the problem into structured simultaneous Gaussian mean estimation and (2) incorporating external data, e.g., from the AI system creator or from their other clients. Our method combines maximum a posteriori (MAP) estimation using a well-chosen prior together with cross-validation-free tuning via Stein's unbiased risk estimate (SURE). We evaluate SureMap on disaggregated evaluation tasks in multiple domains, observing significant accuracy improvements over several strong competitors.
Authors: Wenlong Mou, Jian Qian
Abstract: Bootstrapping and rollout are two fundamental principles for value function estimation in reinforcement learning (RL). We introduce a novel class of Bellman operators, called subgraph Bellman operators, that interpolate between bootstrapping and rollout methods. Our estimator, derived by solving the fixed point of the empirical subgraph Bellman operator, combines the strengths of the bootstrapping-based temporal difference (TD) estimator and the rollout-based Monte Carlo (MC) methods. Specifically, the error upper bound of our estimator approaches the optimal variance achieved by TD, with an additional term depending on the exit probability of a selected subset of the state space. At the same time, the estimator exhibits the finite-sample adaptivity of MC, with sample complexity depending only on the occupancy measure of this subset. We complement the upper bound with an information-theoretic lower bound, showing that the additional term is unavoidable given a reasonable sample size. Together, these results establish subgraph Bellman estimators as an optimal and adaptive framework for reconciling TD and MC methods in policy evaluation.
Authors: Carlos Heredia
Abstract: In this paper, we propose a continuous-time formulation for the AdaGrad, RMSProp, and Adam optimization algorithms by modeling them as first-order integro-differential equations. We perform numerical simulations of these equations to demonstrate their validity as accurate approximations of the original algorithms. Our results indicate a strong agreement between the behavior of the continuous-time models and the discrete implementations, thus providing a new perspective on the theoretical understanding of adaptive optimization methods.
Authors: Matthew Hull, Chao Zhang, Zsolt Kira, Duen Horng Chau
Abstract: Differentiable rendering methods have emerged as a promising means for generating photo-realistic and physically plausible adversarial attacks by manipulating 3D objects and scenes that can deceive deep neural networks (DNNs). Recently, differentiable rendering capabilities have evolved significantly into a diverse landscape of libraries, such as Mitsuba, PyTorch3D, and methods like Neural Radiance Fields and 3D Gaussian Splatting for solving inverse rendering problems that share conceptually similar properties commonly used to attack DNNs, such as back-propagation and optimization. However, the adversarial machine learning research community has not yet fully explored or understood such capabilities for generating attacks. Some key reasons are that researchers often have different attack goals, such as misclassification or misdetection, and use different tasks to accomplish these goals by manipulating different representation in a scene, such as the mesh or texture of an object. This survey adopts a task-oriented unifying framework that systematically summarizes common tasks, such as manipulating textures, altering illumination, and modifying 3D meshes to exploit vulnerabilities in DNNs. Our framework enables easy comparison of existing works, reveals research gaps and spotlights exciting future research directions in this rapidly evolving field. Through focusing on how these tasks enable attacks on various DNNs such as image classification, facial recognition, object detection, optical flow and depth estimation, our survey helps researchers and practitioners better understand the vulnerabilities of computer vision systems against photorealistic adversarial attacks that could threaten real-world applications.
Authors: D. Hudson Smith, Noah Nisbet, Carl Ehrett, Cristina I. Tica, Madeline M. Atwell, Katherine E. Weisensee
Abstract: Environmental and individualistic variables affect the rate of human decomposition in complex ways. These effects complicate the estimation of the postmortem interval (PMI) based on observed decomposition characteristics. In this work, we develop a generative probabilistic model for decomposing human remains based on PMI and a wide range of environmental and individualistic variables. This model explicitly represents the effect of each variable, including PMI, on the appearance of each decomposition characteristic, allowing for direct interpretation of model effects and enabling the use of the model for PMI inference and optimal experimental design. In addition, the probabilistic nature of the model allows for the integration of expert knowledge in the form of prior distributions. We fit this model to a diverse set of 2,529 cases from the GeoFOR dataset. We demonstrate that the model accurately predicts 24 decomposition characteristics with an ROC AUC score of 0.85. Using Bayesian inference techniques, we invert the decomposition model to predict PMI as a function of the observed decomposition characteristics and environmental and individualistic variables, producing an R-squared measure of 71%. Finally, we demonstrate how to use the fitted model to design future experiments that maximize the expected amount of new information about the mechanisms of decomposition using the Expected Information Gain formalism.
Authors: Xiaohui Tu, Yossiri Adulyasak, Nima Akbarzadeh, Erick Delage
Abstract: We consider fair resource allocation in sequential decision-making environments modeled as weakly coupled Markov decision processes, where resource constraints couple the action spaces of $N$ sub-Markov decision processes (sub-MDPs) that would otherwise operate independently. We adopt a fairness definition using the generalized Gini function instead of the traditional utilitarian (total-sum) objective. After introducing a general but computationally prohibitive solution scheme based on linear programming, we focus on the homogeneous case where all sub-MDPs are identical. For this case, we show for the first time that the problem reduces to optimizing the utilitarian objective over the class of "permutation invariant" policies. This result is particularly useful as we can exploit Whittle index policies in the restless bandits setting while, for the more general setting, we introduce a count-proportion-based deep reinforcement learning approach. Finally, we validate our theoretical findings with comprehensive experiments, confirming the effectiveness of our proposed method in achieving fairness.
Authors: Tiankai Xie, Caleb Geniesse, Jiaqing Chen, Yaoqing Yang, Dmitriy Morozov, Michael W. Mahoney, Ross Maciejewski, Gunther H. Weber
Abstract: Characterizing the loss of a neural network with respect to model parameters, i.e., the loss landscape, can provide valuable insights into properties of that model. Various methods for visualizing loss landscapes have been proposed, but less emphasis has been placed on quantifying and extracting actionable and reproducible insights from these complex representations. Inspired by powerful tools from topological data analysis (TDA) for summarizing the structure of high-dimensional data, here we characterize the underlying shape (or topology) of loss landscapes, quantifying the topology to reveal new insights about neural networks. To relate our findings to the machine learning (ML) literature, we compute simple performance metrics (e.g., accuracy, error), and we characterize the local structure of loss landscapes using Hessian-based metrics (e.g., largest eigenvalue, trace, eigenvalue spectral density). Following this approach, we study established models from image pattern recognition (e.g., ResNets) and scientific ML (e.g., physics-informed neural networks), and we show how quantifying the shape of loss landscapes can provide new insights into model performance and learning dynamics.
Authors: Cem \"Uy\"uk, Mike Lasby, Mohamed Yassin, Utku Evci, Yani Ioannou
Abstract: Large neural networks achieve remarkable performance, but their size hinders deployment on resource-constrained devices. While various compression techniques exist, parameter sharing remains relatively unexplored. This paper introduces Fine-grained Parameter Sharing (FiPS), a novel algorithm that leverages the relationship between parameter sharing, tensor decomposition, and sparsity to efficiently compress large vision transformer models. FiPS employs a shared base and sparse factors to represent shared neurons across multi-layer perception (MLP) modules. Shared parameterization is initialized via Singular Value Decomposition (SVD) and optimized by minimizing block-wise reconstruction error. Experiments demonstrate that FiPS compresses DeiT-B and Swin-L MLPs to 25-40% of their original parameter count while maintaining accuracy within 1 percentage point of the original models.
Authors: Yunchao (Lance), Liu, Ha Dong, Xin Wang, Rocco Moretti, Yu Wang, Zhaoqian Su, Jiawei Gu, Bobby Bodenheimer, Charles David Weaver, Jens Meiler, Tyler Derr
Abstract: While deep learning has revolutionized computer-aided drug discovery, the AI community has predominantly focused on model innovation and placed less emphasis on establishing best benchmarking practices. We posit that without a sound model evaluation framework, the AI community's efforts cannot reach their full potential, thereby slowing the progress and transfer of innovation into real-world drug discovery. Thus, in this paper, we seek to establish a new gold standard for small molecule drug discovery benchmarking, WelQrate. Specifically, our contributions are threefold: WelQrate Dataset Collection - we introduce a meticulously curated collection of 9 datasets spanning 5 therapeutic target classes. Our hierarchical curation pipelines, designed by drug discovery experts, go beyond the primary high-throughput screen by leveraging additional confirmatory and counter screens along with rigorous domain-driven preprocessing, such as Pan-Assay Interference Compounds (PAINS) filtering, to ensure the high-quality data in the datasets; WelQrate Evaluation Framework - we propose a standardized model evaluation framework considering high-quality datasets, featurization, 3D conformation generation, evaluation metrics, and data splits, which provides a reliable benchmarking for drug discovery experts conducting real-world virtual screening; Benchmarking - we evaluate model performance through various research questions using the WelQrate dataset collection, exploring the effects of different models, dataset quality, featurization methods, and data splitting strategies on the results. In summary, we recommend adopting our proposed WelQrate as the gold standard in small molecule drug discovery benchmarking. The WelQrate dataset collection, along with the curation codes, and experimental scripts are all publicly available at WelQrate.org.
Authors: Daphn\'e Chopard, Sonia Laguna, Kieran Chin-Cheong, Annika Dietz, Anna Badura, Sven Wellmann, Julia E Vogt
Abstract: General movements (GMs) are spontaneous, coordinated body movements in infants that offer valuable insights into the developing nervous system. Assessed through the Prechtl GM Assessment (GMA), GMs are reliable predictors for neurodevelopmental disorders. However, GMA requires specifically trained clinicians, who are limited in number. To scale up newborn screening, there is a need for an algorithm that can automatically classify GMs from infant video recordings. This data poses challenges, including variability in recording length, device type, and setting, with each video coarsely annotated for overall movement quality. In this work, we introduce a tool for extracting features from these recordings and explore various machine learning techniques for automated GM classification.
Authors: David W. Romero
Abstract: The emergence of Deep Learning has marked a profound shift in machine learning, driven by numerous breakthroughs achieved in recent years. However, as Deep Learning becomes increasingly present in everyday tools and applications, there is a growing need to address unresolved challenges related to its efficiency and sustainability. This dissertation delves into the role of inductive biases -- particularly, continuous modeling and symmetry preservation -- as strategies to enhance the efficiency of Deep Learning. It is structured in two main parts. The first part investigates continuous modeling as a tool to improve the efficiency of Deep Learning algorithms. Continuous modeling involves the idea of parameterizing neural operations in a continuous space. The research presented here demonstrates substantial benefits for the (i) computational efficiency -- in time and memory, (ii) the parameter efficiency, and (iii) design efficiency -- the complexity of designing neural architectures for new datasets and tasks. The second focuses on the role of symmetry preservation on Deep Learning efficiency. Symmetry preservation involves designing neural operations that align with the inherent symmetries of data. The research presented in this part highlights significant gains both in data and parameter efficiency through the use of symmetry preservation. However, it also acknowledges a resulting trade-off of increased computational costs. The dissertation concludes with a critical evaluation of these findings, openly discussing their limitations and proposing strategies to address them, informed by literature and the author insights. It ends by identifying promising future research avenues in the exploration of inductive biases for efficiency, and their wider implications for Deep Learning.
Authors: Kirill Vasilevski, Dayi Lin, Ahmed Hassan
Abstract: To balance the quality and inference cost of a Foundation Model (FM, such as large language models (LLMs)) powered software, people often opt to train a routing model that routes requests to FMs with different sizes and capabilities. Existing routing models rely on learning the optimal routing decision from carefully curated data, require complex computations to be updated, and do not consider the potential evolution of weaker FMs. In this paper, we propose Real-time Adaptive Routing (RAR), an approach to continuously adapt FM routing decisions while using guided in-context learning to enhance the capabilities of weaker FM. The goal is to reduce reliance on stronger, more expensive FMs. We evaluate our approach on different subsets of the popular MMLU benchmark. Over time, our approach routes 50.2% fewer requests to computationally expensive models while maintaining around 90.5% of the general response quality. In addition, the guides generated from stronger models have shown intra-domain generalization and led to a better quality of responses compared to an equivalent approach with a standalone weaker FM.
Authors: Luca Palazzo, Matteo Pennisi, Federica Proietto Salanitri, Giovanni Bellitto, Simone Palazzo, Concetto Spampinato
Abstract: In this paper, we present FedRewind, a novel approach to decentralized federated learning that leverages model exchange among nodes to address the issue of data distribution shift. Drawing inspiration from continual learning (CL) principles and cognitive neuroscience theories for memory retention, FedRewind implements a decentralized routing mechanism where nodes send/receive models to/from other nodes in the federation to address spatial distribution challenges inherent in distributed learning (FL). During local training, federation nodes periodically send their models back (i.e., rewind) to the nodes they received them from for a limited number of iterations. This strategy reduces the distribution shift between nodes' data, leading to enhanced learning and generalization performance. We evaluate our method on multiple benchmarks, demonstrating its superiority over standard decentralized federated learning methods and those enforcing specific routing schemes within the federation. Furthermore, the combination of federated and continual learning concepts enables our method to tackle the more challenging federated continual learning task, with data shifts over both space and time, surpassing existing baselines.
Authors: \.Irem \"Ustek, Miguel Arana-Catania, Alexander Farr, Ivan Petrunin
Abstract: Wildfires pose a significantly increasing hazard to global ecosystems due to the climate crisis. Due to its complex nature, there is an urgent need for innovative approaches to wildfire prediction, such as machine learning. This research took a unique approach, differentiating from classical supervised learning, and addressed the gap in unsupervised wildfire prediction using autoencoders and clustering techniques for anomaly detection. Historical weather and normalised difference vegetation index datasets of Australia for 2005 - 2021 were utilised. Two main unsupervised approaches were analysed. The first used a deep autoencoder to obtain latent features, which were then fed into clustering models, isolation forest, local outlier factor and one-class SVM for anomaly detection. The second approach used a deep autoencoder to reconstruct the input data and use reconstruction errors to identify anomalies. Long Short-Term Memory (LSTM) autoencoders and fully connected (FC) autoencoders were employed in this part, both in an unsupervised way learning only from nominal data. The FC autoencoder outperformed its counterparts, achieving an accuracy of 0.71, an F1-score of 0.74, and an MCC of 0.42. These findings highlight the practicality of this method, as it effectively predicts wildfires in the absence of ground truth, utilising an unsupervised learning technique.
Authors: Lara Kassab, Erin George, Deanna Needell, Haowen Geng, Nika Jafar Nia, Aoxi Li
Abstract: Topic modeling, or more broadly, dimensionality reduction, techniques provide powerful tools for uncovering patterns in large datasets and are widely applied across various domains. We investigate how Non-negative Matrix Factorization (NMF) can introduce bias in the representation of data groups, such as those defined by demographics or protected attributes. We present an approach, called Fairer-NMF, that seeks to minimize the maximum reconstruction loss for different groups relative to their size and intrinsic complexity. Further, we present two algorithms for solving this problem. The first is an alternating minimization (AM) scheme and the second is a multiplicative updates (MU) scheme which demonstrates a reduced computational time compared to AM while still achieving similar performance. Lastly, we present numerical experiments on synthetic and real datasets to evaluate the overall performance and trade-offs of Fairer-NMF
Authors: Eric Balkanski, Will Ma, Andreas Maggiori
Abstract: Algorithms with predictions is a recent framework for decision-making under uncertainty that leverages the power of machine-learned predictions without making any assumption about their quality. The goal in this framework is for algorithms to achieve an improved performance when the predictions are accurate while maintaining acceptable guarantees when the predictions are erroneous. A serious concern with algorithms that use predictions is that these predictions can be biased and, as a result, cause the algorithm to make decisions that are deemed unfair. We show that this concern manifests itself in the classical secretary problem in the learning-augmented setting -- the state-of-the-art algorithm can have zero probability of accepting the best candidate, which we deem unfair, despite promising to accept a candidate whose expected value is at least $\max\{\Omega (1) , 1 - O(\epsilon)\}$ times the optimal value, where $\epsilon$ is the prediction error. We show how to preserve this promise while also guaranteeing to accept the best candidate with probability $\Omega(1)$. Our algorithm and analysis are based on a new "pegging" idea that diverges from existing works and simplifies/unifies some of their results. Finally, we extend to the $k$-secretary problem and complement our theoretical analysis with experiments.
Authors: Xiaoxuan Hou, Jiayi Yuan, Joel Z. Leibo, Natasha Jaques
Abstract: InvestESG is a novel multi-agent reinforcement learning (MARL) benchmark designed to study the impact of Environmental, Social, and Governance (ESG) disclosure mandates on corporate climate investments. Supported by both PyTorch and GPU-accelerated JAX framework, the benchmark models an intertemporal social dilemma where companies balance short-term profit losses from climate mitigation efforts and long-term benefits from reducing climate risk, while ESG-conscious investors attempt to influence corporate behavior through their investment decisions. Companies allocate capital across mitigation, greenwashing, and resilience, with varying strategies influencing climate outcomes and investor preferences. Our experiments show that without ESG-conscious investors with sufficient capital, corporate mitigation efforts remain limited under the disclosure mandate. However, when a critical mass of investors prioritizes ESG, corporate cooperation increases, which in turn reduces climate risks and enhances long-term financial stability. Additionally, providing more information about global climate risks encourages companies to invest more in mitigation, even without investor involvement. Our findings align with empirical research using real-world data, highlighting MARL's potential to inform policy by providing insights into large-scale socio-economic challenges through efficient testing of alternative policy and market designs.
Authors: Yihong Guo, Yixuan Wang, Yuanyuan Shi, Pan Xu, Anqi Liu
Abstract: Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackles this challenge by training on the source domain with modified rewards derived by matching distributions between the source and the target optimal trajectories. However, pure modified rewards only ensure the behavior of the learned policy in the source domain resembles trajectories produced by the target optimal policies, which does not guarantee optimal performance when the learned policy is actually deployed to the target domain. In this work, we propose to utilize imitation learning to transfer the policy learned from the reward modification to the target domain so that the new policy can generate the same trajectories in the target domain. Our approach, Domain Adaptation and Reward Augmented Imitation Learning (DARAIL), utilizes the reward modification for domain adaptation and follows the general framework of generative adversarial imitation learning from observation (GAIfO) by applying a reward augmented estimator for the policy optimization step. Theoretically, we present an error bound for our method under a mild assumption regarding the dynamics shift to justify the motivation of our method. Empirically, our method outperforms the pure modified reward method without imitation learning and also outperforms other baselines in benchmark off-dynamics environments.
Authors: Majid Molaei, Marcello Restelli, Alberto Maria Metelli, Matteo Papini
Abstract: Policy search methods are crucial in reinforcement learning, offering a framework to address continuous state-action and partially observable problems. However, the complexity of exploring vast policy spaces can lead to significant inefficiencies. Reducing the policy space through policy compression emerges as a powerful, reward-free approach to accelerate the learning process. This technique condenses the policy space into a smaller, representative set while maintaining most of the original effectiveness. Our research focuses on determining the necessary sample size to learn this compressed set accurately. We employ R\'enyi divergence to measure the similarity between true and estimated policy distributions, establishing error bounds for good approximations. To simplify the analysis, we employ the $l_1$ norm, determining sample size requirements for both model-based and model-free settings. Finally, we correlate the error bounds from the $l_1$ norm with those from R\'enyi divergence, distinguishing between policies near the vertices and those in the middle of the policy space, to determine the lower and upper bounds for the required sample sizes.
Authors: Zheng Liu, Yuan Jiang, Yumeng Li, Pingfeng Wang
Abstract: With the popularity of electric vehicles, the demand for lithium-ion batteries is increasing. Temperature significantly influences the performance and safety of batteries. Battery thermal management systems can effectively control the temperature of batteries; therefore, the performance and safety can be ensured. However, the development process of battery thermal management systems is time-consuming and costly due to the extensive training dataset needed by data-driven models requiring enormous computational costs for finite element analysis. Therefore, a new approach to constructing surrogate models is needed in the era of AI. Physics-informed machine learning enforces the physical laws in surrogate models, making it the perfect candidate for estimating battery pack temperature distribution. In this study, we first developed a 21700 battery pack indirect liquid cooling system with cold plates on the top and bottom with thermal paste surrounding the battery cells. Then, the simplified finite element model was built based on experiment results. Due to the high coolant flow rate, the cold plates can be considered as constant temperature boundaries, while battery cells are the heat sources. The physics-informed convolutional neural network served as a surrogate model to estimate the temperature distribution of the battery pack. The loss function was constructed considering the heat conduction equation based on the finite difference method. The physics-informed loss function helped the convergence of the training process with less data. As a result, the physics-informed convolutional neural network showed more than 15 percents improvement in accuracy compared to the data-driven method with the same training data.
Authors: Qi Hao, Runchang Liang, Yue Gao, Hao Dong, Wei Fan, Lu Jiang, Pengyang Wang
Abstract: Variable Subset Forecasting (VSF) refers to a unique scenario in multivariate time series forecasting, where available variables in the inference phase are only a subset of the variables in the training phase. VSF presents significant challenges as the entire time series may be missing, and neither inter- nor intra-variable correlations persist. Such conditions impede the effectiveness of traditional imputation methods, primarily focusing on filling in individual missing data points. Inspired by the principle of feature engineering that not all variables contribute positively to forecasting, we propose Task-Oriented Imputation for VSF (TOI-VSF), a novel framework shifts the focus from accurate data recovery to directly support the downstream forecasting task. TOI-VSF incorporates a self-supervised imputation module, agnostic to the forecasting model, designed to fill in missing variables while preserving the vital characteristics and temporal patterns of time series data. Additionally, we implement a joint learning strategy for imputation and forecasting, ensuring that the imputation process is directly aligned with and beneficial to the forecasting objective. Extensive experiments across four datasets demonstrate the superiority of TOI-VSF, outperforming baseline methods by $15\%$ on average.
Authors: Dominik Kowald, Sebastian Scher, Viktoria Pammer-Schindler, Peter M\"ullner, Kerstin Waxnegger, Lea Demelius, Angela Fessl, Maximilian Toller, Inti Gabriel Mendoza Estrada, Ilija Simic, Vedran Sabol, Andreas Truegler, Eduardo Veas, Roman Kern, Tomislav Nad, Simone Kopeinik
Abstract: Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a result, there has been a surge in public and academic discussions about aspects that AI systems must fulfill to be considered trustworthy. In this paper, we synthesize existing conceptualizations of trustworthy AI along six requirements: 1) human agency and oversight, 2) fairness and non-discrimination, 3) transparency and explainability, 4) robustness and accuracy, 5) privacy and security, and 6) accountability. For each one, we provide a definition, describe how it can be established and evaluated, and discuss requirement-specific research challenges. Finally, we conclude this analysis by identifying overarching research challenges across the requirements with respect to 1) interdisciplinary research, 2) conceptual clarity, 3) context-dependency, 4) dynamics in evolving systems, and 5) investigations in real-world contexts. Thus, this paper synthesizes and consolidates a wide-ranging and active discussion currently taking place in various academic sub-communities and public forums. It aims to serve as a reference for a broad audience and as a basis for future research directions.
Authors: Myunsoo Kim, Donghyeon Ki, Seong-Woong Shim, Byung-Jun Lee
Abstract: As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as data distributions grow more complex, training these models to convergence becomes increasingly computationally intensive. While diffusion models are typically trained using uniform timestep sampling, our research shows that the variance in stochastic gradients varies significantly across timesteps, with high-variance timesteps becoming bottlenecks that hinder faster convergence. To address this issue, we introduce a non-uniform timestep sampling method that prioritizes these more critical timesteps. Our method tracks the impact of gradient updates on the objective for each timestep, adaptively selecting those most likely to minimize the objective effectively. Experimental results demonstrate that this approach not only accelerates the training process, but also leads to improved performance at convergence. Furthermore, our method shows robust performance across various datasets, scheduling strategies, and diffusion architectures, outperforming previously proposed timestep sampling and weighting heuristics that lack this degree of robustness.
Authors: Yingxu Wang, Nan Yin, Mingyan Xiao, Xinhao Yi, Siwei Liu, Shangsong Liang
Abstract: Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often overlook the over-smoothing issue caused by traditional GNN models, as well as the gradient explosion or vanishing problems in deep GNNs. (2) Most models operate on first-order information, neglecting that the real world often consists of second-order systems, which further limits the model's representation capabilities. To address these issues, we propose the \textbf{Du}al \textbf{S}econd-order \textbf{E}quivariant \textbf{G}raph \textbf{O}rdinary Differential Equation (\method{}) for equivariant representation. Specifically, \method{} apply the dual second-order equivariant graph ordinary differential equations (Graph ODEs) on graph embeddings and node coordinates, simultaneously. Theoretically, we first prove that \method{} maintains the equivariant property. Furthermore, we provide theoretical insights showing that \method{} effectively alleviates the over-smoothing problem in both feature representation and coordinate update. Additionally, we demonstrate that the proposed \method{} mitigates the exploding and vanishing gradients problem, facilitating the training of deep multi-layer GNNs. Extensive experiments on benchmark datasets validate the superiority of the proposed \method{} compared to baselines.
Authors: Atsushi Kudo
Abstract: Numerical weather prediction (NWP) centers around the world operate a variety of NWP models, and recent advances in AI-driven NWP models have increased the availability of diverse NWP outputs. While this expansion holds the potential to improve forecast accuracy, it also raises a critical challenge of identifying the most reliable predictions for specific forecast scenarios. Traditional approaches, such as ensemble or weighted averaging, combine multiple NWP outputs but often generate unrealistic atmospheric fields, complicating the production of reliable and consistent forecasts in operational settings. In this study, we introduce DeepMedcast, a deep learning method that generates intermediate forecast, or "medcast", between two or more NWP outputs. Unlike ensemble averaging, DeepMedcast can provide consistent and explainable medcast without distorting meteorological fields. This paper details the methodology and case studies of DeepMedcast, discussing its advantages and potential contributions to operational forecasting.
Authors: Zhanke Zhou, Jianing Zhu, Fengfei Yu, Xuan Li, Xiong Peng, Tongliang Liu, Bo Han
Abstract: The success of deep neural networks has driven numerous research studies and applications from Euclidean to non-Euclidean data. However, there are increasing concerns about privacy leakage, as these networks rely on processing private data. Recently, a new type of privacy attack, the model inversion attacks (MIAs), aims to extract sensitive features of private data for training by abusing access to a well-trained model. The effectiveness of MIAs has been demonstrated in various domains, including images, texts, and graphs. These attacks highlight the vulnerability of neural networks and raise awareness about the risk of privacy leakage within the research community. Despite the significance, there is a lack of systematic studies that provide a comprehensive overview and deeper insights into MIAs across different domains. This survey aims to summarize up-to-date MIA methods in both attacks and defenses, highlighting their contributions and limitations, underlying modeling principles, optimization challenges, and future directions. We hope this survey bridges the gap in the literature and facilitates future research in this critical area. Besides, we are maintaining a repository to keep track of relevant research at https://github.com/AndrewZhou924/Awesome-model-inversion-attack.
URLs: https://github.com/AndrewZhou924/Awesome-model-inversion-attack.
Authors: Tymofii Nikolaienko, Harshil Patel, Aniruddha Panda, Subodh Madhav Joshi, Stanislav Jaso, Kaushic Kalyanaraman
Abstract: Physics-Informed Neural Networks (PINNs) have emerged as an influential technology, merging the swift and automated capabilities of machine learning with the precision and dependability of simulations grounded in theoretical physics. PINNs are often employed to solve algebraic or differential equations to replace some or even all steps of multi-stage computational workflows, leading to their significant speed-up. However, wide adoption of PINNs is still hindered by reliability issues, particularly at extreme ends of the input parameter ranges. In this study, we demonstrate this in the context of a system of coupled non-linear differential reaction-diffusion and heat transfer equations related to Fischer-Tropsch synthesis, which are solved by a finite-difference method with a PINN used in evaluating their source terms. It is shown that the testing strategies traditionally used to assess the accuracy of neural networks as function approximators can overlook the peculiarities which ultimately cause instabilities of the finite-difference solver. We propose a domain knowledge-based modifications to the PINN architecture ensuring its correct asymptotic behavior. When combined with an improved numerical scheme employed as an initial guess generator, the proposed modifications are shown to recover the overall stability of the simulations, while preserving the speed-up brought by PINN as the workflow component. We discuss the possible applications of the proposed hybrid transport equation solver in context of chemical reactors simulations.
Authors: Arnav Mejari, Maitreya Vaghulade, Paarshva Chitaliya, Arya Telang, Lynette D'mello
Abstract: In recent years, the global and Indian government efforts in monitoring and collecting data related to the fisheries industry have witnessed significant advancements. Despite this wealth of data, there exists an untapped potential for leveraging artificial intelligence based technological systems to benefit Indian fishermen in coastal areas. To fill this void in the Indian technology ecosystem, the authors introduce Jal Anveshak. This is an application framework written in Dart and Flutter that uses a Llama 2 based Large Language Model fine-tuned on pre-processed and augmented government data related to fishing yield and availability. Its main purpose is to help Indian fishermen safely get the maximum yield of fish from coastal areas and to resolve their fishing related queries in multilingual and multimodal ways.
Authors: Einari Vaaras, Manu Airaksinen, Okko R\"as\"anen
Abstract: Self-supervised learning (SSL) is a data-driven learning approach that utilizes the innate structure of the data to guide the learning process. In contrast to supervised learning, which depends on external labels, SSL utilizes the inherent characteristics of the data to produce its own supervisory signal. However, one frequent issue with SSL methods is representation collapse, where the model outputs a constant input-invariant feature representation. This issue hinders the potential application of SSL methods to new data modalities, as trying to avoid representation collapse wastes researchers' time and effort. This paper introduces a novel SSL algorithm for time-series data called Prediction of Functionals from Masked Latents (PFML). Instead of predicting masked input signals or their latent representations directly, PFML operates by predicting statistical functionals of the input signal corresponding to masked embeddings, given a sequence of unmasked embeddings. The algorithm is designed to avoid representation collapse, rendering it straightforwardly applicable to different time-series data domains, such as novel sensor modalities in clinical data. We demonstrate the effectiveness of PFML through complex, real-life classification tasks across three different data modalities: infant posture and movement classification from multi-sensor inertial measurement unit data, emotion recognition from speech data, and sleep stage classification from EEG data. The results show that PFML is superior to a conceptually similar pre-existing SSL method and competitive against the current state-of-the-art SSL method, while also being conceptually simpler and without suffering from representation collapse.
Authors: Michael Mayr, Georgios C. Chasparis, Josef K\"ung
Abstract: The process industry's high expectations for Digital Twins require modeling approaches that can generalize across tasks and diverse domains with potentially different data dimensions and distributional shifts i.e., Foundational Models. Despite success in natural language processing and computer vision, transfer learning with (self-) supervised signals for pre-training general-purpose models is largely unexplored in the context of Digital Twins in the process industry due to challenges posed by multi-dimensional time-series data, lagged cause-effect dependencies, complex causal structures, and varying number of (exogenous) variables. We propose a novel channel-dependent pre-training strategy that leverages synchronized cause-effect pairs to overcome these challenges by breaking down the multi-dimensional time-series data into pairs of cause-effect variables. Our approach focuses on: (i) identifying highly lagged causal relationships using data-driven methods, (ii) synchronizing cause-effect pairs to generate training samples for channel-dependent pre-training, and (iii) evaluating the effectiveness of this approach in channel-dependent forecasting. Our experimental results demonstrate significant improvements in forecasting accuracy and generalization capability compared to traditional training methods.
Authors: Moritz Schneider, Robert Krug, Narunas Vaskevicius, Luigi Palmieri, Joschka Boedecker
Abstract: Visual Reinforcement Learning (RL) methods often require extensive amounts of data. As opposed to model-free RL, model-based RL (MBRL) offers a potential solution with efficient data utilization through planning. Additionally, RL lacks generalization capabilities for real-world tasks. Prior work has shown that incorporating pre-trained visual representations (PVRs) enhances sample efficiency and generalization. While PVRs have been extensively studied in the context of model-free RL, their potential in MBRL remains largely unexplored. In this paper, we benchmark a set of PVRs on challenging control tasks in a model-based RL setting. We investigate the data efficiency, generalization capabilities, and the impact of different properties of PVRs on the performance of model-based agents. Our results, perhaps surprisingly, reveal that for MBRL current PVRs are not more sample efficient than learning representations from scratch, and that they do not generalize better to out-of-distribution (OOD) settings. To explain this, we analyze the quality of the trained dynamics model. Furthermore, we show that data diversity and network architecture are the most important contributors to OOD generalization performance.
Authors: Fenghua Ling, Kang Chen, Jiye Wu, Tao Han, Jing-Jia Luo, Wanli Ouyang, Lei Bai
Abstract: Seamless forecasting that produces warning information at continuum timescales based on only one system is a long-standing pursuit for weather-climate service. While the rapid advancement of deep learning has induced revolutionary changes in classical forecasting field, current efforts are still focused on building separate AI models for weather and climate forecasts. To explore the seamless forecasting ability based on one AI model, we propose FengWu-Weather to Subseasonal (FengWu-W2S), which builds on the FengWu global weather forecast model and incorporates an ocean-atmosphere-land coupling structure along with a diverse perturbation strategy. FengWu-W2S can generate 6-hourly atmosphere forecasts extending up to 42 days through an autoregressive and seamless manner. Our hindcast results demonstrate that FengWu-W2S reliably predicts atmospheric conditions out to 3-6 weeks ahead, enhancing predictive capabilities for global surface air temperature, precipitation, geopotential height and intraseasonal signals such as the Madden-Julian Oscillation (MJO) and North Atlantic Oscillation (NAO). Moreover, our ablation experiments on forecast error growth from daily to seasonal timescales reveal potential pathways for developing AI-based integrated system for seamless weather-climate forecasting in the future.
Authors: Youngjoon Lee, Jinu Gong, Joonhyuk Kang
Abstract: Given sufficient data from multiple edge devices, federated learning (FL) enables training a shared model without transmitting private data to a central server. However, FL is generally vulnerable to Byzantine attacks from compromised edge devices, which can significantly degrade the model performance. In this paper, we propose a intuitive plugin that can be integrated into existing FL techniques to achieve Byzantine-Resilience. Key idea is to generate virtual data samples and evaluate model consistency scores across local updates to effectively filter out compromised edge devices. By utilizing this scoring mechanism before the aggregation phase, the proposed plugin enables existing FL techniques to become robust against Byzantine attacks while maintaining their original benefits. Numerical results on medical image classification task validate that plugging the proposed approach into representative FL algorithms, effectively achieves Byzantine resilience. Furthermore, the proposed plugin maintains the original convergence properties of the base FL algorithms when no Byzantine attacks are present.
Authors: Vu-Anh Le, Haruko Murakami Wainwright, Hansell Gonzalez-Raymat, Carol Eddy-Dilek
Abstract: Monitored Natural Attenuation (MNA) is gaining prominence as an effective method for managing soil and groundwater contamination due to its cost-efficiency and minimal environmental disruption. Despite its benefits, MNA necessitates extensive groundwater monitoring to ensure that contaminant levels decrease to meet safety standards. This study expands the capabilities of PyLEnM, a Python package designed for long-term environmental monitoring, by incorporating new algorithms to enhance its predictive and analytical functionalities. We introduce methods to estimate the timeframe required for contaminants like Sr-90 and I-129 to reach regulatory safety standards using linear regression and to forecast future contaminant levels with the Bidirectional Long Short-Term Memory (Bi-LSTM) networks. Additionally, Random Forest regression is employed to identify factors influencing the time to reach safety standards. Our methods are illustrated using data from the Savannah River Site (SRS) F-Area, where preliminary findings reveal a notable downward trend in contaminant levels, with variability linked to initial concentrations and groundwater flow dynamics. The Bi-LSTM model effectively predicts contaminant concentrations for the next four years, demonstrating the potential of advanced time series analysis to improve MNA strategies and reduce reliance on manual groundwater sampling. The code, along with its usage instructions, validation, and requirements, is available at: https://github.com/csplevuanh/pylenm_extension.
Authors: Abdullah Abdullah, Fannya Ratana Sandjaja, Ayesha Abdul Majeed, Gyan Wickremasinghe, Karen Rafferty, Vishal Sharma
Abstract: This study investigates uncertainty quantification (UQ) using quantum-classical hybrid machine learning (ML) models for applications in complex and dynamic fields, such as attaining resiliency in supply chain digital twins and financial risk assessment. Although quantum feature transformations have been integrated into ML models for complex data tasks, a gap exists in determining their impact on UQ within their hybrid architectures (quantum-classical approach). This work applies existing UQ techniques for different models within a hybrid framework, examining how quantum feature transformation affects uncertainty propagation. Increasing qubits from 4 to 16 shows varied model responsiveness to outlier detection (OD) samples, which is a critical factor for resilient decision-making in dynamic environments. This work shows how quantum computing techniques can transform data features for UQ, particularly when combined with traditional methods.
Authors: Hossein Hassani, Roozbeh Razavi-Far, Mehrdad Saif, Liang Lin
Abstract: Reinforcement learning (RL) is a sub-domain of machine learning, mainly concerned with solving sequential decision-making problems by a learning agent that interacts with the decision environment to improve its behavior through the reward it receives from the environment. This learning paradigm is, however, well-known for being time-consuming due to the necessity of collecting a large amount of data, making RL suffer from sample inefficiency and difficult generalization. Furthermore, the construction of an explicit reward function that accounts for the trade-off between multiple desiderata of a decision problem is often a laborious task. These challenges have been recently addressed utilizing transfer and inverse reinforcement learning (T-IRL). In this regard, this paper is devoted to a comprehensive review of realizing the sample efficiency and generalization of RL algorithms through T-IRL. Following a brief introduction to RL, the fundamental T-IRL methods are presented and the most recent advancements in each research field have been extensively reviewed. Our findings denote that a majority of recent research works have dealt with the aforementioned challenges by utilizing human-in-the-loop and sim-to-real strategies for the efficient transfer of knowledge from source domains to the target domain under the transfer learning scheme. Under the IRL structure, training schemes that require a low number of experience transitions and extension of such frameworks to multi-agent and multi-intention problems have been the priority of researchers in recent years.
Authors: Hugo Schnoering, Michalis Vazirgiannis
Abstract: Bitcoin, launched in 2008 by Satoshi Nakamoto, established a new digital economy where value can be stored and transferred in a fully decentralized manner - alleviating the need for a central authority. This paper introduces a large scale dataset in the form of a transactions graph representing transactions between Bitcoin users along with a set of tasks and baselines. The graph includes 252 million nodes and 785 million edges, covering a time span of nearly 13 years of and 670 million transactions. Each node and edge is timestamped. As for supervised tasks we provide two labeled sets i. a 33,000 nodes based on entity type and ii. nearly 100,000 Bitcoin addresses labeled with an entity name and an entity type. This is the largest publicly available data set of bitcoin transactions designed to facilitate advanced research and exploration in this domain, overcoming the limitations of existing datasets. Various graph neural network models are trained to predict node labels, establishing a baseline for future research. In addition, several use cases are presented to demonstrate the dataset's applicability beyond Bitcoin analysis. Finally, all data and source code is made publicly available to enable reproducibility of the results.
Authors: Pasquale De Rosa, Y\'erom-David Bromberg, Pascal Felber, Djob Mvondo, Valerio Schiavoni
Abstract: In machine learning (ML), the inference phase is the process of applying pre-trained models to new, unseen data with the objective of making predictions. During the inference phase, end-users interact with ML services to gain insights, recommendations, or actions based on the input data. For this reason, serving strategies are nowadays crucial for deploying and managing models in production environments effectively. These strategies ensure that models are available, scalable, reliable, and performant for real-world applications, such as time series forecasting, image classification, natural language processing, and so on. In this paper, we evaluate the performances of five widely-used model serving frameworks (TensorFlow Serving, TorchServe, MLServer, MLflow, and BentoML) under four different scenarios (malware detection, cryptocoin prices forecasting, image classification, and sentiment analysis). We demonstrate that TensorFlow Serving is able to outperform all the other frameworks in serving deep learning (DL) models. Moreover, we show that DL-specific frameworks (TensorFlow Serving and TorchServe) display significantly lower latencies than the three general-purpose ML frameworks (BentoML, MLFlow, and MLServer).
Authors: Andrea Agostini, Daphn\'e Chopard, Yang Meng, Norbert Fortin, Babak Shahbaba, Stephan Mandt, Thomas M. Sutter, Julia E. Vogt
Abstract: Multimodal data integration and label scarcity pose significant challenges for machine learning in medical settings. To address these issues, we conduct an in-depth evaluation of the newly proposed Multimodal Variational Mixture-of-Experts (MMVM) VAE on the challenging MIMIC-CXR dataset. Our analysis demonstrates that the MMVM VAE consistently outperforms other multimodal VAEs and fully supervised approaches, highlighting its strong potential for real-world medical applications.
Authors: Pooja Aslami, Kejun Chen, Timothy M. Hansen, Malik Hassanaly
Abstract: False data injection attacks (FDIAs) on smart inverters are a growing concern linked to increased renewable energy production. While data-based FDIA detection methods are also actively developed, we show that they remain vulnerable to impactful and stealthy adversarial examples that can be crafted using Reinforcement Learning (RL). We propose to include such adversarial examples in data-based detection training procedure via a continual adversarial RL (CARL) approach. This way, one can pinpoint the deficiencies of data-based detection, thereby offering explainability during their incremental improvement. We show that a continual learning implementation is subject to catastrophic forgetting, and additionally show that forgetting can be addressed by employing a joint training strategy on all generated FDIA scenarios.
Authors: Suraj Racha, Shubh Gupta, Humaira Firdowse, Aastik Solanki, Ganesh Ramakrishnan, Kshitij S. Jadhav
Abstract: Federated Learning (FL) is a pioneering approach in distributed machine learning, enabling collaborative model training across multiple clients while retaining data privacy. However, the inherent heterogeneity due to imbalanced resource representations across multiple clients poses significant challenges, often introducing bias towards the majority class. This issue is particularly prevalent in healthcare settings, where hospitals acting as clients share medical images. To address class imbalance and reduce bias, we propose a co-distillation driven framework in a federated healthcare setting. Unlike traditional federated setups with a designated server client, our framework promotes knowledge sharing among clients to collectively improve learning outcomes. Our experiments demonstrate that in a federated healthcare setting, co-distillation outperforms other federated methods in handling class imbalance. Additionally, we demonstrate that our framework has the least standard deviation with increasing imbalance while outperforming other baselines, signifying the robustness of our framework for FL in healthcare.
Authors: Yalin E. Sagduyu, Tugba Erpek, Aylin Yener, Sennur Ulukus
Abstract: In this paper, we address task-oriented (or goal-oriented) communications where an encoder at the transmitter learns compressed latent representations of data, which are then transmitted over a wireless channel. At the receiver, a decoder performs a machine learning task, specifically for classifying the received signals. The deep neural networks corresponding to the encoder-decoder pair are jointly trained, taking both channel and data characteristics into account. Our objective is to achieve high accuracy in completing the underlying task while minimizing the number of channel uses determined by the encoder's output size. To this end, we propose a multi-round, multi-task learning (MRMTL) approach for the dynamic update of channel uses in multi-round transmissions. The transmitter incrementally sends an increasing number of encoded samples over the channel based on the feedback from the receiver, and the receiver utilizes the signals from a previous round to enhance the task performance, rather than only considering the latest transmission. This approach employs multi-task learning to jointly optimize accuracy across varying number of channel uses, treating each configuration as a distinct task. By evaluating the confidence of the receiver in task decisions, MRMTL decides on whether to allocate additional channel uses in multiple rounds. We characterize both the accuracy and the delay (total number of channel uses) of MRMTL, demonstrating that it achieves the accuracy close to that of conventional methods requiring large numbers of channel uses, but with reduced delay by incorporating signals from a prior round. We consider the CIFAR-10 dataset, convolutional neural network architectures, and AWGN and Rayleigh channel models for performance evaluation. We show that MRMTL significantly improves the efficiency of task-oriented communications, balancing accuracy and latency effectively.
Authors: Jeffrey Olmo, Jared Wilson, Max Forsey, Bryce Hepner, Thomas Vin Howe, David Wingate
Abstract: Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering only activation values and not the effect those activations have on downstream computations. This limits the information available to learn features, and biases the autoencoder towards neglecting features which are represented with small activation values but strongly influence model outputs. To address this, we introduce Gradient SAEs (g-SAEs), which modify the $k$-sparse autoencoder architecture by augmenting the TopK activation function to rely on the gradients of the input activation when selecting the $k$ elements. For a given sparsity level, g-SAEs produce reconstructions that are more faithful to original network performance when propagated through the network. Additionally, we find evidence that g-SAEs learn latents that are on average more effective at steering models in arbitrary contexts. By considering the downstream effects of activations, our approach leverages the dual nature of neural network features as both $\textit{representations}$, retrospectively, and $\textit{actions}$, prospectively. While previous methods have approached the problem of feature discovery primarily focused on the former aspect, g-SAEs represent a step towards accounting for the latter as well.
Authors: Mahsa Khazaei, Azim Ahmadzadeh, Krishna Rukmini Puthucode
Abstract: Quantifying similarities between time series in a meaningful way remains a challenge in time series analysis, despite many advances in the field. Most real-world solutions still rely on a few popular measures, such as Euclidean Distance (EuD), Longest Common Subsequence (LCSS), and Dynamic Time Warping (DTW). The strengths and weaknesses of these measures have been studied extensively, and incremental improvements have been proposed. In this study, however, we present a different similarity measure that fuses the notion of Dubuc's variation from fractal analysis with the Intersection-over-Union (IoU) measure which is widely used in object recognition (also known as the Jaccard Index). In this proof-of-concept paper, we introduce the Multiscale Dubuc Distance (MDD) measure and prove that it is a metric, possessing desirable properties such as the triangle inequality. We use 95 datasets from the UCR Time Series Classification Archive to compare MDD's performance with EuD, LCSS, and DTW. Our experiments show that MDD's overall success, without any case-specific customization, is comparable to DTW with optimized window sizes per dataset. We also highlight several datasets where MDD's performance improves significantly when its single parameter is customized. This customization serves as a powerful tool for gauging MDD's sensitivity to noise. Lastly, we show that MDD's running time is linear in the length of the time series, which is crucial for real-world applications involving very large datasets.
Authors: Simone Carnemolla, Salvatore Calcagno, Simone Palazzo, Daniela Giordano
Abstract: Speech segmentation at both word and phoneme levels is crucial for various speech processing tasks. It significantly aids in extracting meaningful units from an utterance, thus enabling the generation of discrete elements. In this work we propose a model-agnostic framework to perform word boundary detection in a supervised manner also employing a labels augmentation technique and an output-frame selection strategy. We trained and tested on the Buckeye dataset and only tested on TIMIT one, using state-of-the-art encoder models, including pre-trained solutions (Wav2Vec 2.0 and HuBERT), as well as convolutional and convolutional recurrent networks. Our method, with the HuBERT encoder, surpasses the performance of other state-of-the-art architectures, whether trained in supervised or self-supervised settings on the same datasets. Specifically, we achieved F-values of 0.8427 on the Buckeye dataset and 0.7436 on the TIMIT dataset, along with R-values of 0.8489 and 0.7807, respectively. These results establish a new state-of-the-art for both datasets. Beyond the immediate task, our approach offers a robust and efficient preprocessing method for future research in audio tokenization.
Authors: Huizhuo Yuan, Yifeng Liu, Shuang Wu, Xun Zhou, Quanquan Gu
Abstract: Training deep neural networks--and more recently, large models--demands efficient and scalable optimizers. Adaptive gradient algorithms like Adam, AdamW, and their variants have been central to this task. Despite the development of numerous variance reduction algorithms in the past decade aimed at accelerating stochastic optimization in both convex and nonconvex settings, variance reduction has not found widespread success in training deep neural networks or large language models. Consequently, it has remained a less favored approach in modern AI. In this paper, to unleash the power of variance reduction for efficient training of large models, we propose a unified optimization framework, MARS (Make vAriance Reduction Shine), which reconciles preconditioned gradient methods with variance reduction via a scaled stochastic recursive momentum technique. Within our framework, we introduce three instances of MARS that leverage preconditioned gradient updates based on AdamW, Lion, and Shampoo, respectively. We also draw a connection between our algorithms and existing optimizers. Experimental results on training GPT-2 models indicate that MARS consistently outperforms AdamW by a large margin.
Authors: Ermis Soumalias, Jakob Heiss, Jakob Weissteiner, Sven Seuken
Abstract: We study the design of iterative combinatorial auctions (ICAs). The main challenge in this domain is that the bundle space grows exponentially in the number of items. To address this, several papers have recently proposed machine learning (ML)-based preference elicitation algorithms that aim to elicit only the most important information from bidders to maximize efficiency. The SOTA ML-based algorithms elicit bidders' preferences via value queries (i.e., "What is your value for the bundle $\{A,B\}$?"). However, the most popular iterative combinatorial auction in practice elicits information via more practical \emph{demand queries} (i.e., "At prices $p$, what is your most preferred bundle of items?"). In this paper, we examine the advantages of value and demand queries from both an auction design and an ML perspective. We propose a novel ML algorithm that provably integrates the full information from both query types. As suggested by our theoretical analysis, our experimental results verify that combining demand and value queries results in significantly better learning performance. Building on these insights, we present MLHCA, the most efficient ICA ever designed. MLHCA substantially outperforms the previous SOTA in realistic auction settings, delivering large efficiency gains. Compared to the previous SOTA, MLHCA reduces efficiency loss by up to a factor of 10, and in the most challenging and realistic domain, MLHCA outperforms the previous SOTA using 30% fewer queries. Thus, MLHCA achieves efficiency improvements that translate to welfare gains of hundreds of millions of USD, while also reducing the cognitive load on the bidders, establishing a new benchmark both for practicability and for economic impact.
Authors: Cong Fu, Kun Wang, Jiahua Wu, Yizhou Chen, Guangda Huzhang, Yabo Ni, Anxiang Zeng, Zhiming Zhou
Abstract: Modern e-commerce platforms rely heavily on modeling diverse user feedback to provide personalized services. Consequently, multi-task learning has become an integral part of their ranking systems. However, existing multi-task learning methods encounter two main challenges: some lack explicit modeling of task relationships, resulting in inferior performance, while others have limited applicability due to being computationally intensive, having scalability issues, or relying on strong assumptions. To address these limitations and better fit our real-world scenario, pre-rank in Shopee Search, we introduce in this paper ResFlow, a lightweight multi-task learning framework that enables efficient cross-task information sharing via residual connections between corresponding layers of task networks. Extensive experiments on datasets from various scenarios and modalities demonstrate its superior performance and adaptability over state-of-the-art methods. The online A/B tests in Shopee Search showcase its practical value in large-scale industrial applications, evidenced by a 1.29% increase in OPU (order-per-user) without additional system latency. ResFlow is now fully deployed in the pre-rank module of Shopee Search. To facilitate efficient online deployment, we propose a novel offline metric Weighted Recall@K, which aligns well with our online metric OPU, addressing the longstanding online-offline metric misalignment issue. Besides, we propose to fuse scores from the multiple tasks additively when ranking items, which outperforms traditional multiplicative fusion. The code is released at https://github.com/BrunoTruthAlliance/ResFlow
Authors: Dae-Hyeok Lee, Sung-Jin Kim, Si-Hyun Kim
Abstract: The detection of pilots' mental states is critical, as abnormal mental states have the potential to cause catastrophic accidents. This study demonstrates the feasibility of using deep learning techniques to classify different fatigue levels, specifically a normal state, low fatigue, and high fatigue. To the best of our knowledge, this is the first study to classify fatigue levels in pilots. Our approach employs the hybrid deep neural network comprising five convolutional blocks and one long short-term memory block to extract the significant features from electroencephalography signals. Ten pilots participated in the experiment, which was conducted in a simulated flight environment. Compared to four conventional models, our proposed model achieved a superior grand-average accuracy of 0.8801, outperforming other models by at least 0.0599 in classifying fatigue levels. In addition to successfully classifying fatigue levels, our model provided valuable feedback to subjects. Therefore, we anticipate that our study will make the significant contributions to the advancement of autonomous flight and driving technologies, leveraging artificial intelligence in the future.
Authors: Hyeon-Taek Han, Dae-Hyeok Lee, Heon-Gyu Kwak
Abstract: Brain-computer interface (BCI) technology enables direct interaction between humans and computers by analyzing brain signals. Electroencephalogram (EEG) is one of the non-invasive tools used in BCI systems, providing high temporal resolution for real-time applications. However, EEG signals are often affected by a low signal-to-noise ratio, physiological artifacts, and individual variability, representing challenges in extracting distinct features. Also, motor imagery (MI)-based EEG signals could contain features with low correlation to MI characteristics, which might cause the weights of the deep model to become biased towards those features. To address these problems, we proposed the end-to-end deep preprocessing method that effectively enhances MI characteristics while attenuating features with low correlation to MI characteristics. The proposed method consisted of the temporal, spatial, graph, and similarity blocks to preprocess MI-based EEG signals, aiming to extract more discriminative features and improve the robustness. We evaluated the proposed method using the public dataset 2a of BCI Competition IV to compare the performances when integrating the proposed method into the conventional models, including the DeepConvNet, the M-ShallowConvNet, and the EEGNet. The experimental results showed that the proposed method could achieve the improved performances and lead to more clustered feature distributions of MI tasks. Hence, we demonstrated that our proposed method could enhance discriminative features related to MI characteristics.
Authors: Yukino Kawai, Tatsuya Hisada, Kozue Shiomi, Momoko Hayamizu
Abstract: Birds exhibit a variety of flight styles, primarily classified as flapping, which is characterized by rapid up-and-down wing movements, and soaring, which involves gliding with wings outstretched. Each species usually performs specific flight styles, and this has been argued in terms of morphological and physiological adaptation. However, it remains a challenge to evaluate the contribution of each factor to the difference in flight styles. In this study, using phenotypic data from 635 migratory bird species, such as body mass, wing length, and breeding periods, we quantified the relative importance of each feature using Feature Importance and SHAP values, and used them to construct weighted L1 distance matrices and construct NJ trees. Comparison with traditional phylogenetic logistic regression revealed similarity in top-ranked features, but also differences in overall weight distributions and clustering patterns in NJ trees. Our results highlight the complexity of constructing a biologically useful distance matrix from correlated phenotypic features, while the complementary nature of these weighting methods suggests the potential utility of multi-faceted approaches to assessing feature contributions.
Authors: Amanda Vallentin
Abstract: The diagnostic imaging departments are under great pressure due to a growing workload. The number of required scans is growing and there is a shortage of qualified labor. AI solutions for medical imaging applications have shown great potential. However, very few diagnostic imaging models have been approved for hospital use and even fewer are being implemented at the hospitals. The most common reason why software projects fail is poor requirement engineering, especially non-functional requirements (NFRs) can be detrimental to a project. Research shows that machine learning professionals struggle to work with NFRs and that there is a need to adapt NFR frameworks to machine learning, AI-based, software. This study uses qualitative methods to interact with key stakeholders to identify which types of NFRs are important for medical imaging applications. The study was done on a single Danish hospital and found that NFRs of type Efficiency, Accuracy, Interoperability, Reliability, Usability, Adaptability, and Fairness were important to the stakeholders. Especially Efficiency since the diagnostic imaging department is trying to spend as little time as possible on each scan.
Authors: Federico P. Cortese, Antonio Pievatolo
Abstract: Thermal comfort is essential for well-being in urban spaces, especially as cities face increasing heat from urbanization and climate change. Existing thermal comfort models usually overlook temporal dynamics alongside spatial dependencies. We address this problem by introducing a spatio-temporal jump model that clusters data with persistence across both spatial and temporal dimensions. This framework enhances interpretability, minimizes abrupt state changes, and easily handles missing data. We validate our approach through extensive simulations, demonstrating its accuracy in recovering the true underlying partition. When applied to hourly environmental data gathered from a set of weather stations located across the city of Singapore, our proposal identifies meaningful thermal comfort regimes, demonstrating its effectiveness in dynamic urban settings and suitability for real-world monitoring. The comparison of these regimes with feedback on thermal preference indicates the potential of an unsupervised approach to avoid extensive surveys.
Authors: BoHao Chen
Abstract: Partial multi-view clustering (PVC) presents significant challenges practical research problem for data analysis in real-world applications, especially when some views of the data are partially missing. Existing clustering methods struggle to handle incomplete views effectively, leading to suboptimal clustering performance. In this paper, we propose a novel dual optimization framework based on contrastive learning, which aims to maximize the consistency of latent features in incomplete multi-view data and improve clustering performance through deep learning models. By combining a fine-tuned Vision Transformer and k-nearest neighbors (KNN), we fill in missing views and dynamically adjust view weights using self-supervised learning and meta-learning. Experimental results demonstrate that our framework outperforms state-of-the-art clustering models on the BDGP and HW datasets, particularly in handling complex and incomplete multi-view data.
Authors: Zohaib Masood (Ontario Tech University), Miguel Vargas Martin (Ontario Tech University)
Abstract: The use of Large Language Models (LLMs) in software development is rapidly growing, with developers increasingly relying on these models for coding assistance, including security-critical tasks. Our work presents a comprehensive comparison between traditional static analysis tools for cryptographic API misuse detection-CryptoGuard, CogniCrypt, and Snyk Code-and the LLMs-GPT and Gemini. Using benchmark datasets (OWASP, CryptoAPI, and MASC), we evaluate the effectiveness of each tool in identifying cryptographic misuses. Our findings show that GPT 4-o-mini surpasses current state-of-the-art static analysis tools on the CryptoAPI and MASC datasets, though it lags on the OWASP dataset. Additionally, we assess the quality of LLM responses to determine which models provide actionable and accurate advice, giving developers insights into their practical utility for secure coding. This study highlights the comparative strengths and limitations of static analysis versus LLM-driven approaches, offering valuable insights into the evolving role of AI in advancing software security practices.
Authors: Vasisht Duddu, Rui Zhang, N. Asokan
Abstract: Machine learning (ML) defenses protect against various risks to security, privacy, and fairness. Real-life models need simultaneous protection against multiple different risks which necessitates combining multiple defenses. But combining defenses with conflicting interactions in an ML model can be ineffective, incurring a significant drop in the effectiveness of one or more defenses being combined. Practitioners need a way to determine if a given combination can be effective. Experimentally identifying effective combinations can be time-consuming and expensive, particularly when multiple defenses need to be combined. We need an inexpensive, easy-to-use combination technique to identify effective combinations. Ideally, a combination technique should be (a) accurate (correctly identifies whether a combination is effective or not), (b) scalable (allows combining multiple defenses), (c) non-invasive (requires no change to the defenses being combined), and (d) general (is applicable to different types of defenses). Prior works have identified several ad-hoc techniques but none satisfy all the requirements above. We propose a principled combination technique, Def\Con, to identify effective defense combinations. Def\Con meets all requirements, achieving 90% accuracy on eight combinations explored in prior work and 81% in 30 previously unexplored combinations that we empirically evaluate in this paper.
Authors: Ning Bao, Keiichiro Furuya, Gun Suer
Abstract: We search for efficient disentanglers on random Clifford circuits of two-qubit gates arranged in a brick-wall pattern, using the proximal policy optimization (PPO) algorithm \cite{schulman2017proximalpolicyoptimizationalgorithms}. Disentanglers are defined as a set of projective measurements inserted between consecutive entangling layers. An efficient disentangler is a set of projective measurements that minimize the averaged von Neumann entropy of the final state with the least number of total projections possible. The problem is naturally amenable to reinforcement learning techniques by taking the binary matrix representing the projective measurements along the circuit as our state, and actions as bit flipping operations on this binary matrix that add or delete measurements at specified locations. We give rewards to our agent dependent on the averaged von Neumann entropy of the final state and the configuration of measurements, such that the agent learns the optimal policy that will take him from the initial state of no measurements to the optimal measurement state that minimizes the entanglement entropy. Our results indicate that the number of measurements required to disentangle a random quantum circuit is drastically less than the numerical results of measurement-induced phase transition papers. Additionally, the reinforcement learning procedure enables us to characterize the pattern of optimal disentanglers, which is not possible in the works of measurement-induced phase transitions.
Authors: Rishan Mehta, Param Rajpura, Yogesh Kumar Meena
Abstract: Resting-state EEG data in neuroscience research serve as reliable markers for user identification and reveal individual-specific traits. Despite this, the use of resting-state data in EEG classification models is limited. In this work, we propose a feature concatenation approach to enhance decoding models' generalization by integrating resting-state EEG, aiming to improve motor imagery BCI performance and develop a user-generalized model. Using feature concatenation, we combine the EEGNet model, a standard convolutional neural network for EEG signal classification, with functional connectivity measures derived from resting-state EEG data. The findings suggest that although grounded in neuroscience with data-driven learning, the concatenation approach has limited benefits for generalizing models in within-user and across-user scenarios. While an improvement in mean accuracy for within-user scenarios is observed on two datasets, concatenation doesn't benefit across-user scenarios when compared with random data concatenation. The findings indicate the necessity of further investigation on the model interpretability and the effect of random data concatenation on model robustness.
Authors: Trevor Seets, Andreas Velten
Abstract: Fluorescence guided surgery (FGS) is a promising surgical technique that gives surgeons a unique view of tissue that is used to guide their practice by delineating tissue types and diseased areas. As new fluorescent contrast agents are developed that have low fluorescent photon yields, it becomes increasingly important to develop computational models to allow FGS systems to maintain good video quality in real time environments. To further complicate this task, FGS has a difficult bias noise term from laser leakage light (LLL) that represents unfiltered excitation light that can be on the order of the fluorescent signal. Most conventional video denoising methods focus on zero mean noise, and non-causal processing, both of which are violated in FGS. Luckily in FGS, often a co-located reference video is also captured which we use to simulate the LLL and assist in the denoising processes. In this work, we propose an accurate noise simulation pipeline that includes LLL and propose three baseline deep learning based algorithms for FGS video denoising.
Authors: Farnaz Niknia, Ping Wang
Abstract: This paper addresses the challenge of edge caching in dynamic environments, where rising traffic loads strain backhaul links and core networks. We propose a Proximal Policy Optimization (PPO)-based caching strategy that fully incorporates key file attributes such as size, lifetime, importance, and popularity, while also considering random file request arrivals, reflecting more realistic edge caching scenarios. In dynamic environments, changes such as shifts in content popularity and variations in request rates frequently occur, making previously learned policies less effective as they were optimized for earlier conditions. Without adaptation, caching efficiency and response times can degrade. While learning a new policy from scratch in a new environment is an option, it is highly inefficient and computationally expensive. Thus, adapting an existing policy to these changes is critical. To address this, we develop a mechanism that detects changes in content popularity and request rates, ensuring timely adjustments to the caching strategy. We also propose a transfer learning-based PPO algorithm that accelerates convergence in new environments by leveraging prior knowledge. Simulation results demonstrate the significant effectiveness of our approach, outperforming a recent Deep Reinforcement Learning (DRL)-based method.
Authors: Maraz Mia, Darius Derakhshan, Mir Mehedi A. Pritom
Abstract: Phishing has been a prevalent cyber threat that manipulates users into revealing sensitive private information through deceptive tactics, designed to masquerade as trustworthy entities. Over the years, proactively detection of phishing URLs (or websites) has been established as an widely-accepted defense approach. In literature, we often find supervised Machine Learning (ML) models with highly competitive performance for detecting phishing websites based on the extracted features from both phishing and benign (i.e., legitimate) websites. However, it is still unclear if these features or indicators are dependent on a particular dataset or they are generalized for overall phishing detection. In this paper, we delve deeper into this issue by analyzing two publicly available phishing URL datasets, where each dataset has its own set of unique and overlapping features related to URL string and website contents. We want to investigate if overlapping features are similar in nature across datasets and how does the model perform when trained on one dataset and tested on the other. We conduct practical experiments and leverage explainable AI (XAI) methods such as SHAP plots to provide insights into different features' contributions in case of phishing detection to answer our primary question, ``Can features for phishing URL detection be trusted across diverse dataset?''. Our case study experiment results show that features for phishing URL detection can often be dataset-dependent and thus may not be trusted across different datasets even though they share same set of feature behaviors.
Authors: Ahmed Aboulfotouh, Ashkan Eshaghbeigi, Dimitrios Karslidis, Hatem Abou-Zeid
Abstract: Foundational deep learning (DL) models are general models, trained on large, diverse, and unlabelled datasets, typically using self-supervised learning techniques have led to significant advancements especially in natural language processing. These pretrained models can be fine-tuned for related downstream tasks, offering faster development and reduced training costs, while often achieving improved performance. In this work, we introduce Masked Spectrogram Modeling, a novel self-supervised learning approach for pretraining foundational DL models on radio signals. Adopting a Convolutional LSTM architecture for efficient spatio-temporal processing, we pretrain the model with an unlabelled radio dataset collected from over-the-air measurements. Subsequently, the pretrained model is fine-tuned for two downstream tasks: spectrum forecasting and segmentation. Experimental results demonstrate that our methodology achieves competitive performance in both forecasting accuracy and segmentation, validating its effectiveness for developing foundational radio models.
Authors: Shijie Zhou, Huaisheng Zhu, Rohan Sharma, Ruiyi Zhang, Kaiyi Ji, Changyou Chen
Abstract: Diffusion models have emerged as a powerful foundation model for visual generation. With an appropriate sampling process, it can effectively serve as a generative prior to solve general inverse problems. Current posterior sampling based methods take the measurement (i.e., degraded image sample) into the posterior sampling to infer the distribution of the target data (i.e., clean image sample). However, in this manner, we show that high-frequency information can be prematurely introduced during the early stages, which could induce larger posterior estimate errors during the restoration sampling. To address this issue, we first reveal that forming the log posterior gradient with the noisy measurement ( i.e., samples from a diffusion forward process) instead of the clean one can benefit the reverse process. Consequently, we propose a novel diffusion posterior sampling method DPS-CM, which incorporates a Crafted Measurement (i.e., samples generated by a reverse denoising process, compared to random sampling with noise in standard methods) to form the posterior estimate. This integration aims to mitigate the misalignment with the diffusion prior caused by cumulative posterior estimate errors. Experimental results demonstrate that our approach significantly improves the overall capacity to solve general and noisy inverse problems, such as Gaussian deblurring, super-resolution, inpainting, nonlinear deblurring, and tasks with Poisson noise, relative to existing approaches.
Authors: Ho Fung Tsoi, Dylan Rankin, Cecile Caillol, Miles Cranmer, Sridhara Dasu, Javier Duarte, Philip Harris, Elliot Lipeles, Vladimir Loncar
Abstract: We introduce SymbolFit, a framework that automates parametric modeling by using symbolic regression to perform a machine-search for functions that fit the data, while simultaneously providing uncertainty estimates in a single run. Traditionally, constructing a parametric model to accurately describe binned data has been a manual and iterative process, requiring an adequate functional form to be determined before the fit can be performed. The main challenge arises when the appropriate functional forms cannot be derived from first principles, especially when there is no underlying true closed-form function for the distribution. In this work, we address this problem by utilizing symbolic regression, a machine learning technique that explores a vast space of candidate functions without needing a predefined functional form, treating the functional form itself as a trainable parameter. Our approach is demonstrated in data analysis applications in high-energy physics experiments at the CERN Large Hadron Collider (LHC). We demonstrate its effectiveness and efficiency using five real proton-proton collision datasets from new physics searches at the LHC, namely the background modeling in resonance searches for high-mass dijet, trijet, paired-dijet, diphoton, and dimuon events. We also validate the framework using several toy datasets with one and more variables.
Authors: Zhichen Zeng, Xiaolong Liu, Mengyue Hang, Xiaoyi Liu, Qinghai Zhou, Chaofei Yang, Yiqun Liu, Yichen Ruan, Laming Chen, Yuxin Chen, Yujia Hao, Jiaqi Xu, Jade Nie, Xi Liu, Buyun Zhang, Wei Wen, Siyang Yuan, Kai Wang, Wen-Yen Chen, Yiping Han, Huayu Li, Chunzhi Yang, Bo Long, Philip S. Yu, Hanghang Tong, Jiyan Yang
Abstract: Click-through rate (CTR) prediction, which predicts the probability of a user clicking an ad, is a fundamental task in recommender systems. The emergence of heterogeneous information, such as user profile and behavior sequences, depicts user interests from different aspects. A mutually beneficial integration of heterogeneous information is the cornerstone towards the success of CTR prediction. However, most of the existing methods suffer from two fundamental limitations, including (1) insufficient inter-mode interaction due to the unidirectional information flow between modes, and (2) aggressive information aggregation caused by early summarization, resulting in excessive information loss. To address the above limitations, we propose a novel module named InterFormer to learn heterogeneous information interaction in an interleaving style. To achieve better interaction learning, InterFormer enables bidirectional information flow for mutually beneficial learning across different modes. To avoid aggressive information aggregation, we retain complete information in each data mode and use a separate bridging arch for effective information selection and summarization. Our proposed InterFormer achieves state-of-the-art performance on three public datasets and a large-scale industrial dataset.
Authors: Pranav Guruprasad, Negar Mokhberian, Nikhil Varghese, Chandra Khatri, Amol Kelkar
Abstract: Intent discovery is crucial for both building new conversational agents and improving existing ones. While several approaches have been proposed for intent discovery, most rely on clustering to group similar utterances together. Traditional evaluation of these utterance clusters requires intent labels for each utterance, limiting scalability. Although some clustering quality metrics exist that do not require labeled data, they focus solely on cluster geometry while ignoring the linguistic nuances present in conversational transcripts. In this paper, we introduce Keyword-based Utterance Level Clustering Quality (KULCQ), an unsupervised metric that leverages keyword analysis to evaluate clustering quality. We demonstrate KULCQ's effectiveness by comparing it with existing unsupervised clustering metrics and validate its performance through comprehensive ablation studies. Our results show that KULCQ better captures semantic relationships in conversational data while maintaining consistency with geometric clustering principles.
Authors: Alexander E. Siemenn, Basita Das, Kangyu Ji, Fang Sheng, Tonio Buonassisi
Abstract: Integrating autonomous contact-based robotic characterization into self-driving laboratories can enhance measurement quality, reliability, and throughput. While deep learning models support robust autonomy, current methods lack pixel-precision positioning and require extensive labeled data. To overcome these challenges, we propose a self-supervised convolutional neural network with a spatially differentiable loss function, incorporating shape priors to refine predictions of optimal robot contact poses for semiconductor characterization. This network improves valid pose generation by 20.0%, relative to existing models. We demonstrate our network's performance by driving a 4-degree-of-freedom robot to characterize photoconductivity at 3,025 predicted poses across a gradient of perovskite compositions, achieving throughputs over 125 measurements per hour. Spatially mapping photoconductivity onto each drop-casted film reveals regions of inhomogeneity. With this self-supervised deep learning-driven robotic system, we enable high-precision and reliable automation of contact-based characterization techniques at high throughputs, thereby allowing the measurement of previously inaccessible yet important semiconductor properties for self-driving laboratories.
Authors: Arman Ter-Petrosyan, Michael Holden, Jenna A. Bilbrey, Sarah Akers, Christina Doty, Kayla H. Yano, Le Wang, Rajendra Paudel, Eric Lang, Khalid Hattar, Ryan B. Comes, Yingge Du, Bethany E. Matthews, Steven R. Spurgeon
Abstract: The development of high-performance materials for microelectronics, energy storage, and extreme environments depends on our ability to describe and direct property-defining microstructural order. Our present understanding is typically derived from laborious manual analysis of imaging and spectroscopy data, which is difficult to scale, challenging to reproduce, and lacks the ability to reveal latent associations needed for mechanistic models. Here, we demonstrate a multi-modal machine learning (ML) approach to describe order from electron microscopy analysis of the complex oxide La$_{1-x}$Sr$_x$FeO$_3$. We construct a hybrid pipeline based on fully and semi-supervised classification, allowing us to evaluate both the characteristics of each data modality and the value each modality adds to the ensemble. We observe distinct differences in the performance of uni- and multi-modal models, from which we draw general lessons in describing crystal order using computer vision.
Authors: Takuya Kiyokawa, Eiki Nagata, Yoshihisa Tsurumine, Yuhwan Kwon, Takamitsu Matsubara
Abstract: Mobile grasping enhances manipulation efficiency by utilizing robots' mobility. This study aims to enable a commercial off-the-shelf robot for mobile grasping, requiring precise timing and pose adjustments. Self-supervised learning can develop a generalizable policy to adjust the robot's velocity and determine grasp position and orientation based on the target object's shape and pose. Due to mobile grasping's complexity, action primitivization and step-by-step learning are crucial to avoid data sparsity in learning from trial and error. This study simplifies mobile grasping into two grasp action primitives and a moving action primitive, which can be operated with limited degrees of freedom for the manipulator. This study introduces three fully convolutional neural network (FCN) models to predict static grasp primitive, dynamic grasp primitive, and residual moving velocity error from visual inputs. A two-stage grasp learning approach facilitates seamless FCN model learning. The ablation study demonstrated that the proposed method achieved the highest grasping accuracy and pick-and-place efficiency. Furthermore, randomizing object shapes and environments in the simulation effectively achieved generalizable mobile grasping.
Authors: Songting Liu
Abstract: Zero-shot voice conversion aims to transform a source speech utterance to match the timbre of a reference speech from an unseen speaker. Traditional approaches struggle with timbre leakage, insufficient timbre representation, and mismatches between training and inference tasks. We propose Seed-VC, a novel framework that addresses these issues by introducing an external timbre shifter during training to perturb the source speech timbre, mitigating leakage and aligning training with inference. Additionally, we employ a diffusion transformer that leverages the entire reference speech context, capturing fine-grained timbre features through in-context learning. Experiments demonstrate that Seed-VC outperforms strong baselines like OpenVoice and CosyVoice, achieving higher speaker similarity and lower word error rates in zero-shot voice conversion tasks. We further extend our approach to zero-shot singing voice conversion by incorporating fundamental frequency (F0) conditioning, resulting in comparative performance to current state-of-the-art methods. Our findings highlight the effectiveness of Seed-VC in overcoming core challenges, paving the way for more accurate and versatile voice conversion systems.
Authors: Ding Li, Ziqi Zhang, Mengyu Yao, Yifeng Cai, Yao Guo, Xiangqun Chen
Abstract: Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's computation speed but commercial widely-available GPUs usually lack security protection. To this end, scholars introduce TSDP, a method that protects privacy-sensitive weights within TEEs and offloads insensitive weights to GPUs. Nevertheless, current methods do not consider the presence of a knowledgeable adversary who can access abundant publicly available pre-trained models and datasets. This paper investigates the security of existing methods against such a knowledgeable adversary and reveals their inability to fulfill their security promises. Consequently, we introduce a novel partition before training strategy, which effectively separates privacy-sensitive weights from other components of the model. Our evaluation demonstrates that our approach can offer full model protection with a computational cost reduced by a factor of 10. In addition to traditional CNN models, we also demonstrate the scalability to large language models. Our approach can compress the private functionalities of the large language model to lightweight slices and achieve the same level of protection as the shielding-whole-model baseline.
Authors: Thanh Tam Nguyen, Zhao Ren, Trinh Pham, Phi Le Nguyen, Hongzhi Yin, Quoc Viet Hung Nguyen
Abstract: The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation. Traditional visual editing tools require significant expertise, limiting accessibility. Recent strides in instruction-based editing have enabled intuitive interaction with visual content, using natural language as a bridge between user intent and complex editing operations. This survey provides an overview of these techniques, focusing on how LLMs and multimodal models empower users to achieve precise visual modifications without deep technical knowledge. By synthesizing over 100 publications, we explore methods from generative adversarial networks to diffusion models, examining multimodal integration for fine-grained content control. We discuss practical applications across domains such as fashion, 3D scene manipulation, and video synthesis, highlighting increased accessibility and alignment with human intuition. Our survey compares existing literature, emphasizing LLM-empowered editing, and identifies key challenges to stimulate further research. We aim to democratize powerful visual editing across various industries, from entertainment to education. Interested readers are encouraged to access our repository at https://github.com/tamlhp/awesome-instruction-editing.
URLs: https://github.com/tamlhp/awesome-instruction-editing.
Authors: Zhi Zhang, Carlos Misael Madrid Padilla, Xiaokai Luo, Oscar Hernan Madrid Padilla, Daren Wang
Abstract: In this paper, we focus on fully connected deep neural networks utilizing the Rectified Linear Unit (ReLU) activation function for nonparametric estimation. We derive non-asymptotic bounds that lead to convergence rates, addressing both temporal and spatial dependence in the observed measurements. By accounting for dependencies across time and space, our models better reflect the complexities of real-world data, enhancing both predictive performance and theoretical robustness. We also tackle the curse of dimensionality by modeling the data on a manifold, exploring the intrinsic dimensionality of high-dimensional data. We broaden existing theoretical findings of temporal-spatial analysis by applying them to neural networks in more general contexts and demonstrate that our proof techniques are effective for models with short-range dependence. Our empirical simulations across various synthetic response functions underscore the superior performance of our method, outperforming established approaches in the existing literature. These findings provide valuable insights into the strong capabilities of dense neural networks for temporal-spatial modeling across a broad range of function classes.
Authors: Vladimir Braverman, Prathamesh Dharangutte, Shreyas Pai, Vihan Shah, Chen Wang
Abstract: We study the dynamic correlation clustering problem with $\textit{adaptive}$ edge label flips. In correlation clustering, we are given a $n$-vertex complete graph whose edges are labeled either $(+)$ or $(-)$, and the goal is to minimize the total number of $(+)$ edges between clusters and the number of $(-)$ edges within clusters. We consider the dynamic setting with adversarial robustness, in which the $\textit{adaptive}$ adversary could flip the label of an edge based on the current output of the algorithm. Our main result is a randomized algorithm that always maintains an $O(1)$-approximation to the optimal correlation clustering with $O(\log^{2}{n})$ amortized update time. Prior to our work, no algorithm with $O(1)$-approximation and $\text{polylog}{(n)}$ update time for the adversarially robust setting was known. We further validate our theoretical results with experiments on synthetic and real-world datasets with competitive empirical performances. Our main technical ingredient is an algorithm that maintains $\textit{sparse-dense decomposition}$ with $\text{polylog}{(n)}$ update time, which could be of independent interest.
Authors: Yongfan Liu, Hyoukjun Kwon
Abstract: Stereo depth estimation is a fundamental component in augmented reality (AR) applications. Although AR applications require very low latency for their real-time applications, traditional depth estimation models often rely on time-consuming preprocessing steps such as rectification to achieve high accuracy. Also, non standard ML operator based algorithms such as cost volume also require significant latency, which is aggravated on compute resource-constrained mobile platforms. Therefore, we develop hardware-friendly alternatives to the costly cost volume and preprocessing and design two new models based on them, MultiHeadDepth and HomoDepth. Our approaches for cost volume is replacing it with a new group-pointwise convolution-based operator and approximation of consine similarity based on layernorm and dot product. For online stereo rectification (preprocessing), we introduce homograhy matrix prediction network with a rectification positional encoding (RPE), which delivers both low latency and robustness to unrectified images, which eliminates the needs for preprocessing. Our MultiHeadDepth, which includes optimized cost volume, provides 11.8-30.3% improvements in accuracy and 22.9-25.2% reduction in latency compared to a state-of-the-art depth estimation model for AR glasses from industry. Our HomoDepth, which includes optimized preprocessing (Homograhpy + RPE) upon MultiHeadDepth, can process unrectified images and reduce the end-to-end latency by 44.5%. We adopt a multi-task learning framework to handle misaligned stereo inputs on HomoDepth, which reduces theAbsRel error by 10.0-24.3%. The results demonstrate the efficacy of our approaches in achieving both high model performance with low latency, which makes a step forward toward practical depth estimation on future AR devices.
Authors: Fatahlla Moreh (Christian Albrechts University, Kiel, Germany), Yusuf Hasan (Aligarh Muslim University, Aligarh, India), Bilal Zahid Hussain (Texas A&M University, College Station, USA), Mohammad Ammar (Aligarh Muslim University, Aligarh, India), Sven Tomforde (Christian Albrechts University, Kiel, Germany)
Abstract: Micro Crack detection using deep neural networks (DNNs) through an automated pipeline using wave fields interacting with the damaged areas is highly sought after. These high-dimensional spatio-temporal crack data are limited, and these datasets have large dimensions in the temporal domain. The dataset presents a substantial class imbalance, with crack pixels constituting an average of only 5% of the total pixels per sample. This extreme class imbalance poses a challenge for deep learning models with the different micro-scale cracks, as the network can be biased toward predicting the majority class, generally leading to poor detection accuracy. This study builds upon the previous benchmark SpAsE-Net, an asymmetric encoder-decoder network for micro-crack detection. The impact of various activation and loss functions were examined through feature space visualization using the manifold discovery and analysis (MDA) algorithm. The optimized architecture and training methodology achieved an accuracy of 86.85%.
Authors: Laura O'Mahony, Nikola S. Nikolov, David JP O'Sullivan
Abstract: Recent efforts to understand intermediate representations in deep neural networks have commonly attempted to label individual neurons and combinations of neurons that make up linear directions in the latent space by examining extremal neuron activations and the highest direction projections. In this paper, we show that this approach, although yielding a good approximation for many purposes, fails to capture valuable information about the behaviour of a representation. Neural network activations are generally dense, and so a more complex, but realistic scenario is that linear directions encode information at various levels of stimulation. We hypothesise that non-extremal level activations contain complex information worth investigating, such as statistical associations, and thus may be used to locate confounding human interpretable concepts. We explore the value of studying a range of neuron activations by taking the case of mid-level output neuron activations and demonstrate on a synthetic dataset how they can inform us about aspects of representations in the penultimate layer not evident through analysing maximal activations alone. We use our findings to develop a method to curate data from mid-range logit samples for retraining to mitigate spurious correlations, or confounding concepts in the penultimate layer, on real benchmark datasets. The success of our method exemplifies the utility of inspecting non-maximal activations to extract complex relationships learned by models.
Authors: Anna Goldie, Azalia Mirhoseini, Jeff Dean
Abstract: In 2020, we introduced a deep reinforcement learning method capable of generating superhuman chip layouts, which we then published in Nature and open-sourced on GitHub. AlphaChip has inspired an explosion of work on AI for chip design, and has been deployed in state-of-the-art chips across Alphabet and extended by external chipmakers. Even so, a non-peer-reviewed invited paper at ISPD 2023 questioned its performance claims, despite failing to run our method as described in Nature. For example, it did not pre-train the RL method (removing its ability to learn from prior experience), used substantially fewer compute resources (20x fewer RL experience collectors and half as many GPUs), did not train to convergence (standard practice in machine learning), and evaluated on test cases that are not representative of modern chips. Recently, Igor Markov published a meta-analysis of three papers: our peer-reviewed Nature paper, the non-peer-reviewed ISPD paper, and Markov's own unpublished paper (though he does not disclose that he co-authored it). Although AlphaChip has already achieved widespread adoption and impact, we publish this response to ensure that no one is wrongly discouraged from innovating in this impactful area.
Authors: Chi Liu, Jiangxia Cao, Rui Huang, Kai Zheng, Qiang Luo, Kun Gai, Guorui Zhou
Abstract: In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules. Traditionally, the dominant retrieval method has been Embedding-Based Retrieval (EBR) using a Deep Neural Network (DNN) dual-tower structure. However, applying transformer in retrieval tasks has been the focus of recent research, though real-world industrial deployment still presents significant challenges. In this paper, we introduce KuaiFormer, a novel transformer-based retrieval framework deployed in a large-scale content recommendation system. KuaiFormer fundamentally redefines the retrieval process by shifting from conventional score estimation tasks (such as click-through rate estimate) to a transformer-driven Next Action Prediction paradigm. This shift enables more effective real-time interest acquisition and multi-interest extraction, significantly enhancing retrieval performance. KuaiFormer has been successfully integrated into Kuaishou App's short-video recommendation system since May 2024, serving over 400 million daily active users and resulting in a marked increase in average daily usage time of Kuaishou users. We provide insights into both the technical and business aspects of deploying transformer in large-scale recommendation systems, addressing practical challenges encountered during industrial implementation. Our findings offer valuable guidance for engineers and researchers aiming to leverage transformer models to optimize large-scale content recommendation systems.
Authors: Kedi Zheng, Qixin Chen, Yi Wang, Chongqing Kang, Le Xie
Abstract: Having a better understanding of how locational marginal prices (LMPs) change helps in price forecasting and market strategy making. This paper investigates the fundamental distribution of the congestion part of LMPs in high-dimensional Euclidean space using an unsupervised approach. LMP models based on the lossless and lossy DC optimal power flow (DC-OPF) are analyzed to show the overlapping subspace property of the LMP data. The congestion part of LMPs is spanned by certain row vectors of the power transfer distribution factor (PTDF) matrix, and the subspace attributes of an LMP vector uniquely are found to reflect the instantaneous congestion status of all the transmission lines. The proposed method searches for the basis vectors that span the subspaces of congestion LMP data in hierarchical ways. In the bottom-up search, the data belonging to 1-dimensional subspaces are detected, and other data are projected on the orthogonal subspaces. This procedure is repeated until all the basis vectors are found or the basis gap appears. Top-down searching is used to address the basis gap by hyperplane detection with outliers. Once all the basis vectors are detected, the congestion status can be identified. Numerical experiments based on the IEEE 30-bus system, IEEE 118-bus system, Illinois 200-bus system, and Southwest Power Pool are conducted to show the performance of the proposed method.
Authors: Shuai Gong, Chaoran Cui, Chunyun Zhang, Wenna Wang, Xiushan Nie, Lei Zhu
Abstract: Federated domain generalization (FedDG) aims to improve the global model generalization in unseen domains by addressing data heterogeneity under privacy-preserving constraints. A common strategy in existing FedDG studies involves sharing domain-specific knowledge among clients, such as spectrum information, class prototypes, and data styles. However, this knowledge is extracted directly from local client samples, and sharing such sensitive information poses a potential risk of data leakage, which might not fully meet the requirements of FedDG. In this paper, we introduce prompt learning to adapt pre-trained vision-language models (VLMs) in the FedDG scenario, and leverage locally learned prompts as a more secure bridge to facilitate knowledge transfer among clients. Specifically, we propose a novel FedDG framework through Prompt Learning and AggregatioN (PLAN), which comprises two training stages to collaboratively generate local prompts and global prompts at each federated round. First, each client performs both text and visual prompt learning using their own data, with local prompts indirectly synchronized by regarding the global prompts as a common reference. Second, all domain-specific local prompts are exchanged among clients and selectively aggregated into the global prompts using lightweight attention-based aggregators. The global prompts are finally applied to adapt VLMs to unseen target domains. As our PLAN framework requires training only a limited number of prompts and lightweight aggregators, it offers notable advantages in computational and communication efficiency for FedDG. Extensive experiments demonstrate the superior generalization ability of PLAN across four benchmark datasets.
Authors: David Shulman, Itai Dattner
Abstract: This paper introduces an adaptive physics-guided neural network (APGNN) framework for predicting quality attributes from image data by integrating physical laws into deep learning models. The APGNN adaptively balances data-driven and physics-informed predictions, enhancing model accuracy and robustness across different environments. Our approach is evaluated on both synthetic and real-world datasets, with comparisons to conventional data-driven models such as ResNet. For the synthetic data, 2D domains were generated using three distinct governing equations: the diffusion equation, the advection-diffusion equation, and the Poisson equation. Non-linear transformations were applied to these domains to emulate complex physical processes in image form. In real-world experiments, the APGNN consistently demonstrated superior performance in the diverse thermal image dataset. On the cucumber dataset, characterized by low material diversity and controlled conditions, APGNN and PGNN showed similar performance, both outperforming the data-driven ResNet. However, in the more complex thermal dataset, particularly for outdoor materials with higher environmental variability, APGNN outperformed both PGNN and ResNet by dynamically adjusting its reliance on physics-based versus data-driven insights. This adaptability allowed APGNN to maintain robust performance across structured, low-variability settings and more heterogeneous scenarios. These findings underscore the potential of adaptive physics-guided learning to integrate physical constraints effectively, even in challenging real-world contexts with diverse environmental conditions.
Authors: Rutger Hendrix, Federica Proietto Salanitri, Concetto Spampinato, Simone Palazzo, Ulas Bagci
Abstract: We introduce FedEvPrompt, a federated learning approach that integrates principles of evidential deep learning, prompt tuning, and knowledge distillation for distributed skin lesion classification. FedEvPrompt leverages two sets of prompts: b-prompts (for low-level basic visual knowledge) and t-prompts (for task-specific knowledge) prepended to frozen pre-trained Vision Transformer (ViT) models trained in an evidential learning framework to maximize class evidences. Crucially, knowledge sharing across federation clients is achieved only through knowledge distillation on attention maps generated by the local ViT models, ensuring enhanced privacy preservation compared to traditional parameter or synthetic image sharing methodologies. FedEvPrompt is optimized within a round-based learning paradigm, where each round involves training local models followed by attention maps sharing with all federation clients. Experimental validation conducted in a real distributed setting, on the ISIC2019 dataset, demonstrates the superior performance of FedEvPrompt against baseline federated learning algorithms and knowledge distillation methods, without sharing model parameters. In conclusion, FedEvPrompt offers a promising approach for federated learning, effectively addressing challenges such as data heterogeneity, imbalance, privacy preservation, and knowledge sharing.
Authors: Muhammad Zakwan, Giancarlo Ferrari-Trecate
Abstract: The control of large-scale cyber-physical systems requires optimal distributed policies relying solely on limited communication with neighboring agents. However, computing stabilizing controllers for nonlinear systems while optimizing complex costs remains a significant challenge. Neural Networks (NNs), known for their expressivity, can be leveraged to parametrize control policies that yield good performance. However, NNs' sensitivity to small input changes poses a risk of destabilizing the closed-loop system. Many existing approaches enforce constraints on the controllers' parameter space to guarantee closed-loop stability, leading to computationally expensive optimization procedures. To address these problems, we leverage the framework of port-Hamiltonian systems to design continuous-time distributed control policies for nonlinear systems that guarantee closed-loop stability and finite $\mathcal{L}_2$ or incremental $\mathcal{L}_2$ gains, independent of the optimzation parameters of the controllers. This eliminates the need to constrain parameters during optimization, allowing the use of standard techniques such as gradient-based methods. Additionally, we discuss discretization schemes that preserve the dissipation properties of these controllers for implementation on embedded systems. The effectiveness of the proposed distributed controllers is demonstrated through consensus control of non-holonomic mobile robots subject to collision avoidance and averaged voltage regulation with weighted power sharing in DC microgrids.
Authors: Laurent Schmalen, Vincent Lauinger, Jonas Ney, Norbert Wehn, Patrick Matalla, Sebastian Randel, Alexander von Bank, Eike-Manuel Edelmann
Abstract: In this paper, we highlight recent advances in the use of machine learning for implementing equalizers for optical communications. We highlight both algorithmic advances as well as implementation aspects using conventional and neuromorphic hardware.
Authors: Joon Sung Park, Carolyn Q. Zou, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Robb Willer, Percy Liang, Michael S. Bernstein
Abstract: The promise of human behavioral simulation--general-purpose computational agents that replicate human behavior across domains--could enable broad applications in policymaking and social science. We present a novel agent architecture that simulates the attitudes and behaviors of 1,052 real individuals--applying large language models to qualitative interviews about their lives, then measuring how well these agents replicate the attitudes and behaviors of the individuals that they represent. The generative agents replicate participants' responses on the General Social Survey 85% as accurately as participants replicate their own answers two weeks later, and perform comparably in predicting personality traits and outcomes in experimental replications. Our architecture reduces accuracy biases across racial and ideological groups compared to agents given demographic descriptions. This work provides a foundation for new tools that can help investigate individual and collective behavior.
Authors: Paolo De Angelis, Giovanni Trezza, Giulio Barletta, Pietro Asinari, Eliodoro Chiavazzo
Abstract: Artificial Intelligence (AI) in materials science is driving significant advancements in the discovery of advanced materials for energy applications. The recent GNoME protocol identifies over 380,000 novel stable crystals. From this, we identify over 33,000 materials with potential as energy materials forming the Energy-GNoME database. Leveraging Machine Learning (ML) and Deep Learning (DL) tools, our protocol mitigates cross-domain data bias using feature spaces to identify potential candidates for thermoelectric materials, novel battery cathodes, and novel perovskites. Classifiers with both structural and compositional features identify domains of applicability, where we expect enhanced accuracy of the regressors. Such regressors are trained to predict key materials properties like, thermoelectric figure of merit (zT), band gap (Eg), and cathode voltage ($\Delta V_c$). This method significantly narrows the pool of potential candidates, serving as an efficient guide for experimental and computational chemistry investigations and accelerating the discovery of materials suited for electricity generation, energy storage and conversion.
Authors: Sagar Ghosh, Kushal Bose, Swagatam Das
Abstract: The emergence of Deep Convolutional Neural Networks (DCNNs) has been a pervasive tool for accomplishing widespread applications in computer vision. Despite its potential capability to capture intricate patterns inside the data, the underlying embedding space remains Euclidean and primarily pursues contractive convolution. Several instances can serve as a precedent for the exacerbating performance of DCNNs. The recent advancement of neural networks in the hyperbolic spaces gained traction, incentivizing the development of convolutional deep neural networks in the hyperbolic space. In this work, we propose Hyperbolic DCNN based on the Poincar\'{e} Disc. The work predominantly revolves around analyzing the nature of expansive convolution in the context of the non-Euclidean domain. We further offer extensive theoretical insights pertaining to the universal consistency of the expansive convolution in the hyperbolic space. Several simulations were performed not only on the synthetic datasets but also on some real-world datasets. The experimental results reveal that the hyperbolic convolutional architecture outperforms the Euclidean ones by a commendable margin.
Authors: Md. Asif Haider, Ayesha Binte Mostofa, Sk. Sabit Bin Mosaddek, Anindya Iqbal, Toufique Ahmed
Abstract: Generating accurate code review comments remains a significant challenge due to the inherently diverse and non-unique nature of the task output. Large language models pretrained on both programming and natural language data tend to perform well in code-oriented tasks. However, large-scale pretraining is not always feasible due to its environmental impact and project-specific generalizability issues. In this work, first we fine-tune open-source Large language models (LLM) in parameter-efficient, quantized low-rank (QLoRA) fashion on consumer-grade hardware to improve review comment generation. Recent studies demonstrate the efficacy of augmenting semantic metadata information into prompts to boost performance in other code-related tasks. To explore this in code review activities, we also prompt proprietary, closed-source LLMs augmenting the input code patch with function call graphs and code summaries. Both of our strategies improve the review comment generation performance, with function call graph augmented few-shot prompting on the GPT-3.5 model surpassing the pretrained baseline by around 90% BLEU-4 score on the CodeReviewer dataset. Moreover, few-shot prompted Gemini-1.0 Pro, QLoRA fine-tuned Code Llama and Llama 3.1 models achieve competitive results (ranging from 25% to 83% performance improvement) on this task. An additional human evaluation study further validates our experimental findings, reflecting real-world developers' perceptions of LLM-generated code review comments based on relevant qualitative metrics.
Authors: Xujun Wei, Feng Zhang, Renhe Zhang, Wenwen Li, Cuiping Liu, Bin Guo, Jingwei Li, Haoyang Fu, Xu Tang
Abstract: In the past few years, Artificial Intelligence (AI)-based weather forecasting methods have widely demonstrated strong competitiveness among the weather forecasting systems. However, these methods are insufficient for high-spatial-resolution short-term nowcasting within 6 hours, which is crucial for warning short-duration, mesoscale and small-scale weather events. Geostationary satellite remote sensing provides detailed, high spatio-temporal and all-day observations, which can address the above limitations of existing methods. Therefore, this paper proposed an advanced data-driven thermal infrared cloud images forecasting model, "DaYu." Unlike existing data-driven weather forecasting models, DaYu is specifically designed for geostationary satellite observations, with a temporal resolution of 0.5 hours and a spatial resolution of ${0.05}^\circ$ $\times$ ${0.05}^\circ$. DaYu is based on a large-scale transformer architecture, which enables it to capture fine-grained cloud structures and learn fast-changing spatio-temporal evolution features effectively. Moreover, its attention mechanism design achieves a balance in computational complexity, making it practical for applications. DaYu not only achieves accurate forecasts up to 3 hours with a correlation coefficient higher than 0.9, 6 hours higher than 0.8, and 12 hours higher than 0.7, but also detects short-duration, mesoscale, and small-scale weather events with enhanced detail, effectively addressing the shortcomings of existing methods in providing detailed short-term nowcasting within 6 hours. Furthermore, DaYu has significant potential in short-term climate disaster prevention and mitigation.
Authors: Gerardo Duran-Martin, Leandro S\'anchez-Betancourt, Alexander Y. Shestopaloff, Kevin Murphy
Abstract: We propose a unifying framework for methods that perform Bayesian online learning in non-stationary environments. We call the framework BONE, which stands for (B)ayesian (O)nline learning in (N)on-stationary (E)nvironments. BONE provides a common structure to tackle a variety of problems, including online continual learning, prequential forecasting, and contextual bandits. The framework requires specifying three modelling choices: (i) a model for measurements (e.g., a neural network), (ii) an auxiliary process to model non-stationarity (e.g., the time since the last changepoint), and (iii) a conditional prior over model parameters (e.g., a multivariate Gaussian). The framework also requires two algorithmic choices, which we use to carry out approximate inference under this framework: (i) an algorithm to estimate beliefs (posterior distribution) about the model parameters given the auxiliary variable, and (ii) an algorithm to estimate beliefs about the auxiliary variable. We show how this modularity allows us to write many different existing methods as instances of BONE; we also use this framework to propose a new method. We then experimentally compare existing methods with our proposed new method on several datasets; we provide insights into the situations that make one method more suitable than another for a given task.
Authors: Anish Dhir, Ruby Sedgwick, Avinash Kori, Ben Glocker, Mark van der Wilk
Abstract: Current causal discovery approaches require restrictive model assumptions or assume access to interventional data to ensure structure identifiability. These assumptions often do not hold in real-world applications leading to a loss of guarantees and poor accuracy in practice. Recent work has shown that, in the bivariate case, Bayesian model selection can greatly improve accuracy by exchanging restrictive modelling for more flexible assumptions, at the cost of a small probability of error. We extend the Bayesian model selection approach to the important multivariate setting by making the large discrete selection problem scalable through a continuous relaxation. We demonstrate how for our choice of Bayesian non-parametric model, the Causal Gaussian Process Conditional Density Estimator (CGP-CDE), an adjacency matrix can be constructed from the model hyperparameters. This adjacency matrix is then optimised using the marginal likelihood and an acyclicity regulariser, outputting the maximum a posteriori causal graph. We demonstrate the competitiveness of our approach on both synthetic and real-world datasets, showing it is possible to perform multivariate causal discovery without infeasible assumptions using Bayesian model selection.
Authors: Siddharth Roheda
Abstract: In recent years, image synthesis has achieved remarkable advancements, enabling diverse applications in content creation, virtual reality, and beyond. We introduce a novel approach to image generation using Auto-Regressive (AR) modeling, which leverages a next-detail prediction strategy for enhanced fidelity and scalability. While AR models have achieved transformative success in language modeling, replicating this success in vision tasks has presented unique challenges due to the inherent spatial dependencies in images. Our proposed method addresses these challenges by iteratively adding finer details to an image compositionally, constructing it as a hierarchical combination of base and detail image factors. This strategy is shown to be more effective than the conventional next-token prediction and even surpasses the state-of-the-art next-scale prediction approaches. A key advantage of this method is its scalability to higher resolutions without requiring full model retraining, making it a versatile solution for high-resolution image generation.
Authors: Michael Wilson, Tom Needham, Anuj Srivastava
Abstract: Wasserstein distances form a family of metrics on spaces of probability measures that have recently seen many applications. However, statistical analysis in these spaces is complex due to the nonlinearity of Wasserstein spaces. One potential solution to this problem is Linear Optimal Transport (LOT). This method allows one to find a Euclidean embedding, called LOT embedding, of measures in some Wasserstein spaces, but some information is lost in this embedding. So, to understand whether statistical analysis relying on LOT embeddings can make valid inferences about original data, it is helpful to quantify how well these embeddings describe that data. To answer this question, we present a decomposition of the Fr\'echet variance of a set of measures in the 2-Wasserstein space, which allows one to compute the percentage of variance explained by LOT embeddings of those measures. We then extend this decomposition to the Fused Gromov-Wasserstein setting. We also present several experiments that explore the relationship between the dimension of the LOT embedding, the percentage of variance explained by the embedding, and the classification accuracy of machine learning classifiers built on the embedded data. We use the MNIST handwritten digits dataset, IMDB-50000 dataset, and Diffusion Tensor MRI images for these experiments. Our results illustrate the effectiveness of low dimensional LOT embeddings in terms of the percentage of variance explained and the classification accuracy of models built on the embedded data.
Authors: Sanath Budakegowdanadoddi Nagaraju, Brian Bernhard Moser, Tobias Christian Nauen, Stanislav Frolov, Federico Raue, Andreas Dengel
Abstract: Transformer-based Super-Resolution (SR) models have recently advanced image reconstruction quality, yet challenges remain due to computational complexity and an over-reliance on large patch sizes, which constrain fine-grained detail enhancement. In this work, we propose TaylorIR to address these limitations by utilizing a patch size of 1x1, enabling pixel-level processing in any transformer-based SR model. To address the significant computational demands under the traditional self-attention mechanism, we employ the TaylorShift attention mechanism, a memory-efficient alternative based on Taylor series expansion, achieving full token-to-token interactions with linear complexity. Experimental results demonstrate that our approach achieves new state-of-the-art SR performance while reducing memory consumption by up to 60% compared to traditional self-attention-based transformers.
Authors: Yejiang Yang, Zihao Mo, Weiming Xiang
Abstract: This paper proposes a neural network hybrid modeling framework for dynamics learning to promote an interpretable, computationally efficient way of dynamics learning and system identification. First, a low-level model will be trained to learn the system dynamics, which utilizes multiple simple neural networks to approximate the local dynamics generated from data-driven partitions. Then, based on the low-level model, a high-level model will be trained to abstract the low-level neural hybrid system model into a transition system that allows Computational Tree Logic Verification to promote the model's ability with human interaction and verification efficiency.
Authors: Michael Aerni, Javier Rando, Edoardo Debenedetti, Nicholas Carlini, Daphne Ippolito, Florian Tram\`er
Abstract: Large language models memorize parts of their training data. Memorizing short snippets and facts is required to answer questions about the world and to be fluent in any language. But models have also been shown to reproduce long verbatim sequences of memorized text when prompted by a motivated adversary. In this work, we investigate an intermediate regime of memorization that we call non-adversarial reproduction, where we quantify the overlap between model responses and pretraining data when responding to natural and benign prompts. For a variety of innocuous prompt categories (e.g., writing a letter or a tutorial), we show that up to 15% of the text output by popular conversational language models overlaps with snippets from the Internet. In worst cases, we find generations where 100% of the content can be found exactly online. For the same tasks, we find that human-written text has far less overlap with Internet data. We further study whether prompting strategies can close this reproduction gap between models and humans. While appropriate prompting can reduce non-adversarial reproduction on average, we find that mitigating worst-case reproduction of training data requires stronger defenses -- even for benign interactions.
Authors: Tim Kaiser, Nikolas Adaloglou, Markus Kollmann
Abstract: Guidance is an error-correcting technique used to improve the perceptual quality of images generated by diffusion models. Typically, the correction is achieved by linear extrapolation, using an auxiliary diffusion model that has lower performance than the primary model. Using a 2D toy example, we show that it is highly beneficial when the auxiliary model exhibits similar errors as the primary one but stronger. We verify this finding in higher dimensions, where we show that competitive generative performance to state-of-the-art guidance methods can be achieved when the auxiliary model differs from the primary one only by having stronger weight regularization. As an independent contribution, we investigate whether upweighting long-range spatial dependencies improves visual fidelity. The result is a novel guidance method, which we call sliding window guidance (SWG), that guides the primary model with itself by constraining its receptive field. Intriguingly, SWG aligns better with human preferences than state-of-the-art guidance methods while requiring neither training, architectural modifications, nor class conditioning. The code will be released.
Authors: Qi Liu, Yanchen Liu, Ruifeng Li, Chenhong Cao, Yufeng Li, Xingyu Li, Peng Wang, Runhan Feng
Abstract: The integration of intelligent and connected technologies in modern vehicles, while offering enhanced functionalities through Electronic Control Unit and interfaces like OBD-II and telematics, also exposes the vehicle's in-vehicle network (IVN) to potential cyberattacks. In this paper, we consider a specific type of cyberattack known as the injection attack. As demonstrated by empirical data from real-world cybersecurity adversarial competitions(available at https://mimic2024.xctf.org.cn/race/qwmimic2024 ), these injection attacks have excitation effect over time, gradually manipulating network traffic and disrupting the vehicle's normal functioning, ultimately compromising both its stability and safety. To profile the abnormal behavior of attackers, we propose a novel injection attack detector to extract long-term features of attack behavior. Specifically, we first provide a theoretical analysis of modeling the time-excitation effects of the attack using Multi-Dimensional Hawkes Process (MDHP). A gradient descent solver specifically tailored for MDHP, MDHP-GDS, is developed to accurately estimate optimal MDHP parameters. We then propose an injection attack detector, MDHP-Net, which integrates optimal MDHP parameters with MDHP-LSTM blocks to enhance temporal feature extraction. By introducing MDHP parameters, MDHP-Net captures complex temporal features that standard Long Short-Term Memory (LSTM) cannot, enriching temporal dependencies within our customized structure. Extensive evaluations demonstrate the effectiveness of our proposed detection approach.
Authors: Xiaodong Chen, Yuxuan Hu, Jing Zhang, Xiaokang Zhang, Cuiping Li, Hong Chen
Abstract: Large language models (LLMs) based on the Transformer architecture are widely employed across various domains and tasks. However, their increasing size imposes significant hardware demands, limiting practical deployment. To mitigate this, model pruning techniques have been developed to create more efficient models while maintaining high performance. Despite this, post-training after pruning is crucial for performance recovery and can be resource-intensive. This paper investigates the post-training requirements of pruned LLMs and introduces a scaling law to determine the optimal amount of post-training data. Post-training experiments with the Llama-3 and Qwen-2.5 series models, pruned using depth pruning, width pruning, and 2:4 semi-structured pruning, show that higher pruning ratios necessitate more post-training data for performance recovery, whereas larger LLMs require less. The proposed scaling law predicts a model's loss based on its parameter counts before and after pruning, as well as the post-training token counts. Furthermore, we find that the scaling law established from smaller LLMs can be reliably extrapolated to larger LLMs. This work provides valuable insights into the post-training of pruned LLMs and offers a practical scaling law for optimizing post-training data usage.
Authors: Tim Elsner, Paula Usinger, Julius Nehring-Wirxel, Gregor Kobsik, Victor Czech, Yanjiang He, Isaak Lim, Leif Kobbelt
Abstract: In language processing, transformers benefit greatly from text being condensed. This is achieved through a larger vocabulary that captures word fragments instead of plain characters. This is often done with Byte Pair Encoding. In the context of images, tokenisation of visual data is usually limited to regular grids obtained from quantisation methods, without global content awareness. Our work improves tokenisation of visual data by bringing Byte Pair Encoding from 1D to multiple dimensions, as a complementary add-on to existing compression. We achieve this through counting constellations of token pairs and replacing the most frequent token pair with a newly introduced token. The multidimensionality only increases the computation time by a factor of 2 for images, making it applicable even to large datasets like ImageNet within minutes on consumer hardware. This is a lossless preprocessing step. Our evaluation shows improved training and inference performance of transformers on visual data achieved by compressing frequent constellations of tokens: The resulting sequences are shorter, with more uniformly distributed information content, e.g. condensing empty regions in an image into single tokens. As our experiments show, these condensed sequences are easier to process. We additionally introduce a strategy to amplify this compression further by clustering the vocabulary.
Authors: Shangdi Yu, Jessica Shi, Jamison Meindl, David Eisenstat, Xiaoen Ju, Sasan Tavakkol, Laxman Dhulipala, Jakub {\L}\k{a}cki, Vahab Mirrokni, Julian Shun
Abstract: We introduce the ParClusterers Benchmark Suite (PCBS) -- a collection of highly scalable parallel graph clustering algorithms and benchmarking tools that streamline comparing different graph clustering algorithms and implementations. The benchmark includes clustering algorithms that target a wide range of modern clustering use cases, including community detection, classification, and dense subgraph mining. The benchmark toolkit makes it easy to run and evaluate multiple instances of different clustering algorithms, which can be useful for fine-tuning the performance of clustering on a given task, and for comparing different clustering algorithms based on different metrics of interest, including clustering quality and running time. Using PCBS, we evaluate a broad collection of real-world graph clustering datasets. Somewhat surprisingly, we find that the best quality results are obtained by algorithms that not included in many popular graph clustering toolkits. The PCBS provides a standardized way to evaluate and judge the quality-performance tradeoffs of the active research area of scalable graph clustering algorithms. We believe it will help enable fair, accurate, and nuanced evaluation of graph clustering algorithms in the future.
Authors: Ryoma Yataka, Adriano Cardace, Pu Perry Wang, Petros Boufounos, Ryuhei Takahashi
Abstract: Indoor radar perception has seen rising interest due to affordable costs driven by emerging automotive imaging radar developments and the benefits of reduced privacy concerns and reliability under hazardous conditions (e.g., fire and smoke). However, existing radar perception pipelines fail to account for distinctive characteristics of the multi-view radar setting. In this paper, we propose Radar dEtection TRansformer (RETR), an extension of the popular DETR architecture, tailored for multi-view radar perception. RETR inherits the advantages of DETR, eliminating the need for hand-crafted components for object detection and segmentation in the image plane. More importantly, RETR incorporates carefully designed modifications such as 1) depth-prioritized feature similarity via a tunable positional encoding (TPE); 2) a tri-plane loss from both radar and camera coordinates; and 3) a learnable radar-to-camera transformation via reparameterization, to account for the unique multi-view radar setting. Evaluated on two indoor radar perception datasets, our approach outperforms existing state-of-the-art methods by a margin of 15.38+ AP for object detection and 11.77+ IoU for instance segmentation, respectively.
Authors: Nandavardhan R., Somanathan R., Vikram Suresh, Savaridassan P
Abstract: Radiologists and doctors make use of X-ray images of the non-dominant hands of children and infants to assess the possibility of genetic conditions and growth abnormalities. This is done by assessing the difference between the actual extent of growth found using the X-rays and the chronological age of the subject. The assessment was done conventionally using The Greulich Pyle (GP) or Tanner Whitehouse (TW) approach. These approaches require a high level of expertise and may often lead to observer bias. Hence, to automate the process of assessing the X-rays, and to increase its accuracy and efficiency, several machine learning models have been developed. These machine-learning models have several differences in their accuracy and efficiencies, leading to an unclear choice for the suitable model depending on their needs and available resources. Methods: In this study, we have analyzed the 3 most widely used models for the automation of bone age prediction, which are the Xception model, VGG model and CNN model. These models were trained on the preprocessed dataset and the accuracy was measured using the MAE in terms of months for each model. Using this, the comparison between the models was done. Results: The 3 models, Xception, VGG, and CNN models have been tested for accuracy and other relevant factors.
Authors: Fatahlla Moreh (Christian Albrechts University, Kiel, Germany), Yusuf Hasan (Aligarh Muslim University, Aligarh, India), Bilal Zahid Hussain (Texas A&M University, College Station, USA), Mohammad Ammar (Aligarh Muslim University, Aligarh, India), Sven Tomforde (Christian Albrechts University, Kiel, Germany)
Abstract: Internal crack detection has been a subject of focus in structural health monitoring. By focusing on crack detection in structural datasets, it is demonstrated that deep learning (DL) methods can effectively analyze seismic wave fields interacting with micro-scale cracks, which are beyond the resolution of conventional visual inspection. This work explores a novel application of DL-based key point detection technique, where cracks are localized by predicting the coordinates of four key points that define a bounding region of the crack. The study not only opens new research directions for non-visual applications but also effectively mitigates the impact of imbalanced data which poses a challenge for previous DL models, as it can be biased toward predicting the majority class (non-crack regions). Popular DL techniques, such as the Inception blocks, are used and investigated. The model shows an overall reduction in loss when applied to micro-scale crack detection and is reflected in the lower average deviation between the location of actual and predicted cracks, with an average Intersection over Union (IoU) being 0.511 for all micro cracks (greater than 0.00 micrometers) and 0.631 for larger micro cracks (greater than 4 micrometers).
Authors: Shreya Meel, Pasan Dissanayake, Mohamed Nomeir, Sanghamitra Dutta, Sennur Ulukus
Abstract: In a classification task, counterfactual explanations provide the minimum change needed for an input to be classified into a favorable class. We consider the problem of privately retrieving the exact closest counterfactual from a database of accepted samples while enforcing that certain features of the input sample cannot be changed, i.e., they are \emph{immutable}. An applicant (user) whose feature vector is rejected by a machine learning model wants to retrieve the sample closest to them in the database without altering a private subset of their features, which constitutes the immutable set. While doing this, the user should keep their feature vector, immutable set and the resulting counterfactual index information-theoretically private from the institution. We refer to this as immutable private counterfactual retrieval (I-PCR) problem which generalizes PCR to a more practical setting. In this paper, we propose two I-PCR schemes by leveraging techniques from private information retrieval (PIR) and characterize their communication costs. Further, we quantify the information that the user learns about the database and compare it for the proposed schemes.
Authors: Yandong Li, Francesco Monticone
Abstract: Similar to algorithms, which consume time and memory to run, hardware requires resources to function. For devices processing physical waves, implementing operations needs sufficient "space," as dictated by wave physics. How much space is needed to perform a certain function is a fundamental question in optics, with recent research addressing it for given mathematical operations, but not for more general computing tasks, e.g., classification. Inspired by computational complexity theory, we study the "spatial complexity" of optical computing systems in terms of scaling laws - specifically, how their physical dimensions must scale as the dimension of the mathematical operation increases - and propose a new paradigm for designing optical computing systems: space-efficient neuromorphic optics, based on structural sparsity constraints and neural pruning methods motivated by wave physics (notably, the concept of "overlapping nonlocality"). On two mainstream platforms, free-space optics and on-chip integrated photonics, our methods demonstrate substantial size reductions (to 1%-10% the size of conventional designs) with minimal compromise on performance. Our theoretical and computational results reveal a trend of diminishing returns on accuracy as structure dimensions increase, providing a new perspective for interpreting and approaching the ultimate limits of optical computing - a balanced trade-off between device size and accuracy.
Authors: Etienne Russeil, Fabr\'icio Olivetti de Fran\c{c}a, Konstantin Malanchev, Bogdan Burlacu, Emille E. O. Ishida, Marion Leroux, Cl\'ement Michelin, Guillaume Moinard, Emmanuel Gangler
Abstract: Symbolic regression (SR) searches for analytical expressions representing the relationship between a set of explanatory and response variables. Current SR methods assume a single dataset extracted from a single experiment. Nevertheless, frequently, the researcher is confronted with multiple sets of results obtained from experiments conducted with different setups. Traditional SR methods may fail to find the underlying expression since the parameters of each experiment can be different. In this work we present Multi-View Symbolic Regression (MvSR), which takes into account multiple datasets simultaneously, mimicking experimental environments, and outputs a general parametric solution. This approach fits the evaluated expression to each independent dataset and returns a parametric family of functions f(x; theta) simultaneously capable of accurately fitting all datasets. We demonstrate the effectiveness of MvSR using data generated from known expressions, as well as real-world data from astronomy, chemistry and economy, for which an a priori analytical expression is not available. Results show that MvSR obtains the correct expression more frequently and is robust to hyperparameters change. In real-world data, it is able to grasp the group behavior, recovering known expressions from the literature as well as promising alternatives, thus enabling the use of SR to a large range of experimental scenarios.
Authors: Julien Zhou (Thoth, STATIFY), Pierre Gaillard (Thoth), Thibaud Rahier (SODA, MIND), Houssam Zenati (SODA, MIND), Julyan Arbel (STATIFY)
Abstract: We address the problem of stochastic combinatorial semi-bandits, where a player selects among P actions from the power set of a set containing d base items. Adaptivity to the problem's structure is essential in order to obtain optimal regret upper bounds. As estimating the coefficients of a covariance matrix can be manageable in practice, leveraging them should improve the regret. We design "optimistic" covariance-adaptive algorithms relying on online estimations of the covariance structure, called OLS-UCB-C and COS-V (only the variances for the latter). They both yields improved gap-free regret. Although COS-V can be slightly suboptimal, it improves on computational complexity by taking inspiration from ThompsonSampling approaches. It is the first sampling-based algorithm satisfying a T^1/2 gap-free regret (up to poly-logs). We also show that in some cases, our approach efficiently leverages the semi-bandit feedback and outperforms bandit feedback approaches, not only in exponential regimes where P >> d but also when P <= d, which is not covered by existing analyses.
Authors: Mohd Halim Mohd Noor, Ayokunle Olalekan Ige
Abstract: Deep learning, a branch of artificial intelligence, is a data-driven method that uses multiple layers of interconnected units (neurons) to learn intricate patterns and representations directly from raw input data. Empowered by this learning capability, it has become a powerful tool for solving complex problems and is the core driver of many groundbreaking technologies and innovations. Building a deep learning model is challenging due to the algorithm's complexity and the dynamic nature of real-world problems. Several studies have reviewed deep learning concepts and applications. However, the studies mostly focused on the types of deep learning models and convolutional neural network architectures, offering limited coverage of the state-of-the-art deep learning models and their applications in solving complex problems across different domains. Therefore, motivated by the limitations, this study aims to comprehensively review the state-of-the-art deep learning models in computer vision, natural language processing, time series analysis and pervasive computing. We highlight the key features of the models and their effectiveness in solving the problems within each domain. Furthermore, this study presents the fundamentals of deep learning, various deep learning model types and prominent convolutional neural network architectures. Finally, challenges and future directions in deep learning research are discussed to offer a broader perspective for future researchers.
Authors: Donald W. Peltier III, Isaac Kaminer, Abram Clark, Marko Orescanin
Abstract: Understanding the characteristics of swarming autonomous agents is critical for defense and security applications. This article presents a study on using supervised neural network time series classification (NN TSC) to predict key attributes and tactics of swarming autonomous agents for military contexts. Specifically, NN TSC is applied to infer two binary attributes - communication and proportional navigation - which combine to define four mutually exclusive swarm tactics. We identify a gap in literature on using NNs for swarm classification and demonstrate the effectiveness of NN TSC in rapidly deducing intelligence about attacking swarms to inform counter-maneuvers. Through simulated swarm-vs-swarm engagements, we evaluate NN TSC performance in terms of observation window requirements, noise robustness, and scalability to swarm size. Key findings show NNs can predict swarm behaviors with 97% accuracy using short observation windows of 20 time steps, while also demonstrating graceful degradation down to 80% accuracy under 50% noise, as well as excellent scalability to swarm sizes from 10 to 100 agents. These capabilities are promising for real-time decision-making support in defense scenarios by rapidly inferring insights about swarm behavior.
Authors: Qijun Luo, Hengxu Yu, Xiao Li
Abstract: This work presents BAdam, an optimization method that leverages the block coordinate descent (BCD) framework with Adam's update rule. BAdam offers a memory efficient approach to the full parameter finetuning of large language models. We conduct a theoretical convergence analysis for BAdam in the deterministic case. Experimentally, we apply BAdam to finetune the Llama 3-8B and Llama 3-70B models using a single RTX3090-24GB GPU and 4 A100-80GB GPUs, respectively. The results confirm BAdam's efficiency in terms of memory usage, running time, and optimization capability. Furthermore, the downstream performance evaluation based on MT-bench and math benchmarks shows that BAdam outperforms existing memory efficient baselines such as LoRA. It also demonstrates that BAdam can achieve comparable or even superior performance compared to Adam. Finally, the ablation study using SGD's update rule illustrates the suitability of BCD for finetuning LLMs. Our code can be easily integrated into any PyTorch-based codebase and is available at https://github.com/Ledzy/BAdam.
Authors: Chanwook Park, Sourav Saha, Jiachen Guo, Hantao Zhang, Xiaoyu Xie, Miguel A. Bessa, Dong Qian, Wei Chen, Gregory J. Wagner, Jian Cao, Wing Kam Liu
Abstract: Artificial intelligence (AI) has revolutionized software development, shifting from task-specific codes (Software 1.0) to neural network-based approaches (Software 2.0). However, applying this transition in engineering software presents challenges, including low surrogate model accuracy, the curse of dimensionality in inverse design, and rising complexity in physical simulations. We introduce an interpolating neural network (INN), grounded in interpolation theory and tensor decomposition, to realize Engineering Software 2.0 by advancing data training, partial differential equation solving, and parameter calibration. INN offers orders of magnitude fewer trainable/solvable parameters for comparable model accuracy than traditional multi-layer perceptron (MLP) or physics-informed neural networks (PINN). Demonstrated in metal additive manufacturing, INN rapidly constructs an accurate surrogate model of Laser Powder Bed Fusion (L-PBF) heat transfer simulation, achieving sub-10-micrometer resolution for a 10 mm path in under 15 minutes on a single GPU. This makes a transformative step forward across all domains essential to engineering software.
Authors: Derui Wang, Minhui Xue, Bo Li, Seyit Camtepe, Liming Zhu
Abstract: The exploitation of publicly accessible data has led to escalating concerns regarding data privacy and intellectual property (IP) breaches in the age of artificial intelligence. To safeguard both data privacy and IP-related domain knowledge, efforts have been undertaken to render shared data unlearnable for unauthorized models in the wild. Existing methods apply empirically optimized perturbations to the data in the hope of disrupting the correlation between the inputs and the corresponding labels such that the data samples are converted into Unlearnable Examples (UEs). Nevertheless, the absence of mechanisms to verify the robustness of UEs against uncertainty in unauthorized models and their training procedures engenders several under-explored challenges. First, it is hard to quantify the unlearnability of UEs against unauthorized adversaries from different runs of training, leaving the soundness of the defense in obscurity. Particularly, as a prevailing evaluation metric, empirical test accuracy faces generalization errors and may not plausibly represent the quality of UEs. This also leaves room for attackers, as there is no rigid guarantee of the maximal test accuracy achievable by attackers. Furthermore, we find that a simple recovery attack can restore the clean-task performance of the classifiers trained on UEs by slightly perturbing the learned weights. To mitigate the aforementioned problems, in this paper, we propose a mechanism for certifying the so-called $(q, \eta)$-Learnability of an unlearnable dataset via parametric smoothing. A lower certified $(q, \eta)$-Learnability indicates a more robust and effective protection over the dataset. Concretely, we 1) improve the tightness of certified $(q, \eta)$-Learnability and 2) design Provably Unlearnable Examples (PUEs) which have reduced $(q, \eta)$-Learnability.
Authors: Fran\c{c}ois Rozet, G\'er\^ome Andry, Fran\c{c}ois Lanusse, Gilles Louppe
Abstract: Diffusion models recently proved to be remarkable priors for Bayesian inverse problems. However, training these models typically requires access to large amounts of clean data, which could prove difficult in some settings. In this work, we present a novel method based on the expectation-maximization algorithm for training diffusion models from incomplete and noisy observations only. Unlike previous works, our method leads to proper diffusion models, which is crucial for downstream tasks. As part of our method, we propose and motivate an improved posterior sampling scheme for unconditional diffusion models. We present empirical evidence supporting the effectiveness of our method.
Authors: Siba Smarak Panigrahi, Arnab Kumar Mondal
Abstract: This work introduces a novel approach to achieving architecture-agnostic equivariance in deep learning, particularly addressing the limitations of traditional layerwise equivariant architectures and the inefficiencies of the existing architecture-agnostic methods. Building equivariant models using traditional methods requires designing equivariant versions of existing models and training them from scratch, a process that is both impractical and resource-intensive. Canonicalization has emerged as a promising alternative for inducing equivariance without altering model architecture, but it suffers from the need for highly expressive and expensive equivariant networks to learn canonical orientations accurately. We propose a new optimization-based method that employs any non-equivariant network for canonicalization. Our method uses contrastive learning to efficiently learn a canonical orientation and offers more flexibility for the choice of canonicalization network. We empirically demonstrate that this approach outperforms existing methods in achieving equivariance for large pretrained models and significantly speeds up the canonicalization process, making it up to 2 times faster.
Authors: Adibvafa Fallahpour, Mahshid Alinoori, Wenqian Ye, Xu Cao, Arash Afkanpour, Amrit Krishnan
Abstract: Transformers have significantly advanced the modeling of Electronic Health Records (EHR), yet their deployment in real-world healthcare is limited by several key challenges. Firstly, the quadratic computational cost and insufficient context length of these models hinder hospitals' ability in processing the extensive medical histories typical in EHR data. Additionally, existing models employ separate finetuning for each clinical task, complicating maintenance in healthcare environments. Moreover, these models focus exclusively on either clinical prediction or EHR forecasting, lacking proficiency in both tasks. To overcome these limitations, we introduce EHRMamba, a robust foundation model built on the Mamba architecture. EHRMamba can process sequences up to 300% longer than previous models due to its linear computational cost. We also introduce a novel approach to Multitask Prompted Finetuning (MPF) for EHR data, which enables EHRMamba to simultaneously learn multiple clinical tasks in a single finetuning phase, significantly enhancing deployment and cross-task generalization. Furthermore, our model leverages the HL7 FHIR data standard to simplify integration into existing hospital systems. Alongside EHRMamba, we open-source Odyssey, a toolkit designed to support the development and deployment of EHR foundation models, with an emphasis on data standardization and interpretability. Our evaluations on the MIMIC-IV dataset demonstrate that EHRMamba advances state-of-the-art performance across 6 major clinical tasks and excels in EHR forecasting, marking a significant leap forward in the field.
Authors: Shen Yuan, Haotian Liu, Hongteng Xu
Abstract: While following different technical routes, both low-rank and orthogonal adaptation techniques can efficiently adapt large-scale pre-training models in specific tasks or domains based on a small piece of trainable parameters. In this study, we bridge the gap between these two techniques, proposing a simple but effective adaptation method based on Householder reflections. Given a pre-trained model, our method fine-tunes its layers by multiplying each frozen weight matrix with an orthogonal matrix constructed by a chain of learnable Householder reflections (HRs). This HR-based orthogonal fine-tuning is equivalent to an adaptive low-rank adaptation. Moreover, we show that the orthogonality of the reflection planes corresponding to the HRs impacts the model capacity and regularity. The analysis motivates us to regularize the orthogonality of the HRs, leading to different implementations of the proposed Householder reflection adaptation (HRA) method. Compared with state-of-the-art methods, HRA achieves superior performance with fewer learnable parameters when adapting large language models and conditional image generators. The code of the experiments is available at \url{https://github.com/DaShenZi721/HRA}, and the method has been merged into the \href{https://github.com/huggingface/peft}{PEFT} package.
URLs: https://github.com/DaShenZi721/HRA, https://github.com/huggingface/peft
Authors: Jianhui Gao, Benson Chou, Zachary R. McCaw, Hilary Thurston, Paul Varghese, Chuan Hong, Jessica Gronsbell
Abstract: Ensuring that machine learning (ML) models are safe, effective, and equitable across all patient groups is essential for clinical decision-making and for preventing the reinforcement of existing health disparities. This review examines notions of fairness used in ML for health, including a review of why ML models can be unfair and how fairness has been quantified in a wide range of real-world examples. We provide an overview of commonly used fairness metrics and supplement our discussion with a case-study of an openly available electronic health record (EHR) dataset. We also discuss the outlook for future research, highlighting current challenges and opportunities in defining fairness in health.
Authors: Rushuang Zhou, Lei Clifton, Zijun Liu, Kannie W. Y. Chan, David A. Clifton, Yuan-Ting Zhang, Yining Dong
Abstract: The label scarcity problem is the main challenge that hinders the wide application of deep learning systems in automatic cardiovascular diseases (CVDs) detection using electrocardiography (ECG). Tuning pre-trained models alleviates this problem by transferring knowledge learned from large datasets to downstream small datasets. However, bottlenecks in computational efficiency and detection performance limit its clinical applications. It is difficult to improve the detection performance without significantly sacrificing the computational efficiency during model training. Here, we propose a computation-efficient semi-supervised learning paradigm (CE-SSL) for robust and computation-efficient CVDs detection using ECG. It enables a robust adaptation of pre-trained models on downstream datasets with limited supervision and high computational efficiency. First, a random-deactivation technique is developed to achieve robust and fast low-rank adaptation of pre-trained weights. Subsequently, we propose a one-shot rank allocation module to determine the optimal ranks for the update matrices of the pre-trained weights. Finally, a lightweight semi-supervised learning pipeline is introduced to enhance model performance by leveraging labeled and unlabeled data with high computational efficiency. Extensive experiments on four downstream datasets demonstrate that CE-SSL not only outperforms the state-of-the-art methods in multi-label CVDs detection but also consumes fewer GPU footprints, training time, and parameter storage space. As such, this paradigm provides an effective solution for achieving high computational efficiency and robust detection performance in the clinical applications of pre-trained models under limited supervision. Code and Supplementary Materials are available at https://github.com/KAZABANA/CE-SSL
Authors: Konstantinos Vogiatzoglou, Costas Papadimitriou, Vasilis Bontozoglou, Konstantinos Ampountolas
Abstract: Wildland fires pose a terrifying natural hazard, underscoring the urgent need to develop data-driven and physics-informed digital twins for wildfire prevention, monitoring, intervention, and response. In this direction of research, this work introduces a physics-informed neural network (PiNN) designed to learn the unknown parameters of an interpretable wildfire spreading model. The considered modeling approach integrates fundamental physical laws articulated by key model parameters essential for capturing the complex behavior of wildfires. The proposed machine learning framework leverages the theory of artificial neural networks with the physical constraints governing wildfire dynamics, including the first principles of mass and energy conservation. Training of the PiNN for physics-informed parameter identification is realized using synthetic data on the spatiotemporal evolution of one- and two-dimensional firefronts, derived from a high-fidelity simulator, as well as empirical data (ground surface thermal images) from the Troy Fire that occurred on June 19, 2002, in California. The parameter learning results demonstrate the predictive ability of the proposed PiNN in uncovering the unknown coefficients of the wildfire model in one- and two-dimensional fire spreading scenarios as well as the Troy Fire. Additionally, this methodology exhibits robustness by identifying the same parameters even in the presence of noisy data. By integrating this PiNN approach into a comprehensive framework, the envisioned physics-informed digital twin will enhance intelligent wildfire management and risk assessment, providing a powerful tool for proactive and reactive strategies.
Authors: Mayk Caldas Ramos, Christopher J. Collison, Andrew D. White
Abstract: Large language models (LLMs) have emerged as powerful tools in chemistry, significantly impacting molecule design, property prediction, and synthesis optimization. This review highlights LLM capabilities in these domains and their potential to accelerate scientific discovery through automation. We also review LLM-based autonomous agents: LLMs with a broader set of tools to interact with their surrounding environment. These agents perform diverse tasks such as paper scraping, interfacing with automated laboratories, and synthesis planning. As agents are an emerging topic, we extend the scope of our review of agents beyond chemistry and discuss across any scientific domains. This review covers the recent history, current capabilities, and design of LLMs and autonomous agents, addressing specific challenges, opportunities, and future directions in chemistry. Key challenges include data quality and integration, model interpretability, and the need for standard benchmarks, while future directions point towards more sophisticated multi-modal agents and enhanced collaboration between agents and experimental methods. Due to the quick pace of this field, a repository has been built to keep track of the latest studies: https://github.com/ur-whitelab/LLMs-in-science.
Authors: Chethan Krishnamurthy Ramanaik, Arjun Roy, Eirini Ntoutsi
Abstract: Despite advancements in Autoencoders (AEs) for tasks like dimensionality reduction, representation learning and data generation, they remain vulnerable to adversarial attacks. Variational Autoencoders (VAEs), with their probabilistic approach to disentangling latent spaces, show stronger resistance to such perturbations compared to deterministic AEs; however, their resilience against adversarial inputs is still a concern. This study evaluates the robustness of VAEs against non-targeted adversarial attacks by optimizing minimal sample-specific perturbations to cause maximal damage across diverse demographic subgroups (combinations of age and gender). We investigate two questions: whether there are robustness disparities among subgroups, and what factors contribute to these disparities, such as data scarcity and representation entanglement. Our findings reveal that robustness disparities exist but are not always correlated with the size of the subgroup. By using downstream gender and age classifiers and examining latent embeddings, we highlight the vulnerability of subgroups like older women, who are prone to misclassification due to adversarial perturbations pushing their representations toward those of other subgroups.
Authors: Fardin Jalil Piran, Prathyush P. Poduval, Hamza Errahmouni Barkam, Mohsen Imani, Farhad Imani
Abstract: Machine Learning (ML) models combined with in-situ sensing offer a powerful solution to address defect detection challenges in Additive Manufacturing (AM), yet this integration raises critical data privacy concerns, such as data leakage and sensor data compromise, potentially exposing sensitive information about part design and material composition. Differential Privacy (DP), which adds mathematically controlled noise to ML models, provides a way to balance data utility with privacy by concealing identifiable traces from sensor data. However, introducing noise into ML models, especially black-box Artificial Intelligence (AI) models, complicates the prediction of how noise impacts model accuracy. This study presents the Differential Privacy-Hyperdimensional Computing (DP-HD) framework, which leverages Explainable AI (XAI) and the vector symbolic paradigm to quantify noise effects on accuracy. By defining a Signal-to-Noise Ratio (SNR) metric, DP-HD assesses the contribution of training data relative to DP noise, allowing selection of an optimal balance between accuracy and privacy. Experimental results using high-speed melt pool data for anomaly detection in AM demonstrate that DP-HD achieves superior operational efficiency, prediction accuracy, and privacy protection. For instance, with a privacy budget set at 1, DP-HD achieves 94.43% accuracy, outperforming state-of-the-art ML models. Furthermore, DP-HD maintains high accuracy under substantial noise additions to enhance privacy, unlike current models that experience significant accuracy declines under stringent privacy constraints.
Authors: Cameron Allen, Aaron Kirtland, Ruo Yu Tao, Sam Lobel, Daniel Scott, Nicholas Petrocelli, Omer Gottesman, Ronald Parr, Michael L. Littman, George Konidaris
Abstract: Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to -- or knowledge of -- an underlying, unobservable state space. Our metric, the $\lambda$-discrepancy, is the difference between two distinct temporal difference (TD) value estimates, each computed using TD($\lambda$) with a different value of $\lambda$. Since TD($\lambda{=}0$) makes an implicit Markov assumption and TD($\lambda{=}1$) does not, a discrepancy between these estimates is a potential indicator of a non-Markovian state representation. Indeed, we prove that the $\lambda$-discrepancy is exactly zero for all Markov decision processes and almost always non-zero for a broad class of partially observable environments. We also demonstrate empirically that, once detected, minimizing the $\lambda$-discrepancy can help with learning a memory function to mitigate the corresponding partial observability. We then train a reinforcement learning agent that simultaneously constructs two recurrent value networks with different $\lambda$ parameters and minimizes the difference between them as an auxiliary loss. The approach scales to challenging partially observable domains, where the resulting agent frequently performs significantly better (and never performs worse) than a baseline recurrent agent with only a single value network.
Authors: Dongnan Jin, Yali Liu, Qiuzhi Song, Xunju Ma, Yue Liu, Dehao Wu
Abstract: To effectively search for the optimal motion template in dynamic multidimensional space, this paper proposes a novel optimization algorithm, Dynamic Dimension Wrapping (DDW).The algorithm combines Dynamic Time Warping (DTW) and Euclidean distance, and designs a fitness function that adapts to dynamic multidimensional space by establishing a time-data chain mapping across dimensions. This paper also proposes a novel update mechanism,Optimal Dimension Collection (ODC), combined with the search strategy of traditional optimization algorithms, enables DDW to adjust both the dimension values and the number of dimensions of the population individuals simultaneously. In this way, DDW significantly reduces computational complexity and improves search accuracy. Experimental results show that DDW performs excellently in dynamic multidimensional space, outperforming 31 traditional optimization algorithms. This algorithm provides a novel approach to solving dynamic multidimensional optimization problems and demonstrates broad application potential in fields such as motion data analysis.
Authors: Ethan Steinberg, Michael Wornow, Suhana Bedi, Jason Alan Fries, Matthew B. A. McDermott, Nigam H. Shah
Abstract: The growing demand for machine learning in healthcare requires processing increasingly large electronic health record (EHR) datasets, but existing pipelines are not computationally efficient or scalable. In this paper, we introduce meds_reader, an optimized Python package for efficient EHR data processing that is designed to take advantage of many intrinsic properties of EHR data for improved speed. We then demonstrate the benefits of meds_reader by reimplementing key components of two major EHR processing pipelines, achieving 10-100x improvements in memory, speed, and disk usage. The code for meds_reader can be found at https://github.com/som-shahlab/meds_reader.
Authors: Masato Ishii, Akio Hayakawa, Takashi Shibuya, Yuki Mitsufuji
Abstract: In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the model jointly generate audio and video. To enhance alignment between audio-video pairs, we introduce two novel mechanisms in our model. The first one is timestep adjustment, which provides different timestep information to each base model. It is designed to align how samples are generated along with timesteps across modalities. The second one is a new design of the additional modules, termed Cross-Modal Conditioning as Positional Encoding (CMC-PE). In CMC-PE, cross-modal information is embedded as if it represents temporal position information, and the embeddings are fed into the model like positional encoding. Compared with the popular cross-attention mechanism, CMC-PE provides a better inductive bias for temporal alignment in the generated data. Experimental results validate the effectiveness of the two newly introduced mechanisms and also demonstrate that our method outperforms existing methods.
Authors: Yannis Karmim, Marc Lafon, Raphael Fournier S'niehotta, Nicolas Thome
Abstract: Fully connected Graph Transformers (GT) have rapidly become prominent in the static graph community as an alternative to Message-Passing models, which suffer from a lack of expressivity, oversquashing, and under-reaching. However, in a dynamic context, by interconnecting all nodes at multiple snapshots with self-attention, GT loose both structural and temporal information. In this work, we introduce Supra-LAplacian encoding for spatio-temporal TransformErs (SLATE), a new spatio-temporal encoding to leverage the GT architecture while keeping spatio-temporal information. Specifically, we transform Discrete Time Dynamic Graphs into multi-layer graphs and take advantage of the spectral properties of their associated supra-Laplacian matrix. Our second contribution explicitly model nodes' pairwise relationships with a cross-attention mechanism, providing an accurate edge representation for dynamic link prediction. SLATE outperforms numerous state-of-the-art methods based on Message-Passing Graph Neural Networks combined with recurrent models (e.g LSTM), and Dynamic Graph Transformers, on 9 datasets. Code is available at: github.com/ykrmm/SLATE.
Authors: Shao-Ting Chiu, Junyuan Hong, Ulisses Braga-Neto
Abstract: We introduce DeepSets Operator Networks (DeepOSets), an efficient, non-autoregressive neural network architecture for in-context operator learning. In-context learning allows a trained machine learning model to learn from a user prompt without further training. DeepOSets adds in-context learning capabilities to Deep Operator Networks (DeepONets) by combining it with the DeepSets architecture. As the first non-autoregressive model for in-context operator learning, DeepOSets allow the user prompt to be processed in parallel, leading to significant computational savings. Here, we present the application of DeepOSets in the problem of learning supervised learning algorithms, which are operators mapping a finite-dimensional space of labeled data into an infinite-dimensional hypothesis space of prediction functions. In an empirical comparison with a popular autoregressive (transformer-based) model for in-context learning of linear regression in one and five dimensions, DeepOSets reduced the number of model weights by several orders of magnitude and required a fraction of training and inference time. Furthermore, DeepOSets proved to be less sensitive to noise, significantly outperforming the transformer model in noisy settings.
Authors: Daehwan Kim, Haejun Chung, Ikbeom Jang
Abstract: Recent studies have shown that deep neural networks are not well-calibrated and often produce over-confident predictions. The miscalibration issue primarily stems from using cross-entropy in classifications, which aims to align predicted softmax probabilities with one-hot labels. In ordinal regression tasks, this problem is compounded by an additional challenge: the expectation that softmax probabilities should exhibit unimodal distribution is not met with cross-entropy. The ordinal regression literature has focused on learning orders and overlooked calibration. To address both issues, we propose a novel loss function that introduces order-aware calibration, ensuring that prediction confidence adheres to ordinal relationships between classes. It incorporates soft ordinal encoding and order-aware regularization to enforce both calibration and unimodality. Extensive experiments across three popular ordinal regression benchmarks demonstrate that our approach achieves state-of-the-art calibration without compromising accuracy.
Authors: Hojun Chung, Junseo Lee, Minsoo Kim, Dohyeong Kim, Songhwai Oh
Abstract: Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://rllab-snu.github.io/projects/ADD
Authors: Juyoung Yun
Abstract: In deep learning, Residual Networks (ResNets) have proven effective in addressing the vanishing gradient problem, allowing for the successful training of very deep networks. However, skip connections in ResNets can lead to gradient overlap, where gradients from both the learned transformation and the skip connection combine, potentially resulting in overestimated gradients. This overestimation can cause inefficiencies in optimization, as some updates may overshoot optimal regions, affecting weight updates. To address this, we examine Z-score Normalization (ZNorm) as a technique to manage gradient overlap. ZNorm adjusts the gradient scale, standardizing gradients across layers and reducing the negative impact of overlapping gradients. Our experiments demonstrate that ZNorm improves training process, especially in non-convex optimization scenarios common in deep learning, where finding optimal solutions is challenging. These findings suggest that ZNorm can affect the gradient flow, enhancing performance in large-scale data processing where accuracy is critical.
Authors: Yang Xiang, Li Fan, Tulika Saha, Xiaoying Pang, Yushan Pan, Haiyang Zhang, Chengtao Ji
Abstract: Graph clustering is an essential aspect of network analysis that involves grouping nodes into separate clusters. Recent developments in deep learning have resulted in advanced deep graph clustering techniques, which have proven effective in many applications. Nonetheless, these methods often encounter difficulties when dealing with the complexities of real-world graphs, particularly in the presence of noisy edges. Additionally, many denoising graph clustering strategies tend to suffer from lower performance compared to their non-denoised counterparts, training instability, and challenges in scaling to large datasets. To tackle these issues, we introduce a new framework called the Dual Adaptive Assignment Approach for Robust Graph-Based Clustering (RDSA). RDSA consists of three key components: (i) a node embedding module that effectively integrates the graph's topological features and node attributes; (ii) a structure-based soft assignment module that improves graph modularity by utilizing an affinity matrix for node assignments; and (iii) a node-based soft assignment module that identifies community landmarks and refines node assignments to enhance the model's robustness. We assess RDSA on various real-world datasets, demonstrating its superior performance relative to existing state-of-the-art methods. Our findings indicate that RDSA provides robust clustering across different graph types, excelling in clustering effectiveness and robustness, including adaptability to noise, stability, and scalability.
Authors: Christos Fragkathoulas, Vasiliki Papanikou, Evaggelia Pitoura, Evimaria Terzi
Abstract: This paper introduces the first graph-based framework for generating group counterfactual explanations to audit model fairness, a crucial aspect of trustworthy machine learning. Counterfactual explanations are instrumental in understanding and mitigating unfairness by revealing how inputs should change to achieve a desired outcome. Our framework, named Feasible Group Counterfactual Explanations (FGCEs), captures real-world feasibility constraints and constructs subgroups with similar counterfactuals, setting it apart from existing methods. It also addresses key trade-offs in counterfactual generation, including the balance between the number of counterfactuals, their associated costs, and the breadth of coverage achieved. To evaluate these trade-offs and assess fairness, we propose measures tailored to group counterfactual generation. Our experimental results on benchmark datasets demonstrate the effectiveness of our approach in managing feasibility constraints and trade-offs, as well as the potential of our proposed metrics in identifying and quantifying fairness issues.
Authors: Zixuan He, Ziqian Kong, Zhengyu Chen, Yuling Zhan, Zijun Que, Zhengguo Xu
Abstract: Accurate remaining useful life (RUL) predictions are critical to the safe operation of aero-engines. Currently, the RUL prediction task is mainly a regression paradigm with only mean square error as the loss function and lacks research on feature space structure, the latter of which has shown excellent performance in a large number of studies. This paper develops a multi-granularity supervised contrastive (MGSC) framework from plain intuition that samples with the same RUL label should be aligned in the feature space, and address the problems of too large minibatch size and unbalanced samples in the implementation. The RUL prediction with MGSC is implemented on using the proposed multi-phase training strategy. This paper also demonstrates a simple and scalable basic network structure and validates the proposed MGSC strategy on the CMPASS dataset using a convolutional long short-term memory network as a baseline, which effectively improves the accuracy of RUL prediction.
Authors: Elaine Cec\'ilia Gatto, Felipe Nakano Kenji, Jesse Read, Mauri Ferrandin, Ricardo Cerri, Celine Vens
Abstract: Multi-label classification is a type of supervised machine learning that can simultaneously assign multiple labels to an instance. To solve this task, some methods divide the original problem into several sub-problems (local approach), others learn all labels at once (global approach), and others combine several classifiers (ensemble approach). Regardless of the approach used, exploring and learning label correlations is important to improve the classifier predictions. Ensemble of Classifier Chains (ECC) is a well-known multi-label method that considers label correlations and can achieve good overall performance on several multi-label datasets and evaluation measures. However, one of the challenges when working with ECC is the high dimensionality of the label space, which can impose limitations for fully-cascaded chains as the complexity increases regarding feature space expansion. To improve classifier chains, we propose a method to chain disjoint correlated label clusters obtained by applying a partition method in the label space. During the training phase, the ground truth labels of each cluster are used as new features for all of the following clusters. During the test phase, the predicted labels of clusters are used as new features for all the following clusters. Our proposal, called Label Cluster Chains for Multi-Label Classification (LCC-ML), uses multi-label Random Forests as base classifiers in each cluster, combining their predictions to obtain a final multi-label classification. Our proposal obtained better results compared to the original ECC. This shows that learning and chaining disjoint correlated label clusters can better explore and learn label correlations.
Authors: Vincent Hanke, Tom Blanchard, Franziska Boenisch, Iyiola Emmanuel Olatunji, Michael Backes, Adam Dziedzic
Abstract: While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly private data. Recently, various new methods have been proposed to adapt closed LLMs to private data without leaking private information to third parties and/or the LLM provider. In this work, we analyze the privacy protection and performance of the four most recent methods for private adaptation of closed LLMs. By examining their threat models and thoroughly comparing their performance under different privacy levels according to differential privacy (DP), various LLM architectures, and multiple datasets for classification and generation tasks, we find that: (1) all the methods leak query data, i.e., the (potentially sensitive) user data that is queried at inference time, to the LLM provider, (2) three out of four methods also leak large fractions of private training data to the LLM provider while the method that protects private data requires a local open LLM, (3) all the methods exhibit lower performance compared to three private gradient-based adaptation methods for local open LLMs, and (4) the private adaptation methods for closed LLMs incur higher monetary training and query costs than running the alternative methods on local open LLMs. This yields the conclusion that, to achieve truly privacy-preserving LLM adaptations that yield high performance and more privacy at lower costs, taking into account current methods and models, one should use open LLMs.
Authors: Zhangfan Yang, Junkai Ji, Shan He, Jianqiang Li, Ruibin Bai, Zexuan Zhu, Yew Soon Ong
Abstract: Molecular docking enables virtual screening of compound libraries to identify potential ligands that target proteins of interest, a crucial step in drug development; however, as the size of the compound library increases, the computational complexity of traditional docking models increases. Deep learning algorithms can provide data-driven research and development models to increase the speed of the docking process. Unfortunately, few models can achieve superior screening performance compared to that of traditional models. Therefore, a novel deep learning-based docking approach named Dockformer is introduced in this study. Dockformer leverages multimodal information to capture the geometric topology and structural knowledge of molecules and can directly generate binding conformations with the corresponding confidence measures in an end-to-end manner. The experimental results show that Dockformer achieves success rates of 90.53\% and 82.71\% on the PDBbind core set and PoseBusters benchmarks, respectively, and more than a 100-fold increase in the inference process speed, outperforming almost all state-of-the-art docking methods. In addition, the ability of Dockformer to identify the main protease inhibitors of coronaviruses is demonstrated in a real-world virtual screening scenario. Considering its high docking accuracy and screening efficiency, Dockformer can be regarded as a powerful and robust tool in the field of drug design.
Authors: Nadav Benedek, Matan Levy, Mahmood Sharif
Abstract: Neural networks have shown remarkable performance in various tasks, yet they remain susceptible to subtle changes in their input or model parameters. One particularly impactful vulnerability arises through the Bit-Flip Attack (BFA), where flipping a small number of critical bits in a model's parameters can severely degrade its performance. A common technique for inducing bit flips in DRAM is the Row-Hammer attack, which exploits frequent uncached memory accesses to alter data. Identifying susceptible bits can be achieved through exhaustive search or progressive layer-by-layer analysis, especially in quantized networks. In this work, we introduce Impactful Bit-Flip Search (IBS), a novel method for efficiently pinpointing and flipping critical bits in full-precision networks. Additionally, we propose a Weight-Stealth technique that strategically modifies the model's parameters in a way that maintains the float values within the original distribution, thereby bypassing simple range checks often used in tamper detection.
Authors: No\"el Vouitsis, Rasa Hosseinzadeh, Brendan Leigh Ross, Valentin Villecroze, Satya Krishna Gorti, Jesse C. Cresswell, Gabriel Loaiza-Ganem
Abstract: Although diffusion models can generate remarkably high-quality samples, they are intrinsically bottlenecked by their expensive iterative sampling procedure. Consistency models (CMs) have recently emerged as a promising diffusion model distillation method, reducing the cost of sampling by generating high-fidelity samples in just a few iterations. Consistency model distillation aims to solve the probability flow ordinary differential equation (ODE) defined by an existing diffusion model. CMs are not directly trained to minimize error against an ODE solver, rather they use a more computationally tractable objective. As a way to study how effectively CMs solve the probability flow ODE, and the effect that any induced error has on the quality of generated samples, we introduce Direct CMs, which \textit{directly} minimize this error. Intriguingly, we find that Direct CMs reduce the ODE solving error compared to CMs but also result in significantly worse sample quality, calling into question why exactly CMs work well in the first place. Full code is available at: https://github.com/layer6ai-labs/direct-cms.
Authors: Anton Johansson, Arunselvan Ramaswamy
Abstract: The development of robust generative models for highly varied non-stationary time series data is a complex yet important problem. Traditional models for time series data prediction, such as Long Short-Term Memory (LSTM), are inefficient and generalize poorly as they cannot capture complex temporal relationships. In this paper, we present a probabilistic generative model that can be trained to capture temporal information, and that is robust to data errors. We call it Time Deep Latent Gaussian Model (tDLGM). Its novel architecture is inspired by Deep Latent Gaussian Model (DLGM). Our model is trained to minimize a loss function based on the negative log loss. One contributing factor to Time Deep Latent Gaussian Model (tDLGM) robustness is our regularizer, which accounts for data trends. Experiments conducted show that tDLGM is able to reconstruct and generate complex time series data, and that it is robust against to noise and faulty data.
Authors: Till Korten (Helmholtz-Zentrum Dresden-Rossendorf HZDR), Vladimir Rybnikov (Deutsches Elektronen-Synchrotron DESY), Mathias Vogt (Deutsches Elektronen-Synchrotron DESY), Juliane Roensch-Schulenburg (Deutsches Elektronen-Synchrotron DESY), Peter Steinbach (Helmholtz-Zentrum Dresden-Rossendorf HZDR), Najmeh Mirian (Helmholtz-Zentrum Dresden-Rossendorf HZDR)
Abstract: Electron beam accelerators are essential in many scientific and technological fields. Their operation relies heavily on the stability and precision of the electron beam. Traditional diagnostic techniques encounter difficulties in addressing the complex and dynamic nature of electron beams. Particularly in the context of free-electron lasers (FELs), it is fundamentally impossible to measure the lasing-on and lasingoff electron power profiles for a single electron bunch. This is a crucial hurdle in the exact reconstruction of the photon pulse profile. To overcome this hurdle, we developed a machine learning model that predicts the temporal power profile of the electron bunch in the lasing-off regime using machine parameters that can be obtained when lasing is on. The model was statistically validated and showed superior predictions compared to the state-of-the-art batch calibrations. The work we present here is a critical element for a virtual pulse reconstruction diagnostic (VPRD) tool designed to reconstruct the power profile of individual photon pulses without requiring repeated measurements in the lasing-off regime. This promises to significantly enhance the diagnostic capabilities in FELs at large.
Authors: Jan Hansen-Palmus, Michael Truong Le, Oliver Hausd\"orfer, Alok Verma
Abstract: Large Language Models (LLMs) have pushed the frontier of artificial intelligence but are comprised of hundreds of billions of parameters and operations. For faster inference latency, LLMs are deployed on multiple hardware accelerators through various Model Parallelism strategies. Our paper looks into the details on one such strategy - Tensor Parallel - and proposes to reduce latency by compressing inter-accelerator communication. We leverage fine grained quantization techniques to compress selected activations by 3.5 - 4.5x. Our proposed method leads up to 2x reduction of time-to-first-token (TTFT) with negligible model performance degradation.
Authors: Eghbal Rahimikia, Stefan Zohren, Ser-Huang Poon
Abstract: This study develops a financial word embedding using 15 years of business news. Our results show that this specialised language model produces more accurate results than general word embeddings, based on a financial benchmark we established. As an application, we incorporate this word embedding into a simple machine learning model to enhance the HAR model for forecasting realised volatility. This approach statistically and economically outperforms established econometric models. Using an explainable AI method, we also identify key phrases in business news that contribute significantly to volatility, offering insights into language patterns tied to market dynamics.
Authors: Kevin Miller, Andrea L. Bertozzi
Abstract: Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier. A challenge is to identify which points to label to best improve performance while limiting the number of new labels. "Model Change" active learning quantifies the resulting change incurred in the classifier by introducing the additional label(s). We pair this idea with graph-based semi-supervised learning methods, that use the spectrum of the graph Laplacian matrix, which can be truncated to avoid prohibitively large computational and storage costs. We consider a family of convex loss functions for which the acquisition function can be efficiently approximated using the Laplace approximation of the posterior distribution. We show a variety of multiclass examples that illustrate improved performance over prior state-of-art.
Authors: Sitan Chen, Weiyuan Gong
Abstract: Here we revisit one of the prototypical tasks for characterizing the structure of noise in quantum devices: estimating every eigenvalue of an $n$-qubit Pauli noise channel to error $\epsilon$. Prior work [14] proved no-go theorems for this task in the practical regime where one has a limited amount of quantum memory, e.g. any protocol with $\le 0.99n$ ancilla qubits of quantum memory must make exponentially many measurements, provided it is non-concatenating. Such protocols can only interact with the channel by repeatedly preparing a state, passing it through the channel, and measuring immediately afterward. This left open a natural question: does the lower bound hold even for general protocols, i.e. ones which chain together many queries to the channel, interleaved with arbitrary data-processing channels, before measuring? Surprisingly, in this work we show the opposite: there is a protocol that can estimate the eigenvalues of a Pauli channel to error $\epsilon$ using only $O(\log n/\epsilon^2)$ ancilla and $\tilde{O}(n^2/\epsilon^2)$ measurements. In contrast, we show that any protocol with zero ancilla, even a concatenating one, must make $\Omega(2^n/\epsilon^2)$ measurements, which is tight. Our results imply, to our knowledge, the first quantum learning task where logarithmically many qubits of quantum memory suffice for an exponential statistical advantage. Our protocol can be naturally extended to a protocol that learns the eigenvalues of Pauli terms within any subset $A$ of a Pauli channel with $O(\log\log(|A|)/\epsilon^2)$ ancilla and $\tilde{O}(n^2/\epsilon^2)$ measurements.
Authors: S. Dubey, T. E. Browder, S. Kohani, R. Mandal, A. Sibidanov, R. Sinha
Abstract: We report on a novel application of computer vision techniques to extract beyond the Standard Model parameters directly from high energy physics flavor data. We propose a simple but novel data representation that transforms the angular and kinematic distributions into "quasi-images", which are used to train a convolutional neural network to perform regression tasks, similar to fitting. As a proof-of-concept, we train a 34-layer Residual Neural Network to regress on these images and determine information about the Wilson Coefficient $C_{9}$ in Monte Carlo simulations of $B^0 \rightarrow K^{*0}\mu^{+}\mu^{-}$ decays. The method described here can be generalized and may find applicability across a variety of experiments.
Authors: Yingzhou Lu, Minjie Shen, Ling Yue, Chenhao Li, Lulu Chen, Fan Meng, Xiao Wang, David Herrington, Yue Wang, Yue Zhao, Tianfan Fu, Capucine Van Rechem
Abstract: The surge in high-throughput omics data has reshaped the landscape of biological research, underlining the need for powerful, user-friendly data analysis and interpretation tools. This paper presents GenoCraft, a web-based comprehensive software solution designed to handle the entire pipeline of omics data processing. GenoCraft offers a unified platform featuring advanced bioinformatics tools, covering all aspects of omics data analysis. It encompasses a range of functionalities, such as normalization, quality control, differential analysis, network analysis, pathway analysis, and diverse visualization techniques. This software makes state-of-the-art omics data analysis more accessible to a wider range of users. With GenoCraft, researchers and data scientists have access to an array of cutting-edge bioinformatics tools under a user-friendly interface, making it a valuable resource for managing and analyzing large-scale omics data. The API with an interactive web interface is publicly available at https://genocraft.stanford. edu/. We also release all the codes in https://github.com/futianfan/GenoCraft.
URLs: https://genocraft.stanford., https://github.com/futianfan/GenoCraft.
Authors: Shiwei Liu, Guanchen Tao, Yifei Zou, Derek Chow, Zichen Fan, Kauna Lei, Bangfei Pan, Dennis Sylvester, Gregory Kielian, Mehdi Saligane
Abstract: The self-attention mechanism distinguishes transformer-based large language models (LLMs) apart from convolutional and recurrent neural networks. Despite the performance improvement, achieving real-time LLM inference on silicon remains challenging due to the extensive use of Softmax in self-attention. In addition to the non-linearity, the low arithmetic intensity significantly limits processing parallelism, especially when working with longer contexts. To address this challenge, we propose Constant Softmax (ConSmax), a software-hardware co-design that serves as an efficient alternative to Softmax. ConSmax utilizes differentiable normalization parameters to eliminate the need for maximum searching and denominator summation in Softmax. This approach enables extensive parallelization while still executing the essential functions of Softmax. Moreover, a scalable ConSmax hardware design with a bitwidth-split look-up table (LUT) can achieve lossless non-linear operations and support mixed-precision computing. Experimental results show that ConSmax achieves a minuscule power consumption of 0.2mW and an area of 0.0008mm^2 at 1250MHz working frequency in 16nm FinFET technology. For open-source contribution, we further implement our design with the OpenROAD toolchain under SkyWater's 130nm CMOS technology. The corresponding power is 2.69mW and the area is 0.007mm^2. ConSmax achieves 3.35x power savings and 2.75x area savings in 16nm technology, and 3.15x power savings and 4.14x area savings with the open-source EDA toolchain. In the meantime, it also maintains comparable accuracy on the GPT-2 model and the WikiText103 dataset. The project is available at https://github.com/ReaLLMASIC/ConSmax
Authors: Zijun Long, George Killick, Lipeng Zhuang, Gerardo Aragon-Camarasa, Zaiqiao Meng, Richard Mccreadie
Abstract: State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been demonstrated that CE can compromise model generalization and stability. While recent works employing contrastive learning address some of these limitations by enhancing the quality of embeddings and producing better decision boundaries, they often overlook the importance of hard negative mining and rely on resource intensive and slow training using large sample batches. To counter these issues, we introduce a novel approach named CLCE, which integrates Label-Aware Contrastive Learning with CE. Our approach not only maintains the strengths of both loss functions but also leverages hard negative mining in a synergistic way to enhance performance. Experimental results demonstrate that CLCE significantly outperforms CE in Top-1 accuracy across twelve benchmarks, achieving gains of up to 3.52% in few-shot learning scenarios and 3.41% in transfer learning settings with the BEiT-3 model. Importantly, our proposed CLCE approach effectively mitigates the dependency of contrastive learning on large batch sizes such as 4096 samples per batch, a limitation that has previously constrained the application of contrastive learning in budget-limited hardware environments.
Authors: Yulin Shao
Abstract: At the heart of the Internet of Things (IoT) -- a domain witnessing explosive growth -- the imperative for energy efficiency and the extension of device lifespans has never been more pressing. This paper presents DEEP-IoT, an innovative communication paradigm poised to redefine how IoT devices communicate. Through a pioneering feedback channel coding strategy, DEEP-IoT challenges and transforms the traditional transmitter (IoT devices)-centric communication model to one where the receiver (the access point) play a pivotal role, thereby cutting down energy use and boosting device longevity. We not only conceptualize DEEP-IoT but also actualize it by integrating deep learning-enhanced feedback channel codes within a narrow-band system. Simulation results show a significant enhancement in the operational lifespan of IoT cells -- surpassing traditional systems using Turbo and Polar codes by up to 52.71%. This leap signifies a paradigm shift in IoT communications, setting the stage for a future where IoT devices boast unprecedented efficiency and durability.
Authors: Fangqiang Ding, Yunzhou Zhu, Xiangyu Wen, Gaowen Liu, Chris Xiaoxuan Lu
Abstract: Designing egocentric 3D hand pose estimation systems that can perform reliably in complex, real-world scenarios is crucial for downstream applications. Previous approaches using RGB or NIR imagery struggle in challenging conditions: RGB methods are susceptible to lighting variations and obstructions like handwear, while NIR techniques can be disrupted by sunlight or interference from other NIR-equipped devices. To address these limitations, we present ThermoHands, the first benchmark focused on thermal image-based egocentric 3D hand pose estimation, demonstrating the potential of thermal imaging to achieve robust performance under these conditions. The benchmark includes a multi-view and multi-spectral dataset collected from 28 subjects performing hand-object and hand-virtual interactions under diverse scenarios, accurately annotated with 3D hand poses through an automated process. We introduce a new baseline method, TherFormer, utilizing dual transformer modules for effective egocentric 3D hand pose estimation in thermal imagery. Our experimental results highlight TherFormer's leading performance and affirm thermal imaging's effectiveness in enabling robust 3D hand pose estimation in adverse conditions.
Authors: Daniel May, Matthew Taylor, Petr Musilek
Abstract: As distributed energy resources (DERs) grow, the electricity grid faces increased net load variability at the grid edge, impacting operability and reliability. Transactive energy, facilitated through local energy markets, offers a decentralized, indirect demand response solution, with model-free control techniques, such as deep reinforcement learning (DRL), enabling automated, decentralized participation. However, existing studies largely overlook community-level net load variability, focusing instead on socioeconomic metrics. This study addresses this gap by using DRL agents to automate end-user participation in a local energy market (ALEX), where agents act independently to minimize individual energy bills. Results reveal a strong link between bill reduction and decreased net load variability, assessed across metrics such as ramping rate, load factor, and peak demand over various time horizons. Using a no-control baseline, DRL agents are benchmarked against a near-optimal dynamic programming approach. The dynamic programming benchmark achieves reductions of 22.05 percent, 83.92 percent, and 24.09 percent in daily import, export, and peak demand, respectively, while the DRL agents show comparable or superior results with reductions of 21.93 percent, 84.46 percent, and 27.02 percent. This study demonstrates the effectiveness of DRL in decentralized grid management, highlighting its scalability and near-optimal performance in reducing net load variability within community-driven energy markets.
Authors: Hartmut H\"antze, Lina Xu, Christian J. Mertens, Felix J. Dorfner, Leonhard Donle, Felix Busch, Avan Kader, Sebastian Ziegelmayer, Nadine Bayerl, Nassir Navab, Daniel Rueckert, Julia Schnabel, Hugo JWL Aerts, Daniel Truhn, Fabian Bamberg, Jakob Wei{\ss}, Christopher L. Schlett, Steffen Ringhof, Thoralf Niendorf, Tobias Pischon, Hans-Ulrich Kauczor, Tobias Nonnenmacher, Thomas Kr\"oncke, Henry V\"olzke, Jeanette Schulz-Menger, Klaus Maier-Hein, Mathias Prokop, Bram van Ginneken, Alessa Hering, Marcus R. Makowski, Lisa C. Adams, Keno K. Bressem
Abstract: Purpose: To develop and evaluate a deep learning model for multi-organ segmentation of MRI scans. Materials and Methods: The model was trained on 1,200 manually annotated 3D axial MRI scans from the UK Biobank, 221 in-house MRI scans, and 1228 CT scans from the TotalSegmentator dataset. A human-in-the-loop annotation workflow was employed, leveraging cross-modality transfer learning from an existing CT segmentation model to segment 40 anatomical structures. The annotation process began with a model based on transfer learning between CT and MR, which was iteratively refined based on manual corrections to predicted segmentations. The model's performance was evaluated on MRI examinations obtained from the German National Cohort (NAKO) study (n=900) from the AMOS22 dataset (n=60) and from the TotalSegmentator-MRI test data (n=29). The Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD) were used to assess segmentation quality, stratified by organ and scan type. The model and its weights will be open-sourced. Results: MRSegmentator demonstrated high accuracy for well-defined organs (lungs: DSC 0.96, heart: DSC 0.94) and organs with anatomic variability (liver: DSC 0.96, kidneys: DSC 0.95). Smaller structures showed lower accuracy (portal/splenic veins: DSC 0.64, adrenal glands: DSC 0.69). On external validation using NAKO data, mean DSC ranged from 0.85 $\pm$ 0.08 for T2-HASTE to 0.91 $\pm$ 0.05 for in-phase sequences. The model generalized well to CT, achieving mean DSC of 0.84 $\pm$ 0.11 on AMOS CT data. Conclusion: MRSegmentator accurately segments 40 anatomical structures in MRI across diverse datasets and imaging protocols, with additional generalizability to CT images. This open-source model will provide a valuable tool for automated multi-organ segmentation in medical imaging research. It can be downloaded from https://github.com/hhaentze/MRSegmentator.
Authors: Hee-Youl Kwak, Dae-Young Yun, Yongjune Kim, Sang-Hyo Kim, Jong-Seon No
Abstract: Ensuring extremely high reliability in channel coding is essential for 6G networks. The next-generation of ultra-reliable and low-latency communications (xURLLC) scenario within 6G networks requires frame error rate (FER) below $10^{-9}$. However, low-density parity-check (LDPC) codes, the standard in 5G new radio (NR), encounter a challenge known as the error floor phenomenon, which hinders to achieve such low rates. To tackle this problem, we introduce an innovative solution: boosted neural min-sum (NMS) decoder. This decoder operates identically to conventional NMS decoders, but is trained by novel training methods including: i) boosting learning with uncorrected vectors, ii) block-wise training schedule to address the vanishing gradient issue, iii) dynamic weight sharing to minimize the number of trainable weights, iv) transfer learning to reduce the required sample count, and v) data augmentation to expedite the sampling process. Leveraging these training strategies, the boosted NMS decoder achieves the state-of-the art performance in reducing the error floor as well as superior waterfall performance. Remarkably, we fulfill the 6G xURLLC requirement for 5G LDPC codes without a severe error floor. Additionally, the boosted NMS decoder, once its weights are trained, can perform decoding without additional modules, making it highly practical for immediate application. The source code is available at https://github.com/ghy1228/LDPC_Error_Floor.
Authors: Chenyu Huang, Zhengyang Tang, Dongdong Ge, Shixi Hu, Ruoqing Jiang, Benyou Wang, Zizhuo Wang, Xin Zheng
Abstract: Optimization modeling and solving play a critical role in the application of Operations Research (OR) tools to address real-world problems, yet they pose challenges and require extensive expertise from OR experts. With the advent of large language models (LLMs), new opportunities have emerged to streamline and automate these tasks. However, current research predominantly relies on closed-source LLMs such as GPT-4, along with extensive prompt engineering techniques. This reliance stems from the scarcity of high-quality training datasets for optimization modeling, resulting in elevated costs, prolonged processing times, and privacy concerns. To address these challenges, our work is the first to propose a viable path for training open-source LLMs that are capable of optimization modeling as well as developing and executing solver codes, eventually leading to a superior ability for automating optimization modeling and solving. Particularly, we introduce a semi-automated data synthesis framework designed for optimization modeling issues, named OR-Instruct. This framework merges the training data requirements of large models with the unique characteristics of optimization modeling problems, and allows for customizable enhancements tailored to specific scenarios or modeling types. To evaluate the performance of our proposed framework, we present the IndustryOR benchmark, the inaugural industrial standard for evaluating LLMs in solving practical OR problems. Utilizing data synthesized through OR-Instruct, we train various open-source LLMs with a capacity of 7 billion parameters (dubbed ORLMs). The resulting model demonstrates significantly enhanced optimization modeling capabilities, achieving state-of-the-art performance across the NL4OPT, MAMO, and IndustryOR benchmarks. Our code and data are available at \url{https://github.com/Cardinal-Operations/ORLM}.
Authors: Quanqi Hu, Qi Qi, Zhaosong Lu, Tianbao Yang
Abstract: In this paper, we study a class of non-smooth non-convex problems in the form of $\min_{x}[\max_{y\in Y}\phi(x, y) - \max_{z\in Z}\psi(x, z)]$, where both $\Phi(x) = \max_{y\in Y}\phi(x, y)$ and $\Psi(x)=\max_{z\in Z}\psi(x, z)$ are weakly convex functions, and $\phi(x, y), \psi(x, z)$ are strongly concave functions in terms of $y$ and $z$, respectively. It covers two families of problems that have been studied but are missing single-loop stochastic algorithms, i.e., difference of weakly convex functions and weakly convex strongly-concave min-max problems. We propose a stochastic Moreau envelope approximate gradient method dubbed SMAG, the first single-loop algorithm for solving these problems, and provide a state-of-the-art non-asymptotic convergence rate. The key idea of the design is to compute an approximate gradient of the Moreau envelopes of $\Phi, \Psi$ using only one step of stochastic gradient update of the primal and dual variables. Empirically, we conduct experiments on positive-unlabeled (PU) learning and partial area under ROC curve (pAUC) optimization with an adversarial fairness regularizer to validate the effectiveness of our proposed algorithms.
Authors: Yasi Zhang, Peiyu Yu, Yaxuan Zhu, Yingshan Chang, Feng Gao, Ying Nian Wu, Oscar Leong
Abstract: Generative models based on flow matching have attracted significant attention for their simplicity and superior performance in high-resolution image synthesis. By leveraging the instantaneous change-of-variables formula, one can directly compute image likelihoods from a learned flow, making them enticing candidates as priors for downstream tasks such as inverse problems. In particular, a natural approach would be to incorporate such image probabilities in a maximum-a-posteriori (MAP) estimation problem. A major obstacle, however, lies in the slow computation of the log-likelihood, as it requires backpropagating through an ODE solver, which can be prohibitively slow for high-dimensional problems. In this work, we propose an iterative algorithm to approximate the MAP estimator efficiently to solve a variety of linear inverse problems. Our algorithm is mathematically justified by the observation that the MAP objective can be approximated by a sum of $N$ ``local MAP'' objectives, where $N$ is the number of function evaluations. By leveraging Tweedie's formula, we show that we can perform gradient steps to sequentially optimize these objectives. We validate our approach for various linear inverse problems, such as super-resolution, deblurring, inpainting, and compressed sensing, and demonstrate that we can outperform other methods based on flow matching. Code is available at https://github.com/YasminZhang/ICTM.
Authors: Bastian Epping, Alexandre Ren\'e, Moritz Helias, Michael T. Schaub
Abstract: Graph neural networks (GNNs) have emerged as powerful tools for processing relational data in applications. However, GNNs suffer from the problem of oversmoothing, the property that the features of all nodes exponentially converge to the same vector over layers, prohibiting the design of deep GNNs. In this work we study oversmoothing in graph convolutional networks (GCNs) by using their Gaussian process (GP) equivalence in the limit of infinitely many hidden features. By generalizing methods from conventional deep neural networks (DNNs), we can describe the distribution of features at the output layer of deep GCNs in terms of a GP: as expected, we find that typical parameter choices from the literature lead to oversmoothing. The theory, however, allows us to identify a new, non-oversmoothing phase: if the initial weights of the network have sufficiently large variance, GCNs do not oversmooth, and node features remain informative even at large depth. We demonstrate the validity of this prediction in finite-size GCNs by training a linear classifier on their output. Moreover, using the linearization of the GCN GP, we generalize the concept of propagation depth of information from DNNs to GCNs. This propagation depth diverges at the transition between the oversmoothing and non-oversmoothing phase. We test the predictions of our approach and find good agreement with finite-size GCNs. Initializing GCNs near the transition to the non-oversmoothing phase, we obtain networks which are both deep and expressive.
Authors: Soroush Saghafian, Lihi Idan
Abstract: Advanced analytics science methods have enabled combining the power of artificial and human intelligence, creating \textit{centaurs} that allow superior decision-making. Centaurs are hybrid human-algorithm models that combine both formal analytics and human intuition in a symbiotic manner within their learning and reasoning process. We argue that the future of AI development and use in many domains needs to focus more on centaurs as opposed to other AI approaches. This paradigm shift towards centaur-based AI methods raises some fundamental questions: How are centaurs different from other human-in-the-loop methods? What are the most effective methods for creating centaurs? When should centaurs be used, and when should the lead be given to pure AI models? Doesn't the incorporation of human intuition -- which at times can be misleading -- in centaurs' decision-making process degrade its performance compared to pure AI methods? This work aims to address these fundamental questions, focusing on recent advancements in generative AI, and especially in Large Language Models (LLMs), as a main case study to illustrate centaurs' critical essentiality to future AI endeavors.
Authors: David Debot, Pietro Barbiero, Francesco Giannini, Gabriele Ciravegna, Michelangelo Diligenti, Giuseppe Marra
Abstract: The lack of transparency in the decision-making processes of deep learning systems presents a significant challenge in modern artificial intelligence (AI), as it impairs users' ability to rely on and verify these systems. To address this challenge, Concept Bottleneck Models (CBMs) have made significant progress by incorporating human-interpretable concepts into deep learning architectures. This approach allows predictions to be traced back to specific concept patterns that users can understand and potentially intervene on. However, existing CBMs' task predictors are not fully interpretable, preventing a thorough analysis and any form of formal verification of their decision-making process prior to deployment, thereby raising significant reliability concerns. To bridge this gap, we introduce Concept-based Memory Reasoner (CMR), a novel CBM designed to provide a human-understandable and provably-verifiable task prediction process. Our approach is to model each task prediction as a neural selection mechanism over a memory of learnable logic rules, followed by a symbolic evaluation of the selected rule. The presence of an explicit memory and the symbolic evaluation allow domain experts to inspect and formally verify the validity of certain global properties of interest for the task prediction process. Experimental results demonstrate that CMR achieves better accuracy-interpretability trade-offs to state-of-the-art CBMs, discovers logic rules consistent with ground truths, allows for rule interventions, and allows pre-deployment verification.
Authors: Alexandros Kontogiannis, Richard Hodgkinson, Emily L. Manchester
Abstract: We solve a Bayesian inverse Navier-Stokes (N-S) problem that assimilates velocimetry data in order to jointly reconstruct the flow field and learn the unknown N-S parameters. By incorporating a Carreau shear-thinning viscosity model into the N-S problem, we devise an algorithm that learns the most likely Carreau parameters of a shear-thinning fluid, and estimates their uncertainties, from velocimetry data alone. We then conduct a flow-MRI experiment to obtain velocimetry data of an axisymmetric laminar jet through an idealised medical device (FDA nozzle) for a blood analogue fluid. We show that the algorithm can successfully reconstruct the flow field by learning the most likely Carreau parameters, and that the learned parameters are in very good agreement with rheometry measurements. The algorithm accepts any algebraic effective viscosity model, as long as the model is differentiable, and it can be extended to more complicated non-Newtonian fluids (e.g. Oldroyd-B fluid) if a viscoelastic model is incorporated into the N-S problem.
Authors: Yiming Zhou, Zixuan Zeng, Andi Chen, Xiaofan Zhou, Haowei Ni, Shiyao Zhang, Panfeng Li, Liangxi Liu, Mengyao Zheng, Xupeng Chen
Abstract: Exploring the capabilities of Neural Radiance Fields (NeRF) and Gaussian-based methods in the context of 3D scene reconstruction, this study contrasts these modern approaches with traditional Simultaneous Localization and Mapping (SLAM) systems. Utilizing datasets such as Replica and ScanNet, we assess performance based on tracking accuracy, mapping fidelity, and view synthesis. Findings reveal that NeRF excels in view synthesis, offering unique capabilities in generating new perspectives from existing data, albeit at slower processing speeds. Conversely, Gaussian-based methods provide rapid processing and significant expressiveness but lack comprehensive scene completion. Enhanced by global optimization and loop closure techniques, newer methods like NICE-SLAM and SplaTAM not only surpass older frameworks such as ORB-SLAM2 in terms of robustness but also demonstrate superior performance in dynamic and complex environments. This comparative analysis bridges theoretical research with practical implications, shedding light on future developments in robust 3D scene reconstruction across various real-world applications.
Authors: Sitan Chen, Weiyuan Gong, Qi Ye, Zhihan Zhang
Abstract: We study the task of agnostic tomography: given copies of an unknown $n$-qubit state $\rho$ which has fidelity $\tau$ with some state in a given class $C$, find a state which has fidelity $\ge \tau - \epsilon$ with $\rho$. We give a new framework, stabilizer bootstrapping, for designing computationally efficient protocols for this task, and use this to get new agnostic tomography protocols for the following classes: Stabilizer states: We give a protocol that runs in time $\mathrm{poly}(n,1/\epsilon)\cdot (1/\tau)^{O(\log(1/\tau))}$, answering an open question posed by Grewal, Iyer, Kretschmer, Liang [43] and Anshu and Arunachalam [6]. Previous protocols ran in time $\mathrm{exp}(\Theta(n))$ or required $\tau>\cos^2(\pi/8)$. States with stabilizer dimension $n - t$: We give a protocol that runs in time $n^3\cdot(2^t/\tau)^{O(\log(1/\epsilon))}$, extending recent work on learning quantum states prepared by circuits with few non-Clifford gates, which only applied in the realizable setting where $\tau = 1$ [33, 40, 49, 66]. Discrete product states: If $C = K^{\otimes n}$ for some $\mu$-separated discrete set $K$ of single-qubit states, we give a protocol that runs in time $(n/\mu)^{O((1 + \log (1/\tau))/\mu)}/\epsilon^2$. This strictly generalizes a prior guarantee which applied to stabilizer product states [42]. For stabilizer product states, we give a further improved protocol that runs in time $(n^2/\epsilon^2)\cdot (1/\tau)^{O(\log(1/\tau))}$. As a corollary, we give the first protocol for estimating stabilizer fidelity, a standard measure of magic for quantum states, to error $\epsilon$ in $n^3 \mathrm{quasipoly}(1/\epsilon)$ time.
Authors: Sneihil Gopal, David Griffith, Richard A. Rouil, Chunmei Liu
Abstract: The Open Radio Access Network (O-RAN) initiative, characterized by open interfaces and AI/ML-capable RAN Intelligent Controller (RIC), facilitates effective spectrum sharing among RANs. In this context, we introduce AdapShare, an ORAN-compatible solution leveraging Reinforcement Learning (RL) for intent-based spectrum management, with the primary goal of minimizing resource surpluses or deficits in RANs. By employing RL agents, AdapShare intelligently learns network demand patterns and uses them to allocate resources. We demonstrate the efficacy of AdapShare in the spectrum sharing scenario between LTE and NR networks, incorporating real-world LTE resource usage data and synthetic NR usage data to demonstrate its practical use. We use the average surplus or deficit and fairness index to measure the system's performance in various scenarios. AdapShare outperforms a quasi-static resource allocation scheme based on long-term network demand statistics, particularly when available resources are scarce or exceed the aggregate demand from the networks. Lastly, we present a high-level O-RAN compatible architecture using RL agents, which demonstrates the seamless integration of AdapShare into real-world deployment scenarios.
Authors: Ismail Erbas, Aporva Amarnath, Vikas Pandey, Karthik Swaminathan, Naigang Wang, Xavier Intes
Abstract: Fluorescence lifetime imaging (FLI) is a widely used technique in the biomedical field for measuring the decay times of fluorescent molecules, providing insights into metabolic states, protein interactions, and ligand-receptor bindings. However, its broader application in fast biological processes, such as dynamic activity monitoring, and clinical use, such as in guided surgery, is limited by long data acquisition times and computationally demanding data processing. While deep learning has reduced post-processing times, time-resolved data acquisition remains a bottleneck for real-time applications. To address this, we propose a method to achieve real-time FLI using an FPGA-based hardware accelerator. Specifically, we implemented a GRU-based sequence-to-sequence (Seq2Seq) model on an FPGA board compatible with time-resolved cameras. The GRU model balances accurate processing with the resource constraints of FPGAs, which have limited DSP units and BRAM. The limited memory and computational resources on the FPGA require efficient scheduling of operations and memory allocation to deploy deep learning models for low-latency applications. We address these challenges by using STOMP, a queue-based discrete-event simulator that automates and optimizes task scheduling and memory management on hardware. By integrating a GRU-based Seq2Seq model and its compressed version, called Seq2SeqLite, generated through knowledge distillation, we were able to process multiple pixels in parallel, reducing latency compared to sequential processing. We explore various levels of parallelism to achieve an optimal balance between performance and resource utilization. Our results indicate that the proposed techniques achieved a 17.7x and 52.0x speedup over manual scheduling for the Seq2Seq model and the Seq2SeqLite model, respectively.
Authors: Aoran Zhang, Wenbin Zhou, Liyan Xie, Shixiang Zhu
Abstract: Time series data are crucial across diverse domains such as finance and healthcare, where accurate forecasting and decision-making rely on advanced modeling techniques. While generative models have shown great promise in capturing the intricate dynamics inherent in time series, evaluating their performance remains a major challenge. Traditional evaluation metrics fall short due to the temporal dependencies and potential high dimensionality of the features. In this paper, we propose the REcurrent NeurAL (RENAL) Goodness-of-Fit test, a novel and statistically rigorous framework for evaluating generative time series models. By leveraging recurrent neural networks, we transform the time series into conditionally independent data pairs, enabling the application of a chi-square-based goodness-of-fit test to the temporal dependencies within the data. This approach offers a robust, theoretically grounded solution for assessing the quality of generative models, particularly in settings with limited time sequences. We demonstrate the efficacy of our method across both synthetic and real-world datasets, outperforming existing methods in terms of reliability and accuracy. Our method fills a critical gap in the evaluation of time series generative models, offering a tool that is both practical and adaptable to high-stakes applications.
Authors: Wei Xie, Shuoyoucheng Ma, Zhenhua Wang, Enze Wang, Kai Chen, Xiaobing Sun, Baosheng Wang
Abstract: The cognitive mechanism by which Large Language Models (LLMs) solve mathematical problems remains a widely debated and unresolved issue. Currently, there is little interpretable experimental evidence that connects LLMs' problem-solving with human cognitive psychology.To determine if LLMs possess human-like mathematical reasoning, we modified the problems used in the human Cognitive Reflection Test (CRT). Our results show that, even with the use of Chains of Thought (CoT) prompts, mainstream LLMs, including the latest o1 model (noted for its reasoning capabilities), have a high error rate when solving these modified CRT problems. Specifically, the average accuracy rate dropped by up to 50% compared to the original questions.Further analysis of LLMs' incorrect answers suggests that they primarily rely on pattern matching from their training data, which aligns more with human intuition (System 1 thinking) rather than with human-like reasoning (System 2 thinking). This finding challenges the belief that LLMs have genuine mathematical reasoning abilities comparable to humans. As a result, this work may adjust overly optimistic views on LLMs' progress towards artificial general intelligence.
Authors: M. V. Kornilov, V. S. Korolev, K. L. Malanchev, A. D. Lavrukhina, E. Russeil, T. A. Semenikhin, E. Gangler, E. E. O. Ishida, M. V. Pruzhinskaya, A. A. Volnova, S. Sreejith
Abstract: We present coniferest, an open source generic purpose active anomaly detection framework written in Python. The package design and implemented algorithms are described. Currently, static outlier detection analysis is supported via the Isolation forest algorithm. Moreover, Active Anomaly Discovery (AAD) and Pineforest algorithms are available to tackle active anomaly detection problems. The algorithms and package performance are evaluated on a series of synthetic datasets. We also describe a few success cases which resulted from applying the package to real astronomical data in active anomaly detection tasks within the SNAD project.
Authors: Yuqi Gu, Zhongyuan Lyu, Kaizheng Wang
Abstract: We propose a general transfer learning framework for clustering given a main dataset and an auxiliary one about the same subjects. The two datasets may reflect similar but different latent grouping structures of the subjects. We propose an adaptive transfer clustering (ATC) algorithm that automatically leverages the commonality in the presence of unknown discrepancy, by optimizing an estimated bias-variance decomposition. It applies to a broad class of statistical models including Gaussian mixture models, stochastic block models, and latent class models. A theoretical analysis proves the optimality of ATC under the Gaussian mixture model and explicitly quantifies the benefit of transfer. Extensive simulations and real data experiments confirm our method's effectiveness in various scenarios.
Authors: Rokas Gipi\v{s}kis, Ayrton San Joaquin, Ze Shen Chin, Adrian Regenfu{\ss}, Ariel Gil, Koen Holtman
Abstract: There is an urgent need to identify both short and long-term risks from newly emerging types of Artificial Intelligence (AI), as well as available risk management measures. In response, and to support global efforts in regulating AI and writing safety standards, we compile an extensive catalog of risk sources and risk management measures for general-purpose AI (GPAI) systems, complete with descriptions and supporting examples where relevant. This work involves identifying technical, operational, and societal risks across model development, training, and deployment stages, as well as surveying established and experimental methods for managing these risks. To the best of our knowledge, this paper is the first of its kind to provide extensive documentation of both GPAI risk sources and risk management measures that are descriptive, self-contained and neutral with respect to any existing regulatory framework. This work intends to help AI providers, standards experts, researchers, policymakers, and regulators in identifying and mitigating systemic risks from GPAI systems. For this reason, the catalog is released under a public domain license for ease of direct use by stakeholders in AI governance and standards.
Authors: Ali Saeizadeh, Pietro Brach del Prever, Douglas Schonholtz, Raffaele Guida, Emrecan Demirors, Jorge M. Jimenez, Pedram Johari, Tommaso Melodia
Abstract: This demo presents SeizNet, an innovative system for predicting epileptic seizures benefiting from a multi-modal sensor network and utilizing Deep Learning (DL) techniques. Epilepsy affects approximately 65 million people worldwide, many of whom experience drug-resistant seizures. SeizNet aims at providing highly accurate alerts, allowing individuals to take preventive measures without being disturbed by false alarms. SeizNet uses a combination of data collected through either invasive (intracranial electroencephalogram (iEEG)) or non-invasive (electroencephalogram (EEG) and electrocardiogram (ECG)) sensors, and processed by advanced DL algorithms that are optimized for real-time inference at the edge, ensuring privacy and minimizing data transmission. SeizNet achieves > 97% accuracy in seizure prediction while keeping the size and energy restrictions of an implantable device.
Authors: Chika Maduabuchi, Ericmoore Jossou, Matteo Bucci
Abstract: Purpose: High-speed video (HSV) phase detection (PD) segmentation is vital in nuclear reactors, chemical processing, and electronics cooling for detecting vapor, liquid, and microlayer phases. Traditional segmentation models face pixel-level accuracy and generalization issues in multimodal data. MSEG-VCUQ introduces VideoSAM, a hybrid framework leveraging convolutional neural networks (CNNs) and transformer-based vision models to enhance segmentation accuracy and generalizability across complex multimodal PD tasks. Methods: VideoSAM combines U-Net CNN and the Segment Anything Model (SAM) for advanced feature extraction and segmentation across diverse HSV PD modalities, spanning fluids like water, FC-72, nitrogen, and argon under varied heat flux conditions. The framework also incorporates uncertainty quantification (UQ) to assess pixel-based discretization errors, delivering reliable metrics such as contact line density and dry area fraction under experimental conditions. Results: VideoSAM outperforms SAM and modality-specific CNN models in segmentation accuracy, excelling in environments with complex phase boundaries, overlapping bubbles, and dynamic liquid-vapor interactions. Its hybrid architecture supports cross-dataset generalization, adapting effectively to varying modalities. The UQ module provides accurate error estimates, enhancing the reliability of segmentation outputs for advanced HSV PD research. Conclusion: MSEG-VCUQ, via VideoSAM, offers a robust solution for HSV PD segmentation, addressing previous limitations with advanced deep learning and UQ techniques. The open-source datasets and tools introduced enable scalable, precise, and adaptable segmentation for multimodal PD datasets, supporting advancements in HSV analysis and autonomous experimentation. The codes and data used for this paper are publicly available at https://github.com/chikap421/mseg_vcuq
Authors: Suhyeok Jang, Seojin Kim, Jinwoo Shin, Jongheon Jeong
Abstract: The remarkable advances in deep learning have led to the emergence of many off-the-shelf classifiers, e.g., large pre-trained models. However, since they are typically trained on clean data, they remain vulnerable to adversarial attacks. Despite this vulnerability, their superior performance and transferability make off-the-shelf classifiers still valuable in practice, demanding further work to provide adversarial robustness for them in a post-hoc manner. A recently proposed method, denoised smoothing, leverages a denoiser model in front of the classifier to obtain provable robustness without additional training. However, the denoiser often creates hallucination, i.e., images that have lost the semantics of their originally assigned class, leading to a drop in robustness. Furthermore, its noise-and-denoise procedure introduces a significant distribution shift from the original distribution, causing the denoised smoothing framework to achieve sub-optimal robustness. In this paper, we introduce Fine-Tuning with Confidence-Aware Denoised Image Selection (FT-CADIS), a novel fine-tuning scheme to enhance the certified robustness of off-the-shelf classifiers. FT-CADIS is inspired by the observation that the confidence of off-the-shelf classifiers can effectively identify hallucinated images during denoised smoothing. Based on this, we develop a confidence-aware training objective to handle such hallucinated images and improve the stability of fine-tuning from denoised images. In this way, the classifier can be fine-tuned using only images that are beneficial for adversarial robustness. We also find that such a fine-tuning can be done by updating a small fraction of parameters of the classifier. Extensive experiments demonstrate that FT-CADIS has established the state-of-the-art certified robustness among denoised smoothing methods across all $\ell_2$-adversary radius in various benchmarks.
Authors: M. Quattromini, M. A. Bucci, S. Cherubini, O. Semeraro
Abstract: This study presents a novel hybrid approach that combines Graph Neural Networks (GNNs) with Reynolds-Averaged Navier Stokes (RANS) equations to enhance the accuracy of mean flow reconstruction across a range of fluid dynamics applications. Traditional purely data-driven Neural Networks (NNs) models, often struggle maintaining physical consistency. Moreover, they typically require large datasets to achieve reliable performances. The GNN framework, which naturally handles unstructured data such as complex geometries in Computational Fluid Dynamics (CFD), is here integrated with RANS equations as a physical baseline model. The methodology leverages the adjoint method, enabling the use of RANS-derived gradients as optimization terms in the GNN training process. This ensures that the learned model adheres to the governing physics, maintaining physical consistency while improving the prediction accuracy. We test our approach on multiple CFD scenarios, including cases involving generalization with respect to the Reynolds number, sparse measurements, denoising and inpainting of missing portions of the mean flow. The results demonstrate significant improvements in the accuracy of the reconstructed mean flow compared to purely data-driven models, using limited amounts of data in the training dataset. The key strengths of this study are the integration of physical laws into the training process of the GNN, and the ability to achieve high-accuracy predictions with a limited amount of data, making this approach particularly valuable for applications in fluid dynamics where data is often scarce.