Authors: Ming Li, Chenyi Zhang, Qin Li
Abstract: Monotone learning refers to learning processes in which expected performance consistently improves as more training data is introduced. Non-monotone behavior of machine learning has been the topic of a series of recent works, with various proposals that ensure monotonicity by applying transformations or wrappers on learning algorithms. In this work, from a different perspective, we tackle the topic of monotone learning within the framework of Probably Approximately Correct (PAC) learning theory. Following the mechanism that estimates sample complexity of a PAC-learnable problem, we derive a performance lower bound for that problem, and prove the monotonicity of that bound as the sample sizes increase. By calculating the lower bound distribution, we are able to prove that given a PAC-learnable problem with a hypothesis space that is either of finite size or of finite VC dimension, any learning algorithm based on Empirical Risk Minimization (ERM) is monotone if training samples are independent and identically distributed (i.i.d.). We further carry out an experiment on two concrete machine learning problems, one of which has a finite hypothesis set, and the other of finite VC dimension, and compared the experimental data for the empirical risk distributions with the estimated theoretical bound. The results of the comparison have confirmed the monotonicity of learning for the two PAC-learnable problems.
Authors: S. Sanjuan, D. A. M\'endez, R. Arnau, J. M. Calabuig, X. D\'iaz de Ot\'alora Aguirre, F. Estell\'es
Abstract: In this paper we develop a mathematical model combined with machine learning techniques to predict shade-seeking behavior in cows exposed to heat stress. The approach integrates advanced mathematical features, such as time-averaged thermal indices and accumulated heat stress metrics, obtained by mathematical analysis of data from a farm in Titaguas (Valencia, Spain), collected during the summer of 2023. Two predictive models, Random Forests and Neural Networks, are compared for accuracy, robustness, and interpretability. The Random Forest model is highlighted for its balance between precision and explainability, achieving an RMSE of $14.97$. The methodology also employs $5-$fold cross-validation to ensure robustness under real-world conditions. This work not only advances the mathematical modeling of animal behavior but also provides useful insights for mitigating heat stress in livestock through data-driven tools.
Authors: Xiaodi Li, Dingcheng Li, Rujun Gao, Mahmoud Zamani, Latifur Khan
Abstract: Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards previously learned knowledge when it is trained on new tasks. Existing solutions involve storing exemplars from previous classes, regularizing parameters during the fine-tuning process, or assigning different model parameters to each task. The proposed solution LSEBMCL (Latent Space Energy-Based Model for Continual Learning) in this work is to use energy-based models (EBMs) to prevent catastrophic forgetting by sampling data points from previous tasks when training on new ones. The EBM is a machine learning model that associates an energy value with each input data point. The proposed method uses an EBM layer as an outer-generator in the continual learning framework for NLP tasks. The study demonstrates the efficacy of EBM in NLP tasks, achieving state-of-the-art results in all experiments.
Authors: Yanbing Zhou, Xiangmou Qu, Chenlong You, Jiyang Zhou, Jingyue Tang, Xin Zheng, Chunmao Cai, Yingbo Wu
Abstract: Prototype-based federated learning has emerged as a promising approach that shares lightweight prototypes to transfer knowledge among clients with data heterogeneity in a model-agnostic manner. However, existing methods often collect prototypes directly from local models, which inevitably introduce inconsistencies into representation learning due to the biased data distributions and differing model architectures among clients. In this paper, we identify that both statistical and model heterogeneity create a vicious cycle of representation inconsistency, classifier divergence, and skewed prototype alignment, which negatively impacts the performance of clients. To break the vicious cycle, we propose a novel framework named Federated Learning via Semantic Anchors (FedSA) to decouple the generation of prototypes from local representation learning. We introduce a novel perspective that uses simple yet effective semantic anchors serving as prototypes to guide local models in learning consistent representations. By incorporating semantic anchors, we further propose anchor-based regularization with margin-enhanced contrastive learning and anchor-based classifier calibration to correct feature extractors and calibrate classifiers across clients, achieving intra-class compactness and inter-class separability of prototypes while ensuring consistent decision boundaries. We then update the semantic anchors with these consistent and discriminative prototypes, which iteratively encourage clients to collaboratively learn a unified data representation with robust generalization. Extensive experiments under both statistical and model heterogeneity settings show that FedSA significantly outperforms existing prototype-based FL methods on various classification tasks.
Authors: Tristan Deleu
Abstract: Without any assumptions about data generation, multiple causal models may explain our observations equally well. To avoid selecting a single arbitrary model that could result in unsafe decisions if it does not match reality, it is therefore essential to maintain a notion of epistemic uncertainty about our possible candidates. This thesis studies the problem of structure learning from a Bayesian perspective, approximating the posterior distribution over the structure of a causal model, represented as a directed acyclic graph (DAG), given data. It introduces Generative Flow Networks (GFlowNets), a novel class of probabilistic models designed for modeling distributions over discrete and compositional objects such as graphs. They treat generation as a sequential decision making problem, constructing samples of a target distribution defined up to a normalization constant piece by piece. In the first part of this thesis, we present the mathematical foundations of GFlowNets, their connections to existing domains of machine learning and statistics such as variational inference and reinforcement learning, and their extensions beyond discrete problems. In the second part of this thesis, we show how GFlowNets can approximate the posterior distribution over DAG structures of causal Bayesian Networks, along with the parameters of its causal mechanisms, given observational and experimental data.
Authors: Cheng Chen, Geng Tian, Shaoxiang Qin, Senwen Yang, Dingyang Geng, Dongxue Zhan, Jinqiu Yang, David Vidal, Liangzhu Leon Wang
Abstract: Simulation of urban wind environments is crucial for urban planning, pollution control, and renewable energy utilization. However, the computational requirements of high-fidelity computational fluid dynamics (CFD) methods make them impractical for real cities. To address these limitations, this study investigates the effectiveness of the Fourier Neural Operator (FNO) model in predicting flow fields under different wind directions and urban layouts. In this study, we investigate the effectiveness of the Fourier Neural Operator (FNO) model in predicting urban wind conditions under different wind directions and urban layouts. By training the model on velocity data from large eddy simulation data, we evaluate the performance of the model under different urban configurations and wind conditions. The results show that the FNO model can provide accurate predictions while significantly reducing the computational time by 99%. Our innovative approach of dividing the wind field into smaller spatial blocks for training improves the ability of the FNO model to capture wind frequency features effectively. The SDF data also provides important spatial building information, enhancing the model's ability to recognize physical boundaries and generate more realistic predictions. The proposed FNO approach enhances the AI model's generalizability for different wind directions and urban layouts.
Authors: Sergei Kudriashov, Olesya Karpik, Eduard Klyshinsky
Abstract: Although transformer-based models have been dominating the field of deep learning, various studies of their embedding space have shown that they suffer from "representation degeneration problem": embeddings tend to be distributed in a narrow cone, making the latent space highly anisotropic. Increasing the isotropy has shown to improve performance in downstream tasks both in static and contextual language models. However, most of approaches either add inference overhead or require substantial amount of data for model reparametrization. We propose a novel regularization technique based on simplicial geometry to improve the isotropy of latent representations. The core idea of our method is based on maximizing the persistent entropy of barcodes obtained using Vietoris-Rips filtration from contextual embeddings in the underlying latent space. We demonstrate that the method leads to an increase in downstream performance while significantly lowering the anisotropy during fine-tuning by exploiting existing geometric structures instead of reparametrization.
Authors: Jason Weitz, Dmitri Demler, Luke McDermott, Nhan Tran, Javier Duarte
Abstract: We develop a pipeline to streamline neural architecture codesign for physics applications to reduce the need for ML expertise when designing models for novel tasks. Our method employs neural architecture search and network compression in a two-stage approach to discover hardware efficient models. This approach consists of a global search stage that explores a wide range of architectures while considering hardware constraints, followed by a local search stage that fine-tunes and compresses the most promising candidates. We exceed performance on various tasks and show further speedup through model compression techniques such as quantization-aware-training and neural network pruning. We synthesize the optimal models to high level synthesis code for FPGA deployment with the hls4ml library. Additionally, our hierarchical search space provides greater flexibility in optimization, which can easily extend to other tasks and domains. We demonstrate this with two case studies: Bragg peak finding in materials science and jet classification in high energy physics, achieving models with improved accuracy, smaller latencies, or reduced resource utilization relative to the baseline models.
Authors: Zenon Lamprou, Yashar Moshfeghi
Abstract: The rapid advancement of artificial intelligence has resulted in the advent of large language models (LLMs) with the capacity to produce text that closely resembles human communication. These models have been seamlessly integrated into diverse applications, enabling interactive and responsive communication across multiple platforms. The potential utility of chatbots transcends these traditional applications, particularly in research contexts, wherein they can offer valuable insights and facilitate the design of innovative experiments. In this study, we present NSChat, a web-based chatbot system designed to assist in neuroscience research. The system is meticulously designed to function as an experimental instrument rather than a conventional chatbot, necessitating users to input a username and experiment code upon access. This setup facilitates precise data cross-referencing, thereby augmenting the integrity and applicability of the data collected for research purposes. It can be easily expanded to accommodate new basic events as needed; and it allows researchers to integrate their own logging events without the necessity of implementing a separate logging mechanism. It is worth noting that our system was built to assist primarily neuroscience research but is not limited to it, it can easily be adapted to assist information retrieval research or interacting with chat bot agents in general.
Authors: Pascal de Jong, Felix Meigel, Steffen Rulands
Abstract: Whether deep neural networks can exhibit emergent behaviour is not only relevant for understanding how deep learning works, it is also pivotal for estimating potential security risks of increasingly capable artificial intelligence systems. Here, we show that training deep neural networks gives rise to emergent weight morphologies independent of the training data. Specifically, in analogy to condensed matter physics, we derive a theory that predict that the homogeneous state of deep neural networks is unstable in a way that leads to the emergence of periodic channel structures. We verified these structures by performing numerical experiments on a variety of data sets. Our work demonstrates emergence in the training of deep neural networks, which impacts the achievable performance of deep neural networks.
Authors: Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle, Sham Kakade, Mansheej Paul
Abstract: In continual learning, where task data arrives in a sequence, fine-tuning on later tasks will often lead to performance degradation on earlier tasks. This is especially pronounced when these tasks come from diverse domains. In this setting, how can we mitigate catastrophic forgetting of earlier tasks and retain what the model has learned with minimal computational expenses? Inspired by other merging methods, and L2-regression, we propose Sequential Fine-tuning with Averaging (SFA), a method that merges currently training models with earlier checkpoints during the course of training. SOTA approaches typically maintain a data buffer of past tasks or impose a penalty at each gradient step. In contrast, our method achieves comparable results without the need to store past data, or multiple copies of parameters for each gradient step. Furthermore, our method outperforms common merging techniques such as Task Arithmetic, TIES Merging, and WiSE-FT, as well as other penalty methods like L2 and Elastic Weight Consolidation. In turn, our method offers insight into the benefits of merging partially-trained models during training across both image and language domains.
Authors: Ravi G. Patel, T. Patrick Xiao, Sapan Agarwal, Christopher Bennett
Abstract: Recent work has demonstrated that Bayesian neural networks (BNN's) trained with mean field variational inference (MFVI) can be implemented in analog hardware, promising orders of magnitude energy savings compared to the standard digital implementations. However, while Gaussians are typically used as the variational distribution in MFVI, it is difficult to precisely control the shape of the noise distributions produced by sampling analog devices. This paper introduces a method for MFVI training using real device noise as the variational distribution. Furthermore, we demonstrate empirically that the predictive distributions from BNN's with the same weight means and variances converge to the same distribution, regardless of the shape of the variational distribution. This result suggests that analog device designers do not need to consider the shape of the device noise distribution when hardware-implementing BNNs performing MFVI.
Authors: Timo Saala, Lucie Flek, Alexander Jung, Akbar Karimi, Alexander Schmidt, Matthias Schott, Philipp Soldin, Christopher Wiebusch
Abstract: Correlations between input parameters play a crucial role in many scientific classification tasks, since these are often related to fundamental laws of nature. For example, in high energy physics, one of the common deep learning use-cases is the classification of signal and background processes in particle collisions. In many such cases, the fundamental principles of the correlations between observables are often better understood than the actual distributions of the observables themselves. In this work, we present a new adversarial attack algorithm called Random Distribution Shuffle Attack (RDSA), emphasizing the correlations between observables in the network rather than individual feature characteristics. Correct application of the proposed novel attack can result in a significant improvement in classification performance - particularly in the context of data augmentation - when using the generated adversaries within adversarial training. Given that correlations between input features are also crucial in many other disciplines. We demonstrate the RDSA effectiveness on six classification tasks, including two particle collision challenges (using CERN Open Data), hand-written digit recognition (MNIST784), human activity recognition (HAR), weather forecasting (Rain in Australia), and ICU patient mortality (MIMIC-IV), demonstrating a general use case beyond fundamental physics for this new type of adversarial attack algorithms.
Authors: Tao Liu, Qi Xu, Wei Shi, Zhigang Hua, Shuang Yang
Abstract: Session-level dynamic ad load optimization aims to personalize the density and types of delivered advertisements in real time during a user's online session by dynamically balancing user experience quality and ad monetization. Traditional causal learning-based approaches struggle with key technical challenges, especially in handling confounding bias and distribution shifts. In this paper, we develop an offline deep Q-network (DQN)-based framework that effectively mitigates confounding bias in dynamic systems and demonstrates more than 80% offline gains compared to the best causal learning-based production baseline. Moreover, to improve the framework's robustness against unanticipated distribution shifts, we further enhance our framework with a novel offline robust dueling DQN approach. This approach achieves more stable rewards on multiple OpenAI-Gym datasets as perturbations increase, and provides an additional 5% offline gains on real-world ad delivery data. Deployed across multiple production systems, our approach has achieved outsized topline gains. Post-launch online A/B tests have shown double-digit improvements in the engagement-ad score trade-off efficiency, significantly enhancing our platform's capability to serve both consumers and advertisers.
Authors: Shubham Kose, Jin Wei-Kocsis
Abstract: Emerging Knowledge Tracing (KT) models, particularly deep learning and attention-based Knowledge Tracing, have shown great potential in realizing personalized learning analysis via prediction of students' future performance based on their past interactions. The existing methods mainly focus on immediate past interactions or individual concepts without accounting for dependencies between knowledge concept, referred as knowledge concept routes, that can be critical to advance the understanding the students' learning outcomes. To address this, in this paper, we propose an innovative attention-based method by effectively incorporating the domain knowledge of knowledge concept routes in the given curriculum. Additionally, we leverage XES3G5M dataset, a benchmark dataset with rich auxiliary information for knowledge concept routes, to evaluate and compare the performance of our proposed method to the seven State-of-the-art (SOTA) deep learning models.
Authors: Ali Bereyhi, Ben Liang, Gary Boudreau, Ali Afana
Abstract: Error accumulation is effective for gradient sparsification in distributed settings: initially-unselected gradient entries are eventually selected as their accumulated error exceeds a certain level. The accumulation essentially behaves as a scaling of the learning rate for the selected entries. Although this property prevents the slow-down of lateral movements in distributed gradient descent, it can deteriorate convergence in some settings. This work proposes a novel sparsification scheme that controls the learning rate scaling of error accumulation. The development of this scheme follows two major steps: first, gradient sparsification is formulated as an inverse probability (inference) problem, and the Bayesian optimal sparsification mask is derived as a maximum-a-posteriori estimator. Using the prior distribution inherited from Top-$k$, we derive a new sparsification algorithm which can be interpreted as a regularized form of Top-$k$. We call this algorithm regularized Top-$k$ (RegTop-$k$). It utilizes past aggregated gradients to evaluate posterior statistics of the next aggregation. It then prioritizes the local accumulated gradient entries based on these posterior statistics. We validate our derivation through numerical experiments. In distributed linear regression, it is observed that while Top-$k$ remains at a fixed distance from the global optimum, RegTop-$k$ converges to the global optimum at significantly higher compression ratios. We further demonstrate the generalization of this observation by employing RegTop-$k$ in distributed training of ResNet-18 on CIFAR-10, where it noticeably outperforms Top-$k$.
Authors: Yonghao Liu, Fausto Giunchiglia, Ximing Li, Lan Huang, Xiaoyue Feng, Renchu Guan
Abstract: Graph few-shot learning has garnered significant attention for its ability to rapidly adapt to downstream tasks with limited labeled data, sparking considerable interest among researchers. Recent advancements in graph few-shot learning models have exhibited superior performance across diverse applications. Despite their successes, several limitations still exist. First, existing models in the meta-training phase predominantly focus on instance-level features within tasks, neglecting crucial set-level features essential for distinguishing between different categories. Second, these models often utilize query sets directly on classifiers trained with support sets containing only a few labeled examples, overlooking potential distribution shifts between these sets and leading to suboptimal performance. Finally, previous models typically require necessitate abundant labeled data from base classes to extract transferable knowledge, which is typically infeasible in real-world scenarios. To address these issues, we propose a novel model named STAR, which leverages Set funcTions and optimAl tRansport for enhancing unsupervised graph few-shot learning. Specifically, STAR utilizes expressive set functions to obtain set-level features in an unsupervised manner and employs optimal transport principles to align the distributions of support and query sets, thereby mitigating distribution shift effects. Theoretical analysis demonstrates that STAR can capture more task-relevant information and enhance generalization capabilities. Empirically, extensive experiments across multiple datasets validate the effectiveness of STAR. Our code can be found here.
Authors: Zixuan Liang
Abstract: High\-cardinality categorical variables pose significant challenges in machine learning, particularly in terms of computational efficiency and model interpretability. Traditional one\-hot encoding often results in high\-dimensional sparse feature spaces, increasing the risk of overfitting and reducing scalability. This paper introduces novel encoding techniques, including means encoding, low\-rank encoding, and multinomial logistic regression encoding, to address these challenges. These methods leverage sufficient representations to generate compact and informative embeddings of categorical data. We conduct rigorous theoretical analyses and empirical validations on diverse datasets, demonstrating significant improvements in model performance and computational efficiency compared to baseline methods. The proposed techniques are particularly effective in domains requiring scalable solutions for large datasets, paving the way for more robust and efficient applications in machine learning.
Authors: Yinghao Zhu, Xiaochen Zheng, Ahmed Allam, Michael Krauthammer
Abstract: We propose TAMER, a Test-time Adaptive MoE-driven framework for EHR Representation learning. TAMER combines a Mixture-of-Experts (MoE) with Test-Time Adaptation (TTA) to address two critical challenges in EHR modeling: patient population heterogeneity and distribution shifts. The MoE component handles diverse patient subgroups, while TTA enables real-time adaptation to evolving health status distributions when new patient samples are introduced. Extensive experiments across four real-world EHR datasets demonstrate that TAMER consistently improves predictive performance for both mortality and readmission risk tasks when combined with diverse EHR modeling backbones. TAMER offers a promising approach for dynamic and personalized EHR-based predictions in practical clinical settings. Code is publicly available at https://github.com/yhzhu99/TAMER.
Authors: Yunbo Hou, Haoran Ye, Yingxue Zhang, Siyuan Xu, Guojie Song
Abstract: Global placement, a critical step in designing the physical layout of computer chips, is essential to optimize chip performance. Prior global placement methods optimize each circuit design individually from scratch. Their neglect of transferable knowledge limits solution efficiency and chip performance as circuit complexity drastically increases. This study presents TransPlace, a global placement framework that learns to place millions of mixed-size cells in continuous space. TransPlace introduces i) Netlist Graph to efficiently model netlist topology, ii) Cell-flow and relative position encoding to learn SE(2)-invariant representation, iii) a tailored graph neural network architecture for informed parameterization of placement knowledge, and iv) a two-stage strategy for coarse-to-fine placement. Compared to state-of-the-art placement methods, TransPlace-trained on a few high-quality placements-can place unseen circuits with 1.2x speedup while reducing congestion by 30%, timing by 9%, and wirelength by 5%.
Authors: Guoxin Feng
Abstract: The self-attention (SA) mechanism has demonstrated superior performance across various domains, yet it suffers from substantial complexity during both training and inference. The next-generation architecture, aiming at retaining the competitive performance of SA while achieving low-cost inference and efficient long-sequence training, primarily focuses on three approaches: linear attention, linear RNNs, and state space models. Although these approaches achieve reduced complexity than SA, they all have built-in performance degradation factors, such as diminished “spikiness†and compression of historical information. In contrast to these approaches, we propose a novel element-wise attention mechanism, which uses the element-wise squared Euclidean distance, instead of the dot product operation, to compute similarity and approximates the quadratic complexity term $\exp(q_{ic}k_{jc})$ with a Taylor polynomial. This design achieves remarkable efficiency: during training, the element-wise attention has a complexity of $\mathcal{O}(tLD)$, making long-sequence training both computationally and memory efficient, where $L$ is the sequence length, $D$ is the feature dimension, and $t$ is the highest order of the polynomial; during inference, it can be reformulated as recurrent neural networks, achieving a inference complexity of $\mathcal{O}(tD)$. Furthermore, the element-wise attention circumvents the performance degradation factors present in these approaches and achieves performance comparable to SA in both causal and non-causal forms.
Authors: Ding Ning, Varvara Vetrova, Karin R. Bryan, Yun Sing Koh, Andreas Voskou, N'Dah Jean Kouagou, Arnab Sharma
Abstract: This overview paper details the findings from the Diving Deep: Forecasting Sea Surface Temperatures and Anomalies Challenge at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) 2024. The challenge focused on the data-driven predictability of global sea surface temperatures (SSTs), a key factor in climate forecasting, ecosystem management, fisheries management, and climate change monitoring. The challenge involved forecasting SST anomalies (SSTAs) three months in advance using historical data and included a special task of predicting SSTAs nine months ahead for the Baltic Sea. Participants utilized various machine learning approaches to tackle the task, leveraging data from ERA5. This paper discusses the methodologies employed, the results obtained, and the lessons learned, offering insights into the future of climate-related predictive modeling.
Authors: Van Thuy Hoang, Tien-Bach-Thanh Do, Jinho Seo, Seung Charlie Kim, Luong Vuong Nguyen, Duong Nguyen Minh Huy, Hyeon-Ju Jeon, O-Joun Lee
Abstract: The growing demand for halal cosmetic products has exposed significant challenges, especially in Muslim-majority countries. Recently, various machine learning-based strategies, e.g., image-based methods, have shown remarkable success in predicting the halal status of cosmetics. However, these methods mainly focus on analyzing the discrete and specific ingredients within separate cosmetics, which ignore the high-order and complex relations between cosmetics and ingredients. To address this problem, we propose a halal cosmetic recommendation framework, namely HaCKG, that leverages a knowledge graph of cosmetics and their ingredients to explicitly model and capture the relationships between cosmetics and their components. By representing cosmetics and ingredients as entities within the knowledge graph, HaCKG effectively learns the high-order and complex relations between entities, offering a robust method for predicting halal status. Specifically, we first construct a cosmetic knowledge graph representing the relations between various cosmetics, ingredients, and their properties. We then propose a pre-trained relational graph attention network model with residual connections to learn the structural relation between entities in the knowledge graph. The pre-trained model is then fine-tuned on downstream cosmetic data to predict halal status. Extensive experiments on the cosmetic dataset over halal prediction tasks demonstrate the superiority of our model over state-of-the-art baselines.
Authors: Herdiantri Sufriyana, Emily Chia-Yu Su
Abstract: Background: Current nomogram can only be created for regression algorithm. Providing nomogram for any machine learning (ML) algorithms may accelerate model deployment in clinical settings or improve model availability. We developed an R package and web application to construct nomogram with model explainability of any ML algorithms. Methods: We formulated a function to transform an ML prediction model into a nomogram, requiring datasets with: (1) all possible combinations of predictor values; (2) the corresponding outputs of the model; and (3) the corresponding explainability values for each predictor (optional). Web application was also created. Results: Our R package could create 5 types of nomograms for categorical predictors and binary outcome without probability (1), categorical predictors and binary outcome with probability (2) or continuous outcome (3), and categorical with single numerical predictors and binary outcome with probability (4) or continuous outcome (5). Respectively, the first and remaining types optimally allowed maximum 15 and 5 predictors with maximum 3,200 combinations. Web application is provided with such limits. The explainability values were possible for types 2 to 5. Conclusions: Our R package and web application could construct nomogram with model explainability of any ML algorithms using a fair number of predictors.
Authors: Shunxin Guo, Hongsong Wang, Shuxia Lin, Xu Yang, Xin Geng
Abstract: Federated learning is a new framework that protects data privacy and allows multiple devices to cooperate in training machine learning models. Previous studies have proposed multiple approaches to eliminate the challenges posed by non-iid data and inter-domain heterogeneity issues. However, they ignore the \textbf{spatio-temporal} heterogeneity formed by different data distributions of increasing task data in the intra-domain. Moreover, the global data is generally a long-tailed distribution rather than assuming the global data is balanced in practical applications. To tackle the \textbf{spatio-temporal} dilemma, we propose a novel setting named \textbf{Spatio-Temporal Heterogeneity} Federated Learning (STHFL). Specially, the Global-Local Dynamic Prototype (GLDP) framework is designed for STHFL. In GLDP, the model in each client contains personalized layers which can dynamically adapt to different data distributions. For long-tailed data distribution, global prototypes are served as complementary knowledge for the training on classes with few samples in clients without leaking privacy. As tasks increase in clients, the knowledge of local prototypes generated in previous tasks guides for training in the current task to solve catastrophic forgetting. Meanwhile, the global-local prototypes are updated through the moving average method after training local prototypes in clients. Finally, we evaluate the effectiveness of GLDP, which achieves remarkable results compared to state-of-the-art methods in STHFL scenarios.
Authors: Keita Kinjo
Abstract: In recent years, explainability in machine learning has gained importance. In this context, counterfactual explanation (CE), which is an explanation method that uses examples, has attracted attention. However, it has been pointed out that CE is not robust when there are multiple machine-learning models. These problems are important when using machine learning to make safe decisions. In this paper, we propose robust CEs that introduce a new viewpoint - Pareto improvement - and a method that uses multi-objective optimization to generate it. To evaluate the proposed method, we conducted experiments using both simulated and actual data. The results demonstrate that the proposed method is robust and useful. We believe that this research will contribute to a wide range of research areas, such as explainability in machine learning, decision-making, and action planning based on machine learning.
Authors: Sunwoo Kim, Minkyu Kim, Dongmin Park
Abstract: Diffusion models excel in generative tasks, but aligning them with specific objectives while maintaining their versatility remains challenging. Existing fine-tuning methods often suffer from reward over-optimization, while approximate guidance approaches fail to optimize target rewards effectively. Addressing these limitations, we propose a training-free sampling method based on Sequential Monte Carlo (SMC) to sample from the reward-aligned target distribution. Our approach, tailored for diffusion sampling and incorporating tempering techniques, achieves comparable or superior target rewards to fine-tuning methods while preserving diversity and cross-reward generalization. We demonstrate its effectiveness in single-reward optimization, multi-objective scenarios, and online black-box optimization. This work offers a robust solution for aligning diffusion models with diverse downstream objectives without compromising their general capabilities. Code is available at https://github.com/krafton-ai/DAS .
Authors: Fuhang Liang, Rucong Xu, Deng Lin
Abstract: Current deep regression models usually learn in point-wise way that treat each sample as an independent input, neglecting the relative ordering among different data. Consequently, the regression model could neglect the data 's interrelationships, potentially resulting in suboptimal performance. Moreover, the existence of aleatoric uncertainty in the training data may drive the model to capture non-generalizable patterns, contributing to increased overfitting. To address these issues, we propose a novel adaptive pairwise learning framework (AdaPRL) for regression tasks which leverages the relative differences between data points and integrates with deep probabilistic models to quantify the uncertainty associated with the predictions. Additionally, we adapt AdaPRL for applications in multi-task learning and multivariate time series forecasting. Extensive experiments with several real-world regression datasets including recommendation systems, age estimation, time series forecasting, natural language understanding, finance, and industry datasets show that AdaPRL is compatible with different backbone networks in various tasks and achieves state-of-the-art performance on the vast majority of tasks, highlighting its notable potential including enhancing prediction accuracy and ranking ability, increasing generalization capability, improving robustness to noisy data, improving resilience to reduced data, and enhancing interpretability, etc.
Authors: Yousef Emami, Hao Zhou, Luis Almeida, Kai Li
Abstract: Unmanned Aerial Vehicles (UAVs) are increasingly adopted in modern communication networks. However, challenges in decision-making and digital modeling continue to impede their rapid advancement. Reinforcement Learning (RL) algorithms face limitations such as low sample efficiency and limited data versatility, further magnified in UAV communication scenarios. Moreover, Digital Twin (DT) modeling introduces substantial decision-making and data management complexities. RL models, often integrated into DT frameworks, require extensive training data to achieve accurate predictions. In contrast to traditional approaches that focus on class boundaries, Diffusion Models (DMs), a new class of generative AI, learn the underlying probability distribution from the training data and can generate trustworthy new patterns based on this learned distribution. This paper explores the integration of DMs with RL and DT to effectively address these challenges. By combining the data generation capabilities of DMs with the decision-making framework of RL and the modeling accuracy of DT, the integration improves the adaptability and real-time performance of UAV communication. Moreover, the study shows how DMs can alleviate data scarcity, improve policy networks, and optimize dynamic modeling, providing a robust solution for complex UAV communication scenarios.
Authors: Jiale Zhang, Bosen Rao, Chengcheng Zhu, Xiaobing Sun, Qingming Li, Haibo Hu, Xiapu Luo, Qingqing Ye, Shouling Ji
Abstract: Graph Neural Networks (GNNs) have achieved remarkable performance through their message-passing mechanism. However, recent studies have highlighted the vulnerability of GNNs to backdoor attacks, which can lead the model to misclassify graphs with attached triggers as the target class. The effectiveness of recent promising defense techniques, such as fine-tuning or distillation, is heavily contingent on having comprehensive knowledge of the sufficient training dataset. Empirical studies have shown that fine-tuning methods require a clean dataset of 20% to reduce attack accuracy to below 25%, while distillation methods require a clean dataset of 15%. However, obtaining such a large amount of clean data is commonly impractical. In this paper, we propose a practical backdoor mitigation framework, denoted as GRAPHNAD, which can capture high-quality intermediate-layer representations in GNNs to enhance the distillation process with limited clean data. To achieve this, we address the following key questions: How to identify the appropriate attention representations in graphs for distillation? How to enhance distillation with limited data? By adopting the graph attention transfer method, GRAPHNAD can effectively align the intermediate-layer attention representations of the backdoored model with that of the teacher model, forcing the backdoor neurons to transform into benign ones. Besides, we extract the relation maps from intermediate-layer transformation and enforce the relation maps of the backdoored model to be consistent with that of the teacher model, thereby ensuring model accuracy while further reducing the influence of backdoors. Extensive experimental results show that by fine-tuning a teacher model with only 3% of the clean data, GRAPHNAD can reduce the attack success rate to below 5%.
Authors: Bendeg\'uz M. Gy\"or\"ok, Jan H. Hoekstra, Johan Kon, Tam\'as P\'eni, Maarten Schoukens, Roland T\'oth
Abstract: Deep-learning-based nonlinear system identification has shown the ability to produce reliable and highly accurate models in practice. However, these black-box models lack physical interpretability, and often a considerable part of the learning effort is spent on capturing already expected/known behavior due to first-principles-based understanding of some aspects of the system. A potential solution is to integrate prior physical knowledge directly into the model structure, combining the strengths of physics-based modeling and deep-learning-based identification. The most common approach is to use an additive model augmentation structure, where the physics-based and the machine-learning (ML) components are connected in parallel. However, such models are overparametrized, training them is challenging, potentially causing the physics-based part to lose interpretability. To overcome this challenge, this paper proposes an orthogonal projection-based regularization technique to enhance parameter learning, convergence, and even model accuracy in learning-based augmentation of nonlinear baseline models.
Authors: Vyacheslav Kungurtsev, Leonardo Christov Moore, Gustav Sir, Martin Krutsky
Abstract: Causal Learning has emerged as a major theme of AI in recent years, promising to use special techniques to reveal the true nature of cause and effect in a number of important domains. We consider the Epistemology of learning and recognizing true cause and effect phenomena. Through thought exercises on the customary use of the word ''cause'', especially in scientific domains, we investigate what, in practice, constitutes a valid causal claim. We recognize the word's uses across scientific domains in disparate form but consistent function within the scientific paradigm. We highlight fundamental distinctions of practice that can be performed in the natural and social sciences, highlight the importance of many systems of interest being open and irreducible and identify the important notion of Hermeneutic knowledge for social science inquiry. We posit that the distinct properties require that definitive causal claims can only come through an agglomeration of consistent evidence across multiple domains and levels of abstraction, such as empirical, physiological, biochemical, etc. We present Cognitive Science as an exemplary multi-disciplinary field providing omnipresent opportunity for such a Research Program, and highlight the main general modes of practice of scientific inquiry that can adequately merge, rather than place as incorrigibly conflictual, multi-domain multi-abstraction scientific practices and language games.
Authors: Tiago Mendes-Neves, Lu\'is Meireles, Jo\~ao Mendes-Moreira
Abstract: Pitch ownership models allow many types of analysis in soccer and provide valuable assistance to tactical analysts in understanding the game's dynamics. The novelty they provide over event-based analysis is that tracking data incorporates context that event-based data does not possess, like player positioning. This paper proposes a novel approach to building pitch ownership models in soccer games using the K-Nearest Neighbors (KNN) algorithm. Our approach provides a fast inference mechanism that can model different approaches to pitch control using the same algorithm. Despite its flexibility, it uses only three hyperparameters to tune the model, facilitating the tuning process for different player skill levels. The flexibility of the approach allows for the emulation of different methods available in the literature by adjusting a small number of parameters, including adjusting for different levels of uncertainty. In summary, the proposed model provides a new and more flexible strategy for building pitch ownership models, extending beyond just replicating existing algorithms, and can provide valuable insights for tactical analysts and open up new avenues for future research. We thoroughly visualize several examples demonstrating the presented models' strengths and weaknesses. The code is available at github.com/nvsclub/KNNPitchControl.
Authors: Yongfan Lai, Jiabo Chen, Deyun Zhang, Yue Wang, Shijia Geng, Hongyan Li, Shenda Hong
Abstract: Heart disease remains a significant threat to human health. As a non-invasive diagnostic tool, the electrocardiogram (ECG) is one of the most widely used methods for cardiac screening. However, the scarcity of high-quality ECG data, driven by privacy concerns and limited medical resources, creates a pressing need for effective ECG signal generation. Existing approaches for generating ECG signals typically rely on small training datasets, lack comprehensive evaluation frameworks, and overlook potential applications beyond data augmentation. To address these challenges, we propose DiffuSETS, a novel framework capable of generating ECG signals with high semantic alignment and fidelity. DiffuSETS accepts various modalities of clinical text reports and patient-specific information as inputs, enabling the creation of clinically meaningful ECG signals. Additionally, to address the lack of standardized evaluation in ECG generation, we introduce a comprehensive benchmarking methodology to assess the effectiveness of generative models in this domain. Our model achieve excellent results in tests, proving its superiority in the task of ECG generation. Furthermore, we showcase its potential to mitigate data scarcity while exploring novel applications in cardiology education and medical knowledge discovery, highlighting the broader impact of our work.
Authors: Asfia Kawnine, Francis Palma, Seyed Alireza Rahimi Azghadi, Hung Cao
Abstract: This research presents an Encoded Spatial Multi-Tier Federated Learning approach for a comprehensive evaluation of aggregated models for geospatial data. In the client tier, encoding spatial information is introduced to better predict the target outcome. The research aims to assess the performance of these models across diverse datasets and spatial attributes, highlighting variations in predictive accuracy. Using evaluation metrics such as accuracy, our research reveals insights into the complexities of spatial granularity and the challenges of capturing underlying patterns in the data. We extended the scope of federated learning (FL) by having multi-tier along with the functionality of encoding spatial attributes. Our N-tier FL approach used encoded spatial data to aggregate in different tiers. We obtained multiple models that predicted the different granularities of spatial data. Our findings underscore the need for further research to improve predictive accuracy and model generalization, with potential avenues including incorporating additional features, refining model architectures, and exploring alternative modeling approaches. Our experiments have several tiers representing different levels of spatial aspects. We obtained accuracy of 75.62% and 89.52% for the global model without having to train the model using the data constituted with the designated tier. The research also highlights the importance of the proposed approach in real-time applications.
Authors: Antonio Consolo, Edoardo Amaldi, Andrea Manno
Abstract: Decision trees are widely used for classification and regression tasks in a variety of application fields due to their interpretability and good accuracy. During the past decade, growing attention has been devoted to globally optimized decision trees with deterministic or soft splitting rules at branch nodes, which are trained by optimizing the error function over all the tree parameters. In this work, we propose a new variant of soft multivariate regression trees (SRTs) where, for every input vector, the prediction is defined as the linear regression associated to a single leaf node, namely, the leaf node obtained by routing the input vector from the root along the branches with higher probability. SRTs exhibit the conditional computational property, i.e., each prediction depends on a small number of nodes (parameters), and our nonlinear optimization formulation for training them is amenable to decomposition. After showing a universal approximation result for SRTs, we present a decomposition training algorithm including a clustering-based initialization procedure and a heuristic for reassigning the input vectors along the tree. Under mild assumptions, we establish asymptotic convergence guarantees. Experiments on 15 wellknown datasets indicate that our SRTs and decomposition algorithm yield higher accuracy and robustness compared with traditional soft regression trees trained using the nonlinear optimization formulation of Blanquero et al., and a significant reduction in training times as well as a slightly better average accuracy compared with the mixed-integer optimization approach of Bertsimas and Dunn. We also report a comparison with the Random Forest ensemble method.
Authors: Yunmeng Shu, Shaofeng Li, Tian Dong, Yan Meng, Haojin Zhu
Abstract: Personalized Large Language Models (LLMs) have become increasingly prevalent, showcasing the impressive capabilities of models like GPT-4. This trend has also catalyzed extensive research on deploying LLMs on mobile devices. Feasible approaches for such edge-cloud deployment include using split learning. However, previous research has largely overlooked the privacy leakage associated with intermediate representations transmitted from devices to servers. This work is the first to identify model inversion attacks in the split learning framework for LLMs, emphasizing the necessity of secure defense. For the first time, we introduce mutual information entropy to understand the information propagation of Transformer-based LLMs and assess privacy attack performance for LLM blocks. To address the issue of representations being sparser and containing less information than embeddings, we propose a two-stage attack system in which the first part projects representations into the embedding space, and the second part uses a generative model to recover text from these embeddings. This design breaks down the complexity and achieves attack scores of 38%-75% in various scenarios, with an over 60% improvement over the SOTA. This work comprehensively highlights the potential privacy risks during the deployment of personalized LLMs on the edge side.
Authors: Arthur Bousquet, Sugata Banerji, Mark F. Conneely, Shahrzad Jamshidi
Abstract: Age prediction using brain imaging, such as MRIs, has achieved promising results, with several studies identifying the model's residual as a potential biomarker for chronic disease states. In this study, we developed a brain age predictive model using a dataset of 1,220 U.S. veterans (18--80 years) and convolutional neural networks (CNNs) trained on two-dimensional slices of axial T2-weighted fast spin-echo and T2-weighted fluid attenuated inversion recovery MRI images. The model, incorporating a degree-3 polynomial ensemble, achieved an $R^{2}$ of 0.816 on the testing set. Images were acquired at the level of the anterior commissure and the frontal horns of the lateral ventricles. Residual analysis was performed to assess its potential as a biomarker for five ICD-coded conditions: hypertension (HTN), diabetes mellitus (DM), mild traumatic brain injury (mTBI), illicit substance abuse/dependence (SAD), and alcohol abuse/dependence (AAD). Residuals grouped by the number of ICD-coded conditions demonstrated different trends that were statistically significant ($p = 0.002$), suggesting a relationship between disease states and predicted brain age. This association was particularly pronounced in patients over 49 years, where negative residuals (indicating advanced brain aging) correlated with the presence of multiple ICD codes. These findings support the potential of residuals as biomarkers for detecting latent health conditions.
Authors: Wessel L. van Nierop, Nir Shlezinger, Ruud J. G. van Sloun
Abstract: Sequential Monte Carlo (SMC), or particle filtering, is widely used in nonlinear state-space systems, but its performance often suffers from poorly approximated proposal and state-transition distributions. This work introduces a differentiable particle filter that leverages the unsupervised variational SMC objective to parameterize the proposal and transition distributions with a neural network, designed to learn from high-dimensional observations. Experimental results demonstrate that our approach outperforms established baselines in tracking the challenging Lorenz attractor from high-dimensional and partial observations. Furthermore, an evidence lower bound based evaluation indicates that our method offers a more accurate representation of the posterior distribution.
Authors: Eklavya Sarkar, Mathew Magimai. -Doss
Abstract: Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high transferability for bioacoustic processing. This paper investigates (i) whether SSL models pre-trained directly on animal vocalizations offer a significant advantage over those pre-trained on speech, and (ii) whether fine-tuning speech-pretrained models on automatic speech recognition (ASR) tasks can enhance bioacoustic classification. We conduct a comparative analysis using three diverse bioacoustic datasets and two different bioacoustic tasks. Results indicate that pre-training on bioacoustic data provides only marginal improvements over speech-pretrained models, with comparable performance in most scenarios. Fine-tuning on ASR tasks yields mixed outcomes, suggesting that the general-purpose representations learned during SSL pre-training are already well-suited for bioacoustic tasks. These findings highlight the robustness of speech-pretrained SSL models for bioacoustics and imply that extensive fine-tuning may not be necessary for optimal performance.
Authors: Kevin Mancini, Islem Rekik
Abstract: Graph Neural Networks (GNNs) are popular deep learning models designed to process graph-structured data through recursive neighborhood aggregations in the message passing process. When applied to semi-supervised node classification, the message-passing enables GNNs to understand short-range spatial interactions, but also causes them to suffer from over-smoothing and over-squashing. These challenges hinder model expressiveness and prevent the use of deeper models to capture long-range node interactions (LRIs) within the graph. Popular solutions for LRIs detection are either too expensive to process large graphs due to high time complexity or fail to generalize across diverse graph structures. To address these limitations, we propose a mechanism called \emph{information flow control}, which leverages a novel connectivity measure, called \emph{information flow score}, to address over-smoothing and over-squashing with linear computational overhead, supported by theoretical evidence. Finally, to prove the efficacy of our methodology we design DeltaGNN, the first scalable and generalizable approach for detecting long-range and short-range interactions. We benchmark our model across 10 real-world datasets, including graphs with varying sizes, topologies, densities, and homophilic ratios, showing superior performance with limited computational complexity. The implementation of the proposed methods are publicly available at https://github.com/basiralab/DeltaGNN.
Authors: Stefan Mautner, Rolf Backofen, Fabrizio Costa
Abstract: Generative methods for graphs need to be sufficiently flexible to model complex dependencies between sets of nodes. At the same time, the generated graphs need to satisfy domain-dependent feasibility conditions, that is, they should not violate certain constraints that would make their interpretation impossible within the given application domain (e.g. a molecular graph where an atom has a very large number of chemical bounds). Crucially, constraints can involve not only local but also long-range dependencies: for example, the maximal length of a cycle can be bounded. Currently, a large class of generative approaches for graphs, such as methods based on artificial neural networks, is based on message passing schemes. These approaches suffer from information 'dilution' issues that severely limit the maximal range of the dependencies that can be modeled. To address this problem, we propose a generative approach based on the notion of graph grammars. The key novel idea is to introduce a domain-dependent coarsening procedure to provide short-cuts for long-range dependencies. We show the effectiveness of our proposal in two domains: 1) small drugs and 2) RNA secondary structures. In the first case, we compare the quality of the generated molecular graphs via the Molecular Sets (MOSES) benchmark suite, which evaluates the distance between generated and real molecules, their lipophilicity, synthesizability, and drug-likeness. In the second case, we show that the approach can generate very large graphs (with hundreds of nodes) that are accepted as valid examples for a desired RNA family by the "Infernal" covariance model, a state-of-the-art RNA classifier. Our implementation is available on github: github.com/fabriziocosta/GraphLearn
Authors: Sanchit Bedi (Civil Engineering Department, Indian Institute of Technology Delhi, New Delhi, India), Karn Tiwari (Electrical Communications Department, Indian Institute of Science Bengaluru, Bengaluru), Prathosh A. P. (Electrical Communications Department, Indian Institute of Science Bengaluru, Bengaluru), Sri Harsha Kota (Civil Engineering Department, Indian Institute of Technology Delhi, New Delhi, India), N. M. Anoop Krishnan (Civil Engineering Department, Indian Institute of Technology Delhi, New Delhi, India, Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, New Delhi, India)
Abstract: Real-time forecasting of carbon monoxide (CO) concentrations is essential for enabling timely interventions to improve urban air quality. Conventional air quality models often require extensive computational resources for accurate, multi-scale predictions, limiting their practicality for rapid, real-time application. To address this challenge, we introduce the Complex Neural Operator for Air Quality (CoNOAir), a machine learning model that forecast CO concentrations efficiently. CoNOAir demonstrates superior performance over state-of-theart models, such as the Fourier Neural Operator (FNO), in both short-term (hourly) and extended (72-hour) forecasts at a national scale. It excels in capturing extreme pollution events and performs consistently across multiple Indian cities, achieving an R2 above 0.95 for hourly CO predictions across all evaluated locations. CoNOAir equips authorities with an effective tool for issuing early warnings and designing targeted intervention strategies. This work marks a step forward in achieving dependable, real-time CO pollution predictions for densely populated urban centres.
Authors: Nathaniel Hamilton, Kyle Dunlap, Kerianne L Hobbs
Abstract: Recent research using Reinforcement Learning (RL) to learn autonomous control for spacecraft operations has shown great success. However, a recent study showed their performance could be improved by changing the action space, i.e. control outputs, used in the learning environment. This has opened the door for finding more improvements through further changes to the environment. The work in this paper focuses on how changes to the environment's observation space can impact the training and performance of RL agents learning the spacecraft inspection task. The studies are split into two groups. The first looks at the impact of sensors that were designed to help agents learn the task. The second looks at the impact of reference frames, reorienting the agent to see the world from a different perspective. The results show the sensors are not necessary, but most of them help agents learn more optimal behavior, and that the reference frame does not have a large impact, but is best kept consistent.
Authors: Sarath Sivaprasad, Dmitry Kangin, Plamen Angelov, Mario Fritz
Abstract: Aligning machine representations with human understanding is key to improving interpretability of machine learning (ML) models. When classifying a new image, humans often explain their decisions by decomposing the image into concepts and pointing to corresponding regions in familiar images. Current ML explanation techniques typically either trace decision-making processes to reference prototypes, generate attribution maps highlighting feature importance, or incorporate intermediate bottlenecks designed to align with human-interpretable concepts. The proposed method, named COMIX, classifies an image by decomposing it into regions based on learned concepts and tracing each region to corresponding ones in images from the training dataset, assuring that explanations fully represent the actual decision-making process. We dissect the test image into selected internal representations of a neural network to derive prototypical parts (primitives) and match them with the corresponding primitives derived from the training data. In a series of qualitative and quantitative experiments, we theoretically prove and demonstrate that our method, in contrast to post hoc analysis, provides fidelity of explanations and shows that the efficiency is competitive with other inherently interpretable architectures. Notably, it shows substantial improvements in fidelity and sparsity metrics, including 48.82% improvement in the C-insertion score on the ImageNet dataset over the best state-of-the-art baseline.
Authors: Yucheng Ding, Yangwenjian Tan, Xiangyu Liu, Chaoyue Niu, Fandong Meng, Jie Zhou, Ning Liu, Fan Wu, Guihai Chen
Abstract: In many practical natural language applications, user data are highly sensitive, requiring anonymous uploads of text data from mobile devices to the cloud without user identifiers. However, the absence of user identifiers restricts the ability of cloud-based language models to provide personalized services, which are essential for catering to diverse user needs. The trivial method of replacing an explicit user identifier with a static user embedding as model input still compromises data anonymization. In this work, we propose to let each mobile device maintain a user-specific distribution to dynamically generate user embeddings, thereby breaking the one-to-one mapping between an embedding and a specific user. We further theoretically demonstrate that to prevent the cloud from tracking users via uploaded embeddings, the local distributions of different users should either be derived from a linearly dependent space to avoid identifiability or be close to each other to prevent accurate attribution. Evaluation on both public and industrial datasets using different language models reveals a remarkable improvement in accuracy from incorporating anonymous user embeddings, while preserving real-time inference requirement.
Authors: Jiayi Huang, Sangwoo Park, Nicola Paoletti, Osvaldo Simeone
Abstract: Deploying artificial intelligence (AI) models on edge devices involves a delicate balance between meeting stringent complexity constraints, such as limited memory and energy resources, and ensuring reliable performance in sensitive decision-making tasks. One way to enhance reliability is through uncertainty quantification via Bayesian inference. This approach, however, typically necessitates maintaining and running multiple models in an ensemble, which may exceed the computational limits of edge devices. This paper introduces a low-complexity methodology to address this challenge by distilling calibration information from a more complex model. In an offline phase, predictive probabilities generated by a high-complexity cloud-based model are leveraged to determine a threshold based on the typical divergence between the cloud and edge models. At run time, this threshold is used to construct credal sets -- ranges of predictive probabilities that are guaranteed, with a user-selected confidence level, to include the predictions of the cloud model. The credal sets are obtained through thresholding of a divergence measure in the simplex of predictive probabilities. Experiments on visual and language tasks demonstrate that the proposed approach, termed Conformalized Distillation for Credal Inference (CD-CI), significantly improves calibration performance compared to low-complexity Bayesian methods, such as Laplace approximation, making it a practical and efficient solution for edge AI deployments.
Authors: Yossi Arjevani, Joan Bruna, Joe Kileel, Elzbieta Polak, Matthew Trager
Abstract: We study shallow neural networks with polynomial activations. The function space for these models can be identified with a set of symmetric tensors with bounded rank. We describe general features of these networks, focusing on the relationship between width and optimization. We then consider teacher-student problems, that can be viewed as a problem of low-rank tensor approximation with respect to a non-standard inner product that is induced by the data distribution. In this setting, we introduce a teacher-metric discriminant which encodes the qualitative behavior of the optimization as a function of the training data distribution. Finally, we focus on networks with quadratic activations, presenting an in-depth analysis of the optimization landscape. In particular, we present a variation of the Eckart-Young Theorem characterizing all critical points and their Hessian signatures for teacher-student problems with quadratic networks and Gaussian training data.
Authors: Machefer M\'elissande, Michele Ronco, Anne-Claire Thomas, Michael Assouline, Melanie Rabier, Christina Corbane, Felix Rembold
Abstract: Food security is a complex, multidimensional concept challenging to measure comprehensively. Effective anticipation, monitoring, and mitigation of food crises require timely and comprehensive global data. This paper introduces the Harmonized Food Insecurity Dataset (HFID), an open-source resource consolidating four key data sources: the Integrated Food Security Phase Classification (IPC)/Cadre Harmonis\'e (CH) phases, the Famine Early Warning Systems Network (FEWS NET) IPC-compatible phases, and the World Food Program's (WFP) Food Consumption Score (FCS) and reduced Coping Strategy Index (rCSI). Updated monthly and using a common reference system for administrative units, the HFID offers extensive spatial and temporal coverage. It serves as a vital tool for food security experts and humanitarian agencies, providing a unified resource for analyzing food security conditions and highlighting global data disparities. The scientific community can also leverage the HFID to develop data-driven predictive models, enhancing the capacity to forecast and prevent future food crises.
Authors: Xiaofeng Xiao, Khawlah Alharbi, Pengyu Zhang, Hantang Qin, Xubo Yue
Abstract: Causal inference has recently gained notable attention across various fields like biology, healthcare, and environmental science, especially within explainable artificial intelligence (xAI) systems, for uncovering the causal relationships among multiple variables and outcomes. Yet, it has not been fully recognized and deployed in the manufacturing systems. In this paper, we introduce an explainable, scalable, and flexible federated Bayesian learning framework, \texttt{xFBCI}, designed to explore causality through treatment effect estimation in distributed manufacturing systems. By leveraging federated Bayesian learning, we efficiently estimate posterior of local parameters to derive the propensity score for each client without accessing local private data. These scores are then used to estimate the treatment effect using propensity score matching (PSM). Through simulations on various datasets and a real-world Electrohydrodynamic (EHD) printing data, we demonstrate that our approach outperforms standard Bayesian causal inference methods and several state-of-the-art federated learning benchmarks.
Authors: Pablo Barcel\'o, Alexander Kozachinskiy, Miguel Romero Orth, Bernardo Subercaseaux, Jos\'e Verschae
Abstract: Despite the wide use of $k$-Nearest Neighbors as classification models, their explainability properties remain poorly understood from a theoretical perspective. While nearest neighbors classifiers offer interpretability from a "data perspective", in which the classification of an input vector $\bar{x}$ is explained by identifying the vectors $\bar{v}_1, \ldots, \bar{v}_k$ in the training set that determine the classification of $\bar{x}$, we argue that such explanations can be impractical in high-dimensional applications, where each vector has hundreds or thousands of features and it is not clear what their relative importance is. Hence, we focus on understanding nearest neighbor classifications through a "feature perspective", in which the goal is to identify how the values of the features in $\bar{x}$ affect its classification. Concretely, we study abductive explanations such as "minimum sufficient reasons", which correspond to sets of features in $\bar{x}$ that are enough to guarantee its classification, and "counterfactual explanations" based on the minimum distance feature changes one would have to perform in $\bar{x}$ to change its classification. We present a detailed landscape of positive and negative complexity results for counterfactual and abductive explanations, distinguishing between discrete and continuous feature spaces, and considering the impact of the choice of distance function involved. Finally, we show that despite some negative complexity results, Integer Quadratic Programming and SAT solving allow for computing explanations in practice.
Authors: Yanfan Zhu, Issac Lyngaas, Murali Gopalakrishnan Meena, Mary Ellen I. Koran, Bradley Malin, Daniel Moyer, Shunxing Bao, Anuj Kapadia, Xiao Wang, Bennett Landman, Yuankai Huo
Abstract: Recent advancements in AI models are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources. To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE's unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications.
Authors: Mohammad Noorchenarboo, Katarina Grolinger
Abstract: Detecting anomalies in energy consumption data is crucial for identifying energy waste, equipment malfunction, and overall, for ensuring efficient energy management. Machine learning, and specifically deep learning approaches, have been greatly successful in anomaly detection; however, they are black-box approaches that do not provide transparency or explanations. SHAP and its variants have been proposed to explain these models, but they suffer from high computational complexity (SHAP) or instability and inconsistency (e.g., Kernel SHAP). To address these challenges, this paper proposes an explainability approach for anomalies in energy consumption data that focuses on context-relevant information. The proposed approach leverages existing explainability techniques, focusing on SHAP variants, together with global feature importance and weighted cosine similarity to select background dataset based on the context of each anomaly point. By focusing on the context and most relevant features, this approach mitigates the instability of explainability algorithms. Experimental results across 10 different machine learning models, five datasets, and five XAI techniques, demonstrate that our method reduces the variability of explanations providing consistent explanations. Statistical analyses confirm the robustness of our approach, showing an average reduction in variability of approximately 38% across multiple datasets.
Authors: Satchel Grant, Noah D. Goodman, James L. McClelland
Abstract: What types of numeric representations emerge in Neural Networks (NNs)? To what degree do NNs induce abstract, mutable, slot-like numeric variables, and in what situations do these representations emerge? How do these representations change over learning, and how can we understand the neural implementations in ways that are unified across different NNs? In this work, we approach these questions by first training sequence based neural systems using Next Token Prediction (NTP) objectives on numeric tasks. We then seek to understand the neural solutions through the lens of causal abstractions or symbolic algorithms. We use a combination of causal interventions and visualization methods to find that artificial neural models do indeed develop analogs of interchangeable, mutable, latent number variables purely from the NTP objective. We then ask how variations on the tasks and model architectures affect the models' learned solutions to find that these symbol-like numeric representations do not form for every variant of the task, and transformers solve the problem in a notably different way than their recurrent counterparts. We then show how the symbol-like variables change over the course of training to find a strong correlation between the models' task performance and the alignment of their symbol-like representations. Lastly, we show that in all cases, some degree of gradience exists in these neural symbols, highlighting the difficulty of finding simple, interpretable symbolic stories of how neural networks perform numeric tasks. Taken together, our results are consistent with the view that neural networks can approximate interpretable symbolic programs of number cognition, but the particular program they approximate and the extent to which they approximate it can vary widely, depending on the network architecture, training data, extent of training, and network size.
Authors: Julius Berner, Lorenz Richter, Marcin Sendera, Jarrid Rector-Brooks, Nikolay Malkin
Abstract: We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing methods for training such models enforce time-reversal of the generative and noising processes, using either differentiable simulation or off-policy reinforcement learning (RL). We prove equivalences between families of objectives in the limit of infinitesimal discretization steps, linking entropic RL methods (GFlowNets) with continuous-time objects (partial differential equations and path space measures). We further show that an appropriate choice of coarse time discretization during training allows greatly improved sample efficiency and the use of time-local objectives, achieving competitive performance on standard sampling benchmarks with reduced computational cost.
Authors: Seul Lee, Karsten Kreis, Srimukh Prasad Veccham, Meng Liu, Danny Reidenbach, Yuxing Peng, Saee Paliwal, Weili Nie, Arash Vahdat
Abstract: Drug discovery is a complex process that involves multiple scenarios and stages, such as fragment-constrained molecule generation, hit generation and lead optimization. However, existing molecular generative models can only tackle one or two of these scenarios and lack the flexibility to address various aspects of the drug discovery pipeline. In this paper, we present Generalist Molecular generative model (GenMol), a versatile framework that addresses these limitations by applying discrete diffusion to the Sequential Attachment-based Fragment Embedding (SAFE) molecular representation. GenMol generates SAFE sequences through non-autoregressive bidirectional parallel decoding, thereby allowing utilization of a molecular context that does not rely on the specific token ordering and enhanced computational efficiency. Moreover, under the discrete diffusion framework, we introduce fragment remasking, a strategy that optimizes molecules by replacing fragments with masked tokens and regenerating them, enabling effective exploration of chemical space. GenMol significantly outperforms the previous GPT-based model trained on SAFE representations in de novo generation and fragment-constrained generation, and achieves state-of-the-art performance in goal-directed hit generation and lead optimization. These experimental results demonstrate that GenMol can tackle a wide range of drug discovery tasks, providing a unified and versatile approach for molecular design.
Authors: Satchel Grant
Abstract: When can we say that two neural systems are the same? The answer to this question is goal-dependent, and it is often addressed through correlative methods such as Representational Similarity Analysis (RSA) and Centered Kernel Alignment (CKA). What do we miss when we forgo causal explorations, and how can we target specific types of similarity? In this work, we introduce Model Alignment Search (MAS), a method for causally exploring distributed representational similarity. The method learns invertible linear transformations that align a subspace between two distributed networks' representations where causal information can be freely interchanged. We first show that the method can be used to transfer specific causal variables, such as the number of items in a counting task, between networks with different training seeds. We then explore open questions in number cognition by comparing different types of numeric representations in models trained on structurally different numeric tasks. We then explore differences between MAS vs preexisting causal similarity methods, showing MAS to be more resistant to unwanted exchanges. Lastly, we introduce a counterfactual latent auxiliary loss function that helps shape causally relevant alignments even in cases where we do not have causal access to one of the two models for training.
Authors: Ankush Chakrabarty, Gordon Wichern, Vedang M. Deshpande, Abraham P. Vinod, Karl Berntorp, Christopher R. Laughman
Abstract: We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. When applicable, we also incorporate domain-specific physical constraints to improve the accuracy of the NSSM. The major benefit of our approach is that instead of relying solely on data from a single target system, our framework utilizes data from a diverse set of source systems, enabling learning from limited target data, as well as with few online training iterations. Through benchmark examples, we demonstrate the potential of our approach, study the effect of fine-tuning subnetworks rather than full fine-tuning, and report real-world case studies to illustrate the practical application and generalizability of the approach to practical problems with physical-constraints. Specifically, we show that the meta-learned models result in improved downstream performance in model-based state estimation in indoor localization and energy systems.
Authors: Zuyao You, Lingyu Kong, Lingchen Meng, Zuxuan Wu
Abstract: Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unification. Moreover, they primarily focus on recognizing foreground objects without effectively distinguishing them from the background. In this paper, we emphasize the importance of the background and its relationship with the foreground. We introduce FOCUS, the Foreground ObjeCts Universal Segmentation framework that can handle multiple foreground tasks. We develop a multi-scale semantic network using the edge information of objects to enhance image features. To achieve boundary-aware segmentation, we propose a novel distillation method, integrating the contrastive learning strategy to refine the prediction mask in multi-modal feature space. We conduct extensive experiments on a total of 13 datasets across 5 tasks, and the results demonstrate that FOCUS consistently outperforms the state-of-the-art task-specific models on most metrics.
Authors: R{\i}za \"Oz\c{c}elik, Francesca Grisoni
Abstract: "How to evaluate de novo designs proposed by a generative model?" Despite the transformative potential of generative deep learning in drug discovery, this seemingly simple question has no clear answer. The absence of standardized guidelines challenges both the benchmarking of generative approaches and the selection of molecules for prospective studies. In this work, we take a fresh $- \textit{critical}$ and $\textit{constructive} -$ perspective on de novo design evaluation. We systematically investigate widely used evaluation metrics and expose key pitfalls ('traps') that were previously overlooked. In addition, we identify tools ('treasures') and strategies ('ways out') to navigate the complex 'jungle' of generative drug discovery, and strengthen the connections between the molecular and deep learning fields along the way. Our systematic and large-scale results are expected to provide a new lens for evaluating the de novo designs proposed by generative deep learning approaches.
Authors: Nick Polson, Vadim Sokolov
Abstract: Generative methods (Gen-AI) are reviewed with a particular goal to solving tasks in Machine Learning and Bayesian inference. Generative models require one to simulate a large training dataset and to use deep neural networks to solve a supervised learning problem. To do this, we require high dimensional regression methods and tools for dimensionality reduction (a.k.a feature selection). The main advantage of Gen-AI methods is their ability to be model-free and to use deep neural networks to estimate conditional densities or posterior quantiles of interest. To illustrate generative methods, we analyze the well-known Ebola data-set. Finally, we conclude with directions for future research.
Authors: Gursimran Singh, Xinglu Wang, Ivan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, Yong Zhang, Zhenan Fan
Abstract: Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead. This step helps convert raw inputs into tokenized representations that inflate the token sequence for the prefill phase, negatively impacting key Service Level Objectives (SLOs) like time to first token (TTFT) and end-to-end throughput. We introduce Encode-Prefill-Decode (EPD) Disaggregation, a novel framework that separates the encoding, prefill, and decode stages onto dedicated resources. Unlike current systems, which bundle encoding and prefill together, our disaggregation approach alleviates memory bottlenecks, mitigates synchronization delays, and supports flexible batching. Specifically, we employ a new caching mechanism for multimodal tokens, enabling asynchronous transfer of multimodal tokens and introduce an integrated module to find optimal config for EPD system and minimize resource usage while maximizing SLO-based performance metric. Experimental evaluations with popular LMMs show substantial gains in memory efficiency (up to 15$\times$ lesser for encoding-stage GPUs), that supports upto 22$\times$ higher batch sizes, 10$\times$ more number of images/ request, 2.2$\times$ higher kv cache size. Further, it leads to significant improvements in end-to-end throughput (up to 57\% better), and latency metrics (TTFT up to 71\% lower), compared to systems that do not disaggregate. Our findings underscore the potential of EPD disaggregation to enable resource-efficient and high-performance multimodal inference at scale.
Authors: Miriam Doh (UMONS, ULB), Caroline Mazini Rodrigues (LRDE, LIGM), N. Boutry (LRDE), L. Najman (LIGM), Matei Mancas (UMONS), Bernard Gosselin (UMONS)
Abstract: The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to enhance interpretability and transparency. This study extends previous work by integrating semantic concepts derived from human cognitive processes into XAI frameworks to bridge the comprehension gap between model outputs and human understanding. We propose a novel approach combining global and local explanations, using semantic features defined by user-selected facial landmarks to generate similarity maps and textual explanations via large language models (LLMs). The methodology was validated through quantitative experiments and user feedback, demonstrating improved interpretability. Results indicate that our semantic-based approach, particularly the most detailed set, offers a more nuanced understanding of model decisions than traditional methods. User studies highlight a preference for our semantic explanations over traditional pixelbased heatmaps, emphasizing the benefits of human-centric interpretability in AI. This work contributes to the ongoing efforts to create XAI frameworks that align AI models behaviour with human cognitive processes, fostering trust and acceptance in critical applications.
Authors: Qing Wu
Abstract: 3D semantic segmentation is one of the most crucial tasks in driving perception. The ability of a learning-based model to accurately perceive dense 3D surroundings often ensures the safe operation of autonomous vehicles. However, existing LiDAR-based 3D semantic segmentation databases consist of sequentially acquired LiDAR scans that are long-tailed and lack training diversity. In this report, we introduce MixSeg3D, a sophisticated combination of the strong point cloud segmentation model with advanced 3D data mixing strategies. Specifically, our approach integrates the MinkUNet family with LaserMix and PolarMix, two scene-scale data augmentation methods that blend LiDAR point clouds along the ego-scene's inclination and azimuth directions. Through empirical experiments, we demonstrate the superiority of MixSeg3D over the baseline and prior arts. Our team achieved 2nd place in the 3D semantic segmentation track of the 2024 Waymo Open Dataset Challenge.
Authors: Xincheng Wang, Liejun Wang, Yinfeng Yu, Xinxin Jiao
Abstract: Multimodal Sentiment Analysis (MSA) integrates diverse modalities(text, audio, and video) to comprehensively analyze and understand individuals' emotional states. However, the real-world prevalence of incomplete data poses significant challenges to MSA, mainly due to the randomness of modality missing. Moreover, the heterogeneity issue in multimodal data has yet to be effectively addressed. To tackle these challenges, we introduce the Modality-Invariant Bidirectional Temporal Representation Distillation Network (MITR-DNet) for Missing Multimodal Sentiment Analysis. MITR-DNet employs a distillation approach, wherein a complete modality teacher model guides a missing modality student model, ensuring robustness in the presence of modality missing. Simultaneously, we developed the Modality-Invariant Bidirectional Temporal Representation Learning Module (MIB-TRL) to mitigate heterogeneity.
Authors: Malak Mansour, Ahmed Aly, Bahey Tharwat, Sarim Hashmi, Dong An, Ian Reid
Abstract: Large Language Models (LLMs) such as GPT-4, trained on huge amount of datasets spanning multiple domains, exhibit significant reasoning, understanding, and planning capabilities across various tasks. This study presents the first-ever work in Arabic language integration within the Vision-and-Language Navigation (VLN) domain in robotics, an area that has been notably underexplored in existing research. We perform a comprehensive evaluation of state-of-the-art multi-lingual Small Language Models (SLMs), including GPT-4o mini, Llama 3 8B, and Phi-3 medium 14B, alongside the Arabic-centric LLM, Jais. Our approach utilizes the NavGPT framework, a pure LLM-based instruction-following navigation agent, to assess the impact of language on navigation reasoning through zero-shot sequential action prediction using the R2R dataset. Through comprehensive experiments, we demonstrate that our framework is capable of high-level planning for navigation tasks when provided with instructions in both English and Arabic. However, certain models struggled with reasoning and planning in the Arabic language due to inherent limitations in their capabilities, sub-optimal performance, and parsing issues. These findings highlight the importance of enhancing planning and reasoning capabilities in language models for effective navigation, emphasizing this as a key area for further development while also unlocking the potential of Arabic-language models for impactful real-world applications.
Authors: John C. Rollman, Bruce Rogers, Hamed Zaribafzadeh, Daniel Buckland, Ursula Rogers, Jennifer Gagnon, Ozanan Meireles, Lindsay Jennings, Jim Bennett, Jennifer Nicholson, Nandan Lad, Linda Cendales, Andreas Seas, Alessandro Martinino, E. Shelley Hwang, Allan D. Kirk
Abstract: Background: Healthcare has many manual processes that can benefit from automation and augmentation with Generative Artificial Intelligence (AI), the medical billing and coding process. However, current foundational Large Language Models (LLMs) perform poorly when tasked with generating accurate International Classification of Diseases, 10th edition, Clinical Modification (ICD-10-CM) and Current Procedural Terminology (CPT) codes. Additionally, there are many security and financial challenges in the application of generative AI to healthcare. We present a strategy for developing generative AI tools in healthcare, specifically for medical billing and coding, that balances accuracy, accessibility, and patient privacy. Methods: We fine tune the PHI-3 Mini and PHI-3 Medium LLMs using institutional data and compare the results against the PHI-3 base model, a PHI-3 RAG application, and GPT-4o. We use the post operative surgical report as input and the patients billing claim the associated ICD-10, CPT, and Modifier codes as the target result. Performance is measured by accuracy of code generation, proportion of invalid codes, and the fidelity of the billing claim format. Results: Both fine-tuned models performed better or as well as GPT-4o. The Phi-3 Medium fine-tuned model showed the best performance (ICD-10 Recall and Precision: 72%, 72%; CPT Recall and Precision: 77%, 79%; Modifier Recall and Precision: 63%, 64%). The Phi-3 Medium fine-tuned model only fabricated 1% of ICD-10 codes and 0.6% of CPT codes generated. Conclusions: Our study shows that a small model that is fine-tuned on domain-specific data for specific tasks using a simple set of open-source tools and minimal technological and monetary requirements performs as well as the larger contemporary consumer models.
Authors: Prashant Verma
Abstract: Document chunking is a critical task in natural language processing (NLP) that involves dividing a document into meaningful segments. Traditional methods often rely solely on semantic analysis, ignoring the spatial layout of elements, which is crucial for understanding relationships in complex documents. This paper introduces a novel hybrid approach that combines layout structure, semantic analysis, and spatial relationships to enhance the cohesion and accuracy of document chunks. By leveraging bounding box information (bbox) and text embeddings, our method constructs a weighted graph representation of document elements, which is then clustered using spectral clustering. Experimental results demonstrate that this approach outperforms traditional methods, particularly in documents with diverse layouts such as reports, articles, and multi-column designs. The proposed method also ensures that no chunk exceeds a specified token length, making it suitable for use cases where token limits are critical (e.g., language models with input size limitations)
Authors: Jonathan Keane, Sam Keyser, Jeremy Kedziora
Abstract: The use of reward functions to structure AI learning and decision making is core to the current reinforcement learning paradigm; however, without careful design of reward functions, agents can learn to solve problems in ways that may be considered ``undesirable" or ``unethical. Without thorough understanding of the incentives a reward function creates, it can be difficult to impose principled yet general control mechanisms over its behavior. In this paper, we study methods for constructing guardrails for AI agents that use reward functions to learn decision making. We introduce a novel approach, which we call strategy masking, to explicitly learn and then suppress undesirable AI agent behavior. We apply our method to study lying in AI agents and show that strategy masking can effectively modify agent behavior by suppressing, or actively penalizing, the reward dimension for lying such that agents act more honestly while not compromising their ability to perform effectively.
Authors: Sergei Kudriashov, Veronika Zykova, Angelina Stepanova, Yakov Raskind, Eduard Klyshinsky
Abstract: The interpretation of deep learning models is a rapidly growing field, with particular interest in language models. There are various approaches to this task, including training simpler models to replicate neural network predictions and analyzing the latent space of the model. The latter method allows us to not only identify patterns in the model's decision-making process, but also understand the features of its internal structure. In this paper, we analyze the changes in the internal representation of the BERT model when it is trained with additional grammatical modules and data containing new grammatical structures (polypersonality). We find that adding a single grammatical layer causes the model to separate the new and old grammatical systems within itself, improving the overall performance on perplexity metrics.
Authors: Rui Shi, Nedret Billor, Elvan Ceyhan
Abstract: This paper introduces two novel, outlyingness scores (OSs) based on Cluster Catch Digraphs (CCDs): Outbound Outlyingness Score (OOS) and Inbound Outlyingness Score (IOS). These scores enhance the interpretability of outlier detection results. Both OSs employ graph-, density-, and distribution-based techniques, tailored to high-dimensional data with varying cluster shapes and intensities. OOS evaluates the outlyingness of a point relative to its nearest neighbors, while IOS assesses the total ``influence" a point receives from others within its cluster. Both OSs effectively identify global and local outliers, invariant to data collinearity. Moreover, IOS is robust to the masking problems. With extensive Monte Carlo simulations, we compare the performance of both OSs with CCD-based, traditional, and state-of-the-art outlier detection methods. Both OSs exhibit substantial overall improvements over the CCD-based methods in both artificial and real-world data sets, particularly with IOS, which delivers the best overall performance among all the methods, especially in high-dimensional settings. Keywords: Outlier detection, Outlyingness score, Graph-based clustering, Cluster catch digraphs, High-dimensional data.
Authors: Joschka Birk, Frank Gaede, Anna Hallin, Gregor Kasieczka, Martina Mozzanica, Henning Rose
Abstract: We show the first use of generative transformers for generating calorimeter showers as point clouds in a high-granularity calorimeter. Using the tokenizer and generative part of the OmniJet-${\alpha}$ model, we represent the hits in the detector as sequences of integers. This model allows variable-length sequences, which means that it supports realistic shower development and does not need to be conditioned on the number of hits. Since the tokenization represents the showers as point clouds, the model learns the geometry of the showers without being restricted to any particular voxel grid.
Authors: Ziyue Luo, Jia Liu, Myungjin Lee, Ness B. Shroff
Abstract: The recent explosive growth of deep learning (DL) models has necessitated a compelling need for efficient job scheduling for distributed deep learning training with mixed parallelisms (DDLwMP) in GPU clusters. This paper proposes an adaptive shortest-remaining-processing-time-first (A-SRPT) scheduling algorithm, a novel prediction-assisted online scheduling approach designed to mitigate the challenges associated with DL cluster scheduling. By modeling each job as a graph corresponding to heterogeneous Deep Neural Network (DNN) models and their associated distributed training configurations, A-SRPT strategically assigns jobs to the available GPUs, thereby minimizing inter-server communication overhead. Observing that most DDLwMP jobs recur, A-SRPT incorporates a random forest regression model to predict training iterations. Crucially, A-SRPT maps the complex scheduling problem into a single-machine instance, which is addressed optimally by a preemptive "shortest-remaining-processing-time-first" strategy. This optimized solution serves as a guide for actual job scheduling within the GPU clusters, leading to a theoretically provable competitive scheduling efficiency. We conduct extensive real-world testbed and simulation experiments to verify our proposed algorithms.
Authors: Gert Aarts, Kenji Fukushima, Tetsuo Hatsuda, Andreas Ipp, Shuzhe Shi, Lingxiao Wang, Kai Zhou
Abstract: The integration of deep learning techniques and physics-driven designs is reforming the way we address inverse problems, in which accurate physical properties are extracted from complex data sets. This is particularly relevant for quantum chromodynamics (QCD), the theory of strong interactions, with its inherent limitations in observational data and demanding computational approaches. This perspective highlights advances and potential of physics-driven learning methods, focusing on predictions of physical quantities towards QCD physics, and drawing connections to machine learning(ML). It is shown that the fusion of ML and physics can lead to more efficient and reliable problem-solving strategies. Key ideas of ML, methodology of embedding physics priors, and generative models as inverse modelling of physical probability distributions are introduced. Specific applications cover first-principle lattice calculations, and QCD physics of hadrons, neutron stars, and heavy-ion collisions. These examples provide a structured and concise overview of how incorporating prior knowledge such as symmetry, continuity and equations into deep learning designs can address diverse inverse problems across different physical sciences.
Authors: Meira Iske, Hannes Albers, Tobias Knopp, Tobias Kluth
Abstract: Magnetic Particle Imaging (MPI) is an emerging imaging modality based on the magnetic response of superparamagnetic iron oxide nanoparticles to achieve high-resolution and real-time imaging without harmful radiation. One key challenge in the MPI image reconstruction task arises from its underlying noise model, which does not fulfill the implicit Gaussian assumptions that are made when applying traditional reconstruction approaches. To address this challenge, we introduce the Learned Discrepancy Approach, a novel learning-based reconstruction method for inverse problems that includes a learned discrepancy function. It enhances traditional techniques by incorporating an invertible neural network to explicitly model problem-specific noise distributions. This approach does not rely on implicit Gaussian noise assumptions, making it especially suited to handle the sophisticated noise model in MPI and also applicable to other inverse problems. To further advance MPI reconstruction techniques, we introduce the MPI-MNIST dataset - a large collection of simulated MPI measurements derived from the MNIST dataset of handwritten digits. The dataset includes noise-perturbed measurements generated from state-of-the-art model-based system matrices and measurements of a preclinical MPI scanner device. This provides a realistic and flexible environment for algorithm testing. Validated against the MPI-MNIST dataset, our method demonstrates significant improvements in reconstruction quality in terms of structural similarity when compared to classical reconstruction techniques.
Authors: Xiaoshan Zhou, Carol M. Menassa, Vineet R. Kamat
Abstract: Assistive mobile robots are a transformative technology that helps persons with disabilities regain the ability to move freely. Although autonomous wheelchairs significantly reduce user effort, they still require human input to allow users to maintain control and adapt to changing environments. Brain Computer Interface (BCI) stands out as a highly user-friendly option that does not require physical movement. Current BCI systems can understand whether users want to accelerate or decelerate, but they implement these changes in discrete speed steps rather than allowing for smooth, continuous velocity adjustments. This limitation prevents the systems from mimicking the natural, fluid speed changes seen in human self-paced motion. The authors aim to address this limitation by redesigning the perception-action cycle in a BCI controlled robotic system: improving how the robotic agent interprets the user's motion intentions (world state) and implementing these actions in a way that better reflects natural physical properties of motion, such as inertia and damping. The scope of this paper focuses on the perception aspect. We asked and answered a normative question "what computation should the robotic agent carry out to optimally perceive incomplete or noisy sensory observations?" Empirical EEG data were collected, and probabilistic representation that served as world state distributions were learned and evaluated in a Generative Adversarial Network framework. The ROS framework was established that connected with a Gazebo environment containing a digital twin of an indoor space and a virtual model of a robotic wheelchair. Signal processing and statistical analyses were implemented to identity the most discriminative features in the spatial-spectral-temporal dimensions, which are then used to construct the world model for the robotic agent to interpret user motion intentions as a Bayesian observer.
Authors: Zhao Yang, Bing Su, Jiahao Chen, Ji-Rong Wen
Abstract: Predicting multiple functions labeled with Enzyme Commission (EC) numbers from the enzyme sequence is of great significance but remains a challenge due to its sparse multi-label classification nature, i.e., each enzyme is typically associated with only a few labels out of more than 6000 possible EC numbers. However, existing machine learning algorithms generally learn a fixed global representation for each enzyme to classify all functions, thereby they lack interpretability and the fine-grained information of some function-specific local residue fragments may be overwhelmed. Here we present an attention-based framework, namely ProtDETR (Protein Detection Transformer), by casting enzyme function prediction as a detection problem. It uses a set of learnable functional queries to adaptatively extract different local representations from the sequence of residue-level features for predicting different EC numbers. ProtDETR not only significantly outperforms existing deep learning-based enzyme function prediction methods, but also provides a new interpretable perspective on automatically detecting different local regions for identifying different functions through cross-attentions between queries and residue-level features. Code is available at https://github.com/yangzhao1230/ProtDETR.
Authors: Chenxi Yang, Yan Li, Martin Maas, Mustafa Uysal, Ubaid Ullah Hafeez, Arif Merchant, Richard McDougall
Abstract: Storage systems account for a major portion of the total cost of ownership (TCO) of warehouse-scale computers, and thus have a major impact on the overall system's efficiency. Machine learning (ML)-based methods for solving key problems in storage system efficiency, such as data placement, have shown significant promise. However, there are few known practical deployments of such methods. Studying this problem in the context of real-world hyperscale data center deployments at Google, we identify a number of challenges that we believe cause this lack of practical adoption. Specifically, prior work assumes a monolithic model that resides entirely within the storage layer, an unrealistic assumption in real-world data center deployments. We propose a cross-layer approach that moves ML out of the storage system and performs it in the application running on top of it, co-designed with a scheduling algorithm at the storage layer that consumes predictions from these application-level models. This approach combines small, interpretable models with a co-designed heuristic that adapts to different online environments. We build a proof-of-concept of this approach in a production distributed computation framework at Google. Evaluations in a test deployment and large-scale simulation studies using production traces show improvements of as much as 3.47x in TCO savings compared to state of the art baselines. We believe this work represents a significant step towards more practical ML-driven storage placement in warehouse-scale computers.
Authors: Ayush Khot, Xiwei Wang, Avik Roy, Volodymyr Kindratenko, Mark S. Neubauer
Abstract: Current methods commonly used for uncertainty quantification (UQ) in deep learning (DL) models utilize Bayesian methods which are computationally expensive and time-consuming. In this paper, we provide a detailed study of UQ based on evidential deep learning (EDL) for deep neural network models designed to identify jets in high energy proton-proton collisions at the Large Hadron Collider and explore its utility in anomaly detection. EDL is a DL approach that treats learning as an evidence acquisition process designed to provide confidence (or epistemic uncertainty) about test data. Using publicly available datasets for jet classification benchmarking, we explore hyperparameter optimizations for EDL applied to the challenge of UQ for jet identification. We also investigate how the uncertainty is distributed for each jet class, how this method can be implemented for the detection of anomalies, how the uncertainty compares with Bayesian ensemble methods, and how the uncertainty maps onto latent spaces for the models. Our studies uncover some pitfalls of EDL applied to anomaly detection and a more effective way to quantify uncertainty from EDL as compared with the foundational EDL setup. These studies illustrate a methodological approach to interpreting EDL in jet classification models, providing new insights on how EDL quantifies uncertainty and detects out-of-distribution data which may lead to improved EDL methods for DL models applied to classification tasks.
Authors: Samuel Yen-Chi Chen, Huan-Hsin Tseng, Hsin-Yi Lin, Shinjae Yoo
Abstract: The rapid progress in quantum computing (QC) and machine learning (ML) has attracted growing attention, prompting extensive research into quantum machine learning (QML) algorithms to solve diverse and complex problems. Designing high-performance QML models demands expert-level proficiency, which remains a significant obstacle to the broader adoption of QML. A few major hurdles include crafting effective data encoding techniques and parameterized quantum circuits, both of which are crucial to the performance of QML models. Additionally, the measurement phase is frequently overlooked-most current QML models rely on pre-defined measurement protocols that often fail to account for the specific problem being addressed. We introduce a novel approach that makes the observable of the quantum system-specifically, the Hermitian matrix-learnable. Our method features an end-to-end differentiable learning framework, where the parameterized observable is trained alongside the ordinary quantum circuit parameters simultaneously. Using numerical simulations, we show that the proposed method can identify observables for variational quantum circuits that lead to improved outcomes, such as higher classification accuracy, thereby boosting the overall performance of QML models.
Authors: Feiyi Chen, Leilei Zhang, Guansong Pang, Roger Zimmermann, Shuiguang Deng
Abstract: In anomaly detection, methods based on large language models (LLMs) can incorporate expert knowledge, while task-specific smaller models excel at extracting normal patterns and detecting value fluctuations. Inspired by the human nervous system, where the brain stores expert knowledge and the peripheral nervous system and spinal cord handle specific tasks like withdrawal and knee-jerk reflexes, we propose CoLLaTe, a framework designed to facilitate collaboration between LLMs and task-specific models, leveraging the strengths of both. In this work, we first formulate the collaboration process and identify two key challenges in the collaboration between LLMs and task-specific models: (1) the misalignment between the expression domains of LLMs and smaller models, and (2) error accumulation arising from the predictions of both models. To address these challenges, we introduce two key components in CoLLaTe: the alignment module and the collaborative loss function. Through theoretical analysis and experimental validation, we demonstrate that these components effectively mitigate the identified challenges and achieve better performance than LLM based methods and task-specific smaller model.
Authors: Jaehoon Heo, Adiwena Putra, Jieon Yoon, Sungwoong Yune, Hangyeol Lee, Ji-Hoon Kim, Joo-Young Kim
Abstract: Over the past few years, diffusion models have emerged as novel AI solutions, generating diverse multi-modal outputs from text prompts. Despite their capabilities, they face challenges in computing, such as excessive latency and energy consumption due to their iterative architecture. Although prior works specialized in transformer acceleration can be applied, the iterative nature of diffusion models remains unresolved. In this paper, we present EXION, the first SW-HW co-designed diffusion accelerator that solves the computation challenges by exploiting the unique inter- and intra-iteration output sparsity in diffusion models. To this end, we propose two SW-level optimizations. First, we introduce the FFN-Reuse algorithm that identifies and skips redundant computations in FFN layers across different iterations (inter-iteration sparsity). Second, we use a modified eager prediction method that employs two-step leading-one detection to accurately predict the attention score, skipping unnecessary computations within an iteration (intra-iteration sparsity). We also introduce a novel data compaction mechanism named ConMerge, which can enhance HW utilization by condensing and merging sparse matrices into compact forms. Finally, it has a dedicated HW architecture that supports the above sparsity-inducing algorithms, translating high output sparsity into improved energy efficiency and performance. To verify the feasibility of the EXION, we first demonstrate that it has no impact on accuracy in various types of multi-modal diffusion models. We then instantiate EXION in both server- and edge-level settings and compare its performance against GPUs with similar specifications. Our evaluation shows that EXION achieves dramatic improvements in performance and energy efficiency by 3.2-379.3x and 45.1-3067.6x compared to a server GPU and by 42.6-1090.9x and 196.9-4668.2x compared to an edge GPU.
Authors: Vighnesh Subramaniam, Yilun Du, Joshua B. Tenenbaum, Antonio Torralba, Shuang Li, Igor Mordatch
Abstract: Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the training data, recent works have explored how LLMs can be used to generate synthetic data for autonomous self-improvement. However, successive steps of self-improvement can reach a point of diminishing returns. In this work, we propose a complementary approach towards self-improvement where finetuning is applied to a multiagent society of language models. A group of language models, all starting from the same base model, are independently specialized by updating each one using data generated through multiagent interactions among the models. By training each model on independent sets of data, we illustrate how this approach enables specialization across models and diversification over the set of models. As a result, our overall system is able to preserve diverse reasoning chains and autonomously improve over many more rounds of fine-tuning than single-agent self-improvement methods. We quantitatively illustrate the efficacy of the approach across a wide suite of reasoning tasks.
Authors: Zhengyang Tang, Ziniu Li, Zhenyang Xiao, Tian Ding, Ruoyu Sun, Benyou Wang, Dayiheng Liu, Fei Huang, Tianyu Liu, Bowen Yu, Junyang Lin
Abstract: Despite their remarkable performance, the development of Large Language Models (LLMs) faces a critical challenge in scalable oversight: providing effective feedback for tasks where human evaluation is difficult or where LLMs outperform humans. While there is growing interest in using LLMs for critique, current approaches still rely on human annotations or more powerful models, leaving the issue of enhancing critique capabilities without external supervision unresolved. We introduce SCRIT (Self-evolving CRITic), a framework that enables genuine self-evolution of critique abilities. Technically, SCRIT self-improves by training on synthetic data, generated by a contrastive-based self-critic that uses reference solutions for step-by-step critique, and a self-validation mechanism that ensures critique quality through correction outcomes. Implemented with Qwen2.5-72B-Instruct, one of the most powerful LLMs, SCRIT achieves up to a 10.3\% improvement on critique-correction and error identification benchmarks. Our analysis reveals that SCRIT's performance scales positively with data and model size, outperforms alternative approaches, and benefits critically from its self-validation component.
Authors: Boris Kriuk, Keti Sulamanidze, Fedor Kriuk
Abstract: Despite the success of metaheuristic algorithms in solving complex network optimization problems, they often struggle with adaptation, especially in dynamic or high-dimensional search spaces. Traditional approaches can become stuck in local optima, leading to inefficient exploration and suboptimal solutions. Most of the widely accepted advanced algorithms do well either on highly complex or smaller search spaces due to the lack of adaptation. To address these limitations, we present ELENA (Epigenetic Learning through Evolved Neural Adaptation), a new evolutionary framework that incorporates epigenetic mechanisms to enhance the adaptability of the core evolutionary approach. ELENA leverages compressed representation of learning parameters improved dynamically through epigenetic tags that serve as adaptive memory. Three epigenetic tags (mutation resistance, crossover affinity, and stability score) assist with guiding solution space search, facilitating a more intelligent hypothesis landscape exploration. To assess the framework performance, we conduct experiments on three critical network optimization problems: the Traveling Salesman Problem (TSP), the Vehicle Routing Problem (VRP), and the Maximum Clique Problem (MCP). Experiments indicate that ELENA achieves competitive results, often surpassing state-of-the-art methods on network optimization tasks.
Authors: Loay Rashid, Siddharth Roheda, Amit Unde
Abstract: Video restoration plays a pivotal role in revitalizing degraded video content by rectifying imperfections caused by various degradations introduced during capturing (sensor noise, motion blur, etc.), saving/sharing (compression, resizing, etc.) and editing. This paper introduces a novel algorithm designed for scenarios where noise is introduced during video capture, aiming to enhance the visual quality of videos by reducing unwanted noise artifacts. We propose the Latent space LSTM Video Denoiser (LLVD), an end-to-end blind denoising model. LLVD uniquely combines spatial and temporal feature extraction, employing Long Short Term Memory (LSTM) within the encoded feature domain. This integration of LSTM layers is crucial for maintaining continuity and minimizing flicker in the restored video. Moreover, processing frames in the encoded feature domain significantly reduces computations, resulting in a very lightweight architecture. LLVD's blind nature makes it versatile for real, in-the-wild denoising scenarios where prior information about noise characteristics is not available. Experiments reveal that LLVD demonstrates excellent performance for both synthetic and captured noise. Specifically, LLVD surpasses the current State-Of-The-Art (SOTA) in RAW denoising by 0.3dB, while also achieving a 59\% reduction in computational complexity.
Authors: Roman Marchant, Dario Draca, Gilad Francis, Sahand Assadzadeh, Mathew Varidel, Frank Iorfino, Sally Cripps
Abstract: Learning the structure of Bayesian networks from data provides insights into underlying processes and the causal relationships that generate the data, but its usefulness depends on the homogeneity of the data population, a condition often violated in real-world applications. In such cases, using a single network structure for inference can be misleading, as it may not capture sub-population differences. To address this, we propose a novel approach of modelling a mixture of Bayesian networks where component probabilities depend on individual characteristics. Our method identifies both network structures and demographic predictors of sub-population membership, aiding personalised interventions. We evaluate our method through simulations and a youth mental health case study, demonstrating its potential to improve tailored interventions in health, education, and social policy.
Authors: Madhurananda Pahar, Fuxiang Tao, Bahman Mirheidari, Nathan Pevy, Rebecca Bright, Swapnil Gadgil, Lise Sproson, Dorota Braun, Caitlin Illingworth, Daniel Blackburn, Heidi Christensen
Abstract: The early signs of cognitive decline are often noticeable in conversational speech, and identifying those signs is crucial in dealing with later and more serious stages of neurodegenerative diseases. Clinical detection is costly and time-consuming and although there has been recent progress in the automatic detection of speech-based cues, those systems are trained on relatively small databases, lacking detailed metadata and demographic information. This paper presents CognoSpeak and its associated data collection efforts. CognoSpeak asks memory-probing long and short-term questions and administers standard cognitive tasks such as verbal and semantic fluency and picture description using a virtual agent on a mobile or web platform. In addition, it collects multimodal data such as audio and video along with a rich set of metadata from primary and secondary care, memory clinics and remote settings like people's homes. Here, we present results from 126 subjects whose audio was manually transcribed. Several classic classifiers, as well as large language model-based classifiers, have been investigated and evaluated across the different types of prompts. We demonstrate a high level of performance; in particular, we achieved an F1-score of 0.873 using a DistilBERT model to discriminate people with cognitive impairment (dementia and people with mild cognitive impairment (MCI)) from healthy volunteers using the memory responses, fluency tasks and cookie theft picture description. CognoSpeak is an automatic, remote, low-cost, repeatable, non-invasive and less stressful alternative to existing clinical cognitive assessments.
Authors: Chiara Pasini, Oscar Ramponi, Stefano Pandini, Luciana Sartore, Giulia Scalet
Abstract: Lattice structures have great potential for several application fields ranging from medical and tissue engineering to aeronautical one. Their development is further speeded up by the continuing advances in additive manufacturing technologies that allow to overcome issues typical of standard processes and to propose tailored designs. However, the design of lattice structures is still challenging since their properties are considerably affected by numerous factors. The present paper aims to propose, discuss, and compare various modeling approaches to describe, understand, and predict the correlations between the mechanical properties and the void volume fraction of different types of lattice structures fabricated by fused deposition modeling 3D printing. Particularly, four approaches are proposed: (i) a simplified analytical model; (ii) a semi-empirical model combining analytical equations with experimental correction factors; (iii) an artificial neural network trained on experimental data; (iv) numerical simulations by finite element analyses. The comparison among the various approaches, and with experimental data, allows to identify the performances, advantages, and disadvantages of each approach, thus giving important guidelines for choosing the right design methodology based on the needs and available data.
Authors: Taywon Min, Haeone Lee, Hanho Ryu, Yongchan Kwon, Kimin Lee
Abstract: In Reinforcement Learning from Human Feedback (RLHF), it is crucial to learn suitable reward models from human feedback to align large language models (LLMs) with human intentions. However, human feedback can often be noisy, inconsistent, or biased, especially when evaluating complex responses. Such feedback can lead to misaligned reward signals, potentially causing unintended side effects during the RLHF process. To address these challenges, we explore the use of influence functions to measure the impact of human feedback on the performance of reward models. We propose a compute-efficient approximation method that enables the application of influence functions to LLM-based reward models and large-scale preference datasets. In our experiments, we demonstrate two key applications of influence functions: (1) detecting common forms of labeler bias in human feedback datasets and (2) guiding labelers to refine their strategies to align more closely with expert feedback. By quantifying the impact of human feedback on reward models, we believe that influence functions can enhance feedback interpretability and contribute to scalable oversight in RLHF, helping labelers provide more accurate and consistent feedback. Source code is available at https://github.com/mintaywon/IF_RLHF
Authors: Pablo Loyola, Kento Hasegawa, Andres Hoyos-Idobro, Kazuo Ono, Toyotaro Suzumura, Yu Hirate, Masanao Yamaoka
Abstract: While Annealing Machines (AM) have shown increasing capabilities in solving complex combinatorial problems, positioning themselves as a more immediate alternative to the expected advances of future fully quantum solutions, there are still scaling limitations. In parallel, Graph Neural Networks (GNN) have been recently adapted to solve combinatorial problems, showing competitive results and potentially high scalability due to their distributed nature. We propose a merging approach that aims at retaining both the accuracy exhibited by AMs and the representational flexibility and scalability of GNNs. Our model considers a compression step, followed by a supervised interaction where partial solutions obtained from the AM are used to guide local GNNs from where node feature representations are obtained and combined to initialize an additional GNN-based solver that handles the original graph's target problem. Intuitively, the AM can solve the combinatorial problem indirectly by infusing its knowledge into the GNN. Experiments on canonical optimization problems show that the idea is feasible, effectively allowing the AM to solve size problems beyond its original limits.
Authors: Aswini Kumar Patra, Soraisham Elizabeth Devi, Tejashwini Gajurel
Abstract: Alzheimer's disease (AD) progresses through distinct stages, from early mild cognitive impairment (EMCI) to late mild cognitive impairment (LMCI) and eventually to AD. Accurate identification of these stages, especially distinguishing LMCI from EMCI, is crucial for developing pre-dementia treatments but remains challenging due to subtle and overlapping imaging features. This study proposes a minimal-feature machine learning framework that leverages structural MRI data, focusing on the hippocampus and amygdala as regions of interest. The framework addresses the curse of dimensionality through feature selection, utilizes region-specific voxel information, and implements innovative data organization to enhance classification performance by reducing noise. The methodology integrates dimensionality reduction techniques such as PCA and t-SNE with state-of-the-art classifiers, achieving the highest accuracy of 88.46%. This framework demonstrates the potential for efficient and accurate staging of AD progression while providing valuable insights for clinical applications.
Authors: Lucas C. Cordeiro, Matthew L. Daggitt, Julien Girard-Satabin, Omri Isac, Taylor T. Johnson, Guy Katz, Ekaterina Komendantskaya, Augustin Lemesle, Edoardo Manino, Artjoms \v{S}inkarovs, Haoze Wu
Abstract: Neural network verification is a new and rapidly developing field of research. So far, the main priority has been establishing efficient verification algorithms and tools, while proper support from the programming language perspective has been considered secondary or unimportant. Yet, there is mounting evidence that insights from the programming language community may make a difference in the future development of this domain. In this paper, we formulate neural network verification challenges as programming language challenges and suggest possible future solutions.
Authors: Haris Bin Zia, Aravindh Raman, Ignacio Castro, Gareth Tyson
Abstract: The Fediverse, a group of interconnected servers providing a variety of interoperable services (e.g. micro-blogging in Mastodon) has gained rapid popularity. This sudden growth, partly driven by Elon Musk's acquisition of Twitter, has created challenges for administrators though. This paper focuses on one particular challenge: content moderation, e.g. the need to remove spam or hate speech. While centralized platforms like Facebook and Twitter rely on automated tools for moderation, their dependence on massive labeled datasets and specialized infrastructure renders them impractical for decentralized, low-resource settings like the Fediverse. In this work, we design and evaluate FedMod, a collaborative content moderation system based on federated learning. Our system enables servers to exchange parameters of partially trained local content moderation models with similar servers, creating a federated model shared among collaborating servers. FedMod demonstrates robust performance on three different content moderation tasks: harmful content detection, bot content detection, and content warning assignment, achieving average per-server macro-F1 scores of 0.71, 0.73, and 0.58, respectively.
Authors: Soyeong Jeong, Kangsan Kim, Jinheon Baek, Sung Ju Hwang
Abstract: Retrieval-Augmented Generation (RAG) is a powerful strategy to address the issue of generating factually incorrect outputs in foundation models by retrieving external knowledge relevant to queries and incorporating it into their generation process. However, existing RAG approaches have primarily focused on textual information, with some recent advancements beginning to consider images, and they largely overlook videos, a rich source of multimodal knowledge capable of representing events, processes, and contextual details more effectively than any other modality. While a few recent studies explore the integration of videos in the response generation process, they either predefine query-associated videos without retrieving them according to queries, or convert videos into the textual descriptions without harnessing their multimodal richness. To tackle these, we introduce VideoRAG, a novel framework that not only dynamically retrieves relevant videos based on their relevance with queries but also utilizes both visual and textual information of videos in the output generation. Further, to operationalize this, our method revolves around the recent advance of Large Video Language Models (LVLMs), which enable the direct processing of video content to represent it for retrieval and seamless integration of the retrieved videos jointly with queries. We experimentally validate the effectiveness of VideoRAG, showcasing that it is superior to relevant baselines.
Authors: Zhifan Song, Yuan Zhang, Abd Al Rahman M. Abu Ebayyeh
Abstract: Detecting small targets in drone imagery is challenging due to low resolution, complex backgrounds, and dynamic scenes. We propose EDNet, a novel edge-target detection framework built on an enhanced YOLOv10 architecture, optimized for real-time applications without post-processing. EDNet incorporates an XSmall detection head and a Cross Concat strategy to improve feature fusion and multi-scale context awareness for detecting tiny targets in diverse environments. Our unique C2f-FCA block employs Faster Context Attention to enhance feature extraction while reducing computational complexity. The WIoU loss function is employed for improved bounding box regression. With seven model sizes ranging from Tiny to XL, EDNet accommodates various deployment environments, enabling local real-time inference and ensuring data privacy. Notably, EDNet achieves up to a 5.6% gain in mAP@50 with significantly fewer parameters. On an iPhone 12, EDNet variants operate at speeds ranging from 16 to 55 FPS, providing a scalable and efficient solution for edge-based object detection in challenging drone imagery. The source code and pre-trained models are available at: https://github.com/zsniko/EDNet.
Authors: Mathieu Delcluze, Antoine Khoury, Cl\'emence Vast, Valerio Arnaudo, L\'ea Briand, Walid Bendada, Thomas Bouab\c{c}a
Abstract: The streaming service Deezer heavily relies on the search to help users navigate through its extensive music catalog. Nonetheless, it is primarily designed to find specific items and does not lead directly to a smooth listening experience. We present Text2Playlist, a stand-alone tool that addresses these limitations. Text2Playlist leverages generative AI, music information retrieval and recommendation systems to generate query-specific and personalized playlists, successfully deployed at scale.
Authors: Malte Grunert, Max Gro{\ss}mann, Erich Runge
Abstract: Does a machine learning model actually gain an understanding of the material space? We answer this question in the affirmative on the example of the OptiMate model, a graph attention network trained to predict the optical properties of semiconductors and insulators. By applying the UMAP dimensionality reduction technique to its latent embeddings, we demonstrate that the model captures a nuanced and interpretable representation of the materials space, reflecting chemical and physical principles, without any user-induced bias. This enables clustering of almost 10,000 materials based on optical properties and chemical similarities. Beyond this understanding, we demonstrate how the learned material space can be used to identify more sustainable alternatives to critical materials in energy-related technologies, such as photovoltaics. These findings demonstrate the dual utility of machine learning models in materials science: Accurately predicting material properties while providing insights into the underlying materials space. The approach demonstrates the broader potential of leveraging learned materials spaces for the discovery and design of materials for diverse applications, and is easily applicable to any state-of-the-art machine learning model.
Authors: Junyong Lee, JeiHee Cho, Shiho Kim
Abstract: In the Noisy Intermediate-Scale Quantum (NISQ) era, using variational quantum algorithms (VQAs) to solve optimization problems has become a key application. However, these algorithms face significant challenges, such as choosing an effective initial set of parameters and the limited quantum processing time that restricts the number of optimization iterations. In this study, we introduce a new framework for optimizing parameterized quantum circuits (PQCs) that employs a classical optimizer, inspired by Model-Agnostic Meta-Learning (MAML) technique. This approach aim to achieve better parameter initialization that ensures fast convergence. Our framework features a classical neural network, called Learner}, which interacts with a PQC using the output of Learner as an initial parameter. During the pre-training phase, Learner is trained with a meta-objective based on the quantum circuit cost function. In the adaptation phase, the framework requires only a few PQC updates to converge to a more accurate value, while the learner remains unchanged. This method is highly adaptable and is effectively extended to various Hamiltonian optimization problems. We validate our approach through experiments, including distribution function mapping and optimization of the Heisenberg XYZ Hamiltonian. The result implies that the Learner successfully estimates initial parameters that generalize across the problem space, enabling fast adaptation.
Authors: Ryan Whetten, Lucas Maison, Titouan Parcollet, Marco Dinarelli, Yannick Est\`eve
Abstract: In Self-Supervised Learning (SSL), pre-training and evaluation are resource intensive. In the speech domain, current indicators of the quality of SSL models during pre-training, such as the loss, do not correlate well with downstream performance. Consequently, it is often difficult to gauge the final downstream performance in a cost efficient manner during pre-training. In this work, we propose unsupervised efficient methods that give insights into the quality of the pre-training of SSL speech models, namely, measuring the cluster quality and rank of the embeddings of the SSL model. Results show that measures of cluster quality and rank correlate better with downstream performance than the pre-training loss with only one hour of unlabeled audio, reducing the need for GPU hours and labeled data in SSL model evaluation.
Authors: Sauda Adiv Hanum, Ashim Dey, Muhammad Ashad Kabir
Abstract: The skin, as the largest organ of the human body, is vulnerable to a diverse array of conditions collectively known as skin lesions, which encompass various dermatoses. Diagnosing these lesions presents significant challenges for medical practitioners due to the subtle visual differences that are often imperceptible to the naked eye. While not all skin lesions are life-threatening, certain types can act as early indicators of severe diseases, including skin cancers, underscoring the critical need for timely and accurate diagnostic methods. Deep learning algorithms have demonstrated remarkable potential in facilitating the early detection and prognosis of skin lesions. This study advances the field by curating a comprehensive and diverse dataset comprising 39 categories of skin lesions, synthesized from five publicly available datasets. Using this dataset, the performance of five state-of-the-art deep learning models -- MobileNetV2, Xception, InceptionV3, EfficientNetB1, and Vision Transformer - is rigorously evaluated. To enhance the accuracy and robustness of these models, attention mechanisms such as the Efficient Channel Attention (ECA) and the Convolutional Block Attention Module (CBAM) are incorporated into their architectures. Comprehensive evaluation across multiple performance metrics reveals that the Vision Transformer model integrated with CBAM outperforms others, achieving an accuracy of 93.46%, precision of 94%, recall of 93%, F1-score of 93%, and specificity of 93.67%. These results underscore the significant potential of the proposed system in supporting medical professionals with accurate and efficient prognostic tools for diagnosing a broad spectrum of skin lesions. The dataset and code used in this study can be found at https://github.com/akabircs/Skin-Lesions-Classification.
URLs: https://github.com/akabircs/Skin-Lesions-Classification.
Authors: Johann Wenckstern, Eeshaan Jain, Kiril Vasilev, Matteo Pariset, Andreas Wicki, Gabriele Gut, Charlotte Bunne
Abstract: Spatial proteomics technologies have transformed our understanding of complex tissue architectures by enabling simultaneous analysis of multiple molecular markers and their spatial organization. The high dimensionality of these data, varying marker combinations across experiments and heterogeneous study designs pose unique challenges for computational analysis. Here, we present Virtual Tissues (VirTues), a foundation model framework for biological tissues that operates across the molecular, cellular and tissue scale. VirTues introduces innovations in transformer architecture design, including a novel tokenization scheme that captures both spatial and marker dimensions, and attention mechanisms that scale to high-dimensional multiplex data while maintaining interpretability. Trained on diverse cancer and non-cancer tissue datasets, VirTues demonstrates strong generalization capabilities without task-specific fine-tuning, enabling cross-study analysis and novel marker integration. As a generalist model, VirTues outperforms existing approaches across clinical diagnostics, biological discovery and patient case retrieval tasks, while providing insights into tissue function and disease mechanisms.
Authors: Kevin Fu, Pierce Howell, Shalin Jain, Harish Ravichandar
Abstract: Cooperative heterogeneous multi-agent tasks require agents to effectively coordinate their behaviors while accounting for their relative capabilities. Learning-based solutions to this challenge span between two extremes: i) shared-parameter methods, which encode diverse behaviors within a single architecture by assigning an ID to each agent, and are sample-efficient but result in limited behavioral diversity; ii) independent methods, which learn a separate policy for each agent, and show greater behavioral diversity but lack sample-efficiency. Prior work has also explored selective parameter-sharing, allowing for a compromise between diversity and efficiency. None of these approaches, however, effectively generalize to unseen agents or teams. We present Capability-Aware Shared Hypernetworks (CASH), a novel architecture for heterogeneous multi-agent coordination that generates sufficient diversity while maintaining sample-efficiency via soft parameter-sharing hypernetworks. Intuitively, CASH allows the team to learn common strategies using a shared encoder, which are then adapted according to the team's individual and collective capabilities with a hypernetwork, allowing for zero-shot generalization to unseen teams and agents. We present experiments across two heterogeneous coordination tasks and three standard learning paradigms (imitation learning, on- and off-policy reinforcement learning). CASH is able to outperform baseline architectures in success rate and sample efficiency when evaluated on unseen teams and agents despite using less than half of the learnable parameters.
Authors: Steffen Dereich, Arnulf Jentzen, Adrian Riekert
Abstract: Deep learning methods - usually consisting of a class of deep neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method - are nowadays omnipresent in data-driven learning problems as well as in scientific computing tasks such as optimal control (OC) and partial differential equation (PDE) problems. In practically relevant learning tasks, often not the plain-vanilla standard SGD optimization method is employed to train the considered class of DNNs but instead more sophisticated adaptive and accelerated variants of the standard SGD method such as the popular Adam optimizer are used. Inspired by the classical Polyak-Ruppert averaging approach, in this work we apply averaged variants of the Adam optimizer to train DNNs to approximately solve exemplary scientific computing problems in the form of PDEs and OC problems. We test the averaged variants of Adam in a series of learning problems including physics-informed neural network (PINN), deep backward stochastic differential equation (deep BSDE), and deep Kolmogorov approximations for PDEs (such as heat, Black-Scholes, Burgers, and Allen-Cahn PDEs), including DNN approximations for OC problems, and including DNN approximations for image classification problems (ResNet for CIFAR-10). In each of the numerical examples the employed averaged variants of Adam outperform the standard Adam and the standard SGD optimizers, particularly, in the situation of the scientific machine learning problems. The Python source codes for the numerical experiments associated to this work can be found on GitHub at https://github.com/deeplearningmethods/averaged-adam.
Authors: Akhil S Anand, Shambhuraj Sawant, Dirk Reinhardt, Sebastien Gros
Abstract: AI models that predict the future behavior of a system (a.k.a. predictive AI models) are central to intelligent decision-making. However, decision-making using predictive AI models often results in suboptimal performance. This is primarily because AI models are typically constructed to best fit the data, and hence to predict the most likely future rather than to enable high-performance decision-making. The hope that such prediction enables high-performance decisions is neither guaranteed in theory nor established in practice. In fact, there is increasing empirical evidence that predictive models must be tailored to decision-making objectives for performance. In this paper, we establish formal (necessary and sufficient) conditions that a predictive model (AI-based or not) must satisfy for a decision-making policy established using that model to be optimal. We then discuss their implications for building predictive AI models for sequential decision-making.
Authors: Yongqi Dong, Bart van Arem, Haneen Farah
Abstract: Automated Vehicles (AVs) hold promise for revolutionizing transportation by improving road safety, traffic efficiency, and overall mobility. Despite the steady advancement in high-level AVs in recent years, the transition to full automation entails a period of mixed traffic, where AVs of varying automation levels coexist with human-driven vehicles (HDVs). Making AVs socially compliant and understood by human drivers is expected to improve the safety and efficiency of mixed traffic. Thus, ensuring AVs compatibility with HDVs and social acceptance is crucial for their successful and seamless integration into mixed traffic. However, research in this critical area of developing Socially Compliant AVs (SCAVs) remains sparse. This study carries out the first comprehensive scoping review to assess the current state of the art in developing SCAVs, identifying key concepts, methodological approaches, and research gaps. An expert interview was also conducted to identify critical research gaps and expectations towards SCAVs. Based on the scoping review and expert interview input, a conceptual framework is proposed for the development of SCAVs. The conceptual framework is evaluated using an online survey targeting researchers, technicians, policymakers, and other relevant professionals worldwide. The survey results provide valuable validation and insights, affirming the significance of the proposed conceptual framework in tackling the challenges of integrating AVs into mixed-traffic environments. Additionally, future research perspectives and suggestions are discussed, contributing to the research and development agenda of SCAVs.
Authors: Guojun Xiong, Haichuan Wang, Yuqi Pan, Saptarshi Mandal, Sanket Shah, Niclas Boehmer, Milind Tambe
Abstract: Restless multi-armed bandits (RMABs) have been highly successful in optimizing sequential resource allocation across many domains. However, in many practical settings with highly scarce resources, where each agent can only receive at most one resource, such as healthcare intervention programs, the standard RMAB framework falls short. To tackle such scenarios, we introduce Finite-Horizon Single-Pull RMABs (SPRMABs), a novel variant in which each arm can only be pulled once. This single-pull constraint introduces additional complexity, rendering many existing RMAB solutions suboptimal or ineffective. %To address this, we propose using dummy states to duplicate the system, ensuring that once an arm is activated, it transitions exclusively within the dummy states. To address this shortcoming, we propose using \textit{dummy states} that expand the system and enforce the one-pull constraint. We then design a lightweight index policy for this expanded system. For the first time, we demonstrate that our index policy achieves a sub-linearly decaying average optimality gap of $\tilde{\mathcal{O}}\left(\frac{1}{\rho^{1/2}}\right)$ for a finite number of arms, where $\rho$ is the scaling factor for each arm cluster. Extensive simulations validate the proposed method, showing robust performance across various domains compared to existing benchmarks.
Authors: Aur\'elien Decelle, Alfonso de Jes\'us Navas G\'omez, Beatriz Seoane
Abstract: Maximum-entropy methods, rooted in the inverse Ising/Potts problem from statistical mechanics, have become indispensable tools for modeling pairwise interactions in disciplines such as bioinformatics, ecology, and neuroscience. Despite their remarkable success, these methods often overlook high-order interactions that may be crucial in complex systems. Conversely, while modern machine learning approaches can capture such interactions, existing interpretable frameworks are computationally expensive, making it impractical to assess the relevance of high-order interactions in real-world scenarios. Restricted Boltzmann Machines (RBMs) offer a computationally efficient alternative by encoding statistical correlations via hidden nodes in a bipartite neural network. Here, we present a method that maps RBMs exactly onto generalized Potts models with interactions of arbitrary high order. This approach leverages large-$N$ approximations, facilitated by the simple architecture of the RBM, to enable the efficient extraction of effective many-body couplings with minimal computational cost. This mapping also enables the development of a general formal framework for the extraction of effective higher-order interactions in arbitrarily complex probabilistic models. Additionally, we introduce a robust formalism for gauge fixing within the generalized Potts model. We validate our method by accurately recovering two- and three-body interactions from synthetic datasets. Additionally, applying our framework to protein sequence data demonstrates its effectiveness in reconstructing protein contact maps, achieving performance comparable to state-of-the-art inverse Potts models. These results position RBMs as a powerful and efficient tool for investigating high-order interactions in complex systems.
Authors: Neha Verma, Kenton Murray, Kevin Duh
Abstract: With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the memory constraints of different hardware. In this work, we present a novel approach to model compression by merging similar parameter groups within a model, rather than pruning away less important parameters. Specifically, we select, align, and merge separate feed-forward sublayers in Transformer models, and test our method on language modeling, image classification, and machine translation. With our method, we demonstrate performance comparable to the original models while combining more than a third of model feed-forward sublayers, and demonstrate improved performance over a strong layer-pruning baseline. For instance, we can remove over 21% of total parameters from a Vision Transformer, while maintaining 99% of its original performance. Additionally, we observe that some groups of feed-forward sublayers exhibit high activation similarity, which may help explain their surprising mergeability.
Authors: Jonah Marks, Joseph Gomes
Abstract: Transition states are a critical bottleneck in chemical transformations. Significant efforts have been made to develop algorithms that efficiently locate transition states on potential energy surfaces. However, the computational cost of ab-initio potential energy surface evaluation limits the size of chemical systems that can routinely studied. In this work, we develop and fine-tune a graph neural network potential energy function suitable for describing organic chemical reactions and use it to rapidly identify transition state guess structures. We successfully refine guess structures and locate a transition state in each test system considered and reduce the average number of ab-initio calculations by 47% though use of the graph neural network potential energy function. Our results show that modern machine learning models have reached levels of reliability whereby they can be used to accelerate routine computational chemistry tasks.
Authors: Sheng Zhang, Yunhao Fan, Kotaro Shimizu, Gia-Wei Chern
Abstract: We review the recent development of machine-learning (ML) force-field frameworks for Landau-Lifshitz-Gilbert (LLG) dynamics simulations of itinerant electron magnets, focusing on the general theory and implementations of symmetry-invariant representations of spin configurations. The crucial properties that such magnetic descriptors must satisfy are differentiability with respect to spin rotations and invariance to both lattice point-group symmetry and internal spin rotation symmetry. We propose an efficient implementation based on the concept of reference irreducible representations, modified from the group-theoretical power-spectrum and bispectrum methods. The ML framework is demonstrated using the s-d models, which are widely applied in spintronics research. We show that LLG simulations based on local fields predicted by the trained ML models successfully reproduce representative non-collinear spin structures, including 120$^\circ$, tetrahedral, and skyrmion crystal orders of the triangular-lattice s-d models. Large-scale thermal quench simulations enabled by ML models further reveal intriguing freezing dynamics and glassy stripe states consisting of skyrmions and bi-merons. Our work highlights the utility of ML force-field approach to dynamical modeling of complex spin orders in itinerant electron magnets.
Authors: Armin Askari, Alexandre d'Aspremont, Laurent El Ghaoui
Abstract: Due to its linear complexity, naive Bayes classification remains an attractive supervised learning method, especially in very large-scale settings. We propose a sparse version of naive Bayes, which can be used for feature selection. This leads to a combinatorial maximum-likelihood problem, for which we provide an exact solution in the case of binary data, or a bound in the multinomial case. We prove that our convex relaxation bounds becomes tight as the marginal contribution of additional features decreases, using a priori duality gap bounds dervied from the Shapley-Folkman theorem. We show how to produce primal solutions satisfying these bounds. Both binary and multinomial sparse models are solvable in time almost linear in problem size, representing a very small extra relative cost compared to the classical naive Bayes. Numerical experiments on text data show that the naive Bayes feature selection method is as statistically effective as state-of-the-art feature selection methods such as recursive feature elimination, $l_1$-penalized logistic regression and LASSO, while being orders of magnitude faster.
Authors: Xiuqin Xu, Hanqiu Peng, Ying Chen
Abstract: Modern time series data often display complex nonlinear dependencies along with irregular regime-switching behaviors. These features present technical challenges in modeling, inference, and in offering insightful understanding into the underlying stochastic phenomena. To tackle these challenges, we introduce a novel modeling framework known as the Deep Switching State Space Model (DS$^3$M). This framework is engineered to make accurate forecasts for such time series while adeptly identifying the irregular regimes hidden within the dynamics. These identifications not only have significant economic ramifications but also contribute to a deeper understanding of the underlying phenomena. In DS$^3$M, the architecture employs discrete latent variables to represent regimes and continuous latent variables to account for random driving factors. By melding a Recurrent Neural Network (RNN) with a nonlinear Switching State Space Model (SSSM), we manage to capture the nonlinear dependencies and irregular regime-switching behaviors, governed by a Markov chain and parameterized using multilayer perceptrons. We validate the effectiveness and regime identification capabilities of DS$^3$M through short- and long-term forecasting tests on a wide array of simulated and real-world datasets, spanning sectors such as healthcare, economics, traffic, meteorology, and energy. Experimental results reveal that DS$^3$M outperforms several state-of-the-art models in terms of forecasting accuracy, while providing meaningful regime identifications.
Authors: T. Windeatt
Abstract: Despite being effective in many application areas, Deep Neural Networks (DNNs) are vulnerable to being attacked. In object recognition, the attack takes the form of a small perturbation added to an image, that causes the DNN to misclassify, but to a human appears no different. Adversarial attacks lead to defences that are themselves subject to attack, and the attack/ defence strategies provide important information about the properties of DNNs. In this paper, a novel method of detecting adversarial attacks is proposed for an ensemble of Deep Neural Networks (DNNs) solving two-class pattern recognition problems. The ensemble is combined using Walsh coefficients which are capable of approximating Boolean functions and thereby controlling the decision boundary complexity. The hypothesis in this paper is that decision boundaries with high curvature allow adversarial perturbations to be found, but change the curvature of the decision boundary, which is then approximated in a different way by Walsh coefficients compared to the clean images. Besides controlling boundary complexity, the coefficients also measure the correlation with class labels, which may aid in understanding the learning and transferability properties of DNNs. While the experiments here use images, the proposed approach of modelling two-class ensemble decision boundaries could in principle be applied to any application area.
Authors: Xiaoying Zhi, Varun Babbar, Rundong Liu, Pheobe Sun, Fran Silavong, Ruibo Shi, Sean Moran
Abstract: The subject of green AI has been gaining attention within the deep learning community given the recent trend of ever larger and more complex neural network models. Existing solutions for reducing the computational load of training at inference time usually involve pruning the network parameters. Pruning schemes often create extra overhead either by iterative training and fine-tuning for static pruning or repeated computation of a dynamic pruning graph. We propose a new parameter pruning strategy for learning a lighter-weight sub-network that minimizes the energy cost while maintaining comparable performance to the fully parameterised network on given downstream tasks. Our proposed pruning scheme is green-oriented, as it only requires a one-off training to discover the optimal static sub-networks by dynamic pruning methods. The pruning scheme consists of a binary gating module and a polarizing loss function to uncover sub-networks with user-defined sparsity. Our method enables pruning and training simultaneously, which saves energy in both the training and inference phases and avoids extra computational overhead from gating modules at inference time. Our results on CIFAR-10, CIFAR-100, and Tiny Imagenet suggest that our scheme can remove 50% of connections in deep networks with <1% reduction in classification accuracy. Compared to other related pruning methods, our method demonstrates a lower drop in accuracy for equivalent reductions in computational cost.
Authors: Haochen Shi, Xinyao Liu, Fengmao Lv, Hongtao Xue, Jie Hu, Shengdong Du, Tianrui Li
Abstract: In the era of big data, the issue of data quality has become increasingly prominent. One of the main challenges is the problem of duplicate data, which can arise from repeated entry or the merging of multiple data sources. These "dirty data" problems can significantly limit the effective application of big data. To address the issue of data deduplication, we propose a pre-trained deduplication model based on active learning, which is the first work that utilizes active learning to address the problem of deduplication at the semantic level. The model is built on a pre-trained Transformer and fine-tuned to solve the deduplication problem as a sequence to classification task, which firstly integrate the transformer with active learning into an end-to-end architecture to select the most valuable data for deduplication model training, and also firstly employ the R-Drop method to perform data augmentation on each round of labeled data, which can reduce the cost of manual labeling and improve the model's performance. Experimental results demonstrate that our proposed model outperforms previous state-of-the-art (SOTA) for deduplicated data identification, achieving up to a 28% improvement in Recall score on benchmark datasets.
Authors: Bingxu Zhang, Changjun Fan, Shixuan Liu, Kuihua Huang, Xiang Zhao, Jincai Huang, Zhong Liu
Abstract: Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power. Early works in this domain mainly focus on studying the graph isomorphism recognition ability of GNNs, and recent works try to leverage the properties such as subgraph counting and connectivity learning to characterize the expressive power of GNNs, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for models for enhancing expressive power under different forms of definition. Concretely, the models are reviewed based on three categories, i.e., Graph feature enhancement, Graph topology enhancement, and GNNs architecture enhancement.
Authors: Younghyun Cho, James W. Demmel, Micha{\l} Derezi\'nski, Haoyun Li, Hengrui Luo, Michael W. Mahoney, Riley J. Murray
Abstract: Algorithms from Randomized Numerical Linear Algebra (RandNLA) are known to be effective in handling high-dimensional computational problems, providing high-quality empirical performance as well as strong probabilistic guarantees. However, their practical application is complicated by the fact that the user needs to set various algorithm-specific tuning parameters which are different than those used in traditional NLA. This paper demonstrates how a surrogate-based autotuning approach can be used to address fundamental problems of parameter selection in RandNLA algorithms. In particular, we provide a detailed investigation of surrogate-based autotuning for sketch-and-precondition (SAP) based randomized least squares methods, which have been one of the great success stories in modern RandNLA. Empirical results show that our surrogate-based autotuning approach can achieve near-optimal performance with much less tuning cost than a random search (up to about 4x fewer trials of different parameter configurations). Moreover, while our experiments focus on least squares, our results demonstrate a general-purpose autotuning pipeline applicable to any kind of RandNLA algorithm.
Authors: Kathl\'en Kohn, Anna-Laura Sattelberger, Vahid Shahverdi
Abstract: The set of functions parameterized by a linear fully-connected neural network is a determinantal variety. We investigate the subvariety of functions that are equivariant or invariant under the action of a permutation group. Examples of such group actions are translations or $90^\circ$ rotations on images. We describe such equivariant or invariant subvarieties as direct products of determinantal varieties, from which we deduce their dimension, degree, Euclidean distance degree, and their singularities. We fully characterize invariance for arbitrary permutation groups, and equivariance for cyclic groups. We draw conclusions for the parameterization and the design of equivariant and invariant linear networks in terms of sparsity and weight-sharing properties. We prove that all invariant linear functions can be parameterized by a single linear autoencoder with a weight-sharing property imposed by the cycle decomposition of the considered permutation. The space of rank-bounded equivariant functions has several irreducible components, so it can not be parameterized by a single network-but each irreducible component can. Finally, we show that minimizing the squared-error loss on our invariant or equivariant networks reduces to minimizing the Euclidean distance from determinantal varieties via the Eckart-Young theorem.
Authors: Zahra Alijani, Vojtech Molek
Abstract: Designing effective neural networks requires tuning architectural elements. This study integrates fractional calculus into neural networks by introducing fractional order derivatives (FDO) as tunable parameters in activation functions, allowing diverse activation functions by adjusting the FDO. We evaluate these fractional activation functions on various datasets and network architectures, comparing their performance with traditional and new activation functions. Our experiments assess their impact on accuracy, time complexity, computational overhead, and memory usage. Results suggest fractional activation functions, particularly fractional Sigmoid, offer benefits in some scenarios. Challenges related to consistency and efficiency remain. Practical implications and limitations are discussed.
Authors: Zilong Zhao, Robert Birke, Lydia Chen
Abstract: Tabular data synthesis is crucial for addressing privacy and security concerns in industries reliant on tabular data. While recent advancements adopt large language models (LLMs) for realistic tabular data generation, their long training times and limited reusability hinder practical applications. In this paper, we propose Tabula, a tabular data synthesizer that leverages the structure of LLM. Unlike state-of-the-art (SOTA) LLM-based tabular data synthesizers that rely on pre-trained LLMs, Tabula discards the pre-trained weights originally designed for natural language tasks, focusing instead on a tailored approach for tabular data. In addition, Tabula introduces a token sequence compression strategy that significantly reduces training time while maintaining data quality, alongside a novel token padding method that improves sequence alignment across training batches. Experiments on six datasets show that Tabula achieves superior synthetic data utility compared to current SOTA methods. Additionally, the results demonstrate that Tabula model trained on tabular datasets serves effectively as a foundational model for synthesizing new tabular datasets. Furthermore, the proposed padding method outperforms the conventional left and right padding strategies. Finally, the results highlight that Tabula averagely reduces training time per epoch by 46.2% compared to state-of-the-art LLM approaches while achieving higher data utility. Our code is available at https://github.com/zhao-zilong/Tabula
Authors: Qianxiong Xu, Cheng Long, Ziyue Li, Sijie Ruan, Rui Zhao, Zhishuai Li
Abstract: Sensors are commonly deployed to perceive the environment. However, due to the high cost, sensors are usually sparsely deployed. Kriging is the tailored task to infer the unobserved nodes (without sensors) using the observed source nodes (with sensors). The essence of kriging task is transferability. Recently, several inductive spatio-temporal kriging methods have been proposed based on graph neural networks, being trained based on a graph built on top of observed nodes via pretext tasks such as masking nodes out and reconstructing them. However, the graph in training is inevitably much sparser than the graph in inference that includes all the observed and unobserved nodes. The learned pattern cannot be well generalized for inference, denoted as graph gap. To address this issue, we first present a novel Increment training strategy: instead of masking nodes (and reconstructing them), we add virtual nodes into the training graph so as to mitigate the graph gap issue naturally. Nevertheless, the empty-shell virtual nodes without labels could have bad-learned features and lack supervision signals. To solve these issues, we pair each virtual node with its most similar observed node and fuse their features together; to enhance the supervision signal, we construct reliable pseudo labels for virtual nodes. As a result, the learned pattern of virtual nodes could be safely transferred to real unobserved nodes for reliable kriging. We name our new Kriging model with Increment Training Strategy as KITS. Extensive experiments demonstrate that KITS consistently outperforms existing kriging methods by large margins, e.g., the improvement over MAE score could be as high as 18.33%.
Authors: Julia A. Meister, Khuong An Nguyen
Abstract: With the proliferation of increasingly complicated Deep Learning architectures, data synthesis is a highly promising technique to address the demand of data-hungry models. However, reliably assessing the quality of a 'synthesiser' model's output is an open research question with significant associated risks for high-stake domains. To address this challenge, we propose a unique synthesis algorithm that generates data from high-confidence feature space regions based on the Conformal Prediction framework. We support our proposed algorithm with a comprehensive exploration of the core parameter's influence, an in-depth discussion of practical advice, and an extensive empirical evaluation of five benchmark datasets. To show our approach's versatility on ubiquitous real-world challenges, the datasets were carefully selected for their variety of difficult characteristics: low sample count, class imbalance, and non-separability. In all trials, training sets extended with our confident synthesised data performed at least as well as the original set and frequently significantly improved Deep Learning performance by up to 61 percentage points F1-score.
Authors: Zhiyu Liu, Zhi Han, Yandong Tang, Xi-Le Zhao, Yao Wang
Abstract: This paper considers the problem of recovering a tensor with an underlying low-tubal-rank structure from a small number of corrupted linear measurements. Traditional approaches tackling such a problem require the computation of tensor Singular Value Decomposition (t-SVD), that is a computationally intensive process, rendering them impractical for dealing with large-scale tensors. Aim to address this challenge, we propose an efficient and effective low-tubal-rank tensor recovery method based on a factorization procedure akin to the Burer-Monteiro (BM) method. Precisely, our fundamental approach involves decomposing a large tensor into two smaller factor tensors, followed by solving the problem through factorized gradient descent (FGD). This strategy eliminates the need for t-SVD computation, thereby reducing computational costs and storage requirements. We provide rigorous theoretical analysis to ensure the convergence of FGD under both noise-free and noisy situations. Additionally, it is worth noting that our method does not require the precise estimation of the tensor tubal-rank. Even in cases where the tubal-rank is slightly overestimated, our approach continues to demonstrate robust performance. A series of experiments have been carried out to demonstrate that, as compared to other popular ones, our approach exhibits superior performance in multiple scenarios, in terms of the faster computational speed and the smaller convergence error.
Authors: Guruprerana Shabadi, Nathana\"el Fijalkow, Th\'eo Matricon
Abstract: The field of reinforcement learning (RL) is concerned with algorithms for learning optimal policies in unknown stochastic environments. Programmatic RL studies representations of policies as programs, meaning involving higher order constructs such as control loops. Despite attracting a lot of attention at the intersection of the machine learning and formal methods communities, very little is known on the theoretical front about programmatic RL: what are good classes of programmatic policies? How large are optimal programmatic policies? How can we learn them? The goal of this paper is to give first answers to these questions, initiating a theoretical study of programmatic RL. Considering a class of gridworld environments, we define a class of programmatic policies. Our main contributions are to place upper bounds on the size of optimal programmatic policies, and to construct an algorithm for synthesizing them. These theoretical findings are complemented by a prototype implementation of the algorithm.
Authors: Yihang Gao, Chuanyang Zheng, Enze Xie, Han Shi, Tianyang Hu, Yu Li, Michael K. Ng, Zhenguo Li, Zhaoqiang Liu
Abstract: Besides natural language processing, transformers exhibit extraordinary performance in solving broader applications, including scientific computing and computer vision. Previous works try to explain this from the expressive power and capability perspectives that standard transformers are capable of performing some algorithms. To empower transformers with algorithmic capabilities and motivated by the recently proposed looped transformer, we design a novel transformer framework, dubbed Algorithm Transformer (abbreviated as AlgoFormer). We provide an insight that efficient transformer architectures can be designed by leveraging prior knowledge of tasks and the underlying structure of potential algorithms. Compared with the standard transformer and vanilla looped transformer, the proposed AlgoFormer can perform efficiently in algorithm representation in some specific tasks. In particular, inspired by the structure of human-designed learning algorithms, our transformer framework consists of a pre-transformer that is responsible for task preprocessing, a looped transformer for iterative optimization algorithms, and a post-transformer for producing the desired results after post-processing. We provide theoretical evidence of the expressive power of the AlgoFormer in solving some challenging problems, mirroring human-designed algorithms. Furthermore, some theoretical and empirical results are presented to show that the designed transformer has the potential to perform algorithm representation and learning. Experimental results demonstrate the empirical superiority of the proposed transformer in that it outperforms the standard transformer and vanilla looped transformer in some specific tasks. An extensive experiment on real language tasks (e.g., neural machine translation of German and English, and text classification) further validates the expressiveness and effectiveness of AlgoFormer.
Authors: Antonina Krajewska, Ewa Niewiadomska-Szynkiewicz
Abstract: We present a novel method for matrix completion, specifically designed for matrices where one dimension significantly exceeds the other. Our Columns Selected Matrix Completion (CSMC) method combines Column Subset Selection and Low-Rank Matrix Completion to efficiently reconstruct incomplete datasets. In each step, CSMC solves a convex optimization problem. We introduce two algorithms to implement CSMC, each tailored to problems of different sizes. A formal analysis is provided, outlining the necessary assumptions and the probability of obtaining a correct solution. To assess the impact of matrix size, rank, and the ratio of missing entries on solution quality and computation time, we conducted experiments on synthetic data. The method was also applied to two real-world problems: recommendation systems and image inpainting. Our results show that CSMC provides solutions of the same quality as state-of-the-art matrix completion algorithms based on convex optimization, while achieving significant reductions in computational runtime.
Authors: Dawei Zhan
Abstract: Bayesian optimization (BO) algorithm is very popular for solving low-dimensional expensive optimization problems. Extending Bayesian optimization to high dimension is a meaningful but challenging task. One of the major challenges is that it is difficult to find good infill solutions as the acquisition functions are also high-dimensional. In this work, we propose the expected coordinate improvement (ECI) criterion for high-dimensional Bayesian optimization. The proposed ECI criterion measures the potential improvement we can get by moving the current best solution along one coordinate. The proposed approach selects the coordinate with the highest ECI value to refine in each iteration and covers all the coordinates gradually by iterating over the coordinates. The greatest advantage of the proposed ECI-BO (expected coordinate improvement based Bayesian optimization) algorithm over the standard BO algorithm is that the infill selection problem of the proposed algorithm is always a one-dimensional problem thus can be easily solved. Numerical experiments show that the proposed algorithm can achieve significantly better results than the standard BO algorithm and competitive results when compared with five state-of-the-art high-dimensional BOs. This work provides a simple but efficient approach for high-dimensional Bayesian optimization.
Authors: Sike Wang, Pan Zhou, Jia Li, Hua Huang
Abstract: Second-order optimizers, maintaining a matrix termed a preconditioner, are superior to first-order optimizers in both theory and practice. The states forming the preconditioner and its inverse root restrict the maximum size of models trained by second-order optimizers. To address this, compressing 32-bit optimizer states to lower bitwidths has shown promise in reducing memory usage. However, current approaches only pertain to first-order optimizers. In this paper, we propose the first 4-bit second-order optimizers, exemplified by 4-bit Shampoo, maintaining performance similar to that of 32-bit ones. We show that quantizing the eigenvector matrix of the preconditioner in 4-bit Shampoo is remarkably better than quantizing the preconditioner itself both theoretically and experimentally. By rectifying the orthogonality of the quantized eigenvector matrix, we enhance the approximation of the preconditioner's eigenvector matrix, which also benefits the computation of its inverse 4-th root. Besides, we find that linear square quantization slightly outperforms dynamic tree quantization when quantizing second-order optimizer states. Evaluation on various networks for image classification and natural language modeling demonstrates that our 4-bit Shampoo achieves comparable performance to its 32-bit counterpart while being more memory-efficient.
Authors: Francisco B\'erchez-Moreno, V\'ictor M. Vargas, Rafael Ayll\'on-Gavil\'an, David Guijo-Rubio, C\'esar Herv\'as-Mart\'inez, Juan C. Fern\'andez, Pedro A. Guti\'errez
Abstract: dlordinal is a new Python library that unifies many recent deep ordinal classification methodologies available in the literature. Developed using PyTorch as underlying framework, it implements the top performing state-of-the-art deep learning techniques for ordinal classification problems. Ordinal approaches are designed to leverage the ordering information present in the target variable. Specifically, it includes loss functions, various output layers, dropout techniques, soft labelling methodologies, and other classification strategies, all of which are appropriately designed to incorporate the ordinal information. Furthermore, as the performance metrics to assess novel proposals in ordinal classification depend on the distance between target and predicted classes in the ordinal scale, suitable ordinal evaluation metrics are also included. dlordinal is distributed under the BSD-3-Clause license and is available at https://github.com/ayrna/dlordinal.
Authors: Charlie Blake, Constantin Eichenberg, Josef Dean, Lukas Balles, Luke Y. Prince, Bj\"orn Deiseroth, Andres Felipe Cruz-Salinas, Carlo Luschi, Samuel Weinbach, Douglas Orr
Abstract: The Maximal Update Parametrization ($\mu$P) aims to make the optimal hyperparameters (HPs) of a model independent of its size, allowing them to be swept using a cheap proxy model rather than the full-size target model. We present a new scheme, u-$\mu$P, which improves upon $\mu$P by combining it with Unit Scaling, a method for designing models that makes them easy to train in low-precision. The two techniques have a natural affinity: $\mu$P ensures that the scale of activations is independent of model size, and Unit Scaling ensures that activations, weights and gradients begin training with a scale of one. This synthesis opens the door to a simpler scheme, whose default values are near-optimal. This in turn facilitates a more efficient sweeping strategy, with u-$\mu$P models reaching a loss that is equal to or lower than comparable $\mu$P models and working out-of-the-box in FP8.
Authors: Kira M. D\"usterwald, Samo Hromadka, Makoto Yamada
Abstract: The performance of unsupervised methods such as clustering depends on the choice of distance metric between features, or ground metric. Commonly, ground metrics are decided with heuristics or learned via supervised algorithms. However, since many interesting datasets are unlabelled, unsupervised ground metric learning approaches have been introduced. One promising option employs Wasserstein singular vectors (WSVs), which emerge when computing optimal transport distances between features and samples simultaneously. WSVs are effective, but can be prohibitively computationally expensive in some applications: $\mathcal{O}(n^2m^2(n \log(n) + m \log(m))$ for $n$ samples and $m$ features. In this work, we propose to augment the WSV method by embedding samples and features on trees, on which we compute the tree-Wasserstein distance (TWD). We demonstrate theoretically and empirically that the algorithm converges to a better approximation of the standard WSV approach than the best known alternatives, and does so with $\mathcal{O}(n^3+m^3+mn)$ complexity. In addition, we prove that the initial tree structure can be chosen flexibly, since tree geometry does not constrain the richness of the approximation up to the number of edge weights. This proof suggests a fast and recursive algorithm for computing the tree parameter basis set, which we find crucial to realising the efficiency gains at scale. Finally, we employ the tree-WSV algorithm to several single-cell RNA sequencing genomics datasets, demonstrating its scalability and utility for unsupervised cell-type clustering problems. These results poise unsupervised ground metric learning with TWD as a low-rank approximation of WSV with the potential for widespread application.
Authors: Jiahai Feng, Stuart Russell, Jacob Steinhardt
Abstract: Pretrained language models (LMs) can generalize to implications of facts that they are finetuned on. For example, if finetuned on ``John Doe lives in Tokyo," LMs can correctly answer ``What language do the people in John Doe's city speak?'' with ``Japanese''. However, little is known about the mechanisms that enable this generalization or how they are learned during pretraining. We introduce extractive structures as a framework for describing how components in LMs (e.g., MLPs or attention heads) coordinate to enable this generalization. The structures consist of informative components that store training facts as weight changes, and upstream and downstream extractive components that query and process the stored information to produce the correct implication. We hypothesize that extractive structures are learned during pretraining when encountering implications of previously known facts. This yields two predictions: a data ordering effect where extractive structures can be learned only if facts precede their implications, and a weight grafting effect where extractive structures can be transferred to predict counterfactual implications. We empirically demonstrate these phenomena in the OLMo-7b, Llama 3-8b, Gemma 2-9b, and Qwen 2-7b models. Of independent interest, our results also indicate that fact learning can occur at both early and late layers, which lead to different forms of generalization.
Authors: Xianliang Xu, Ye Li, Zhongyi Huang
Abstract: Neural operators are aiming at approximating operators mapping between Banach spaces of functions, achieving much success in the field of scientific computing. Compared to certain deep learning-based solvers, such as Physics-Informed Neural Networks (PINNs), Deep Ritz Method (DRM), neural operators can solve a class of Partial Differential Equations (PDEs). Although much work has been done to analyze the approximation and generalization error of neural operators, there is still a lack of analysis on their training error. In this work, we conduct the convergence analysis of gradient descent for the wide shallow neural operators and physics-informed shallow neural operators within the framework of Neural Tangent Kernel (NTK). The core idea lies on the fact that over-parameterization and random initialization together ensure that each weight vector remains near its initialization throughout all iterations, yielding the linear convergence of gradient descent. In this work, we demonstrate that under the setting of over-parametrization, gradient descent can find the global minimum regardless of whether it is in continuous time or discrete time.
Authors: Jonathan Garc\'ia, Philipp Petersen
Abstract: We prove that a classifier with a Barron-regular decision boundary can be approximated with a rate of high polynomial degree by ReLU neural networks with three hidden layers when a margin condition is assumed. In particular, for strong margin conditions, high-dimensional discontinuous classifiers can be approximated with a rate that is typically only achievable when approximating a low-dimensional smooth function. We demonstrate how these expression rate bounds imply fast-rate learning bounds that are close to $n^{-1}$ where $n$ is the number of samples. In addition, we carry out comprehensive numerical experimentation on binary classification problems with various margins. We study three different dimensions, with the highest dimensional problem corresponding to images from the MNIST data set.
Authors: Xiangfei Qiu, Xingjian Wu, Yan Lin, Chenjuan Guo, Jilin Hu, Bin Yang
Abstract: Multivariate time series forecasting is crucial for various applications, such as financial investment, energy management, weather forecasting, and traffic optimization. However, accurate forecasting is challenging due to two main factors. First, real-world time series often show heterogeneous temporal patterns caused by distribution shifts over time. Second, correlations among channels are complex and intertwined, making it hard to model the interactions among channels precisely and flexibly. In this study, we address these challenges by proposing a general framework called DUET, which introduces dual clustering on the temporal and channel dimensions to enhance multivariate time series forecasting. First, we design a Temporal Clustering Module (TCM) that clusters time series into fine-grained distributions to handle heterogeneous temporal patterns. For different distribution clusters, we design various pattern extractors to capture their intrinsic temporal patterns, thus modeling the heterogeneity. Second, we introduce a novel Channel-Soft-Clustering strategy and design a Channel Clustering Module (CCM), which captures the relationships among channels in the frequency domain through metric learning and applies sparsification to mitigate the adverse effects of noisy channels. Finally, DUET combines TCM and CCM to incorporate both the temporal and channel dimensions. Extensive experiments on 25 real-world datasets from 10 application domains, demonstrate the state-of-the-art performance of DUET.
Authors: Zihao Zheng, Yuanchun Li, Jiayu Chen, Peng Zhou, Xiang Chen, Yunxin Liu
Abstract: Enhancing the computational efficiency of on-device Deep Neural Networks (DNNs) remains a significant challengein mobile and edge computing. As we aim to execute increasingly complex tasks with constrained computational resources, much of the research has focused on compressing neural network structures and optimizing systems. Although many studies have focused on compressing neural network structures and parameters or optimizing underlying systems, there has been limited attention on optimizing the fundamental building blocks of neural networks: the neurons. In this study, we deliberate on a simple but important research question: Can we design artificial neurons that offer greater efficiency than the traditional neuron paradigm? Inspired by the threshold mechanisms and the excitation-inhibition balance observed in biological neurons, we propose a novel artificial neuron model, Threshold Neurons. Using Threshold Neurons, we can construct neural networks similar to those with traditional artificial neurons, while significantly reducing hardware implementation complexity. Our extensive experiments validate the effectiveness of neural networks utilizing Threshold Neurons, achieving substantial power savings of 7.51x to 8.19x and area savings of 3.89x to 4.33x at the kernel level, with minimal loss in precision. Furthermore, FPGA-based implementations of these networks demonstrate 2.52x power savings and 1.75x speed enhancements at the system level. The source code will be made available upon publication.
Authors: Daniel Paleka, Abhimanyu Pallavi Sudhir, Alejandro Alvarez, Vineeth Bhat, Adam Shen, Evan Wang, Florian Tram\`er
Abstract: Forecasting is a task that is difficult to evaluate: the ground truth can only be known in the future. Recent work showing LLM forecasters rapidly approaching human-level performance begs the question: how can we benchmark and evaluate these forecasters instantaneously? Following the consistency check framework, we measure the performance of forecasters in terms of the consistency of their predictions on different logically-related questions. We propose a new, general consistency metric based on arbitrage: for example, if a forecasting AI illogically predicts that both the Democratic and Republican parties have 60% probability of winning the 2024 US presidential election, an arbitrageur can trade against the forecaster's predictions and make a profit. We build an automated evaluation system that generates a set of base questions, instantiates consistency checks from these questions, elicits the predictions of the forecaster, and measures the consistency of the predictions. We then build a standard, proper-scoring-rule forecasting benchmark, and show that our (instantaneous) consistency metrics correlate with LLM forecasters' ground truth Brier scores (which are only known in the future). We also release a consistency benchmark that resolves in 2028, providing a long-term evaluation tool for forecasting.
Authors: Changchang Yin, Shihan Fu, Bingsheng Yao, Thai-Hoang Pham, Weidan Cao, Dakuo Wang, Jeffrey Caterino, Ping Zhang
Abstract: Sepsis is an organ dysfunction caused by a deregulated immune response to an infection. Early sepsis prediction and identification allow for timely intervention, leading to improved clinical outcomes. Clinical calculators (e.g., the six-organ dysfunction assessment of SOFA) play a vital role in sepsis identification within clinicians' workflow, providing evidence-based risk assessments essential for sepsis diagnosis. However, artificial intelligence (AI) sepsis prediction models typically generate a single sepsis risk score without incorporating clinical calculators for assessing organ dysfunctions, making the models less convincing and transparent to clinicians. To bridge the gap, we propose to mimic clinicians' workflow with a novel framework SepsisCalc to integrate clinical calculators into the predictive model, yielding a clinically transparent and precise model for utilization in clinical settings. Practically, clinical calculators usually combine information from multiple component variables in Electronic Health Records (EHR), and might not be applicable when the variables are (partially) missing. We mitigate this issue by representing EHRs as temporal graphs and integrating a learning module to dynamically add the accurately estimated calculator to the graphs. Experimental results on real-world datasets show that the proposed model outperforms state-of-the-art methods on sepsis prediction tasks. Moreover, we developed a system to identify organ dysfunctions and potential sepsis risks, providing a human-AI interaction tool for deployment, which can help clinicians understand the prediction outputs and prepare timely interventions for the corresponding dysfunctions, paving the way for actionable clinical decision-making support for early intervention.
Authors: Guoxing Tang, Yugen Du, Xia Chen, Yingwei Luo, Benchi Ma
Abstract: Nowadays, there are many similar services available on the internet, making Quality of Service (QoS) a key concern for users. Since collecting QoS values for all services through user invocations is impractical, predicting QoS values is a more feasible approach. Matrix factorization is considered an effective prediction method. However, most existing matrix factorization algorithms focus on capturing global similarities between users and services, overlooking the local similarities between users and their similar neighbors, as well as the non-interactive effects between users and services. This paper proposes a matrix factorization approach based on user information entropy and region bias, which utilizes a similarity measurement method based on fuzzy information entropy to identify similar neighbors of users. Simultaneously, it integrates the region bias between each user and service linearly into matrix factorization to capture the non-interactive features between users and services. This method demonstrates improved predictive performance in more realistic and complex network environments. Additionally, numerous experiments are conducted on real-world QoS datasets. The experimental results show that the proposed method outperforms some of the state-of-the-art methods in the field at matrix densities ranging from 5% to 20%.
Authors: Sanghyeon Park, Soo-Mook Moon
Abstract: Large deep learning models have achieved remarkable success but are resource-intensive, posing challenges such as memory usage. We introduce CURing, a novel model compression method based on CUR matrix decomposition, which approximates weight matrices as the product of selected columns (C) and rows (R), and a small linking matrix (U). We apply this decomposition to weights chosen based on the combined influence of their magnitudes and activations. By identifying and retaining informative rows and columns, CURing significantly reduces model size with minimal performance loss. For example, it reduces Llama3.1-8B's parameters to 7.32B (-9%) in just 129 seconds, over 20 times faster than prior compression methods.
Authors: Benjamin J. Choi, Griffin Milsap, Clara A. Scholl, Francesco Tenore, Mattson Ogg
Abstract: Current machine learning (ML)-based algorithms for filtering electroencephalography (EEG) time series data face challenges related to cumbersome training times, regularization, and accurate reconstruction. To address these shortcomings, we present an ML filtration algorithm driven by a logistic covariance-targeted adversarial denoising autoencoder (TADA). We hypothesize that the expressivity of a targeted, correlation-driven convolutional autoencoder will enable effective time series filtration while minimizing compute requirements (e.g., runtime, model size). Furthermore, we expect that adversarial training with covariance rescaling will minimize signal degradation. To test this hypothesis, a TADA system prototype was trained and evaluated on the task of removing electromyographic (EMG) noise from EEG data in the EEGdenoiseNet dataset, which includes EMG and EEG data from 67 subjects. The TADA filter surpasses conventional signal filtration algorithms across quantitative metrics (Correlation Coefficient, Temporal RRMSE, Spectral RRMSE), and performs competitively against other deep learning architectures at a reduced model size of less than 400,000 trainable parameters. Further experimentation will be necessary to assess the viability of TADA on a wider range of deployment cases.
Authors: Willian T. Lunardi, Abdulrahman Banabila, Dania Herzalla, Martin Andreoni
Abstract: Anomaly detection involves identifying data patterns that deviate from the anticipated norm. Traditional methods struggle in high-dimensional spaces due to the curse of dimensionality. In recent years, self-supervised learning, particularly through contrastive objectives, has driven advances in anomaly detection. However, vanilla contrastive learning struggles to align with the unique demands of anomaly detection, as it lacks a pretext task tailored to the homogeneous nature of In-Distribution (ID) data and the diversity of Out-of-Distribution (OOD) anomalies. Methods that attempt to address these challenges, such as introducing hard negatives through synthetic outliers, Outlier Exposure (OE), and supervised objectives, often rely on pretext tasks that fail to balance compact clustering of ID samples with sufficient separation from OOD data. In this work, we propose Focused In-distribution Representation Modeling (FIRM), a contrastive learning objective specifically designed for anomaly detection. Unlike existing approaches, FIRM incorporates synthetic outliers into its pretext task in a way that actively shapes the representation space, promoting compact clustering of ID samples while enforcing strong separation from outliers. This formulation addresses the challenges of class collision, enhancing both the compactness of ID representations and the discriminative power of the learned feature space. We show that FIRM surpasses other contrastive methods in standard benchmarks, significantly enhancing anomaly detection compared to both traditional and supervised contrastive learning objectives. Our ablation studies confirm that FIRM consistently improves the quality of representations and shows robustness across a range of scoring methods. The code is available at: https://github.com/willtl/firm.
Authors: Takashi Furuya, Hiroyuki Kusumoto, Koichi Taniguchi, Naoya Kanno, Kazuma Suetake
Abstract: Gaussian mixture distributions are commonly employed to represent general probability distributions. Despite the importance of using Gaussian mixtures for uncertainty estimation, the entropy of a Gaussian mixture cannot be calculated analytically. In this paper, we study the approximate entropy represented as the sum of the entropies of unimodal Gaussian distributions with mixing coefficients. This approximation is easy to calculate analytically regardless of dimension, but there is a lack of theoretical guarantees. We theoretically analyze the approximation error between the true and the approximate entropy to reveal when this approximation works effectively. This error is essentially controlled by how far apart each Gaussian component of the Gaussian mixture is. To measure such separation, we introduce the ratios of the distances between the means to the sum of the variances of each Gaussian component of the Gaussian mixture, and we reveal that the error converges to zero as the ratios tend to infinity. In addition, the probabilistic estimate indicates that this convergence situation is more likely to occur in higher-dimensional spaces. Therefore, our results provide a guarantee that this approximation works well for high-dimensional problems, such as neural networks that involve a large number of parameters.
Authors: Nikhil Parthasarathy, S. M. Ali Eslami, Jo\~ao Carreira, Olivier J. H\'enaff
Abstract: Humans learn powerful representations of objects and scenes by observing how they evolve over time. Yet, outside of specific tasks that require explicit temporal understanding, static image pretraining remains the dominant paradigm for learning visual foundation models. We question this mismatch, and ask whether video pretraining can yield visual representations that bear the hallmarks of human perception: generalisation across tasks, robustness to perturbations, and consistency with human judgements. To that end we propose a novel procedure for curating videos, and develop a contrastive framework which learns from the complex transformations therein. This simple paradigm for distilling knowledge from videos, called VITO, yields general representations that far outperform prior video pretraining methods on image understanding tasks, and image pretraining methods on video understanding tasks. Moreover, VITO representations are significantly more robust to natural and synthetic deformations than image-, video-, and adversarially-trained ones. Finally, VITO's predictions are strongly aligned with human judgements, surpassing models that were specifically trained for that purpose. Together, these results suggest that video pretraining could be a simple way of learning unified, robust, and human-aligned representations of the visual world.
Authors: Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Shinichiro Omachi
Abstract: Image Super-Resolution (SR) is essential for a wide range of computer vision and image processing tasks. Investigating infrared (IR) image (or thermal images) super-resolution is a continuing concern within the development of deep learning. This survey aims to provide a comprehensive perspective of IR image super-resolution, including its applications, hardware imaging system dilemmas, and taxonomy of image processing methodologies. In addition, the datasets and evaluation metrics in IR image super-resolution tasks are also discussed. Furthermore, the deficiencies in current technologies and possible promising directions for the community to explore are highlighted. To cope with the rapid development in this field, we intend to regularly update the relevant excellent work at \url{https://github.com/yongsongH/Infrared_Image_SR_Survey
Authors: Armin Moin, Atta Badii, Stephan G\"unnemann, Moharram Challenger
Abstract: Various architecture frameworks for software, systems, and enterprises have been proposed in the literature. They identified several stakeholders and defined modeling perspectives, architecture viewpoints, and views to frame and address stakeholder concerns. However, the stakeholders with data science and Machine Learning (ML) related concerns, such as data scientists and data engineers, are yet to be included in existing architecture frameworks. Only this way can we envision a holistic system architecture description of an ML-enabled system. Note that the ML component behavior and functionalities are special and should be distinguished from traditional software system behavior and functionalities. The main reason is that the actual functionality should be inferred from data instead of being specified at design time. Additionally, the structural models of ML components, such as ML model architectures, are typically specified using different notations and formalisms from what the Software Engineering (SE) community uses for software structural models. Yet, these two aspects, namely ML and non-ML, are becoming so intertwined that it necessitates an extension of software architecture frameworks and modeling practices toward supporting ML-enabled system architectures. In this paper, we address this gap through an empirical study using an online survey instrument. We surveyed 61 subject matter experts from over 25 organizations in 10 countries.
Authors: Moaad Khamlich, Federico Pichi, Gianluigi Rozza
Abstract: Reduced order models (ROMs) are widely used in scientific computing to tackle high-dimensional systems. However, traditional ROM methods may only partially capture the intrinsic geometric characteristics of the data. These characteristics encompass the underlying structure, relationships, and essential features crucial for accurate modeling. To overcome this limitation, we propose a novel ROM framework that integrates optimal transport (OT) theory and neural network-based methods. Specifically, we investigate the Kernel Proper Orthogonal Decomposition (kPOD) method exploiting the Wasserstein distance as the custom kernel, and we efficiently train the resulting neural network (NN) employing the Sinkhorn algorithm. By leveraging an OT-based nonlinear reduction, the presented framework can capture the geometric structure of the data, which is crucial for accurate learning of the reduced solution manifold. When compared with traditional metrics such as mean squared error or cross-entropy, exploiting the Sinkhorn divergence as the loss function enhances stability during training, robustness against overfitting and noise, and accelerates convergence. To showcase the approach's effectiveness, we conduct experiments on a set of challenging test cases exhibiting a slow decay of the Kolmogorov n-width. The results show that our framework outperforms traditional ROM methods in terms of accuracy and computational efficiency.
Authors: Sharath Koorathota, Nikolas Papadopoulos, Jia Li Ma, Shruti Kumar, Xiaoxiao Sun, Arunesh Mittal, Patrick Adelman, Paul Sajda
Abstract: Vision Transformers (ViT) have advanced computer vision, yet their efficacy in complex tasks like driving remains less explored. This study enhances ViT by integrating human eye gaze, captured via eye-tracking, to increase prediction accuracy in driving scenarios under uncertainty in both real-world and virtual reality scenarios. First, we establish the significance of human eye gaze in left-right driving decisions, as observed in both human subjects and a ViT model. By comparing the similarity between human fixation maps and ViT attention weights, we reveal the dynamics of overlap across individual heads and layers. This overlap demonstrates that fixation data can guide the model in distributing its attention weights more effectively. We introduce the fixation-attention intersection (FAX) loss, a novel loss function that significantly improves ViT performance under high uncertainty conditions. Our results show that ViT, when trained with FAX loss, aligns its attention with human gaze patterns. This gaze-informed approach has significant potential for driver behavior analysis, as well as broader applications in human-centered AI systems, extending ViT's use to complex visual environments.
Authors: Rahul Parhi, Michael Unser
Abstract: We investigate the function-space optimality (specifically, the Banach-space optimality) of a large class of shallow neural architectures with multivariate nonlinearities/activation functions. To that end, we construct a new family of Banach spaces defined via a regularization operator, the $k$-plane transform, and a sparsity-promoting norm. We prove a representer theorem that states that the solution sets to learning problems posed over these Banach spaces are completely characterized by neural architectures with multivariate nonlinearities. These optimal architectures have skip connections and are tightly connected to orthogonal weight normalization and multi-index models, both of which have received recent interest in the neural network community. Our framework is compatible with a number of classical nonlinearities including the rectified linear unit (ReLU) activation function, the norm activation function, and the radial basis functions found in the theory of thin-plate/polyharmonic splines. We also show that the underlying spaces are special instances of reproducing kernel Banach spaces and variation spaces. Our results shed light on the regularity of functions learned by neural networks trained on data, particularly with multivariate nonlinearities, and provide new theoretical motivation for several architectural choices found in practice.
Authors: YoonHaeng Hur, Yuehaw Khoo
Abstract: We show the outlier robustness and noise stability of practical matching procedures based on distance profiles. Although the idea of matching points based on invariants like distance profiles has a long history in the literature, there has been little understanding of the theoretical properties of such procedures, especially in the presence of outliers and noise. We provide a theoretical analysis showing that under certain probabilistic settings, the proposed matching procedure is successful with high probability even in the presence of outliers and noise. We demonstrate the performance of the proposed method using a real data example and provide simulation studies to complement the theoretical findings. Lastly, we extend the concept of distance profiles to the abstract setting and connect the proposed matching procedure to the Gromov-Wasserstein distance and its lower bound, with a new sample complexity result derived based on the properties of distance profiles. This paper contributes to the literature by providing theoretical underpinnings of the matching procedures based on invariants like distance profiles, which have been widely used in practice but have rarely been analyzed theoretically.
Authors: Costas Mylonas, Donata Boric, Leila Luttenberger Maric, Alexandros Tsitsanis, Eleftheria Petrianou, Magda Foti
Abstract: This study explores the interaction between aggregators and building occupants in activating flexibility through Demand Response (DR) programs, with a focus on reinforcing the resilience of the energy system considering the uncertainties presented by Renewable Energy Sources (RES). Firstly, it introduces a methodology of optimizing aggregated flexibility provision strategies in environments with limited data, utilizing Discrete Fourier Transformation (DFT) and clustering techniques to identify building occupants' activity patterns. Secondly, the study assesses the disaggregated flexibility provision of Heating Ventilation and Air Conditioning (HVAC) systems during DR events, employing machine learning and optimization techniques for precise, device-level analysis. The first approach offers a non-intrusive pathway for aggregators to provide flexibility services in environments of a single smart meter for the whole building's consumption, while the second approach maximizes the amount of flexibility in the case of dedicated metering devices to the HVAC systems by carefully considering building occupants' thermal comfort profiles. Through the application of data-driven techniques and encompassing case studies from both industrial and residential buildings, this paper not only unveils pivotal opportunities for aggregators in the balancing and emerging flexibility markets but also successfully develops and demonstrates end-to-end practical tools for aggregators.
Authors: Charles Goddard, Shamane Siriwardhana, Malikeh Ehghaghi, Luke Meyers, Vlad Karpukhin, Brian Benedict, Mark McQuade, Jacob Solawetz
Abstract: The rapid expansion of the open-source language model landscape presents an opportunity to merge the competencies of these model checkpoints by combining their parameters. Advances in transfer learning, the process of fine-tuning pretrained models for specific tasks, has resulted in the development of vast amounts of task-specific models, typically specialized in individual tasks and unable to utilize each other's strengths. Model merging facilitates the creation of multitask models without the need for additional training, offering a promising avenue for enhancing model performance and versatility. By preserving the intrinsic capabilities of the original models, model merging addresses complex challenges in AI - including the difficulties of catastrophic forgetting and multitask learning. To support this expanding area of research, we introduce MergeKit, a comprehensive, open-source library designed to facilitate the application of model merging strategies. MergeKit offers an extensible framework to efficiently merge models on any hardware, providing utility to researchers and practitioners. To date, thousands of models have been merged by the open-source community, leading to the creation of some of the worlds most powerful open-source model checkpoints, as assessed by the Open LLM Leaderboard. The library is accessible at https://github.com/arcee-ai/MergeKit.
Authors: Halid Ziya Yerebakan, Yoshihisa Shinagawa, Gerardo Hermosillo Valadez
Abstract: Organ segmentation is a fundamental task in medical imaging since it is useful for many clinical automation pipelines. However, some tasks do not require full segmentation. Instead, a classifier can identify the selected organ without segmenting the entire volume. In this study, we demonstrate a classifier based method to obtain organ labels in real time by using a large context size with a sparse data sampling strategy. Although our method operates as an independent classifier at query locations, it can generate full segmentations by querying grid locations at any resolution, offering faster performance than segmentation algorithms. We compared our method with existing segmentation techniques, demonstrating its superior runtime potential for practical applications in medical imaging.
Authors: Chenpeng Yu, Xing Fang, Hui Liu
Abstract: The immune checkpoint inhibitors have demonstrated promising clinical efficacy across various tumor types, yet the percentage of patients who benefit from them remains low. The bindings between tumor antigens and HLA-I/TCR molecules determine the antigen presentation and T-cell activation, thereby playing an important role in the immunotherapy response. In this paper, we propose UnifyImmun, a unified cross-attention transformer model designed to simultaneously predict the bindings of peptides to both receptors, providing more comprehensive evaluation of antigen immunogenicity. We devise a two-phase strategy using virtual adversarial training that enables these two tasks to reinforce each other mutually, by compelling the encoders to extract more expressive features. Our method demonstrates superior performance in predicting both pHLA and pTCR binding on multiple independent and external test sets. Notably, on a large-scale COVID-19 pTCR binding test set without any seen peptide in training set, our method outperforms the current state-of-the-art methods by more than 10\%. The predicted binding scores significantly correlate with the immunotherapy response and clinical outcomes on two clinical cohorts. Furthermore, the cross-attention scores and integrated gradients reveal the amino-acid sites critical for peptide binding to receptors. In essence, our approach marks a significant step toward comprehensive evaluation of antigen immunogenicity.
Authors: Yuyan Wang, Cheenar Banerjee, Samer Chucri, Fabio Soldo, Sriraj Badam, Ed H. Chi, Minmin Chen
Abstract: It has become increasingly clear that recommender systems that overly focus on short-term engagement prevents users from exploring diverse interests, ultimately hurting long-term user experience. To tackle this challenge, numerous diversification algorithms have been proposed. These algorithms typically rely on measures of item similarity, aiming to maximize the dissimilarity across items in the final set of recommendations. However, in this work, we demonstrate the benefits of going beyond item-level similarities by utilizing higher-level user understanding--specifically, user intents that persist across multiple interactions--in diversification. Our approach is motivated by the observation that user behaviors on online platforms are largely driven by their underlying intents. Therefore, recommendations should ensure that diverse user intents are accurately represented. While intent has primarily been studied in the context of search, it is less clear how to incorporate real-time dynamic intent predictions into recommender systems. To address this gap, we develop a probabilistic intent-based whole-page diversification framework for the final stage of a recommender system. Starting with a prior belief of user intents, the proposed framework sequentially selects items for each position based on these beliefs and subsequently updates posterior beliefs about the intents. This approach ensures that different user intents are represented on a page, towards optimizing long-term user experience. We experiment with the intent diversification framework on YouTube, the world's largest video recommendation platform, serving billions of users daily. Live experiments on a diverse set of intents show that the proposed framework increases Daily Active Users (DAU) and overall user enjoyment, validating its effectiveness in facilitating long-term planning.
Authors: Dehong Xu, Ruiqi Gao, Wen-Hao Zhang, Xue-Xin Wei, Ying Nian Wu
Abstract: This paper investigates the conformal isometry hypothesis as a potential explanation for hexagonal periodic patterns in grid cell response maps. The hypothesis posits that grid cell activity forms a high-dimensional vector in neural space, encoding the agent's position in 2D physical space. As the agent moves, this vector rotates within a 2D manifold in the neural space, driven by a recurrent neural network. The conformal hypothesis suggests that this neural manifold is a conformally isometric embedding of physical space, where local displacements in neural space are proportional to those in physical space. In this paper, we conduct numerical experiments to show that this hypothesis leads to the hexagon periodic patterns of grid cells, agnostic to the choice of transformation models. Furthermore, we present a theoretical understanding that hexagon patterns emerge by minimizing our loss function because hexagon flat torus exhibits minimal deviation from local conformal isometry. In addition, we propose a conformal modulation of the agent's input velocity, enabling the recurrent neural network of grid cells to satisfy the conformal isometry hypothesis automatically.
Authors: Chankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
Abstract: Decoder-only large language model (LLM)-based embedding models are beginning to outperform BERT or T5-based embedding models in general-purpose text embedding tasks, including dense vector-based retrieval. In this work, we introduce the NV-Embed model, incorporating architectural designs, training procedures, and curated datasets to significantly enhance the performance of LLM as a versatile embedding model, while maintaining its simplicity and reproducibility. For model architecture, we propose a latent attention layer to obtain pooled embeddings, which consistently improves retrieval and downstream task accuracy compared to mean pooling or using the last
Authors: Niccolo Anceschi, Federico Ferrari, David B. Dunson, Himel Mallick
Abstract: It is increasingly common in a wide variety of applied settings to collect data of multiple different types on the same set of samples. Our particular focus in this article is on studying relationships between such multiview features and responses. A motivating application arises in the context of precision medicine where multi-omics data are collected to correlate with clinical outcomes. It is of interest to infer dependence within and across views while combining multimodal information to improve the prediction of outcomes. The signal-to-noise ratio can vary substantially across views, motivating more nuanced statistical tools beyond standard late and early fusion. This challenge comes with the need to preserve interpretability, select features, and obtain accurate uncertainty quantification. We propose a joint additive factor regression model (JAFAR) with a structured additive design, accounting for shared and view-specific components. We ensure identifiability via a novel dependent cumulative shrinkage process (D-CUSP) prior. We provide an efficient implementation via a partially collapsed Gibbs sampler and extend our approach to allow flexible feature and outcome distributions. Prediction of time-to-labor onset from immunome, metabolome, and proteome data illustrates performance gains against state-of-the-art competitors. Our open-source software (R package) is available at https://github.com/niccoloanceschi/jafar.
Authors: Roman Vashurin, Ekaterina Fadeeva, Artem Vazhentsev, Lyudmila Rvanova, Akim Tsvigun, Daniil Vasilev, Rui Xing, Abdelrahman Boda Sadallah, Kirill Grishchenkov, Sergey Petrakov, Alexander Panchenko, Timothy Baldwin, Preslav Nakov, Maxim Panov, Artem Shelmanov
Abstract: The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent evaluation of novel UQ techniques over various text generation tasks. Our benchmark also supports the assessment of confidence normalization methods in terms of their ability to provide interpretable scores. Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches. Code: https://github.com/IINemo/lm-polygraph Benchmark: https://huggingface.co/LM-Polygraph
URLs: https://github.com/IINemo/lm-polygraph, https://huggingface.co/LM-Polygraph
Authors: Vlad Hondru, Florinel Alin Croitoru, Shervin Minaee, Radu Tudor Ionescu, Nicu Sebe
Abstract: In this work, we survey recent studies on masked image modeling (MIM), an approach that emerged as a powerful self-supervised learning technique in computer vision. The MIM task involves masking some information, e.g.~pixels, patches, or even latent representations, and training a model, usually an autoencoder, to predicting the missing information by using the context available in the visible part of the input. We identify and formalize two categories of approaches on how to implement MIM as a pretext task, one based on reconstruction and one based on contrastive learning. Then, we construct a taxonomy and review the most prominent papers in recent years. We complement the manually constructed taxonomy with a dendrogram obtained by applying a hierarchical clustering algorithm. We further identify relevant clusters via manually inspecting the resulting dendrogram. Our review also includes datasets that are commonly used in MIM research. We aggregate the performance results of various masked image modeling methods on the most popular datasets, to facilitate the comparison of competing methods. Finally, we identify research gaps and propose several interesting directions of future work. We supplement our survey with the following public repository containing organized references: https://github.com/vladhondru25/MIM-Survey.
Authors: Mark K. Transtrum, Gus L. W. Hart, Tyler J. Jarvis, Jared P. Whitehead
Abstract: A central problem in data science is to use potentially noisy samples of an unknown function to predict values for unseen inputs. In classical statistics, predictive error is understood as a trade-off between the bias and the variance that balances model simplicity with its ability to fit complex functions. However, over-parameterized models exhibit counterintuitive behaviors, such as "double descent" in which models of increasing complexity exhibit decreasing generalization error. Others may exhibit more complicated patterns of predictive error with multiple peaks and valleys. Neither double descent nor multiple descent phenomena are well explained by the bias-variance decomposition. We introduce a novel decomposition that we call the generalized aliasing decomposition (GAD) to explain the relationship between predictive performance and model complexity. The GAD decomposes the predictive error into three parts: 1) model insufficiency, which dominates when the number of parameters is much smaller than the number of data points, 2) data insufficiency, which dominates when the number of parameters is much greater than the number of data points, and 3) generalized aliasing, which dominates between these two extremes. We demonstrate the applicability of the GAD to diverse applications, including random feature models from machine learning, Fourier transforms from signal processing, solution methods for differential equations, and predictive formation enthalpy in materials discovery. Because key components of the GAD can be explicitly calculated from the relationship between model class and samples without seeing any data labels, it can answer questions related to experimental design and model selection before collecting data or performing experiments. We further demonstrate this approach on several examples and discuss implications for predictive modeling and data science.
Authors: Awj Twam, Megan Jacobsen, Rachel Glenn, Peng Wei, Jia Sun, Ann Klopp, Aradhana M. Venkatesan, David Fuentes
Abstract: Cervical cancer remains the fourth most common malignancy amongst women worldwide.1 Concurrent chemoradiotherapy (CRT) serves as the mainstay definitive treatment regimen for locally advanced cervical cancers and includes external beam radiation followed by brachytherapy.2 Integral to radiotherapy treatment planning is the routine contouring of both the target tumor at the level of the cervix, associated gynecologic anatomy and the adjacent organs at risk (OARs). However, manual contouring of these structures is both time and labor intensive and associated with known interobserver variability that can impact treatment outcomes. While multiple tools have been developed to automatically segment OARs and the high-risk clinical tumor volume (HR-CTV) using computed tomography (CT) images,3,4,5,6 the development of deep learning-based tumor segmentation tools using routine T2-weighted (T2w) magnetic resonance imaging (MRI) addresses an unmet clinical need to improve the routine contouring of both anatomical structures and cervical cancers, thereby increasing quality and consistency of radiotherapy planning. This work applied a novel deep-learning model (PocketNet) to segment the cervix, vagina, uterus, and tumor(s) on T2w MRI. The performance of the PocketNet architecture was evaluated, when trained on data via 5-fold cross validation. PocketNet achieved a mean Dice-Sorensen similarity coefficient (DSC) exceeding 70% for tumor segmentation and 80% for organ segmentation. These results suggest that PocketNet is robust to variations in contrast protocols, providing reliable segmentation of the regions of interest.
Authors: Eleonora Lopez, Luigi Sigillo, Federica Colonnese, Massimo Panella, Danilo Comminiello
Abstract: Generating images from brain waves is gaining increasing attention due to its potential to advance brain-computer interface (BCI) systems by understanding how brain signals encode visual cues. Most of the literature has focused on fMRI-to-Image tasks as fMRI is characterized by high spatial resolution. However, fMRI is an expensive neuroimaging modality and does not allow for real-time BCI. On the other hand, electroencephalography (EEG) is a low-cost, non-invasive, and portable neuroimaging technique, making it an attractive option for future real-time applications. Nevertheless, EEG presents inherent challenges due to its low spatial resolution and susceptibility to noise and artifacts, which makes generating images from EEG more difficult. In this paper, we address these problems with a streamlined framework based on the ControlNet adapter for conditioning a latent diffusion model (LDM) through EEG signals. We conduct experiments and ablation studies on popular benchmarks to demonstrate that the proposed method beats other state-of-the-art models. Unlike these methods, which often require extensive preprocessing, pretraining, different losses, and captioning models, our approach is efficient and straightforward, requiring only minimal preprocessing and a few components. The code is available at https://github.com/LuigiSigillo/GWIT.
Authors: Lauren Nicole DeLong, Yojana Gadiya, Paola Galdi, Jacques D. Fleuriot, Daniel Domingo-Fern\'andez
Abstract: Neurosymbolic (NeSy) artificial intelligence describes the combination of logic or rule-based techniques with neural networks. Compared to neural approaches, NeSy methods often possess enhanced interpretability, which is particularly promising for biomedical applications like drug discovery. However, since interpretability is broadly defined, there are no clear guidelines for assessing the biological plausibility of model interpretations. To assess interpretability in the context of drug discovery, we devise a novel prediction task, called drug mechanism-of-action (MoA) deconvolution, with an associated, tailored knowledge graph (KG), MoA-net. We then develop the MoA Retrieval System (MARS), a NeSy approach for drug discovery which leverages logical rules with learned rule weights. Using this interpretable feature alongside domain knowledge, we find that MARS and other NeSy approaches on KGs are susceptible to reasoning shortcuts, in which the prediction of true labels is driven by "degree-bias" rather than the domain-based rules. Subsequently, we demonstrate ways to identify and mitigate this. Thereafter, MARS achieves performance on par with current state-of-the-art models while producing model interpretations aligned with known MoAs.
Authors: Chen Liu, Tobias Ritschel
Abstract: We propose a method to reproduce dynamic appearance textures with space-stationary but time-varying visual statistics. While most previous work decomposes dynamic textures into static appearance and motion, we focus on dynamic appearance that results not from motion but variations of fundamental properties, such as rusting, decaying, melting, and weathering. To this end, we adopt the neural ordinary differential equation (ODE) to learn the underlying dynamics of appearance from a target exemplar. We simulate the ODE in two phases. At the "warm-up" phase, the ODE diffuses a random noise to an initial state. We then constrain the further evolution of this ODE to replicate the evolution of visual feature statistics in the exemplar during the generation phase. The particular innovation of this work is the neural ODE achieving both denoising and evolution for dynamics synthesis, with a proposed temporal training scheme. We study both relightable (BRDF) and non-relightable (RGB) appearance models. For both we introduce new pilot datasets, allowing, for the first time, to study such phenomena: For RGB we provide 22 dynamic textures acquired from free online sources; For BRDFs, we further acquire a dataset of 21 flash-lit videos of time-varying materials, enabled by a simple-to-construct setup. Our experiments show that our method consistently yields realistic and coherent results, whereas prior works falter under pronounced temporal appearance variations. A user study confirms our approach is preferred to previous work for such exemplars.
Authors: Wannita Takerngsaksiri, Jirat Pasuksmit, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Ruixiong Zhang, Fan Jiang, Jing Li, Evan Cook, Kun Chen, Ming Wu
Abstract: Recently, Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks (e.g., from a given issue to source code). However, existing work is evaluated based on historical benchmark datasets, rarely considers human feedback at each stage of the automated software development process, and has not been deployed in practice. In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plans and source code for a given task. We design, implement, and deploy the HULA framework into Atlassian JIRA for internal uses. Through a multi-stage evaluation of the HULA framework, Atlassian software engineers perceive that HULA can minimize the overall development time and effort, especially in initiating a coding plan and writing code for straightforward tasks. On the other hand, challenges around code quality remain a concern in some cases. We draw lessons learned and discuss opportunities for future work, which will pave the way for the advancement of LLM-based agents in software development.
Authors: Moyang Guo, Yuepeng Hu, Zhengyuan Jiang, Zeyu Li, Amir Sadovnik, Arka Daw, Neil Gong
Abstract: While text-to-image models offer numerous benefits, they also pose significant societal risks. Detecting AI-generated images is crucial for mitigating these risks. Detection methods can be broadly categorized into passive and watermark-based approaches: passive detectors rely on artifacts present in AI-generated images, whereas watermark-based detectors proactively embed watermarks into such images. A key question is which type of detector performs better in terms of effectiveness, robustness, and efficiency. However, the current literature lacks a comprehensive understanding of this issue. In this work, we aim to bridge that gap by developing ImageDetectBench, the first comprehensive benchmark to compare the effectiveness, robustness, and efficiency of passive and watermark-based detectors. Our benchmark includes four datasets, each containing a mix of AI-generated and non-AI-generated images. We evaluate five passive detectors and four watermark-based detectors against eight types of common perturbations and three types of adversarial perturbations. Our benchmark results reveal several interesting findings. For instance, watermark-based detectors consistently outperform passive detectors, both in the presence and absence of perturbations. Based on these insights, we provide recommendations for detecting AI-generated images, e.g., when both types of detectors are applicable, watermark-based detectors should be the preferred choice. Our code and data are publicly available at https://github.com/moyangkuo/ImageDetectBench.git.
Authors: Abulikemu Abuduweili, Chenyang Yuan, Changliu Liu, Frank Permenter
Abstract: The denoising process of diffusion models can be interpreted as an approximate projection of noisy samples onto the data manifold. Moreover, the noise level in these samples approximates their distance to the underlying manifold. Building on this insight, we propose a novel method to enhance sample generation by aligning the estimated noise level with the true distance of noisy samples to the manifold. Specifically, we introduce a noise level correction network, leveraging a pre-trained denoising network, to refine noise level estimates during the denoising process. Additionally, we extend this approach to various image restoration tasks by integrating task-specific constraints, including inpainting, deblurring, super-resolution, colorization, and compressed sensing. Experimental results demonstrate that our method significantly improves sample quality in both unconstrained and constrained generation scenarios. Notably, the proposed noise level correction framework is compatible with existing denoising schedulers (e.g., DDIM), offering additional performance improvements.
Authors: Kyle Stein, Andrew Arash Mahyari, Guillermo Francia, Eman El-Sheikh
Abstract: Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through weight fine-tuning, much less attention has been given to detecting backdoored samples directly. Given the vast datasets used in training, manual inspection for backdoor triggers is impractical, and even state-of-the-art defense mechanisms fail to fully neutralize their impact. To address this gap, we introduce a groundbreaking method to detect unseen backdoored images during both training and inference. Leveraging the transformative success of prompt tuning in Vision Language Models (VLMs), our approach trains learnable text prompts to differentiate clean images from those with hidden backdoor triggers. Experiments demonstrate the exceptional efficacy of this method, achieving an impressive average accuracy of 86% across two renowned datasets for detecting unseen backdoor triggers, establishing a new standard in backdoor defense.
Authors: Jingruo Sun, Wenzhi Gao, Ellen Vitercik, Yinyu Ye
Abstract: Online linear programming (OLP) has found broad applications in revenue management and resource allocation. State-of-the-art OLP algorithms achieve low regret by repeatedly solving linear programming (LP) subproblems that incorporate updated resource information. However, LP-based methods are computationally expensive and often inefficient for large-scale applications. In contrast, recent first-order OLP algorithms are more computationally efficient but typically suffer from worse regret guarantees. To address these shortcomings, we propose a new algorithm that combines the strengths of LP-based and first-order OLP methods. The algorithm re-solves the LP subproblems periodically at a predefined frequency $f$ and uses the latest dual prices to guide online decision-making. In addition, a first-order method runs in parallel during each interval between LP re-solves, smoothing resource consumption. Our algorithm achieves $\mathscr{O}(\log (T/f) + \sqrt{f})$ regret, delivering a "wait-less" online decision-making process that balances the computational efficiency of first-order methods and the superior regret guarantee of LP-based methods.
Authors: Benjamin Steenhoek, Kalpathy Sivaraman, Renata Saldivar Gonzalez, Yevhen Mohylevskyy, Roshanak Zilouchian Moghaddam, Wei Le
Abstract: This paper presents the first empirical study of a vulnerability detection and fix tool with professional software developers on real projects that they own. We implemented DeepVulGuard, an IDE-integrated tool based on state-of-the-art detection and fix models, and show that it has promising performance on benchmarks of historic vulnerability data. DeepVulGuard scans code for vulnerabilities (including identifying the vulnerability type and vulnerable region of code), suggests fixes, provides natural-language explanations for alerts and fixes, leveraging chat interfaces. We recruited 17 professional software developers at Microsoft, observed their usage of the tool on their code, and conducted interviews to assess the tool's usefulness, speed, trust, relevance, and workflow integration. We also gathered detailed qualitative feedback on users' perceptions and their desired features. Study participants scanned a total of 24 projects, 6.9k files, and over 1.7 million lines of source code, and generated 170 alerts and 50 fix suggestions. We find that although state-of-the-art AI-powered detection and fix tools show promise, they are not yet practical for real-world use due to a high rate of false positives and non-applicable fixes. User feedback reveals several actionable pain points, ranging from incomplete context to lack of customization for the user's codebase. Additionally, we explore how AI features, including confidence scores, explanations, and chat interaction, can apply to vulnerability detection and fixing. Based on these insights, we offer practical recommendations for evaluating and deploying AI detection and fix models. Our code and data are available at https://doi.org/10.6084/m9.figshare.26367139.
Authors: Chuan He
Abstract: In this paper, we consider an unconstrained stochastic optimization problem where the objective function exhibits high-order smoothness. Specifically, we propose a new stochastic first-order method (SFOM) with multi-extrapolated momentum, in which multiple extrapolations are performed in each iteration, followed by a momentum update based on these extrapolations. We demonstrate that the proposed SFOM can accelerate optimization by exploiting the high-order smoothness of the objective function $f$. Assuming that the $p$th-order derivative of $f$ is Lipschitz continuous for some $p\ge2$, and under additional mild assumptions, we establish that our method achieves a sample complexity of $\widetilde{\mathcal{O}}(\epsilon^{-(3p+1)/p})$ for finding a point $x$ such that $\mathbb{E}[\|\nabla f(x)\|]\le\epsilon$. To the best of our knowledge, this is the first SFOM to leverage arbitrary-order smoothness of the objective function for acceleration, resulting in a sample complexity that improves upon the best-known results without assuming the mean-squared smoothness condition. Preliminary numerical experiments validate the practical performance of our method and support our theoretical findings.
Authors: Ryo Ide, Lei Yang
Abstract: Smoke detection using Deep Neural Networks (DNNs) is an effective approach for early wildfire detection. However, because smoke is temporally and spatially anomalous, there are limitations in collecting sufficient training data. This raises overfitting and bias concerns in existing DNN-based wildfire detection models. Thus, we introduce WARP (Wildfire Adversarial Robustness Procedure), the first model-agnostic framework for evaluating the adversarial robustness of DNN-based wildfire detection models. WARP addresses limitations in smoke image diversity using global and local adversarial attack methods. The global attack method uses image-contextualized Gaussian noise, while the local attack method uses patch noise injection, tailored to address critical aspects of wildfire detection. Leveraging WARP's model-agnostic capabilities, we assess the adversarial robustness of real-time Convolutional Neural Networks (CNNs) and Transformers. The analysis revealed valuable insights into the models' limitations. Specifically, the global attack method demonstrates that the Transformer model has more than 70% precision degradation than the CNN against global noise. In contrast, the local attack method shows that both models are susceptible to cloud image injections when detecting smoke-positive instances, suggesting a need for model improvements through data augmentation. WARP's comprehensive robustness analysis contributed to the development of wildfire-specific data augmentation strategies, marking a step toward practicality.
Authors: Xinhao Li, Yi Wang, Jiashuo Yu, Xiangyu Zeng, Yuhan Zhu, Haian Huang, Jianfei Gao, Kunchang Li, Yinan He, Chenting Wang, Yu Qiao, Yali Wang, Limin Wang
Abstract: Long-context modeling is a critical capability for multimodal large language models (MLLMs), enabling them to process long-form contents with implicit memorization. Despite its advances, handling extremely long videos remains challenging due to the difficulty in maintaining crucial features over extended sequences. This paper introduces a Hierarchical visual token Compression (HiCo) method designed for high-fidelity representation and a practical context modeling system VideoChat-Flash tailored for multimodal long-sequence processing. HiCo capitalizes on the redundancy of visual information in long videos to compress long video context from the clip-level to the video-level, reducing the compute significantly while preserving essential details. VideoChat-Flash features a multi-stage short-to-long learning scheme, a rich dataset of real-world long videos named LongVid, and an upgraded "Needle-In-A-video-Haystack" (NIAH) for evaluating context capacities. In extensive experiments, VideoChat-Flash shows the leading performance on both mainstream long and short video benchmarks at the 2B and 7B model scale. It firstly gets 99.1% accuracy over 10,000 frames in NIAH among open-source models.
Authors: Linhao Huang, Xue Jiang, Zhiqiang Wang, Wentao Mo, Xi Xiao, Bo Han, Yongjie Yin, Feng Zheng
Abstract: Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models--a common and practical real world scenario--remains unexplored. In this paper, we pioneer an investigation into the transferability of adversarial video samples across V-MLLMs. We find that existing adversarial attack methods face significant limitations when applied in black-box settings for V-MLLMs, which we attribute to the following shortcomings: (1) lacking generalization in perturbing video features, (2) focusing only on sparse key-frames, and (3) failing to integrate multimodal information. To address these limitations and deepen the understanding of V-MLLM vulnerabilities in black-box scenarios, we introduce the Image-to-Video MLLM (I2V-MLLM) attack. In I2V-MLLM, we utilize an image-based multimodal model (IMM) as a surrogate model to craft adversarial video samples. Multimodal interactions and temporal information are integrated to disrupt video representations within the latent space, improving adversarial transferability. In addition, a perturbation propagation technique is introduced to handle different unknown frame sampling strategies. Experimental results demonstrate that our method can generate adversarial examples that exhibit strong transferability across different V-MLLMs on multiple video-text multimodal tasks. Compared to white-box attacks on these models, our black-box attacks (using BLIP-2 as surrogate model) achieve competitive performance, with average attack success rates of 55.48% on MSVD-QA and 58.26% on MSRVTT-QA for VideoQA tasks, respectively. Our code will be released upon acceptance.
Authors: Mohammad Nadeem, Shahab Saquib Sohail, Erik Cambria, Bj\"orn W. Schuller, Amir Hussain
Abstract: The advent of text-to-video generation models has revolutionized content creation as it produces high-quality videos from textual prompts. However, concerns regarding inherent biases in such models have prompted scrutiny, particularly regarding gender representation. Our study investigates the presence of gender bias in OpenAI's Sora, a state-of-the-art text-to-video generation model. We uncover significant evidence of bias by analyzing the generated videos from a diverse set of gender-neutral and stereotypical prompts. The results indicate that Sora disproportionately associates specific genders with stereotypical behaviors and professions, which reflects societal prejudices embedded in its training data.
Authors: Zongxia Li, Xiyang Wu, Hongyang Du, Huy Nghiem, Guangyao Shi
Abstract: Multimodal Vision Language Models (VLMs) have emerged as a transformative technology at the intersection of computer vision and natural language processing, enabling machines to perceive and reason about the world through both visual and textual modalities. For example, models such as CLIP, Claude, and GPT-4V demonstrate strong reasoning and understanding abilities on visual and textual data and beat classical single modality vision models on zero-shot classification. Despite their rapid advancements in research and growing popularity in applications, a comprehensive survey of existing studies on VLMs is notably lacking, particularly for researchers aiming to leverage VLMs in their specific domains. To this end, we provide a systematic overview of VLMs in the following aspects: model information of the major VLMs developed over the past five years (2019-2024); the main architectures and training methods of these VLMs; summary and categorization of the popular benchmarks and evaluation metrics of VLMs; the applications of VLMs including embodied agents, robotics, and video generation; the challenges and issues faced by current VLMs such as hallucination, fairness, and safety. Detailed collections including papers and model repository links are listed in https://github.com/zli12321/Awesome-VLM-Papers-And-Models.git.
URLs: https://github.com/zli12321/Awesome-VLM-Papers-And-Models.git.
Authors: Kanefumi Matsuyama, Kefan Su, Jiangxing Wang, Deheng Ye, Zongqing Lu
Abstract: Cooperative multi-agent reinforcement learning (MARL) aims to develop agents that can collaborate effectively. However, most cooperative MARL methods overfit training agents, making learned policies not generalize well to unseen collaborators, which is a critical issue for real-world deployment. Some methods attempt to address the generalization problem but require prior knowledge or predefined policies of new teammates, limiting real-world applications. To this end, we propose a hierarchical MARL approach to enable generalizable cooperation via role diversity, namely CORD. CORD's high-level controller assigns roles to low-level agents by maximizing the role entropy with constraints. We show this constrained objective can be decomposed into causal influence in role that enables reasonable role assignment, and role heterogeneity that yields coherent, non-redundant role clusters. Evaluated on a variety of cooperative multi-agent tasks, CORD achieves better performance than baselines, especially in generalization tests. Ablation studies further demonstrate the efficacy of the constrained objective in generalizable cooperation.
Authors: Zhenglai Li, Jun Wang, Chang Tang, Xinzhong Zhu, Wei Zhang, Xinwang Liu
Abstract: Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC is potentially not fully leverage the multi-view information, since the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, a theoretical analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches both on eight benchmark MvC datasets and two spatially resolved transcriptomics datasets.
Authors: Eric Chen, Xi Chen, Arian Maleki, Shirin Jalali
Abstract: Unrolled networks have become prevalent in various computer vision and imaging tasks. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm, defining the loss function, and determining the number of convolutional layers, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train, fine-tune the neural network, and optimize for its performance. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive ablation study to discuss the impact of each of the choices involved in designing unrolled networks and present practical recommendations based on our findings. We anticipate that this study will help scientists and engineers design unrolled networks for their applications and diagnose problems within their networks efficiently.
Authors: Gianfranco Cortes, Xiaoda Qu, Baba C. Vemuri
Abstract: Nonrigid registration is vital to medical image analysis but remains challenging for diffusion MRI (dMRI) due to its high-dimensional, orientation-dependent nature. While classical methods are accurate, they are computationally demanding, and deep neural networks, though efficient, have been underexplored for nonrigid dMRI registration compared to structural imaging. We present a novel, deep learning framework for model-free, nonrigid registration of raw diffusion MRI data that does not require explicit reorientation. Unlike previous methods relying on derived representations such as diffusion tensors or fiber orientation distribution functions, in our approach, we formulate the registration as an equivariant diffeomorphism of position-and-orientation space. Central to our method is an $\mathsf{SE}(3)$-equivariant UNet that generates velocity fields while preserving the geometric properties of a raw dMRI's domain. We introduce a new loss function based on the maximum mean discrepancy in Fourier space, implicitly matching ensemble average propagators across images. Experimental results on Human Connectome Project dMRI data demonstrate competitive performance compared to state-of-the-art approaches, with the added advantage of bypassing the overhead for estimating derived representations. This work establishes a foundation for data-driven, geometry-aware dMRI registration directly in the acquisition space.
Authors: Maximilian Alber, Stephan Tietz, Jonas Dippel, Timo Milbich, Timoth\'ee Lesort, Panos Korfiatis, Moritz Kr\"ugener, Beatriz Perez Cancer, Neelay Shah, Alexander M\"ollers, Philipp Seegerer, Alexandra Carpen-Amarie, Kai Standvoss, Gabriel Dernbach, Edwin de Jong, Simon Schallenberg, Andreas Kunft, Helmut Hoffer von Ankershoffen, Gavin Schaeferle, Patrick Duffy, Matt Redlon, Philipp Jurmeister, David Horst, Lukas Ruff, Klaus-Robert M\"uller, Frederick Klauschen, Andrew Norgan
Abstract: Recent advances in digital pathology have demonstrated the effectiveness of foundation models across diverse applications. In this report, we present Atlas, a novel vision foundation model based on the RudolfV approach. Our model was trained on a dataset comprising 1.2 million histopathology whole slide images, collected from two medical institutions: Mayo Clinic and Charit\'e - Universt\"atsmedizin Berlin. Comprehensive evaluations show that Atlas achieves state-of-the-art performance across twenty-one public benchmark datasets, even though it is neither the largest model by parameter count nor by training dataset size.
Authors: David McAllister, Matthew Tancik, Jiaming Song, Angjoo Kanazawa
Abstract: Large-scale AI model training divides work across thousands of GPUs, then synchronizes gradients across them at each step. This incurs a significant network burden that only centralized, monolithic clusters can support, driving up infrastructure costs and straining power systems. We propose Decentralized Diffusion Models, a scalable framework for distributing diffusion model training across independent clusters or datacenters by eliminating the dependence on a centralized, high-bandwidth networking fabric. Our method trains a set of expert diffusion models over partitions of the dataset, each in full isolation from one another. At inference time, the experts ensemble through a lightweight router. We show that the ensemble collectively optimizes the same objective as a single model trained over the whole dataset. This means we can divide the training burden among a number of "compute islands," lowering infrastructure costs and improving resilience to localized GPU failures. Decentralized diffusion models empower researchers to take advantage of smaller, more cost-effective and more readily available compute like on-demand GPU nodes rather than central integrated systems. We conduct extensive experiments on ImageNet and LAION Aesthetics, showing that decentralized diffusion models FLOP-for-FLOP outperform standard diffusion models. We finally scale our approach to 24 billion parameters, demonstrating that high-quality diffusion models can now be trained with just eight individual GPU nodes in less than a week.