Authors: Xirui Tang (College of Computer Sciences, Northeastern University, Boston, MA, USA), Feiyang Li (Department of Computer Science, University of Illinois Urbana-Champaign, Champaign, IL, USA), Zinan Cao (Department of General Systems Studies, The University of Tokyo, Tokyo, Japan), Qixuan Yu (College of Computing, Georgia Institute of Technology, Atlanta, GA, USA), Yulu Gong (School of Informatics, Computing, and Cyber Systems, Northern Arizona University, Flagstaff, AZ, USA)
Abstract: In this paper, an improved method for VR user experience prediction is investigated by introducing a sparrow search algorithm and a random forest algorithm improved by an iterative local search-optimised sparrow search algorithm. The study firstly conducted a statistical analysis of the data, and then trained and tested using the traditional random forest model, the random forest model improved by the sparrow search algorithm, and the random forest algorithm improved based on the iterative local search-sparrow search algorithm, respectively. The results show that the traditional random forest model has a prediction accuracy of 93% on the training set but only 73.3% on the test set, which is poor in generalisation; whereas the model improved by the sparrow search algorithm has a prediction accuracy of 94% on the test set, which is improved compared with the traditional model. What is more noteworthy is that the improved model based on the iterative local search-sparrow search algorithm achieves 100% accuracy on both the training and test sets, which is significantly better than the other two methods. These research results provide new ideas and methods for VR user experience prediction, especially the improved model based on the iterative local search-sparrow search algorithm performs well and is able to more accurately predict and classify the user's VR experience. In the future, the application of this method in other fields can be further explored, and its effectiveness can be verified through real cases to promote the development of AI technology in the field of user experience.
Authors: Peter Manshausen, Yair Cohen, Jaideep Pathak, Mike Pritchard, Piyush Garg, Morteza Mardani, Karthik Kashinath, Simon Byrne, Noah Brenowitz
Abstract: Data assimilation of observational data into full atmospheric states is essential for weather forecast model initialization. Recently, methods for deep generative data assimilation have been proposed which allow for using new input data without retraining the model. They could also dramatically accelerate the costly data assimilation process used in operational regional weather models. Here, in a central US testbed, we demonstrate the viability of score-based data assimilation in the context of realistically complex km-scale weather. We train an unconditional diffusion model to generate snapshots of a state-of-the-art km-scale analysis product, the High Resolution Rapid Refresh. Then, using score-based data assimilation to incorporate sparse weather station data, the model produces maps of precipitation and surface winds. The generated fields display physically plausible structures, such as gust fronts, and sensitivity tests confirm learnt physics through multivariate relationships. Preliminary skill analysis shows the approach already outperforms a naive baseline of the High-Resolution Rapid Refresh system itself. By incorporating observations from 40 weather stations, 10\% lower RMSEs on left-out stations are attained. Despite some lingering imperfections such as insufficiently disperse ensemble DA estimates, we find the results overall an encouraging proof of concept, and the first at km-scale. It is a ripe time to explore extensions that combine increasingly ambitious regional state generators with an increasing set of in situ, ground-based, and satellite remote sensing data streams.
Authors: Jiaming Yan
Abstract: Recent advancements in artificial intelligence (AI) have positioned deep learning (DL) as a pivotal technology in fields like computer vision, data mining, and natural language processing. A critical factor in DL performance is the selection of neural network architecture. Traditional predefined architectures often fail to adapt to different data distributions, making it challenging to achieve optimal performance. Neural architecture search (NAS) offers a solution by automatically designing architectures tailored to specific datasets. However, the effectiveness of NAS diminishes on long-tailed datasets, where a few classes have abundant samples, and many have few, leading to biased models.In this paper, we explore to improve the searching and training performance of NAS on long-tailed datasets. Specifically, we first discuss the related works about NAS and the deep learning method for long-tailed datasets.Then, we focus on an existing work, called SSF-NAS, which integrates the self-supervised learning and fair differentiable NAS to making NAS achieve better performance on long-tailed datasets.An detailed description about the fundamental techniques for SSF-NAS is provided in this paper, including DARTS, FairDARTS, and Barlow Twins. Finally, we conducted a series of experiments on the CIFAR10-LT dataset for performance evaluation, where the results are align with our expectation.
Authors: Yunjin Tong
Abstract: In a landscape where scientific discovery is increasingly driven by data, the integration of machine learning (ML) with traditional scientific methodologies has emerged as a transformative approach. This paper introduces a novel, data-driven framework that synergizes physics-based priors with advanced ML techniques to address the computational and practical limitations inherent in first-principle-based methods and brute-force machine learning methods. Our framework showcases four algorithms, each embedding a specific physics-based prior tailored to a particular class of nonlinear systems, including separable and nonseparable Hamiltonian systems, hyperbolic partial differential equations, and incompressible fluid dynamics. The intrinsic incorporation of physical laws preserves the system's intrinsic symmetries and conservation laws, ensuring solutions are physically plausible and computationally efficient. The integration of these priors also enhances the expressive power of neural networks, enabling them to capture complex patterns typical in physical phenomena that conventional methods often miss. As a result, our models outperform existing data-driven techniques in terms of prediction accuracy, robustness, and predictive capability, particularly in recognizing features absent from the training set, despite relying on small datasets, short training periods, and small sample sizes.
Authors: Dianhui Wang, Gang Dang
Abstract: Temporal data modelling techniques with neural networks are useful in many domain applications, including time-series forecasting and control engineering. This paper aims at developing a recurrent version of stochastic configuration networks (RSCNs) for problem solving, where we have no underlying assumption on the dynamic orders of the input variables. Given a collection of historical data, we first build an initial RSCN model in the light of a supervisory mechanism, followed by an online update of the output weights by using a projection algorithm. Some theoretical results are established, including the echo state property, the universal approximation property of RSCNs for both the offline and online learnings, and the convergence of the output weights. The proposed RSCN model is remarkably distinguished from the well-known echo state networks (ESNs) in terms of the way of assigning the input random weight matrix and a special structure of the random feedback matrix. A comprehensive comparison study among the long short-term memory (LSTM) network, the original ESN, and several state-of-the-art ESN methods such as the simple cycle reservoir (SCR), the polynomial ESN (PESN), the leaky-integrator ESN (LIESN) and RSCN is carried out. Numerical results clearly indicate that the proposed RSCN performs favourably over all of the datasets.
Authors: Jes\'us Armenta-Segura, Grigori Sidorov
Abstract: In the japanese anime industry, predicting whether an upcoming product will be popular is crucial. This paper presents a dataset and methods on predicting anime popularity using a multimodal textimage dataset constructed exclusively from freely available internet sources. The dataset was built following rigorous standards based on real-life investment experiences. A deep neural network architecture leveraging GPT-2 and ResNet-50 to embed the data was employed to investigate the correlation between the multimodal text-image input and a popularity score, discovering relevant strengths and weaknesses in the dataset. To measure the accuracy of the model, mean squared error (MSE) was used, obtaining a best result of 0.011 when considering all inputs and the full version of the deep neural network, compared to the benchmark MSE 0.412 obtained with traditional TF-IDF and PILtotensor vectorizations. This is the first proposal to address such task with multimodal datasets, revealing the substantial benefit of incorporating image information, even when a relatively small model (ResNet-50) was used to embed them.
Authors: Shubhabrata Mukherjee, Cory Beard, Sejun Song
Abstract: Semantic Communication can transform the way we transmit information, prioritizing meaningful and effective content over individual symbols or bits. This evolution promises significant benefits, including reduced latency, lower bandwidth usage, and higher throughput compared to traditional communication. However, the development of Semantic Communication faces a crucial challenge: the need for universal metrics to benchmark the joint effects of semantic information loss and energy consumption. This research introduces an innovative solution: the ``Energy-Optimized Semantic Loss'' (EOSL) function, a novel multi-objective loss function that effectively balances semantic information loss and energy consumption. Through comprehensive experiments on transformer models, including energy benchmarking, we demonstrate the remarkable effectiveness of EOSL-based model selection. We have established that EOSL-based transformer model selection achieves up to 83\% better similarity-to-power ratio (SPR) compared to BLEU score-based selection and 67\% better SPR compared to solely lowest power usage-based selection. Furthermore, we extend the applicability of EOSL to diverse and varying contexts, inspired by the principles of Meta-Learning. By cumulatively applying EOSL, we enable the model selection system to adapt to this change, leveraging historical EOSL values to guide the learning process. This work lays the foundation for energy-efficient model selection and the development of green semantic communication.
Authors: Faqian Guan, Tianqing Zhu, Hui Sun, Wanlei Zhou, Philip S. Yu
Abstract: Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for handling such data and have shown impressive performance in many applications. However, GNNs may contain of sensitive information and susceptible to privacy attacks. For example, link stealing is a type of attack in which attackers infer whether two nodes are linked or not. Previous link stealing attacks primarily relied on posterior probabilities from the target GNN model, neglecting the significance of node features. Additionally, variations in node classes across different datasets lead to different dimensions of posterior probabilities. The handling of these varying data dimensions posed a challenge in using a single model to effectively conduct link stealing attacks on different datasets. To address these challenges, we introduce Large Language Models (LLMs) to perform link stealing attacks on GNNs. LLMs can effectively integrate textual features and exhibit strong generalizability, enabling attacks to handle diverse data dimensions across various datasets. We design two distinct LLM prompts to effectively combine textual features and posterior probabilities of graph nodes. Through these designed prompts, we fine-tune the LLM to adapt to the link stealing attack task. Furthermore, we fine-tune the LLM using multiple datasets and enable the LLM to learn features from different datasets simultaneously. Experimental results show that our approach significantly enhances the performance of existing link stealing attack tasks in both white-box and black-box scenarios. Our method can execute link stealing attacks across different datasets using only a single model, making link stealing attacks more applicable to real-world scenarios.
Authors: Mingtian Tan, Mike A. Merrill, Vinayak Gupta, Tim Althoff, Thomas Hartvigsen
Abstract: Large language models (LLMs) are being applied to time series tasks, particularly time series forecasting. However, are language models actually useful for time series? After a series of ablation studies on three recent and popular LLM-based time series forecasting methods, we find that removing the LLM component or replacing it with a basic attention layer does not degrade the forecasting results -- in most cases the results even improved. We also find that despite their significant computational cost, pretrained LLMs do no better than models trained from scratch, do not represent the sequential dependencies in time series, and do not assist in few-shot settings. Additionally, we explore time series encoders and reveal that patching and attention structures perform similarly to state-of-the-art LLM-based forecasters.
Authors: Abdur Rashid, Parag Biswas, Angona Biswas, MD Abdullah Al Nasim, Kishor Datta Gupta, Roy George
Abstract: Artificial intelligence (AI) has become a crucial instrument for streamlining processes in various industries, including electrical power systems, as a result of recent digitalization. Algorithms for artificial intelligence are data-driven models that are based on statistical learning theory and are used as a tool to take use of the data that the power system and its users generate. Initially, we perform a thorough literature analysis of artificial intelligence (AI) applications related to renewable energy (RE). Next, we present a thorough analysis of renewable energy factories and assess their suitability, along with a list of the most widely used and appropriate AI algorithms. Nine AI-based strategies are identified here to assist Renewable Energy (RE) in contemporary power systems. This survey paper comprises an extensive review of the several AI techniques used for renewable energy as well as a methodical analysis of the literature for the study of various intelligent system application domains across different disciplines of renewable energy. This literature review identifies the performance and outcomes of nine different research methods by assessing them, and it aims to distill valuable insights into their strengths and limitations. This study also addressed three main topics: using AI technology for renewable power generation, utilizing AI for renewable energy forecasting, and optimizing energy systems. Additionally, it explored AI's superiority over conventional models in controllability, data handling, cyberattack prevention, smart grid implementation, robotics- AI's significance in shaping the future of the energy industry. Furthermore, this article outlines future directions in the integration of AI for renewable energy.
Authors: Kai Shao, Rui Wang, Yixue Hao, Long Hu, Min Chen
Abstract: Depression recognition based on physiological signals such as functional near-infrared spectroscopy (fNIRS) and electroencephalogram (EEG) has made considerable progress. However, most existing studies ignore the complementarity and semantic consistency of multimodal physiological signals under the same stimulation task in complex spatio-temporal patterns. In this paper, we introduce a multimodal physiological signals representation learning framework using Siamese architecture via multiscale contrasting for depression recognition (MRLMC). First, fNIRS and EEG are transformed into different but correlated data based on a time-domain data augmentation strategy. Then, we design a spatio-temporal contrasting module to learn the representation of fNIRS and EEG through weight-sharing multiscale spatio-temporal convolution. Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG. Extensive experiments on publicly available and self-collected multimodal physiological signals datasets indicate that MRLMC outperforms the state-of-the-art models. Moreover, our proposed framework is capable of transferring to multimodal time series downstream tasks.
Authors: Zhiwei Yao
Abstract: Class imbalance is a common issue in real-world data distributions, negatively impacting the training of accurate classifiers. Traditional approaches to mitigate this problem fall into three main categories: class re-balancing, information transfer, and representation learning. This paper introduces a novel approach to enhance performance on long-tailed datasets by optimizing the backbone architecture through neural architecture search (NAS). Our research shows that an architecture's accuracy on a balanced dataset does not reliably predict its performance on imbalanced datasets. This necessitates a complete NAS run on long-tailed datasets, which can be computationally expensive. To address this computational challenge, we focus on existing work, called IMB-NAS, which proposes efficiently adapting a NAS super-network trained on a balanced source dataset to an imbalanced target dataset. A detailed description of the fundamental techniques for IMB-NAS is provided in this paper, including NAS and architecture transfer. Among various adaptation strategies, we find that the most effective approach is to retrain the linear classification head with reweighted loss while keeping the backbone NAS super-network trained on the balanced source dataset frozen. Finally, we conducted a series of experiments on the imbalanced CIFAR dataset for performance evaluation. Our conclusions are the same as those proposed in the IMB-NAS paper.
Authors: Kenta Tsutsui, Shany Biton Brimer, Noam Ben-Moshe, Jean Marc Sellal, Julien Oster, Hitoshi Mori, Yoshifumi Ikeda, Takahide Arai, Shintaro Nakano, Ritsushi Kato, Joachim A. Behar
Abstract: Atrial fibrillation (AF) is a common atrial arrhythmia that impairs quality of life and causes embolic stroke, heart failure and other complications. Recent advancements in machine learning (ML) and deep learning (DL) have shown potential for enhancing diagnostic accuracy. It is essential for DL models to be robust and generalizable across variations in ethnicity, age, sex, and other factors. Although a number of ECG database have been made available to the research community, none includes a Japanese population sample. Saitama Heart Database Atrial Fibrillation (SHDB-AF) is a novel open-sourced Holter ECG database from Japan, containing data from 100 unique patients with paroxysmal AF. Each record in SHDB-AF is 24 hours long and sampled at 200 Hz, totaling 24 million seconds of ECG data.
Authors: Zahra Sadeghi, Stan Matwin
Abstract: Global sensitivity analysis (GSA) aims to detect influential input factors that lead a model to arrive at a certain decision and is a significant approach for mitigating the computational burden of processing high dimensional data. In this paper, we provide a comprehensive review and a comparison on global sensitivity analysis methods. Additionally, we propose a methodology for evaluating the efficacy of these methods by conducting a case study on MNIST digit dataset. Our study goes through the underlying mechanism of widely used GSA methods and highlights their efficacy through a comprehensive methodology.
Authors: Xianda Chen (Frank), Kehua Chen (Frank), Meixin Zhu (Frank), Hao (Frank), Yang, Shaojie Shen, Xuesong Wang, Yinhai Wang
Abstract: Car-following (CF) modeling, a fundamental component in microscopic traffic simulation, has attracted increasing interest of researchers in the past decades. In this study, we propose an adaptable personalized car-following framework -MetaFollower, by leveraging the power of meta-learning. Specifically, we first utilize Model-Agnostic Meta-Learning (MAML) to extract common driving knowledge from various CF events. Afterward, the pre-trained model can be fine-tuned on new drivers with only a few CF trajectories to achieve personalized CF adaptation. We additionally combine Long Short-Term Memory (LSTM) and Intelligent Driver Model (IDM) to reflect temporal heterogeneity with high interpretability. Unlike conventional adaptive cruise control (ACC) systems that rely on predefined settings and constant parameters without considering heterogeneous driving characteristics, MetaFollower can accurately capture and simulate the intricate dynamics of car-following behavior while considering the unique driving styles of individual drivers. We demonstrate the versatility and adaptability of MetaFollower by showcasing its ability to adapt to new drivers with limited training data quickly. To evaluate the performance of MetaFollower, we conduct rigorous experiments comparing it with both data-driven and physics-based models. The results reveal that our proposed framework outperforms baseline models in predicting car-following behavior with higher accuracy and safety. To the best of our knowledge, this is the first car-following model aiming to achieve fast adaptation by considering both driver and temporal heterogeneity based on meta-learning.
Authors: Ezgi Korkmaz
Abstract: Deep neural policies have recently been installed in a diverse range of settings, from biotechnology to automated financial systems. However, the utilization of deep neural networks to approximate the value function leads to concerns on the decision boundary stability, in particular, with regard to the sensitivity of policy decision making to indiscernible, non-robust features due to highly non-convex and complex deep neural manifolds. These concerns constitute an obstruction to understanding the reasoning made by deep neural policies, and their foundational limitations. Hence, it is crucial to develop techniques that aim to understand the sensitivities in the learnt representations of neural network policies. To achieve this we introduce a theoretically founded method that provides a systematic analysis of the unstable directions in the deep neural policy decision boundary across both time and space. Through experiments in the Arcade Learning Environment (ALE), we demonstrate the effectiveness of our technique for identifying correlated directions of instability, and for measuring how sample shifts remold the set of sensitive directions in the neural policy landscape. Most importantly, we demonstrate that state-of-the-art robust training techniques yield learning of disjoint unstable directions, with dramatically larger oscillations over time, when compared to standard training. We believe our results reveal the fundamental properties of the decision process made by reinforcement learning policies, and can help in constructing reliable and robust deep neural policies.
Authors: Yang Lin, Muqing Li, Ziyi Zhu, Yinqiu Feng, Lingxi Xiao, Zexi Chen
Abstract: The prediction of disease risk factors can screen vulnerable groups for effective prevention and treatment, so as to reduce their morbidity and mortality. Machine learning has a great demand for high-quality labeling information, and labeling noise in medical big data poses a great challenge to efficient disease risk warning methods. Therefore, this project intends to study the robust learning algorithm and apply it to the early warning of infectious disease risk. A dynamic truncated loss model is proposed, which combines the traditional mutual entropy implicit weight feature with the mean variation feature. It is robust to label noise. A lower bound on training loss is constructed, and a method based on sampling rate is proposed to reduce the gradient of suspected samples to reduce the influence of noise on training results. The effectiveness of this method under different types of noise was verified by using a stroke screening data set as an example. This method enables robust learning of data containing label noise.
Authors: Yukun Zhang
Abstract: This study presents a novel approach that leverages Neural Ordinary Differential Equations (Neural ODEs) to unravel the intricate relationships between inputs and outputs in Large Language Models (LLMs), and employs robust control to fine-tune outputs to meet predefined standards. Central to our methodology is the transformation of LLM inputs and outputs into a lower-dimensional latent space, facilitating a detailed examination of the information processing pathways within LLMs. Neural ODEs play a pivotal role in this investigation by providing a dynamic model that captures the continuous evolution of data within the LLMs. Additionally, robust control mechanisms are applied to strategically adjust the model's outputs, ensuring they not only maintain high quality and reliability but also adhere to specific performance criteria. This fusion of Neural ODEs and robust control represents a significant advancement in LLM interpretability, offering a comprehensive framework that elucidates the previously opaque mechanisms of these complex models. Our empirical results validate the effectiveness of this integrated approach, making a substantial contribution to the field of explainable AI by merging advanced machine learning techniques with the critical need for transparency and control in AI outputs.
Authors: Tao Huang, Ziyang Chen, Jiayang Meng, Qingyu Huang, Xu Yang, Xun Yi, Ibrahim Khalil
Abstract: In the context of machine unlearning, the primary challenge lies in effectively removing traces of private data from trained models while maintaining model performance and security against privacy attacks like membership inference attacks. Traditional gradient-based unlearning methods often rely on extensive historical gradients, which becomes impractical with high unlearning ratios and may reduce the effectiveness of unlearning. Addressing these limitations, we introduce Mini-Unlearning, a novel approach that capitalizes on a critical observation: unlearned parameters correlate with retrained parameters through contraction mapping. Our method, Mini-Unlearning, utilizes a minimal subset of historical gradients and leverages this contraction mapping to facilitate scalable, efficient unlearning. This lightweight, scalable method significantly enhances model accuracy and strengthens resistance to membership inference attacks. Our experiments demonstrate that Mini-Unlearning not only works under higher unlearning ratios but also outperforms existing techniques in both accuracy and security, offering a promising solution for applications requiring robust unlearning capabilities.
Authors: Yefan Zhou, Jianlong Chen, Qinxue Cao, Konstantin Sch\"urholt, Yaoqing Yang
Abstract: This paper considers "model diagnosis", which we formulate as a classification problem. Given a pre-trained neural network (NN), the goal is to predict the source of failure from a set of failure modes (such as a wrong hyperparameter, inadequate model size, and insufficient data) without knowing the training configuration of the pre-trained NN. The conventional diagnosis approach uses training and validation errors to determine whether the model is underfitting or overfitting. However, we show that rich information about NN performance is encoded in the optimization loss landscape, which provides more actionable insights than validation-based measurements. Therefore, we propose a diagnosis method called MD tree based on loss landscape metrics and experimentally demonstrate its advantage over classical validation-based approaches. We verify the effectiveness of MD tree in multiple practical scenarios: (1) use several models trained on one dataset to diagnose a model trained on another dataset, essentially a few-shot dataset transfer problem; (2) use small models (or models trained with small data) to diagnose big models (or models trained with big data), essentially a scale transfer problem. In a dataset transfer task, MD tree achieves an accuracy of 87.7%, outperforming validation-based approaches by 14.88%. Our code is available at https://github.com/YefanZhou/ModelDiagnosis.
Authors: Ziyu Zhao, Leilei Gan, Guoyin Wang, Yuwei Hu, Tao Shen, Hongxia Yang, Kun Kuang, Fei Wu
Abstract: Low-Rank Adaptation (LoRA) offers an efficient way to fine-tune large language models (LLMs). Its modular and plug-and-play nature allows the integration of various domain-specific LoRAs, enhancing LLM capabilities. Open-source platforms like Huggingface and Modelscope have introduced a new computational paradigm, Uploadable Machine Learning (UML). In UML, contributors use decentralized data to train specialized adapters, which are then uploaded to a central platform to improve LLMs. This platform uses these domain-specific adapters to handle mixed-task requests requiring personalized service. Previous research on LoRA composition either focuses on specific tasks or fixes the LoRA selection during training. However, in UML, the pool of LoRAs is dynamically updated with new uploads, requiring a generalizable selection mechanism for unseen LoRAs. Additionally, the mixed-task nature of downstream requests necessitates personalized services. To address these challenges, we propose Retrieval-Augmented Mixture of LoRA Experts (RAMoLE), a framework that adaptively retrieves and composes multiple LoRAs based on input prompts. RAMoLE has three main components: LoraRetriever for identifying and retrieving relevant LoRAs, an on-the-fly MoLE mechanism for coordinating the retrieved LoRAs, and efficient batch inference for handling heterogeneous requests. Experimental results show that RAMoLE consistently outperforms baselines, highlighting its effectiveness and scalability.
Authors: Yicheng Zhou, Pengfei Wang, Hao Dong, Denghui Zhang, Dingqi Yang, Yanjie Fu, Pengyang Wang
Abstract: Urban traffic speed prediction aims to estimate the future traffic speed for improving urban transportation services. Enormous efforts have been made to exploit Graph Neural Networks (GNNs) for modeling spatial correlations and temporal dependencies of traffic speed evolving patterns, regularized by graph topology.While achieving promising results, current traffic speed prediction methods still suffer from ignoring topology-free patterns, which cannot be captured by GNNs. To tackle this challenge, we propose a generic model for enabling the current GNN-based methods to preserve topology-free patterns. Specifically, we first develop a Dual Cross-Scale Transformer (DCST) architecture, including a Spatial Transformer and a Temporal Transformer, to preserve the cross-scale topology-free patterns and associated dynamics, respectively. Then, to further integrate both topology-regularized/-free patterns, we propose a distillation-style learning framework, in which the existing GNN-based methods are considered as the teacher model, and the proposed DCST architecture is considered as the student model. The teacher model would inject the learned topology-regularized patterns into the student model for integrating topology-free patterns. The extensive experimental results demonstrated the effectiveness of our methods.
Authors: Ding Wang
Abstract: Gas recognition technology has received considerable attention from researchers in recent years. Nevertheless, the gas recognition area has faced obstacles in implementing deep learning-based recognition solutions due to the absence of standardized protocols. To tackle this problem, we suggest using two sets of specialized evaluation measures for gas recognition algorithms. These metrics will make it easier to examine the performance of these algorithms on various datasets. In addition, we provide a new model called the Wavelet Attention GRU (WAG), which is based on the wavelet attention mechanism. This method facilitates the more efficient retrieval of sensor signals. Compared to other models, WAG significantly decreases the number of sensors needed by 75% while obtaining an identification accuracy of 98.33%. This suggests that WAG is a potential approach for advancing gas recognition algorithms.
Authors: Quentin Renau, Emma Hart
Abstract: Algorithm-selection (AS) methods are essential in order to obtain the best performance from a portfolio of solvers over large sets of instances. However, many AS methods rely on an analysis phase, e.g. where features are computed by sampling solutions and used as input in a machine-learning model. For AS to be efficient, it is therefore important that this analysis phase is not computationally expensive. We propose a method for identifying easy instances which can be solved quickly using a generalist solver without any need for algorithm-selection. This saves computational budget associated with feature-computation which can then be used elsewhere in an AS pipeline, e.g., enabling additional function evaluations on hard problems. Experiments on the BBOB dataset in two settings (batch and streaming) show that identifying easy instances results in substantial savings in function evaluations. Re-allocating the saved budget to hard problems provides gains in performance compared to both the virtual best solver (VBS) computed with the original budget, the single best solver (SBS) and a trained algorithm-selector.
Authors: Vismaya V S, Bharath V Nair, Sishu Shankar Muni
Abstract: This paper explores the prediction of the dynamics of piecewise smooth maps using various deep learning models. We have shown various novel ways of predicting the dynamics of piecewise smooth maps using deep learning models. Moreover, we have used machine learning models such as Decision Tree Classifier, Logistic Regression, K-Nearest Neighbor, Random Forest, and Support Vector Machine for predicting the border collision bifurcation in the 1D normal form map and the 1D tent map. Further, we classified the regular and chaotic behaviour of the 1D tent map and the 2D Lozi map using deep learning models like Convolutional Neural Network (CNN), ResNet50, and ConvLSTM via cobweb diagram and phase portraits. We also classified the chaotic and hyperchaotic behaviour of the 3D piecewise smooth map using deep learning models such as the Feed Forward Neural Network (FNN), Long Short-Term Memory (LSTM), and Recurrent Neural Network (RNN). Finally, deep learning models such as Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) are used for reconstructing the two parametric charts of 2D border collision bifurcation normal form map.
Authors: Ricardo In\'acio, Vitor Cerqueira, Mar\'ilia Barandas, Carlos Soares
Abstract: The effectiveness of univariate forecasting models is often hampered by conditions that cause them stress. A model is considered to be under stress if it shows a negative behaviour, such as higher-than-usual errors or increased uncertainty. Understanding the factors that cause stress to forecasting models is important to improve their reliability, transparency, and utility. This paper addresses this problem by contributing with a novel framework called MAST (Meta-learning and data Augmentation for Stress Testing). The proposed approach aims to model and characterize stress in univariate time series forecasting models, focusing on conditions where they exhibit large errors. In particular, MAST is a meta-learning approach that predicts the probability that a given model will perform poorly on a given time series based on a set of statistical time series features. MAST also encompasses a novel data augmentation technique based on oversampling to improve the metadata concerning stress. We conducted experiments using three benchmark datasets that contain a total of 49.794 time series to validate the performance of MAST. The results suggest that the proposed approach is able to identify conditions that lead to large errors. The method and experiments are publicly available in a repository.
Authors: Mahdi Mohammadizadeh, Arash Mozhdehi, Yani Ioannou, Xin Wang
Abstract: Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skewness of the distribution of classes; therefore, tend to be biased towards the majority class(es). Conventional methods typically tackle this problem through the assignment of weights to each one of the class samples based on a function of their loss, which can lead to over-fitting on outliers. In this paper, we propose a meta-learning algorithm, named Meta-GCN, for adaptively learning the example weights by simultaneously minimizing the unbiased meta-data set loss and optimizing the model weights through the use of a small unbiased meta-data set. Through experiments, we have shown that Meta-GCN outperforms state-of-the-art frameworks and other baselines in terms of accuracy, the area under the receiver operating characteristic (AUC-ROC) curve, and macro F1-Score for classification tasks on two different datasets.
Authors: Yudan Wang, Shaofeng Zou, Yue Wang
Abstract: Distributionally Robust Reinforcement Learning (DR-RL) aims to derive a policy optimizing the worst-case performance within a predefined uncertainty set. Despite extensive research, previous DR-RL algorithms have predominantly favored model-based approaches, with limited availability of model-free methods offering convergence guarantees or sample complexities. This paper proposes a model-free DR-RL algorithm leveraging the Multi-level Monte Carlo (MLMC) technique to close such a gap. Our innovative approach integrates a threshold mechanism that ensures finite sample requirements for algorithmic implementation, a significant improvement than previous model-free algorithms. We develop algorithms for uncertainty sets defined by total variation, Chi-square divergence, and KL divergence, and provide finite sample analyses under all three cases. Remarkably, our algorithms represent the first model-free DR-RL approach featuring finite sample complexity for total variation and Chi-square divergence uncertainty sets, while also offering an improved sample complexity and broader applicability compared to existing model-free DR-RL algorithms for the KL divergence model. The complexities of our method establish the tightest results for all three uncertainty models in model-free DR-RL, underscoring the effectiveness and efficiency of our algorithm, and highlighting its potential for practical applications.
Authors: Vivek Myers, Chongyi Zheng, Anca Dragan, Sergey Levine, Benjamin Eysenbach
Abstract: Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distances in stochastic settings have been stymied by an important limitation: these prior approaches do not satisfy the triangle inequality. This is not merely a definitional concern, but translates to an inability to generalize and find shortest paths. In this paper, we build on prior work in contrastive learning and quasimetrics to show how successor features learned by contrastive learning (after a change of variables) form a temporal distance that does satisfy the triangle inequality, even in stochastic settings. Importantly, this temporal distance is computationally efficient to estimate, even in high-dimensional and stochastic settings. Experiments in controlled settings and benchmark suites demonstrate that an RL algorithm based on these new temporal distances exhibits combinatorial generalization (i.e., "stitching") and can sometimes learn more quickly than prior methods, including those based on quasimetrics.
Authors: Disha Makhija, Xing Han, Joydeep Ghosh, Yejin Kim
Abstract: Achieving fairness across diverse clients in Federated Learning (FL) remains a significant challenge due to the heterogeneity of the data and the inaccessibility of sensitive attributes from clients' private datasets. This study addresses this issue by introducing \texttt{EquiFL}, a novel approach designed to enhance both local and global fairness in federated learning environments. \texttt{EquiFL} incorporates a fairness term into the local optimization objective, effectively balancing local performance and fairness. The proposed coordination mechanism also prevents bias from propagating across clients during the collaboration phase. Through extensive experiments across multiple benchmarks, we demonstrate that \texttt{EquiFL} not only strikes a better balance between accuracy and fairness locally at each client but also achieves global fairness. The results also indicate that \texttt{EquiFL} ensures uniform performance distribution among clients, thus contributing to performance fairness. Furthermore, we showcase the benefits of \texttt{EquiFL} in a real-world distributed dataset from a healthcare application, specifically in predicting the effects of treatments on patients across various hospital locations.
Authors: Kassi Muhammad, Teef David, Giulia Nassisid, Tina Farus
Abstract: As telecommunications networks become increasingly complex, the integration of advanced technologies such as network digital twins and generative artificial intelligence (AI) emerges as a pivotal solution to enhance network operations and resilience. This paper explores the synergy between network digital twins, which provide a dynamic virtual representation of physical networks, and generative AI, particularly focusing on Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). We propose a novel architectural framework that incorporates these technologies to significantly improve predictive maintenance, network scenario simulation, and real-time data-driven decision-making. Through extensive simulations, we demonstrate how generative AI can enhance the accuracy and operational efficiency of network digital twins, effectively handling real-world complexities such as unpredictable traffic loads and network failures. The findings suggest that this integration not only boosts the capability of digital twins in scenario forecasting and anomaly detection but also facilitates a more adaptive and intelligent network management system.
Authors: Jeremy McMahan, Young Wu, Yudong Chen, Xiaojin Zhu, Qiaomin Xie
Abstract: We study security threats to Markov games due to information asymmetry and misinformation. We consider an attacker player who can spread misinformation about its reward function to influence the robust victim player's behavior. Given a fixed fake reward function, we derive the victim's policy under worst-case rationality and present polynomial-time algorithms to compute the attacker's optimal worst-case policy based on linear programming and backward induction. Then, we provide an efficient inception ("planting an idea in someone's mind") attack algorithm to find the optimal fake reward function within a restricted set of reward functions with dominant strategies. Importantly, our methods exploit the universal assumption of rationality to compute attacks efficiently. Thus, our work exposes a security vulnerability arising from standard game assumptions under misinformation.
Authors: Zhihui Tian, John Upchurch, G. Austin Simon, Jos\'e Dubeux, Alina Zare, Chang Zhao, Joel B. Harley
Abstract: Understanding and quantifying ecosystem services are crucial for sustainable environmental management, conservation efforts, and policy-making. The advancement of remote sensing technology and machine learning techniques has greatly facilitated this process. Yet, ground truth labels, such as biodiversity, are very difficult and expensive to measure. In addition, more easily obtainable proxy labels, such as land use, often fail to capture the complex heterogeneity of the ecosystem. In this paper, we demonstrate how land use proxy labels can be implemented with a soft, multi-label classifier to predict ecosystem services with complex heterogeneity.
Authors: Bruce Rushing
Abstract: Mixture of experts is a prediction aggregation method in machine learning that aggregates the predictions of specialized experts. This method often outperforms Bayesian methods despite the Bayesian having stronger inductive guarantees. We argue that this is due to the greater functional capacity of mixture of experts. We prove that in a limiting case of mixture of experts will have greater capacity than equivalent Bayesian methods, which we vouchsafe through experiments on non-limiting cases. Finally, we conclude that mixture of experts is a type of abductive reasoning in the Peircian sense of hypothesis construction.
Authors: Hongkang Li, Meng Wang, Shuai Zhang, Sijia Liu, Pin-Yu Chen
Abstract: Efficient training and inference algorithms, such as low-rank adaption and model pruning, have shown impressive performance for learning Transformer-based large foundation models. However, due to the technical challenges of the non-convex optimization caused by the complicated architecture of Transformers, the theoretical study of why these methods can be applied to learn Transformers is mostly elusive. To the best of our knowledge, this paper shows the first theoretical analysis of the property of low-rank and sparsity of one-layer Transformers by characterizing the trained model after convergence using stochastic gradient descent. By focusing on a data model based on label-relevant and label-irrelevant patterns, we quantify that the gradient updates of trainable parameters are low-rank, which depends on the number of label-relevant patterns. We also analyze how model pruning affects the generalization while improving computation efficiency and conclude that proper magnitude-based pruning has a slight effect on the testing performance. We implement numerical experiments to support our findings.
Authors: Abhinav Narayan Harish, Larry Heck, Josiah P. Hanna, Zsolt Kira, Andrew Szot
Abstract: We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill), a new method that enables reinforcement learning (RL) to perform long-horizon robot control problems by distilling behaviors from auxiliary RL tasks. AuxDistill achieves this by concurrently carrying out multi-task RL with auxiliary tasks, which are easier to learn and relevant to the main task. A weighted distillation loss transfers behaviors from these auxiliary tasks to solve the main task. We demonstrate that AuxDistill can learn a pixels-to-actions policy for a challenging multi-stage embodied object rearrangement task from the environment reward without demonstrations, a learning curriculum, or pre-trained skills. AuxDistill achieves $2.3 \times$ higher success than the previous state-of-the-art baseline in the Habitat Object Rearrangement benchmark and outperforms methods that use pre-trained skills and expert demonstrations.
Authors: Xueping Gong, Jiheng Zhang
Abstract: Dynamic pricing, the practice of adjusting prices based on contextual factors, has gained significant attention due to its impact on revenue maximization. In this paper, we address the contextual dynamic pricing problem, which involves pricing decisions based on observable product features and customer characteristics. We propose a novel algorithm that achieves improved regret bounds while minimizing assumptions about the problem. Our algorithm discretizes the unknown noise distribution and combines the upper confidence bounds with a layered data partitioning technique to effectively regulate regret in each episode. These techniques effectively control the regret associated with pricing decisions, leading to the minimax optimality. Specifically, our algorithm achieves a regret upper bound of $\tilde{\mathcal{O}}(\rho_{\mathcal{V}}^{\frac{1}{3}}(\delta) T^{\frac{2}{3}})$, where $\rho_{\mathcal{V}}(\delta)$ represents the estimation error of the valuation function. Importantly, this bound matches the lower bound up to logarithmic terms, demonstrating the minimax optimality of our approach. Furthermore, our method extends beyond linear valuation models commonly used in dynamic pricing by considering general function spaces. We simplify the estimation process by reducing it to general offline regression oracles, making implementation more straightforward.
Authors: Anish Acharya, Inderjit S Dhillon, Sujay Sanghavi
Abstract: Data pruning, the combinatorial task of selecting a small and informative subset from a large dataset, is crucial for mitigating the enormous computational costs associated with training data-hungry modern deep learning models at scale. Since large-scale data collections are invariably noisy, developing data pruning strategies that remain robust even in the presence of corruption is critical in practice. Unfortunately, the existing heuristics for (robust) data pruning lack theoretical coherence and rely on heroic assumptions, that are, often unattainable, by the very nature of the problem setting. Moreover, these strategies often yield sub-optimal neural scaling laws even compared to random sampling, especially in scenarios involving strong corruption and aggressive pruning rates -- making provably robust data pruning an open challenge. In response, in this work, we propose Geometric Median ($\gm$) Matching -- a herding~\citep{welling2009herding} style greedy algorithm -- that yields a $k$-subset such that the mean of the subset approximates the geometric median of the (potentially) noisy dataset. Theoretically, we show that $\gm$ Matching enjoys an improved $\gO(1/k)$ scaling over $\gO(1/\sqrt{k})$ scaling of uniform sampling; while achieving the optimal breakdown point of 1/2 even under arbitrary corruption. Extensive experiments across popular deep learning benchmarks indicate that $\gm$ Matching consistently outperforms prior state-of-the-art; the gains become more profound at high rates of corruption and aggressive pruning rates; making $\gm$ Matching a strong baseline for future research in robust data pruning.
Authors: Jianyuan Bo, Yuan Fang
Abstract: Graph matching has important applications in pattern recognition and beyond. Current approaches predominantly adopt supervised learning, demanding extensive labeled data which can be limited or costly. Meanwhile, self-supervised learning methods for graph matching often require additional side information such as extra categorical information and input features, limiting their application to the general case. Moreover, designing the optimal graph augmentations for self-supervised graph matching presents another challenge to ensure robustness and efficacy. To address these issues, we introduce a novel Graph-centric Contrastive framework for Graph Matching (GCGM), capitalizing on a vast pool of graph augmentations for contrastive learning, yet without needing any side information. Given the variety of augmentation choices, we further introduce a Boosting-inspired Adaptive Augmentation Sampler (BiAS), which adaptively selects more challenging augmentations tailored for graph matching. Through various experiments, our GCGM surpasses state-of-the-art self-supervised methods across various datasets, marking a significant step toward more effective, efficient and general graph matching.
Authors: Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu, Gautam Kamath, Ayush Sekhari, Seth Neel
Abstract: We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning methods is to remove the effects of training on poisoned data. We experimentally demonstrate that, while existing unlearning methods have been demonstrated to be effective in a number of evaluation settings (e.g., alleviating membership inference attacks), they fail to remove the effects of data poisoning, across a variety of types of poisoning attacks (indiscriminate, targeted, and a newly-introduced Gaussian poisoning attack) and models (image classifiers and LLMs); even when granted a relatively large compute budget. In order to precisely characterize unlearning efficacy, we introduce new evaluation metrics for unlearning based on data poisoning. Our results suggest that a broader perspective, including a wider variety of evaluations, is required to avoid a false sense of confidence in machine unlearning procedures for deep learning without provable guarantees. Moreover, while unlearning methods show some signs of being useful to efficiently remove poisoned datapoints without having to retrain, our work suggests that these methods are not yet "ready for prime time", and currently provide limited benefit over retraining.
Authors: Vahid Jebraeeli, Bo Jiang, Hamid Krim, Derya Cansever
Abstract: The challenge of limited availability of data for training in machine learning arises in many applications and the impact on performance and generalization is serious. Traditional data augmentation methods aim to enhance training with a moderately sufficient data set. Generative models like Generative Adversarial Networks (GANs) often face problematic convergence when generating significant and diverse data samples. Diffusion models, though effective, still struggle with high computational cost and long training times. This paper introduces an innovative Expansive Synthesis model that generates large-scale, high-fidelity datasets from minimal samples. The proposed approach exploits expander graph mappings and feature interpolation to synthesize expanded datasets while preserving the intrinsic data distribution and feature structural relationships. The rationale of the model is rooted in the non-linear property of neural networks' latent space and in its capture by a Koopman operator to yield a linear space of features to facilitate the construction of larger and enriched consistent datasets starting with a much smaller dataset. This process is optimized by an autoencoder architecture enhanced with self-attention layers and further refined for distributional consistency by optimal transport. We validate our Expansive Synthesis by training classifiers on the generated datasets and comparing their performance to classifiers trained on larger, original datasets. Experimental results demonstrate that classifiers trained on synthesized data achieve performance metrics on par with those trained on full-scale datasets, showcasing the model's potential to effectively augment training data. This work represents a significant advancement in data generation, offering a robust solution to data scarcity and paving the way for enhanced data availability in machine learning applications.
Authors: Wenyu Du, Shuang Cheng, Tongxu Luo, Zihan Qiu, Zeyu Huang, Ka Chun Cheung, Reynold Cheng, Jie Fu
Abstract: Language models (LMs) exhibit impressive performance and generalization capabilities. However, LMs struggle with the persistent challenge of catastrophic forgetting, which undermines their long-term sustainability in continual learning (CL). Existing approaches usually address the issue by incorporating old task data or task-wise inductive bias into LMs. However, old data and accurate task information are often unavailable or costly to collect, hindering the availability of current CL approaches for LMs. To address this limitation, we introduce $\textbf{MIGU}$ ($\textbf{M}$agn$\textbf{I}$tude-based $\textbf{G}$radient $\textbf{U}$pdating for continual learning), a rehearsal-free and task-label-free method that only updates the model parameters with large magnitudes of output in LMs' linear layers. MIGU is based on our observation that the L1-normalized magnitude distribution of the output in LMs' linear layers is different when the LM models deal with different task data. By imposing this simple constraint on the gradient update process, we can leverage the inherent behaviors of LMs, thereby unlocking their innate CL abilities. Our experiments demonstrate that MIGU is universally applicable to all three LM architectures (T5, RoBERTa, and Llama2), delivering state-of-the-art or on-par performance across continual finetuning and continual pre-training settings on four CL benchmarks. For example, MIGU brings a 15.2% average accuracy improvement over conventional parameter-efficient finetuning baselines in a 15-task CL benchmark. MIGU can also seamlessly integrate with all three existing CL types to further enhance performance. Code is available at \href{https://github.com/wenyudu/MIGU}{this https URL}.
Authors: Yuzhou Chen, Jose Frias, Yulia R. Gel
Abstract: Graph contrastive learning (GCL) has recently emerged as a new concept which allows for capitalizing on the strengths of graph neural networks (GNNs) to learn rich representations in a wide variety of applications which involve abundant unlabeled information. However, existing GCL approaches largely tend to overlook the important latent information on higher-order graph substructures. We address this limitation by introducing the concepts of topological invariance and extended persistence on graphs to GCL. In particular, we propose a new contrastive mode which targets topological representations of the two augmented views from the same graph, yielded by extracting latent shape properties of the graph at multiple resolutions. Along with the extended topological layer, we introduce a new extended persistence summary, namely, extended persistence landscapes (EPL) and derive its theoretical stability guarantees. Our extensive numerical results on biological, chemical, and social interaction graphs show that the new Topological Graph Contrastive Learning (TopoGCL) model delivers significant performance gains in unsupervised graph classification for 11 out of 12 considered datasets and also exhibits robustness under noisy scenarios.
Authors: Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang, Sebastian Reich, Andrew M. Stuart
Abstract: In this paper, we study efficient approximate sampling for probability distributions known up to normalization constants. We specifically focus on a problem class arising in Bayesian inference for large-scale inverse problems in science and engineering applications. The computational challenges we address with the proposed methodology are: (i) the need for repeated evaluations of expensive forward models; (ii) the potential existence of multiple modes; and (iii) the fact that gradient of, or adjoint solver for, the forward model might not be feasible. While existing Bayesian inference methods meet some of these challenges individually, we propose a framework that tackles all three systematically. Our approach builds upon the Fisher-Rao gradient flow in probability space, yielding a dynamical system for probability densities that converges towards the target distribution at a uniform exponential rate. This rapid convergence is advantageous for the computational burden outlined in (i). We apply Gaussian mixture approximations with operator splitting techniques to simulate the flow numerically; the resulting approximation can capture multiple modes thus addressing (ii). Furthermore, we employ the Kalman methodology to facilitate a derivative-free update of these Gaussian components and their respective weights, addressing the issue in (iii). The proposed methodology results in an efficient derivative-free sampler flexible enough to handle multi-modal distributions: Gaussian Mixture Kalman Inversion (GMKI). The effectiveness of GMKI is demonstrated both theoretically and numerically in several experiments with multimodal target distributions, including proof-of-concept and two-dimensional examples, as well as a large-scale application: recovering the Navier-Stokes initial condition from solution data at positive times.
Authors: Van Tung Pham, Yist Lin, Tao Han, Wei Li, Jun Zhang, Lu Lu, Yuxuan Wang
Abstract: Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce speech-text alignment, and high insertion errors especially in domain mismatch conditions. This paper presents a comprehensive solution to address these issues. We begin by investigating more thoughtful fine-tuning schemes. Next, we propose a matching loss to enhance alignment between modalities. Finally, we explore training and inference methods to mitigate high insertion errors. Experimental results on the Librispeech corpus demonstrate that partially fine-tuning the encoder and LLM using parameter-efficient methods, such as LoRA, is the most cost-effective approach. Additionally, the matching loss improves modality alignment, enhancing performance. The proposed training and inference methods significantly reduce insertion errors.
Authors: Dong Liu, Meng Jiang
Abstract: This paper introduces novel methodologies, the Distance Recomputator and Topology Reconstructor, aimed at enhancing Graph Neural Networks (GNNs). The Distance Recomputator dynamically recalibrates node distances within k-hop neighborhoods using a dynamic encoding scheme, thereby improving the accuracy and adaptability of node representations. Concurrently, the Topology Reconstructor adjusts local graph structures based on computed "similarity distances," optimizing network configurations for improved learning outcomes. These methods address the limitations of static node representations and fixed aggregation schemes in traditional GNNs, offering a more nuanced approach to modeling complex and dynamic graph topologies. Furthermore, our experimental evaluations demonstrate significant performance advantages over existing methods across various benchmark datasets. The proposed Distance Recomputator and Topology Reconstructor not only enhance node relationship modeling accuracy but also optimize information aggregation efficiency through an asynchronous aggregation mechanism. This approach proves particularly effective in scenarios involving dynamic or large-scale graphs, showcasing the methods' robustness and applicability in real-world graph learning tasks.
Authors: Amrutha Varshini Ramesh, Vignesh Ganapathiraman, Issam H. Laradji, Mark Schmidt
Abstract: Training large language models (LLMs) for pretraining or adapting to new tasks and domains has become increasingly critical as their applications expand. However, as the model and the data sizes grow, the training process presents significant memory challenges, often requiring a prohibitive amount of GPU memory that may not be readily available. Existing methods such as low-rank adaptation (LoRA) add trainable low-rank matrix factorizations, altering the training dynamics and limiting the model's parameter search to a low-rank subspace. GaLore, a more recent method, employs Gradient Low-Rank Projection to reduce the memory footprint, in the full parameter training setting. However GaLore can only be applied to a subset of the LLM layers that satisfy the "reversibility" property, thus limiting their applicability. In response to these challenges, we introduce BlockLLM, an approach inspired by block coordinate descent. Our method carefully selects and updates a very small subset of the trainable parameters without altering any part of its architecture and training procedure. BlockLLM achieves state-of-the-art performance in both finetuning and pretraining tasks, while reducing the memory footprint of the underlying optimization process. Our experiments demonstrate that fine-tuning with only less than 5% of the parameters, BlockLLM achieves state-of-the-art perplexity scores on the GLUE benchmarks. On Llama model pretrained on C4 dataset, BlockLLM is able to train with significantly less memory than the state-of-the-art, while still maintaining competitive performance.
Authors: Sebastian Rodriguez Beltran, Marlon Tobaben, Niki Loppi, Antti Honkela
Abstract: Differentially private stochastic gradient descent (DP-SGD) is the standard algorithm for training machine learning models under differential privacy (DP). The major drawback of DP-SGD is the drop in utility which prior work has comprehensively studied. However, in practice another major drawback that hinders the large-scale deployment is the significantly higher computational cost. We conduct a comprehensive empirical study to quantify the computational cost of training deep learning models under DP and benchmark methods that aim at reducing the cost. Among these are more efficient implementations of DP-SGD and training with lower precision. Finally, we study the scaling behaviour using up to 80 GPUs.
Authors: Valentin Margraf, Marcel Wever, Sandra Gilhuber, Gabriel Marques Tavares, Thomas Seidl, Eyke H\"ullermeier
Abstract: In settings where only a budgeted amount of labeled data can be afforded, active learning seeks to devise query strategies for selecting the most informative data points to be labeled, aiming to enhance learning algorithms' efficiency and performance. Numerous such query strategies have been proposed and compared in the active learning literature. However, the community still lacks standardized benchmarks for comparing the performance of different query strategies. This particularly holds for the combination of query strategies with different learning algorithms into active learning pipelines and examining the impact of the learning algorithm choice. To close this gap, we propose ALPBench, which facilitates the specification, execution, and performance monitoring of active learning pipelines. It has built-in measures to ensure evaluations are done reproducibly, saving exact dataset splits and hyperparameter settings of used algorithms. In total, ALPBench consists of 86 real-world tabular classification datasets and 5 active learning settings, yielding 430 active learning problems. To demonstrate its usefulness and broad compatibility with various learning algorithms and query strategies, we conduct an exemplary study evaluating 9 query strategies paired with 8 learning algorithms in 2 different settings. We provide ALPBench here: https://github.com/ValentinMargraf/ActiveLearningPipelines.
URLs: https://github.com/ValentinMargraf/ActiveLearningPipelines.
Authors: Manuel Madeira, Clement Vignac, Dorina Thanou, Pascal Frossard
Abstract: Graph diffusion models have emerged as state-of-the-art techniques in graph generation, yet integrating domain knowledge into these models remains challenging. Domain knowledge is particularly important in real-world scenarios, where invalid generated graphs hinder deployment in practical applications. Unconstrained and conditioned graph generative models fail to guarantee such domain-specific structural properties. We present ConStruct, a novel framework that allows for hard-constraining graph diffusion models to incorporate specific properties, such as planarity or acyclicity. Our approach ensures that the sampled graphs remain within the domain of graphs that verify the specified property throughout the entire trajectory in both the forward and reverse processes. This is achieved by introducing a specific edge-absorbing noise model and a new projector operator. ConStruct demonstrates versatility across several structural and edge-deletion invariant constraints and achieves state-of-the-art performance for both synthetic benchmarks and attributed real-world datasets. For example, by leveraging planarity in digital pathology graph datasets, the proposed method outperforms existing baselines and enhances generated data validity by up to 71.1 percentage points.
Authors: Stephan Hasler, Lydia Fischer
Abstract: Machine learning is more and more applied in critical application areas like health and driver assistance. To minimize the risk of wrong decisions, in such applications it is necessary to consider the certainty of a classification to reject uncertain samples. An established tool for this are reject curves that visualize the trade-off between the number of rejected samples and classification performance metrics. We argue that common reject curves are too abstract and hard to interpret by non-experts. We propose Stacked Confusion Reject Plots (SCORE) that offer a more intuitive understanding of the used data and the classifier's behavior. We present example plots on artificial Gaussian data to document the different options of SCORE and provide the code as a Python package.
Authors: Federico Matteucci, Vadim Arzamasov, Jose Cribeiro-Ramallo, Marco Heyden, Konstantin Ntounas, Klemens B\"ohm
Abstract: Experimental studies are a cornerstone of machine learning (ML) research. A common, but often implicit, assumption is that the results of a study will generalize beyond the study itself, e.g. to new data. That is, there is a high probability that repeating the study under different conditions will yield similar results. Despite the importance of the concept, the problem of measuring generalizability remains open. This is probably due to the lack of a mathematical formalization of experimental studies. In this paper, we propose such a formalization and develop a quantifiable notion of generalizability. This notion allows to explore the generalizability of existing studies and to estimate the number of experiments needed to achieve the generalizability of new studies. To demonstrate its usefulness, we apply it to two recently published benchmarks to discern generalizable and non-generalizable results. We also publish a Python module that allows our analysis to be repeated for other experimental studies.
Authors: Nghia D. Nguyen, Hieu Trung Nguyen, Ang Li, Hoang Pham, Viet Anh Nguyen, Khoa D. Doan
Abstract: Intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which hinders remembering past knowledge. To mitigate this issue, existing Continual Learning (CL) approaches either retain exemplars for replay, regularize learning, or allocate dedicated capacity for new tasks. This paper investigates an unexplored CL direction for incremental learning called Incremental Latent Rectification or ILR. In a nutshell, ILR learns to propagate with correction (or rectify) the representation from the current trained DNN backward to the representation space of the old task, where performing predictive decisions is easier. This rectification process only employs a chain of small representation mapping networks, called rectifier units. Empirical experiments on several continual learning benchmarks, including CIFAR10, CIFAR100, and Tiny ImageNet, demonstrate the effectiveness and potential of this novel CL direction compared to existing representative CL methods.
Authors: Philipp Vaeth, Alexander M. Fruehwald, Benjamin Paassen, Magda Gregorova
Abstract: To sample from an unconditionally trained Denoising Diffusion Probabilistic Model (DDPM), classifier guidance adds conditional information during sampling, but the gradients from classifiers, especially those not trained on noisy images, are often unstable. This study conducts a gradient analysis comparing robust and non-robust classifiers, as well as multiple gradient stabilization techniques. Experimental results demonstrate that these techniques significantly improve the quality of class-conditional samples for non-robust classifiers by providing more stable and informative classifier guidance gradients. The findings highlight the importance of gradient stability in enhancing the performance of classifier guidance, especially on non-robust classifiers.
Authors: Jielin Chen, Rudi Stouffs
Abstract: Despite the suitability of graphs for capturing the relational structures inherent in architectural layout designs, there is a notable dearth of research on interpreting architectural design space using graph-based representation learning and exploring architectural design graph generation. Concurrently, disentangled representation learning in graph generation faces challenges such as node permutation invariance and representation expressiveness. To address these challenges, we introduce an unsupervised disentangled representation learning framework, Style-based Edge-augmented Variational Graph Auto-Encoder (SE-VGAE), aiming to generate architectural layout in the form of attributed adjacency multi-graphs while prioritizing representation disentanglement. The framework is designed with three alternative pipelines, each integrating a transformer-based edge-augmented encoder, a latent space disentanglement module, and a style-based decoder. These components collectively facilitate the decomposition of latent factors influencing architectural layout graph generation, enhancing generation fidelity and diversity. We also provide insights into optimizing the framework by systematically exploring graph feature augmentation schemes and evaluating their effectiveness for disentangling architectural layout representation through extensive experiments. Additionally, we contribute a new benchmark large-scale architectural layout graph dataset extracted from real-world floor plan images to facilitate the exploration of graph data-based architectural design representation space interpretation. This study pioneered disentangled representation learning for the architectural layout graph generation. The code and dataset of this study will be open-sourced.
Authors: Zhen Chen, Yong Liao, Youpeng Zhao, Zipeng Dai, Jian Zhao
Abstract: Cooperative Multi-Agent Reinforcement Learning (CMARL) strategies are well known to be vulnerable to adversarial perturbations. Previous works on adversarial attacks have primarily focused on white-box attacks that directly perturb the states or actions of victim agents, often in scenarios with a limited number of attacks. However, gaining complete access to victim agents in real-world environments is exceedingly difficult. To create more realistic adversarial attacks, we introduce a novel method that involves injecting traitor agents into the CMARL system. We model this problem as a Traitor Markov Decision Process (TMDP), where traitors cannot directly attack the victim agents but can influence their formation or positioning through collisions. In TMDP, traitors are trained using the same MARL algorithm as the victim agents, with their reward function set as the negative of the victim agents' reward. Despite this, the training efficiency for traitors remains low because it is challenging for them to directly associate their actions with the victim agents' rewards. To address this issue, we propose the Curiosity-Driven Adversarial Attack (CuDA2) framework. CuDA2 enhances the efficiency and aggressiveness of attacks on the specified victim agents' policies while maintaining the optimal policy invariance of the traitors. Specifically, we employ a pre-trained Random Network Distillation (RND) module, where the extra reward generated by the RND module encourages traitors to explore states unencountered by the victim agents. Extensive experiments on various scenarios from SMAC demonstrate that our CuDA2 framework offers comparable or superior adversarial attack capabilities compared to other baselines.
Authors: Irina Perfilievaa, Nicolas Madrid, Manuel Ojeda-Aciego, Piotr Artiemjew, Agnieszka Niemczynowicz
Abstract: Despite the number of successful applications of the Extreme Learning Machine (ELM), we show that its underlying foundational principles do not have a rigorous mathematical justification. Specifically, we refute the proofs of two main statements, and we also create a dataset that provides a counterexample to the ELM learning algorithm and explain its design, which leads to many such counterexamples. Finally, we provide alternative statements of the foundations, which justify the efficiency of ELM in some theoretical cases.
Authors: Jessica Schrouff, Alexis Bellot, Amal Rannen-Triki, Alan Malek, Isabela Albuquerque, Arthur Gretton, Alexander D'Amour, Silvia Chiappa
Abstract: Failures of fairness or robustness in machine learning predictive settings can be due to undesired dependencies between covariates, outcomes and auxiliary factors of variation. A common strategy to mitigate these failures is data balancing, which attempts to remove those undesired dependencies. In this work, we define conditions on the training distribution for data balancing to lead to fair or robust models. Our results display that, in many cases, the balanced distribution does not correspond to selectively removing the undesired dependencies in a causal graph of the task, leading to multiple failure modes and even interference with other mitigation techniques such as regularization. Overall, our results highlight the importance of taking the causal graph into account before performing data balancing.
Authors: Jirko Rubruck, Jan P. Bauer, Andrew Saxe, Christopher Summerfield
Abstract: Deep neural networks learn increasingly complex functions over the course of training. Here, we show both empirically and theoretically that learning of the target function is preceded by an early phase in which networks learn the optimal constant solution (OCS) - that is, initial model responses mirror the distribution of target labels, while entirely ignoring information provided in the input. Using a hierarchical category learning task, we derive exact solutions for learning dynamics in deep linear networks trained with bias terms. Even when initialized to zero, this simple architectural feature induces substantial changes in early dynamics. We identify hallmarks of this early OCS phase and illustrate how these signatures are observed in deep linear networks and larger, more complex (and nonlinear) convolutional neural networks solving a hierarchical learning task based on MNIST and CIFAR10. We explain these observations by proving that deep linear networks necessarily learn the OCS during early learning. To further probe the generality of our results, we train human learners over the course of three days on the category learning task. We then identify qualitative signatures of this early OCS phase in terms of the dynamics of true negative (correct-rejection) rates. Surprisingly, we find the same early reliance on the OCS in the behaviour of human learners. Finally, we show that learning of the OCS can emerge even in the absence of bias terms and is equivalently driven by generic correlations in the input data. Overall, our work suggests the OCS as a universal learning principle in supervised, error-corrective learning, and the mechanistic reasons for its prevalence.
Authors: Jintao Yan, Tan Chen, Yuxuan Sun, Zhaojun Nan, Sheng Zhou, Zhisheng Niu
Abstract: Leveraging the computing and sensing capabilities of vehicles, vehicular federated learning (VFL) has been applied to edge training for connected vehicles. The dynamic and interconnected nature of vehicular networks presents unique opportunities to harness direct vehicle-to-vehicle (V2V) communications, enhancing VFL training efficiency. In this paper, we formulate a stochastic optimization problem to optimize the VFL training performance, considering the energy constraints and mobility of vehicles, and propose a V2V-enhanced dynamic scheduling (VEDS) algorithm to solve it. The model aggregation requirements of VFL and the limited transmission time due to mobility result in a stepwise objective function, which presents challenges in solving the problem. We thus propose a derivative-based drift-plus-penalty method to convert the long-term stochastic optimization problem to an online mixed integer nonlinear programming (MINLP) problem, and provide a theoretical analysis to bound the performance gap between the online solution and the offline optimal solution. Further analysis of the scheduling priority reduces the original problem into a set of convex optimization problems, which are efficiently solved using the interior-point method. Experimental results demonstrate that compared with the state-of-the-art benchmarks, the proposed algorithm enhances the image classification accuracy on the CIFAR-10 dataset by 3.18% and reduces the average displacement errors on the Argoverse trajectory prediction dataset by 10.21%.
Authors: Fu Feng, Yucheng Xie, Jing Wang, Xin Geng
Abstract: The expansion of model parameters underscores the significance of pre-trained models; however, the constraints encountered during model deployment necessitate models of variable sizes. Consequently, the traditional pre-training and fine-tuning paradigm fails to address the initialization problem when target models are incompatible with pre-trained models. We tackle this issue from a multitasking perspective and introduce \textbf{WAVE}, which incorporates a set of shared \textbf{W}eight templates for \textbf{A}daptive initialization of \textbf{V}ariable-siz\textbf{E}d Models. During initialization, target models will initialize the corresponding weight scalers tailored to their model size, which are sufficient to learn the connection rules of weight templates based on the Kronecker product from a limited amount of data. For the construction of the weight templates, WAVE utilizes the \textit{Learngene} framework, which structurally condenses common knowledge from ancestry models into weight templates as the learngenes through knowledge distillation. This process allows the integration of pre-trained models' knowledge into structured knowledge according to the rules of weight templates. We provide a comprehensive benchmark for the learngenes, and extensive experiments demonstrate the efficacy of WAVE. The results show that WAVE achieves state-of-the-art performance when initializing models with various depth and width, and even outperforms the direct pre-training of $n$ entire models, particularly for smaller models, saving approximately $n\times$ and $5\times$ in computational and storage resources, respectively. WAVE simultaneously achieves the most efficient knowledge transfer across a series of datasets, specifically achieving an average improvement of 1.8\% and 1.2\% on 7 downstream datasets.
Authors: Ge Chen, Yulan Hu, Sheng Ouyang, Yong Liu, Cuicui Luo
Abstract: Graph autoencoders (GAEs), as a kind of generative self-supervised learning approach, have shown great potential in recent years. GAEs typically rely on distance-based criteria, such as mean-square-error (MSE), to reconstruct the input graph. However, relying solely on a single reconstruction criterion may lead to a loss of distinctiveness in the reconstructed graph, causing nodes to collapse into similar representations and resulting in sub-optimal performance. To address this issue, we have developed a simple yet effective strategy to preserve the necessary distinctness in the reconstructed graph. Inspired by the knowledge distillation technique, we found that the dual encoder-decoder architecture of GAEs can be viewed as a teacher-student relationship. Therefore, we propose transferring the knowledge of distinctness from the raw graph to the reconstructed graph, achieved through a simple KL constraint. Specifically, we compute pairwise node similarity scores in the raw graph and reconstructed graph. During the training process, the KL constraint is optimized alongside the reconstruction criterion. We conducted extensive experiments across three types of graph tasks, demonstrating the effectiveness and generality of our strategy. This indicates that the proposed approach can be employed as a plug-and-play method to avoid vague reconstructions and enhance overall performance.
Authors: Johan Obando-Ceron, Jo\~ao G. M. Ara\'ujo, Aaron Courville, Pablo Samuel Castro
Abstract: Deep reinforcement learning (deep RL) has achieved tremendous success on various domains through a combination of algorithmic design and careful selection of hyper-parameters. Algorithmic improvements are often the result of iterative enhancements built upon prior approaches, while hyper-parameter choices are typically inherited from previous methods or fine-tuned specifically for the proposed technique. Despite their crucial impact on performance, hyper-parameter choices are frequently overshadowed by algorithmic advancements. This paper conducts an extensive empirical study focusing on the reliability of hyper-parameter selection for value-based deep reinforcement learning agents, including the introduction of a new score to quantify the consistency and reliability of various hyper-parameters. Our findings not only help establish which hyper-parameters are most critical to tune, but also help clarify which tunings remain consistent across different training regimes.
Authors: Andrea Pollastro, Francesco Isgr\`o, Roberto Prevete
Abstract: Over the past few decades, electroencephalography (EEG) monitoring has become a pivotal tool for diagnosing neurological disorders, particularly for detecting seizures. Epilepsy, one of the most prevalent neurological diseases worldwide, affects approximately the 1 \% of the population. These patients face significant risks, underscoring the need for reliable, continuous seizure monitoring in daily life. Most of the techniques discussed in the literature rely on supervised Machine Learning (ML) methods. However, the challenge of accurately labeling variations in epileptic EEG waveforms complicates the use of these approaches. Additionally, the rarity of ictal events introduces an high imbalancing within the data, which could lead to poor prediction performance in supervised learning approaches. Instead, a semi-supervised approach allows to train the model only on data not containing seizures, thus avoiding the issues related to the data imbalancing. This work proposes a semi-supervised approach for detecting epileptic seizures from EEG data, utilizing a novel Deep Learning-based method called SincVAE. This proposal incorporates the learning of an ad-hoc array of bandpass filter as a first layer of a Variational Autoencoder (VAE), potentially eliminating the preprocessing stage where informative band frequencies are identified and isolated. Results indicate that SincVAE improves seizure detection in EEG data and is capable of identifying early seizures during the preictal stage as well as monitoring patients throughout the postictal stage.
Authors: Pranav Ajit Nair, Arun Sai Suggala
Abstract: Large language models (LLMs) have recently demonstrated remarkable performance across diverse language tasks. But their deployment is often constrained by their substantial computational and storage requirements. Quantization has emerged as a key technique for addressing this challenge, enabling the compression of large models with minimal impact on performance. The recent GPTQ algorithm, a post-training quantization (PTQ) method, has proven highly effective for compressing LLMs, sparking a wave of research that leverages GPTQ as a core component. Recognizing the pivotal role of GPTQ in the PTQ landscape, we introduce CDQuant, a simple and scalable alternative to GPTQ with improved performance. CDQuant uses coordinate descent to minimize the layer-wise reconstruction loss to achieve high-quality quantized weights. Our algorithm is easy to implement and scales efficiently to models with hundreds of billions of parameters. Through extensive evaluation on the PaLM2 model family, we demonstrate that CDQuant consistently outperforms GPTQ across diverse model sizes and quantization levels. In particular, for INT2 quantization of PaLM2-Otter, CDQuant achieves a 10% reduction in perplexity compared to GPTQ.
Authors: Vyacheslav Kungurtsev, Petr Rysavy, Fadwa Idlahcen, Pavel Rytir, Ales Wodecki
Abstract: In this paper, we present a guide to the foundations of learning Dynamic Bayesian Networks (DBNs) from data in the form of multiple samples of trajectories for some length of time. We present the formalism for a generic as well as a set of common types of DBNs for particular variable distributions. We present the analytical form of the models, with a comprehensive discussion on the interdependence between structure and weights in a DBN model and their implications for learning. Next, we give a broad overview of learning methods and describe and categorize them based on the most important statistical features, and how they treat the interplay between learning structure and weights. We give the analytical form of the likelihood and Bayesian score functions, emphasizing the distinction from the static case. We discuss functions used in optimization to enforce structural requirements. We briefly discuss more complex extensions and representations. Finally we present a set of comparisons in different settings for various distinct but representative algorithms across the variants.
Authors: Juan Cervino, Md Asadullah Turja, Hesham Mostafa, Nageen Himayat, Alejandro Ribeiro
Abstract: Training Graph Neural Networks (GNNs) on large graphs presents unique challenges due to the large memory and computing requirements. Distributed GNN training, where the graph is partitioned across multiple machines, is a common approach to training GNNs on large graphs. However, as the graph cannot generally be decomposed into small non-interacting components, data communication between the training machines quickly limits training speeds. Compressing the communicated node activations by a fixed amount improves the training speeds, but lowers the accuracy of the trained GNN. In this paper, we introduce a variable compression scheme for reducing the communication volume in distributed GNN training without compromising the accuracy of the learned model. Based on our theoretical analysis, we derive a variable compression method that converges to a solution equivalent to the full communication case, for all graph partitioning schemes. Our empirical results show that our method attains a comparable performance to the one obtained with full communication. We outperform full communication at any fixed compression ratio for any communication budget.
Authors: Samuel Yang-Zhao, Kee Siong Ng
Abstract: We consider the problem of privacy protection in Reinforcement Learning (RL) algorithms that operate over population processes, a practical but understudied setting that includes, for example, the control of epidemics in large populations of dynamically interacting individuals. In this setting, the RL algorithm interacts with the population over $T$ time steps by receiving population-level statistics as state and performing actions which can affect the entire population at each time step. An individual's data can be collected across multiple interactions and their privacy must be protected at all times. We clarify the Bayesian semantics of Differential Privacy (DP) in the presence of correlated data in population processes through a Pufferfish Privacy analysis. We then give a meta algorithm that can take any RL algorithm as input and make it differentially private. This is achieved by taking an approach that uses DP mechanisms to privatize the state and reward signal at each time step before the RL algorithm receives them as input. Our main theoretical result shows that the value-function approximation error when applying standard RL algorithms directly to the privatized states shrinks quickly as the population size and privacy budget increase. This highlights that reasonable privacy-utility trade-offs are possible for differentially private RL algorithms in population processes. Our theoretical findings are validated by experiments performed on a simulated epidemic control problem over large population sizes.
Authors: Aashiq Muhamed, Oscar Li, David Woodruff, Mona Diab, Virginia Smith
Abstract: Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer state memory, they typically rely on dense projection matrices, which can introduce computational and memory overheads. In this work, we propose Grass (GRAdient Stuctured Sparsification), a novel approach that leverages sparse projections to transform gradients into structured sparse updates. This design not only significantly reduces memory usage for optimizer states but also minimizes gradient memory footprint, computation, and communication costs, leading to substantial throughput improvements. Extensive experiments on pretraining and finetuning tasks demonstrate that Grass achieves competitive performance to full-rank training and existing projection-based methods. Notably, Grass enables half-precision pretraining of a 13B parameter LLaMA model on a single 40GB A100 GPU--a feat infeasible for previous methods--and yields up to a $2\times$ throughput improvement on an 8-GPU system. Code can be found at https://github.com/aashiqmuhamed/GRASS .
Authors: Boris van Breugel, Jonathan Crabb\'e, Rob Davis, Mihaela van der Schaar
Abstract: Tabular data is one of the most ubiquitous modalities, yet the literature on tabular generative foundation models is lagging far behind its text and vision counterparts. Creating such a model is hard, due to the heterogeneous feature spaces of different tabular datasets, tabular metadata (e.g. dataset description and feature headers), and tables lacking prior knowledge (e.g. feature order). In this work we propose LaTable: a novel tabular diffusion model that addresses these challenges and can be trained across different datasets. Through extensive experiments we find that LaTable outperforms baselines on in-distribution generation, and that finetuning LaTable can generate out-of-distribution datasets better with fewer samples. On the other hand, we explore the poor zero-shot performance of LaTable, and what it may teach us about building generative tabular foundation models with better zero- and few-shot generation capabilities.
Authors: Xi Xiao, Wentao Wang, Jiacheng Xie, Lijing Zhu, Gaofei Chen, Zhengji Li, Tianyang Wang, Min Xu
Abstract: Drug target binding affinity (DTA) is a key criterion for drug screening. Existing experimental methods are time-consuming and rely on limited structural and domain information. While learning-based methods can model sequence and structural information, they struggle to integrate contextual data and often lack comprehensive modeling of drug-target interactions. In this study, we propose a novel DTA prediction method, termed HGTDP-DTA, which utilizes dynamic prompts within a hybrid Graph-Transformer framework. Our method generates context-specific prompts for each drug-target pair, enhancing the model's ability to capture unique interactions. The introduction of prompt tuning further optimizes the prediction process by filtering out irrelevant noise and emphasizing task-relevant information, dynamically adjusting the input features of the molecular graph. The proposed hybrid Graph-Transformer architecture combines structural information from Graph Convolutional Networks (GCNs) with sequence information captured by Transformers, facilitating the interaction between global and local information. Additionally, we adopted the multi-view feature fusion method to project molecular graph views and affinity subgraph views into a common feature space, effectively combining structural and contextual information. Experiments on two widely used public datasets, Davis and KIBA, show that HGTDP-DTA outperforms state-of-the-art DTA prediction methods in both prediction performance and generalization ability.
Authors: Feijie Wu, Zitao Li, Yaliang Li, Bolin Ding, Jing Gao
Abstract: Large language models (LLMs) show amazing performance on many domain-specific tasks after fine-tuning with some appropriate data. However, many domain-specific data are privately distributed across multiple owners. Thus, this dilemma raises the interest in how to perform LLM fine-tuning in federated learning (FL). However, confronted with limited computation and communication capacities, FL clients struggle to fine-tune an LLM effectively. To this end, we introduce FedBiOT, a resource-efficient LLM fine-tuning approach to FL. Specifically, our method involves the server generating a compressed LLM and aligning its performance with the full model. Subsequently, the clients fine-tune a lightweight yet important part of the compressed model, referred to as an adapter. Notice that as the server has no access to the private data owned by the clients, the data used for alignment by the server has a different distribution from the one used for fine-tuning by clients. We formulate the problem into a bi-level optimization problem to minimize the negative effect of data discrepancy and derive the updating rules for the server and clients. We conduct extensive experiments on LLaMA-2, empirically showing that the adapter has exceptional performance when reintegrated into the global LLM. The results also indicate that the proposed FedBiOT significantly reduces resource consumption compared to existing benchmarks, all while achieving comparable performance levels.
Authors: Talfan Evans, Nikhil Parthasarathy, Hamza Merzic, Olivier J. Henaff
Abstract: Data curation is an essential component of large-scale pretraining. In this work, we demonstrate that jointly selecting batches of data is more effective for learning than selecting examples independently. Multimodal contrastive objectives expose the dependencies between data and thus naturally yield criteria for measuring the joint learnability of a batch. We derive a simple and tractable algorithm for selecting such batches, which significantly accelerate training beyond individually-prioritized data points. As performance improves by selecting from larger super-batches, we also leverage recent advances in model approximation to reduce the associated computational overhead. As a result, our approach--multimodal contrastive learning with joint example selection (JEST)--surpasses state-of-the-art models with up to 13$\times$ fewer iterations and 10$\times$ less computation. Essential to the performance of JEST is the ability to steer the data selection process towards the distribution of smaller, well-curated datasets via pretrained reference models, exposing the level of data curation as a new dimension for neural scaling laws.
Authors: Claas Voelcker, Tyler Kastner, Igor Gilitschenski, Amir-massoud Farahmand
Abstract: We investigate the impact of auxiliary learning tasks such as observation reconstruction and latent self-prediction on the representation learning problem in reinforcement learning. We also study how they interact with distractions and observation functions in the MDP. We provide a theoretical analysis of the learning dynamics of observation reconstruction, latent self-prediction, and TD learning in the presence of distractions and observation functions under linear model assumptions. With this formalization, we are able to explain why latent-self prediction is a helpful \emph{auxiliary task}, while observation reconstruction can provide more useful features when used in isolation. Our empirical analysis shows that the insights obtained from our learning dynamics framework predicts the behavior of these loss functions beyond the linear model assumption in non-linear neural networks. This reinforces the usefulness of the linear model framework not only for theoretical analysis, but also practical benefit for applied problems.
Authors: Arijit Sehanobish, Avinava Dubey, Krzysztof Choromanski, Somnath Basu Roy Chowdhury, Deepali Jain, Vikas Sindhwani, Snigdha Chaturvedi
Abstract: Recent efforts to scale Transformer models have demonstrated rapid progress across a wide range of tasks (Wei et al., 2022). However, fine-tuning these models for downstream tasks is expensive due to their large parameter counts. Parameter-efficient fine-tuning (PEFT) approaches have emerged as a viable alternative by allowing us to fine-tune models by updating only a small number of parameters. In this work, we propose a general framework for parameter efficient fine-tuning (PEFT), based on structured unrestricted-rank matrices (SURM) which can serve as a drop-in replacement for popular approaches such as Adapters and LoRA. Unlike other methods like LoRA, SURMs provides more flexibility in finding the right balance between compactness and expressiveness. This is achieved by using low displacement rank matrices (LDRMs), which hasn't been used in this context before. SURMs remain competitive with baselines, often providing significant quality improvements while using a smaller parameter budget. SURMs achieve 5-7% accuracy gains on various image classification tasks while replacing low-rank matrices in LoRA. It also results in up to 12x reduction of the number of parameters in adapters (with virtually no loss in quality) on the GLUE benchmark.
Authors: Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham Kakade, Lucas Janson
Abstract: Shampoo, a second-order optimization algorithm which uses a Kronecker product preconditioner, has recently garnered increasing attention from the machine learning community. The preconditioner used by Shampoo can be viewed either as an approximation of the Gauss--Newton component of the Hessian or the covariance matrix of the gradients maintained by Adagrad. We provide an explicit and novel connection between the $\textit{optimal}$ Kronecker product approximation of these matrices and the approximation made by Shampoo. Our connection highlights a subtle but common misconception about Shampoo's approximation. In particular, the $\textit{square}$ of the approximation used by the Shampoo optimizer is equivalent to a single step of the power iteration algorithm for computing the aforementioned optimal Kronecker product approximation. Across a variety of datasets and architectures we empirically demonstrate that this is close to the optimal Kronecker product approximation. Additionally, for the Hessian approximation viewpoint, we empirically study the impact of various practical tricks to make Shampoo more computationally efficient (such as using the batch gradient and the empirical Fisher) on the quality of Hessian approximation.
Authors: Connor Kissane, Robert Krzyzanowski, Joseph Isaac Bloom, Arthur Conmy, Neel Nanda
Abstract: Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse, interpretable features, and have been applied to MLP layers and the residual stream. In this work we train SAEs on attention layer outputs and show that also here SAEs find a sparse, interpretable decomposition. We demonstrate this on transformers from several model families and up to 2B parameters. We perform a qualitative study of the features computed by attention layers, and find multiple families: long-range context, short-range context and induction features. We qualitatively study the role of every head in GPT-2 Small, and estimate that at least 90% of the heads are polysemantic, i.e. have multiple unrelated roles. Further, we show that Sparse Autoencoders are a useful tool that enable researchers to explain model behavior in greater detail than prior work. For example, we explore the mystery of why models have so many seemingly redundant induction heads, use SAEs to motivate the hypothesis that some are long-prefix whereas others are short-prefix, and confirm this with more rigorous analysis. We use our SAEs to analyze the computation performed by the Indirect Object Identification circuit (Wang et al.), validating that the SAEs find causally meaningful intermediate variables, and deepening our understanding of the semantics of the circuit. We open-source the trained SAEs and a tool for exploring arbitrary prompts through the lens of Attention Output SAEs.
Authors: Jiahe Huang, Guandao Yang, Zichen Wang, Jeong Joon Park
Abstract: We introduce a general framework for solving partial differential equations (PDEs) using generative diffusion models. In particular, we focus on the scenarios where we do not have the full knowledge of the scene necessary to apply classical solvers. Most existing forward or inverse PDE approaches perform poorly when the observations on the data or the underlying coefficients are incomplete, which is a common assumption for real-world measurements. In this work, we propose DiffusionPDE that can simultaneously fill in the missing information and solve a PDE by modeling the joint distribution of the solution and coefficient spaces. We show that the learned generative priors lead to a versatile framework for accurately solving a wide range of PDEs under partial observation, significantly outperforming the state-of-the-art methods for both forward and inverse directions.
Authors: Adyasha Mohanty, Grace Gao
Abstract: Global Navigation Satellite Systems (GNSS)-based positioning plays a crucial role in various applications, including navigation, transportation, logistics, mapping, and emergency services. Traditional GNSS positioning methods are model-based and they utilize satellite geometry and the known properties of satellite signals. However, model-based methods have limitations in challenging environments and often lack adaptability to uncertain noise models. This paper highlights recent advances in Machine Learning (ML) and its potential to address these limitations. It covers a broad range of ML methods, including supervised learning, unsupervised learning, deep learning, and hybrid approaches. The survey provides insights into positioning applications related to GNSS such as signal analysis, anomaly detection, multi-sensor integration, prediction, and accuracy enhancement using ML. It discusses the strengths, limitations, and challenges of current ML-based approaches for GNSS positioning, providing a comprehensive overview of the field.
Authors: Parham Zolfaghari, Vitor Fortes Rey, Lala Ray, Hyun Kim, Sungho Suh, Paul Lukowicz
Abstract: The proliferation of deep learning has significantly advanced various fields, yet Human Activity Recognition (HAR) has not fully capitalized on these developments, primarily due to the scarcity of labeled datasets. Despite the integration of advanced Inertial Measurement Units (IMUs) in ubiquitous wearable devices like smartwatches and fitness trackers, which offer self-labeled activity data from users, the volume of labeled data remains insufficient compared to domains where deep learning has achieved remarkable success. Addressing this gap, in this paper, we propose a novel approach to improve wearable sensor-based HAR by introducing a pose-to-sensor network model that generates sensor data directly from 3D skeleton pose sequences. our method simultaneously trains the pose-to-sensor network and a human activity classifier, optimizing both data reconstruction and activity recognition. Our contributions include the integration of simultaneous training, direct pose-to-sensor generation, and a comprehensive evaluation on the MM-Fit dataset. Experimental results demonstrate the superiority of our framework with significant performance improvements over baseline methods.
Authors: Shravan Cheekati, Mridul Gupta, Vibha Raghu, Pranav Raj
Abstract: Age-related language patterns play a crucial role in understanding linguistic differences and developing age-appropriate communication strategies. However, the lack of comprehensive and diverse datasets has hindered the progress of research in this area. To address this issue, we present TextAge, a curated text dataset that maps sentences to the age and age group of the producer, as well as an underage (under 13) label. TextAge covers a wide range of ages and includes both spoken and written data from various sources such as CHILDES, Meta, Poki Poems-by-kids, JUSThink, and the TV show "Survivor." The dataset undergoes extensive cleaning and preprocessing to ensure data quality and consistency. We demonstrate the utility of TextAge through two applications: Underage Detection and Generational Classification. For Underage Detection, we train a Naive Bayes classifier, fine-tuned RoBERTa, and XLNet models to differentiate between language patterns of minors and young-adults and over. For Generational Classification, the models classify language patterns into different age groups (kids, teens, twenties, etc.). The models excel at classifying the "kids" group but struggle with older age groups, particularly "fifties," "sixties," and "seventies," likely due to limited data samples and less pronounced linguistic differences. TextAge offers a valuable resource for studying age-related language patterns and developing age-sensitive language models. The dataset's diverse composition and the promising results of the classification tasks highlight its potential for various applications, such as content moderation, targeted advertising, and age-appropriate communication. Future work aims to expand the dataset further and explore advanced modeling techniques to improve performance on older age groups.
Authors: F. Paonessa, G. Virone, S. Kianoush, A. Nordio, S. Savazzi
Abstract: This paper empirically investigates the body induced electromagnetic (EM) effects, namely the human body blockage, by conducting indoor measurement campaigns in the unexplored sub-THz W-band (75-110 GHz) and G-band (170-260 GHz). The proposed analysis focuses on both the alterations of channel frequency response induced by body presence, fully or partially obstructing the line-of-sight (LoS) between transmitter and recevier, as well as on the channel impulse response (CIR) for selected movements of the target, i.e. crossing the LoS of the radio link. Modelling of large scale parameters is also presented using a phantom body object. The proposed study has applications in device-free radio localization and radio frequency (RF) sensing scenarios where the EM radiation or environmental radio signals are collected and processed to detect and locate people without requiring them to wear any electronic devices. Although preliminary, the study reveals that discrimination of the blockage micro-movements is possible, achieving higher precision compared to classical RF sensing and localization using cm-scale wavelengths (2.4-6GHz bands).
Authors: Atitaya Phoemsuk, Vahid Abolghasemi
Abstract: Coronary Artery Disease (CAD) diagnostic to be a major global cause of death, necessitating innovative solutions. Addressing the critical importance of early CAD detection and its impact on the mortality rate, we propose the potential of one-dimensional convolutional neural networks (1D-CNN) to enhance detection accuracy and reduce network complexity. This study goes beyond traditional diagnostic methodologies, leveraging the remarkable ability of 1D-CNN to interpret complex patterns within Electrocardiogram (ECG) signals without depending on feature extraction techniques. We explore the impact of varying sample lengths on model performance and conduct experiments involving layers reduction. The ECG data employed were obtained from the PhysioNet databases, namely the MIMIC III and Fantasia datasets, with respective sampling frequencies of 125 Hz and 250 Hz. The highest accuracy for unseen data obtained with a sample length of 250. These initial findings demonstrate the potential of 1D-CNNs in CAD diagnosis using ECG signals and highlight the sample size's role in achieving high accuracy.
Authors: Nathan C. L. Kong, Dae Lee, Huyen Do, Dae Hoon Park, Cong Xu, Hongda Mao, Jonathan Chung
Abstract: Electrocardiograms (ECGs) and photoplethysmograms (PPGs) are generally used to monitor an individual's cardiovascular health. In clinical settings, ECGs and fingertip PPGs are the main signals used for assessing cardiovascular health, but the equipment necessary for their collection precludes their use in daily monitoring. Although PPGs obtained from wrist-worn devices are susceptible to noise due to motion, they have been widely used to continuously monitor cardiovascular health because of their convenience. Therefore, we would like to combine the ease with which PPGs can be collected with the information that ECGs provide about cardiovascular health by developing models to synthesize ECG signals from paired PPG signals. We tackled this problem using generative adversarial networks (GANs) and found that models trained using the original GAN formulations can be successfully used to synthesize ECG signals from which heart rate can be extracted using standard signal processing pipelines. Incorporating a frequency-domain constraint to model training improved the stability of model performance and also the performance on heart rate estimation.
Authors: Irina Zhang, Jim Denholm, Azam Hamidinekoo, Oskar {\AA}lund, Christopher Bagnall, Joana Pal\'es Huix, Michal Sulikowski, Ortensia Vito, Arthur Lewis, Robert Unwin, Magnus Soderberg, Nikolay Burlutskiy, Talha Qaiser
Abstract: Accurate segmentation of glomerulus instances attains high clinical significance in the automated analysis of renal biopsies to aid in diagnosing and monitoring kidney disease. Analyzing real-world histopathology images often encompasses inter-observer variability and requires a labor-intensive process of data annotation. Therefore, conventional supervised learning approaches generally achieve sub-optimal performance when applied to external datasets. Considering these challenges, we present a semi-supervised learning approach for glomeruli segmentation based on the weak-to-strong consistency framework validated on multiple real-world datasets. Our experimental results on 3 independent datasets indicate superior performance of our approach as compared with existing supervised baseline models such as U-Net and SegFormer.
Authors: Alex Lence, Ahmad Fall, Federica Granese, Blaise Hanczar, Joe-Elie Salem, Jean-Daniel Zucker, Edi Prifti
Abstract: In this work, we address the challenge of reconstructing the complete 12-lead ECG signal from incomplete parts of it. We focus on two main scenarii: (i) reconstructing missing signal segments within an ECG lead and (ii) recovering missing leads from a single-lead. We propose a model with a U-Net architecture trained on a novel objective function to address the reconstruction problem. This function incorporates both spatial and temporal aspects of the ECG by combining the distance in amplitude between the reconstructed and real signals with the signal trend. Through comprehensive assessments using both a real-life dataset and a publicly accessible one, we demonstrate that the proposed approach consistently outperforms state-of-the-art methods based on generative adversarial networks and a CopyPaste strategy. Our proposed model demonstrates superior performance in standard distortion metrics and preserves critical ECG characteristics, particularly the P, Q, R, S, and T wave coordinates. Two emerging clinical applications emphasize the relevance of our work. The first is the increasing need to digitize paper-stored ECGs for utilization in AI-based applications (automatic annotation and risk-quantification), often limited to digital ECG complete 10s recordings. The second is the widespread use of wearable devices that record ECGs but typically capture only a small subset of the 12 standard leads. In both cases, a non-negligible amount of information is lost or not recorded, which our approach aims to recover to overcome these limitations.
Authors: Jack Kilgallen, Barak Pearlmutter, Jeffery Mark Siskind
Abstract: Within neuroimgaing studies it is a common practice to perform repetitions of trials in an experiment when working with a noisy class of data acquisition system, such as electroencephalography (EEG) or magnetoencephalography (MEG). While this approach can be useful in some experimental designs, it presents significant limitations for certain types of analyses, such as identifying the category of an object observed by a subject. In this study we demonstrate that when trials relating to a single object are allowed to appear in both the training and testing sets, almost any classification algorithm is capable of learning the representation of an object given only category labels. This ability to learn object representations is of particular significance as it suggests that the results of several published studies which predict the category of observed objects from EEG signals may be affected by a subtle form of leakage which has inflated their reported accuracies. We demonstrate the ability of both simple classification algorithms, and sophisticated deep learning models, to learn object representations given only category labels. We do this using two datasets; the Kaneshiro et al. (2015) dataset and the Gifford et al. (2022) dataset. Our results raise doubts about the true generalizability of several published models and suggests that the reported performance of these models may be significantly inflated.
Authors: Changyu Du, Stavros Nousias, Andr\'e Borrmann
Abstract: Facing increasingly complex BIM authoring software and the accompanying expensive learning costs, designers often seek to interact with the software in a more intelligent and lightweight manner. They aim to automate modeling workflows, avoiding obstacles and difficulties caused by software usage, thereby focusing on the design process itself. To address this issue, we proposed an LLM-based autonomous agent framework that can function as a copilot in the BIM authoring tool, answering software usage questions, understanding the user's design intentions from natural language, and autonomously executing modeling tasks by invoking the appropriate tools. In a case study based on the BIM authoring software Vectorworks, we implemented a software prototype to integrate the proposed framework seamlessly into the BIM authoring scenario. We evaluated the planning and reasoning capabilities of different LLMs within this framework when faced with complex instructions. Our work demonstrates the significant potential of LLM-based agents in design automation and intelligent interaction.
Authors: Arshia Afzal, Grigorios Chrysos, Volkan Cevher, Mahsa Shoaran
Abstract: EEG-based seizure detection models face challenges in terms of inference speed and memory efficiency, limiting their real-time implementation in clinical devices. This paper introduces a novel graph-based residual state update mechanism (REST) for real-time EEG signal analysis in applications such as epileptic seizure detection. By leveraging a combination of graph neural networks and recurrent structures, REST efficiently captures both non-Euclidean geometry and temporal dependencies within EEG data. Our model demonstrates high accuracy in both seizure detection and classification tasks. Notably, REST achieves a remarkable 9-fold acceleration in inference speed compared to state-of-the-art models, while simultaneously demanding substantially less memory than the smallest model employed for this task. These attributes position REST as a promising candidate for real-time implementation in clinical devices, such as Responsive Neurostimulation or seizure alert systems.
Authors: Ge Cao, Zhen Peng
Abstract: The radio wave propagation channel is central to the performance of wireless communication systems. In this paper, we introduce a novel machine learning-empowered methodology for wireless channel modeling. The key ingredients include a point-cloud-based neural network and a Spherical Harmonics encoder with light probes. Our approach offers several significant advantages, including the flexibility to adjust antenna radiation patterns and transmitter/receiver locations, the capability to predict radio power maps, and the scalability of large-scale wireless scenes. As a result, it lays the groundwork for an end-to-end pipeline for network planning and deployment optimization. The proposed work is validated in various outdoor and indoor radio environments.
Authors: Dinuka Sandun Udayantha, Kavindu Weerasinghe, Nima Wickramasinghe, Akila Abeyratne, Kithmin Wickremasinghe, Jithangi Wanigasinghe, Anjula De Silva, Chamira Edussooriya
Abstract: The neonatal period is the most vulnerable time for the development of seizures. Seizures in the immature brain lead to detrimental consequences, therefore require early diagnosis. The gold-standard for neonatal seizure detection currently relies on continuous video-EEG monitoring; which involves recording multi-channel electroencephalogram (EEG) alongside real-time video monitoring within a neonatal intensive care unit (NICU). However, video-EEG monitoring technology requires clinical expertise and is often limited to technologically advanced and resourceful settings. Cost-effective new techniques could help the medical fraternity make an accurate diagnosis and advocate treatment without delay. In this work, a novel explainable deep learning model to automate the neonatal seizure detection process with a reduced EEG montage is proposed, which employs convolutional nets, graph attention layers, and fully connected layers. Beyond its ability to detect seizures in real-time with a reduced montage, this model offers the unique advantage of real-time interpretability. By evaluating the performance on the Zenodo dataset with 10-fold cross-validation, the presented model achieves an absolute improvement of 8.31% and 42.86% in area under curve (AUC) and recall, respectively.
Authors: Igor Carrara (UniCA, CRONOS), Theodore Papadopoulo (UniCA, CRONOS)
Abstract: Electroencephalographic signals are represented as multidimensional datasets. We introduce an enhancement to the augmented covariance method (ACM), exploiting more thoroughly its mathematical properties, in order to improve motor imagery classification.Standard ACM emerges as a combination of phase space reconstruction of dynamical systems and of Riemannian geometry. Indeed, it is based on the construction of a Symmetric Positive Definite matrix to improve classification. But this matrix also has a Block-Toeplitz structure that was previously ignored. This work treats such matrices in the real manifold to which they belong: the set of Block-Toeplitz SPD matrices. After some manipulation, this set is can be seen as the product of an SPD manifold and a Siegel Disk Space.The proposed methodology was tested using the MOABB framework with a within-session evaluation procedure. It achieves a similar classification performance to ACM, which is typically better than -- or at worse comparable to -- state-of-the-art methods. But, it also improves consequently the computational efficiency over ACM, making it even more suitable for real time experiments.
Authors: Chi-Sheng Chen, Chun-Shu Wei
Abstract: Decoding images from non-invasive electroencephalographic (EEG) signals has been a grand challenge in understanding how the human brain process visual information in real-world scenarios. To cope with the issues of signal-to-noise ratio and nonstationarity, this paper introduces a MUltimodal Similarity-keeping contrastivE learning (MUSE) framework for zero-shot EEG-based image classification. We develop a series of multivariate time-series encoders tailored for EEG signals and assess the efficacy of regularized contrastive EEG-Image pretraining using an extensive visual EEG dataset. Our method achieves state-of-the-art performance, with a top-1 accuracy of 19.3% and a top-5 accuracy of 48.8% in 200-way zero-shot image classification. Furthermore, we visualize neural patterns via model interpretation, shedding light on the visual processing dynamics in the human brain. The code repository for this work is available at: https://github.com/ChiShengChen/MUSE_EEG.
Authors: Javier Garc\'ia Ciudad, Morten M{\o}rup, Birgitte Rahbek Kornum, Alexander Neergaard Zahid
Abstract: In human sleep staging models, augmenting the temporal context of the input to the range of tens of minutes has recently demonstrated performance improvement. In contrast, the temporal context of mouse sleep staging models is typically in the order of tens of seconds. While long-term time patterns are less clear in mouse sleep, increasing the temporal context further than that of the current mouse sleep staging models might still result in a performance increase, given that the current methods only model very short term patterns. In this study, we examine the influence of increasing the temporal context in mouse sleep staging up to 15 minutes in three mouse cohorts using two recent and high-performing human sleep staging models that account for long-term dependencies. These are compared to two prominent mouse sleep staging models that use a local context of 12 s and 20 s, respectively. An increase in context up to 28 s is observed to have a positive impact on sleep stage classification performance, especially in REM sleep. However, the impact is limited for longer context windows. One of the human sleep scoring models, L-SeqSleepNet, outperforms both mouse models in all cohorts. This suggests that mouse sleep staging can benefit from more temporal context than currently used.
Authors: Jorge Ortigoso-Narro, Fernando Diaz-de-Maria, Mohammad Mahdi Dehshibi, Ana Tajadura-Jim\'enez
Abstract: Chronic Low Back Pain (CLBP) afflicts millions globally, significantly impacting individuals' well-being and imposing economic burdens on healthcare systems. While artificial intelligence (AI) and deep learning offer promising avenues for analyzing pain-related behaviors to improve rehabilitation strategies, current models, including convolutional neural networks (CNNs), recurrent neural networks, and graph-based neural networks, have limitations. These approaches often focus singularly on the temporal dimension or require complex architectures to exploit spatial interrelationships within multivariate time series data. To address these limitations, we introduce \hbox{L-SFAN}, a lightweight CNN architecture incorporating 2D filters designed to meticulously capture the spatial-temporal interplay of data from motion capture and surface electromyography sensors. Our proposed model, enhanced with an oriented global pooling layer and multi-head self-attention mechanism, prioritizes critical features to better understand CLBP and achieves competitive classification accuracy. Experimental results on the EmoPain database demonstrate that our approach not only enhances performance metrics with significantly fewer parameters but also promotes model interpretability, offering valuable insights for clinicians in managing CLBP. This advancement underscores the potential of AI in transforming healthcare practices for chronic conditions like CLBP, providing a sophisticated framework for the nuanced analysis of complex biomedical data.
Authors: Thomas Kite, Uzair Tahamid Siam, Brian Ayers, Nicholas Houstis, Aaron D Aguirre
Abstract: Machine learning (ML) applied to routine patient monitoring within intensive care units (ICUs) has the potential to improve care by providing clinicians with novel insights into each patient's health and expected response to interventions. This paper applies deep learning to a large volume of unlabeled electrocardiogram (ECG) telemetry signals, which are commonly used for continuous patient monitoring in hospitals but have important differences from the standard, single time-point 12-lead ECG used in many prior machine learning studies. We applied self-supervised learning to pretrain a spectrum of deep networks on approximately 147,000 hours of ECG telemetry data. Our approach leverages this dataset to train models that significantly improve performance on four distinct downstream tasks compared with direct supervised learning using labeled data. These pretrained models enable medically useful predictions and estimates in smaller patient cohorts that are typically limited by the scarcity of labels. Notably, we demonstrate that our pretrained networks can continuously annotate ECG telemetry signals, thereby providing monitoring capabilities that are often unavailable due to the requirement for specialized expertise and time-consuming professional annotations.
Authors: Yidong Zhu, Nadia B Aimandi, Mohammad Arif Ul Alam
Abstract: In the U.S., over a third of adults are pre-diabetic, with 80\% unaware of their status. This underlines the need for better glucose monitoring to prevent type 2 diabetes and related heart diseases. Existing wearable glucose monitors are limited by the lack of models trained on small datasets, as collecting extensive glucose data is often costly and impractical. Our study introduces a novel machine learning method using modified recurrence plots in the frequency domain to improve glucose level prediction accuracy from wearable device data, even with limited datasets. This technique combines advanced signal processing with machine learning to extract more meaningful features. We tested our method against existing models using historical data, showing that our approach surpasses the current 87\% accuracy benchmark in predicting real-time interstitial glucose levels.
Authors: Wei Huang, Ning Wang, Panpan Feng, Haiyan Wang, Zongmin Wang, Bing Zhou
Abstract: Electrocardiograms (ECG), which record the electrophysiological activity of the heart, have become a crucial tool for diagnosing these diseases. In recent years, the application of deep learning techniques has significantly improved the performance of ECG signal classification. Multi-resolution feature analysis, which captures and processes information at different time scales, can extract subtle changes and overall trends in ECG signals, showing unique advantages. However, common multi-resolution analysis methods based on simple feature addition or concatenation may lead to the neglect of low-resolution features, affecting model performance. To address this issue, this paper proposes the Multi-Resolution Mutual Learning Network (MRM-Net). MRM-Net includes a dual-resolution attention architecture and a feature complementary mechanism. The dual-resolution attention architecture processes high-resolution and low-resolution features in parallel. Through the attention mechanism, the high-resolution and low-resolution branches can focus on subtle waveform changes and overall rhythm patterns, enhancing the ability to capture critical features in ECG signals. Meanwhile, the feature complementary mechanism introduces mutual feature learning after each layer of the feature extractor. This allows features at different resolutions to reinforce each other, thereby reducing information loss and improving model performance and robustness. Experiments on the PTB-XL and CPSC2018 datasets demonstrate that MRM-Net significantly outperforms existing methods in multi-label ECG classification performance. The code for our framework will be publicly available at https://github.com/wxhdf/MRM.
Authors: Anshuman Gaharwar, Parth Parag Kulkarni, Joshua Dickey, Mubarak Shah
Abstract: Missing/erroneous data is a major problem in today's world. Collected seismic data sometimes contain gaps due to multitude of reasons like interference and sensor malfunction. Gaps in seismic waveforms hamper further signal processing to gain valuable information. Plethora of techniques are used for data reconstruction in other domains like image, video, audio, but translation of those methods to address seismic waveforms demands adapting them to lengthy sequence inputs, which is practically complex. Even if that is accomplished, high computational costs and inefficiency would still persist in these predominantly convolution-based reconstruction models. In this paper, we present a transformer-based deep learning model, Xi-Net, which utilizes multi-faceted time and frequency domain inputs for accurate waveform reconstruction. Xi-Net converts the input waveform to frequency domain, employs separate encoders for time and frequency domains, and one decoder for getting reconstructed output waveform from the fused features. 1D shifted-window transformer blocks form the elementary units of all parts of the model. To the best of our knowledge, this is the first transformer-based deep learning model for seismic waveform reconstruction. We demonstrate this model's prowess by filling 0.5-1s random gaps in 120s waveforms, resembling the original waveform quite closely. The code, models can be found at: https://github.com/Anshuman04/waveformReconstructor.
Authors: Marwan Dhuheir, Aiman Erbad, Ala Al-Fuqaha, Mohsen Guizani
Abstract: Recently, Unmanned Aerial Vehicles (UAVs) have attracted the attention of researchers in academia and industry for providing wireless services to ground users in diverse scenarios like festivals, large sporting events, natural and man-made disasters due to their advantages in terms of versatility and maneuverability. However, the limited resources of UAVs (e.g., energy budget and different service requirements) can pose challenges for adopting UAVs for such applications. Our system model considers a UAV swarm that navigates an area, providing wireless communication to ground users with RIS support to improve the coverage of the UAVs. In this work, we introduce an optimization model with the aim of maximizing the throughput and UAVs coverage through optimal path planning of UAVs and multi-RIS phase configurations. The formulated optimization is challenging to solve using standard linear programming techniques, limiting its applicability in real-time decision-making. Therefore, we introduce a two-step solution using deep reinforcement learning and particle swarm optimization. We conduct extensive simulations and compare our approach to two competitive solutions presented in the recent literature. Our simulation results demonstrate that our adopted approach is 20 \% better than the brute-force approach and 30\% better than the baseline solution in terms of QoS.
Authors: Guillaume Staerman, Virginie Loison, Thomas Moreau
Abstract: Physiological signal analysis often involves identifying events crucial to understanding biological dynamics. Traditional methods rely on handcrafted procedures or supervised learning, presenting challenges such as expert dependence, lack of robustness, and the need for extensive labeled data. Data-driven methods like Convolutional Dictionary Learning (CDL) offer an alternative but tend to produce spurious detections. This work introduces UNHaP (Unmix Noise from Hawkes Processes), a novel approach addressing the joint learning of temporal structures in events and the removal of spurious detections. Leveraging marked Hawkes processes, UNHaP distinguishes between events of interest and spurious ones. By treating the event detection output as a mixture of structured and unstructured events, UNHaP efficiently unmixes these processes and estimates their parameters. This approach significantly enhances the understanding of event distributions while minimizing false detection rates.
Authors: Shengzhe Lyu, Yongliang Chen, Di Duan, Renqi Jia, Weitao Xu
Abstract: In the realm of smart sensing with the Internet of Things, earable devices are empowered with the capability of multi-modality sensing and intelligence of context-aware computing, leading to its wide usage in Human Activity Recognition (HAR). Nonetheless, unlike the movements captured by Inertial Measurement Unit (IMU) sensors placed on the upper or lower body, those motion signals obtained from earable devices show significant changes in amplitudes and patterns, especially in the presence of dynamic and unpredictable head movements, posing a significant challenge for activity classification. In this work, we present EarDA, an adversarial-based domain adaptation system to extract the domain-independent features across different sensor locations. Moreover, while most deep learning methods commonly rely on training with substantial amounts of labeled data to offer good accuracy, the proposed scheme can release the potential usage of publicly available smartphone-based IMU datasets. Furthermore, we explore the feasibility of applying a filter-based data processing method to mitigate the impact of head movement. EarDA, the proposed system, enables more data-efficient and accurate activity sensing. It achieves an accuracy of 88.8% under HAR task, demonstrating a significant 43% improvement over methods without domain adaptation. This clearly showcases its effectiveness in mitigating domain gaps.
Authors: Julia Werner, Bhavya Kohli, Paul Palomero Bernardo, Christoph Gerum, Oliver Bringmann
Abstract: Epilepsy is the most common, chronic, neurological disease worldwide and is typically accompanied by reoccurring seizures. Neuro implants can be used for effective treatment by suppressing an upcoming seizure upon detection. Due to the restricted size and limited battery lifetime of those medical devices, the employed approach also needs to be limited in size and have low energy requirements. We present an energy-efficient seizure detection approach involving a TC-ResNet and time-series analysis which is suitable for low-power edge devices. The presented approach allows for accurate seizure detection without preceding feature extraction while considering the stringent hardware requirements of neural implants. The approach is validated using the CHB-MIT Scalp EEG Database with a 32-bit floating point model and a hardware suitable 4-bit fixed point model. The presented method achieves an accuracy of 95.28%, a sensitivity of 92.34% and an AUC score of 0.9384 on this dataset with 4-bit fixed point representation. Furthermore, the power consumption of the model is measured with the low-power AI accelerator UltraTrail, which only requires 495 nW on average. Due to this low-power consumption this classification approach is suitable for real-time seizure detection on low-power wearable devices such as neural implants.
Authors: Jason Stock, Kyle Hilburn, Imme Ebert-Uphoff, Charles Anderson
Abstract: We introduce a transformer-based neural network to generate high-resolution (3km) synthetic radar reflectivity fields at scale from geostationary satellite imagery. This work aims to enhance short-term convective-scale forecasts of high-impact weather events and aid in data assimilation for numerical weather prediction over the United States. Compared to convolutional approaches, which have limited receptive fields, our results show improved sharpness and higher accuracy across various composite reflectivity thresholds. Additional case studies over specific atmospheric phenomena support our quantitative findings, while a novel attribution method is introduced to guide domain experts in understanding model outputs.
Authors: Yangdi Lu, Wenbo He
Abstract: Noisy labels are ubiquitous in real-world datasets, especially in the large-scale ones derived from crowdsourcing and web searching. It is challenging to train deep neural networks with noisy datasets since the networks are prone to overfitting the noisy labels during training, resulting in poor generalization performance. During an early learning phase, deep neural networks have been observed to fit the clean samples before memorizing the mislabeled samples. In this paper, we dig deeper into the representation distributions in the early learning phase and find that, regardless of their noisy labels, learned representations of images from the same category still congregate together. Inspired by it, we propose a framework that trains the model with new synthetic samples to mitigate the impact of noisy labels. Specifically, we propose a mixing strategy to create the synthetic samples by aggregating original samples with their top-K nearest neighbours, wherein the weights are calculated using a mixture model learning from the per-sample loss distribution. To enhance the performance in the presence of extreme label noise, we estimate the soft targets by gradually correcting the noisy labels. Furthermore, we demonstrate that the estimated soft targets yield a more accurate approximation to ground truth labels and the proposed method produces a superior quality of learned representations with more separated and clearly bounded clusters. The extensive experiments in two benchmarks (CIFAR-10 and CIFAR-100) and two larg-scale real-world datasets (Clothing1M and Webvision) demonstrate that our approach outperforms the state-of-the-art methods and robustness of the learned representation.
Authors: Tennessee Hickling, Dennis Prangle
Abstract: Normalizing flows are a flexible class of probability distributions, expressed as transformations of a simple base distribution. A limitation of standard normalizing flows is representing distributions with heavy tails, which arise in applications to both density estimation and variational inference. A popular current solution to this problem is to use a heavy tailed base distribution. Examples include the tail adaptive flow (TAF) methods of Laszkiewicz et al (2022). We argue this can lead to poor performance due to the difficulty of optimising neural networks, such as normalizing flows, under heavy tailed input. This problem is demonstrated in our paper. We propose an alternative: use a Gaussian base distribution and a final transformation layer which can produce heavy tails. We call this approach tail transform flow (TTF). Experimental results show this approach outperforms current methods, especially when the target distribution has large dimension or tail weight.
Authors: Haorui Wang, Marta Skreta, Cher-Tian Ser, Wenhao Gao, Lingkai Kong, Felix Streith-Kalthoff, Chenru Duan, Yuchen Zhuang, Yue Yu, Yanqiao Zhu, Yuanqi Du, Al\'an Aspuru-Guzik, Kirill Neklyudov, Chao Zhang
Abstract: Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box objectives in molecular discovery, traverse chemical space by performing random mutations and crossovers, leading to a large number of expensive objective evaluations. In this work, we ameliorate this shortcoming by incorporating chemistry-aware Large Language Models (LLMs) into EAs. Namely, we redesign crossover and mutation operations in EAs using LLMs trained on large corpora of chemical information. We perform extensive empirical studies on both commercial and open-source models on multiple tasks involving property optimization, molecular rediscovery, and structure-based drug design, demonstrating that the joint usage of LLMs with EAs yields superior performance over all baseline models across single- and multi-objective settings. We demonstrate that our algorithm improves both the quality of the final solution and convergence speed, thereby reducing the number of required objective evaluations. Our code is available at http://github.com/zoom-wang112358/MOLLEO
Authors: Lingxi Xiao, Jinxin Hu, Yutian Yang, Yinqiu Feng, Zichao Li, Zexi Chen
Abstract: Most of the existing wavelet image processing techniques are carried out in the form of single-scale reconstruction and multiple iterations. However, processing high-quality fMRI data presents problems such as mixed noise and excessive computation time. This project proposes the use of matrix operations by combining mixed noise elimination methods with wavelet analysis to replace traditional iterative algorithms. Functional magnetic resonance imaging (fMRI) of the auditory cortex of a single subject is analyzed and compared to the wavelet domain signal processing technology based on repeated times and the world's most influential SPM8. Experiments show that this algorithm is the fastest in computing time, and its detection effect is comparable to the traditional iterative algorithm. However, this has a higher practical value for the processing of FMRI data. In addition, the wavelet analysis method proposed signal processing to speed up the calculation rate.
Authors: Tianyu Han, Sven Nebelung, Firas Khader, Jakob Nikolas Kather, Daniel Truhn
Abstract: Denoising diffusion models offer a promising approach to accelerating magnetic resonance imaging (MRI) and producing diagnostic-level images in an unsupervised manner. However, our study demonstrates that even tiny worst-case potential perturbations transferred from a surrogate model can cause these models to generate fake tissue structures that may mislead clinicians. The transferability of such worst-case perturbations indicates that the robustness of image reconstruction may be compromised due to MR system imperfections or other sources of noise. Moreover, at larger perturbation strengths, diffusion models exhibit Gaussian noise-like artifacts that are distinct from those observed in supervised models and are more challenging to detect. Our results highlight the vulnerability of current state-of-the-art diffusion-based reconstruction models to possible worst-case perturbations and underscore the need for further research to improve their robustness and reliability in clinical settings.
Authors: Gyanna Gao, Hao-Yu Liao, Zhenhong Hu
Abstract: Numerous studies have demonstrated the manifold benefits of tennis, such as increasing overall physical and mental health. Unfortunately, many children and youth from low-income families are unable to engage in this sport mainly due to financial constraints such as private lesson expenses as well as logistical concerns to and back from such lessons and clinics. While several tennis self-training systems exist, they are often tailored for professionals and are prohibitively expensive. The present study aims to classify tennis players' skill levels and classify tennis strokes into phases characterized by motion attributes for a future development of an AI-based tennis self-training model for affordable and convenient applications running on devices used in daily life such as an iPhone or an Apple Watch for tennis skill improvement. We collected motion data, including Motion Yaw, Roll and Pitch from inertial measurement units (IMUs) worn by participating junior tennis players. For this pilot study, data from twelve participants were processed using Support Vector Machine (SVM) algorithms. The SVM models demonstrated an overall accuracy of 77% in classifying players as beginners or intermediates, with low rates of false positives and false negatives, effectively distinguishing skill levels. Additionally, the tennis swings were successfully classified into five phases based on the collected motion data. These findings indicate that SVM-based classification can be a reliable foundation for developing an equitable and accessible AI-driven tennis training system.
Authors: Platon Lukyanenko, Joshua Mayourian, Mingxuan Liua, John K. Triedman, Sunil J. Ghelani, William G. La Cava
Abstract: Several recent high-impact studies leverage large hospital-owned electrocardiographic (ECG) databases to model and predict patient mortality. MIMIC-IV, released September 2023, is the first comparable public dataset and includes 800,000 ECGs from a U.S. hospital system. Previously, the largest public ECG dataset was Code-15, containing 345,000 ECGs collected during routine care in Brazil. These datasets now provide an excellent resource for a broader audience to explore ECG survival modeling. Here, we benchmark survival model performance on Code-15 and MIMIC-IV with two neural network architectures, compare four deep survival modeling approaches to Cox regressions trained on classifier outputs, and evaluate performance at one to ten years. Our results yield AUROC and concordance scores comparable to past work (circa 0.8) and reasonable AUPRC scores (MIMIC-IV: 0.4-0.5, Code-15: 0.05-0.13) considering the fraction of ECG samples linked to a mortality (MIMIC-IV: 27\%, Code-15: 4\%). When evaluating models on the opposite dataset, AUROC and concordance values drop by 0.1-0.15, which may be due to cohort differences. All code and results are made public.
Authors: Niful Islam, Khan Md Hasib, Fahmida Akter Joti, Asif Karim, Sami Azam
Abstract: Skin cancer is a major concern to public health, accounting for one-third of the reported cancers. If not detected early, the cancer has the potential for severe consequences. Recognizing the critical need for effective skin cancer classification, we address the limitations of existing models, which are often too large to deploy in areas with limited computational resources. In response, we present a knowledge distillation based approach for creating a lightweight yet high-performing classifier. The proposed solution involves fusing three models, namely ResNet152V2, ConvNeXtBase, and ViT Base, to create an effective teacher model. The teacher model is then employed to guide a lightweight student model of size 2.03 MB. This student model is further compressed to 469.77 KB using 16-bit quantization, enabling smooth incorporation into edge devices. With six-stage image preprocessing, data augmentation, and a rigorous ablation study, the model achieves an impressive accuracy of 98.75% on the HAM10000 dataset and 98.94% on the Kaggle dataset in classifying benign and malignant skin cancers. With its high accuracy and compact size, our model appears to be a potential choice for accurate skin cancer classification, particularly in resource-constrained settings.
Authors: Ryan Liu, Jiayi Geng, Joshua C. Peterson, Ilia Sucholutsky, Thomas L. Griffiths
Abstract: In order for AI systems to communicate effectively with people, they must understand how we make decisions. However, people's decisions are not always rational, so the implicit internal models of human decision-making in Large Language Models (LLMs) must account for this. Previous empirical evidence seems to suggest that these implicit models are accurate -- LLMs offer believable proxies of human behavior, acting how we expect humans would in everyday interactions. However, by comparing LLM behavior and predictions to a large dataset of human decisions, we find that this is actually not the case: when both simulating and predicting people's choices, a suite of cutting-edge LLMs (GPT-4o & 4-Turbo, Llama-3-8B & 70B, Claude 3 Opus) assume that people are more rational than we really are. Specifically, these models deviate from human behavior and align more closely with a classic model of rational choice -- expected value theory. Interestingly, people also tend to assume that other people are rational when interpreting their behavior. As a consequence, when we compare the inferences that LLMs and people draw from the decisions of others using another psychological dataset, we find that these inferences are highly correlated. Thus, the implicit decision-making models of LLMs appear to be aligned with the human expectation that other people will act rationally, rather than with how people actually act.
Authors: Jyotishka Datta, Nicholas G. Polson
Abstract: Deep Independent Component Estimation (DICE) has many applications in modern day machine learning as a feature engineering extraction method. We provide a novel latent variable representation of independent component analysis that enables both point estimates via expectation-maximization (EM) and full posterior sampling via Markov Chain Monte Carlo (MCMC) algorithms. Our methodology also applies to flow-based methods for nonlinear feature extraction. We discuss how to implement conditional posteriors and envelope-based methods for optimization. Through this representation hierarchy, we unify a number of hitherto disjoint estimation procedures. We illustrate our methodology and algorithms on a numerical example. Finally, we conclude with directions for future research.
Authors: Yifan Yang, Yutong Mao, Xufu Liu, Xiao Liu
Abstract: The human brain is a complex, dynamic network, which is commonly studied using functional magnetic resonance imaging (fMRI) and modeled as network of Regions of interest (ROIs) for understanding various brain functions. Recent studies utilize deep learning approaches to learn the brain network representation based on functional connectivity (FC) profile, broadly falling into two main categories. The Fixed-FC approaches, utilizing the FC profile which represents the linear temporal relation within the brain network, are limited by failing to capture informative brain temporal dynamics. On the other hand, the Dynamic-FC approaches, modeling the evolving FC profile over time, often exhibit less satisfactory performance due to challenges in handling the inherent noisy nature of fMRI data. To address these challenges, we propose Brain Masked Auto-Encoder (BrainMAE) for learning representations directly from fMRI time-series data. Our approach incorporates two essential components: a region-aware graph attention mechanism designed to capture the relationships between different brain ROIs, and a novel self-supervised masked autoencoding framework for effective model pre-training. These components enable the model to capture rich temporal dynamics of brain activity while maintaining resilience to inherent noise in fMRI data. Our experiments demonstrate that BrainMAE consistently outperforms established baseline methods by significant margins in four distinct downstream tasks. Finally, leveraging the model's inherent interpretability, our analysis of model-generated representations reveals findings that resonate with ongoing research in the field of neuroscience.
Authors: Yuyang Sun, Jingyu Lei, Panagiotis Kosmas
Abstract: Understanding the complex relationships of biomarkers in diabetes is pivotal for advancing treatment strategies, a pressing need in diabetes research. This study applies Bayesian network structure learning to analyze the Shanghai Type 1 and Type 2 diabetes mellitus datasets, revealing complex relationships among key diabetes-related biomarkers. The constructed Bayesian network presented notable predictive accuracy, particularly for Type 2 diabetes mellitus, with root mean squared error (RMSE) of 18.23 mg/dL, as validated through leave-one-domain experiments and Clarke error grid analysis. This study not only elucidates the intricate dynamics of diabetes through a deeper understanding of biomarker interplay but also underscores the significant potential of integrating data-driven and knowledge-driven methodologies in the realm of personalized diabetes management. Such an approach paves the way for more custom and effective treatment strategies, marking a notable advancement in the field.
Authors: Mohamed F. Mansour
Abstract: We describe a new method for estimating the direction of sound in a reverberant environment from basic principles of sound propagation. The method utilizes SNR-adaptive features from time-delay and energy of the directional components after acoustic wave decomposition of the observed sound field to estimate the line-of-sight direction under noisy and reverberant conditions. The effectiveness of the approach is established with real-data of different microphone array configurations under various usage scenarios.
Authors: Christophe Bonneville, Nathan Bieberdorf, Arun Hegde, Mark Asta, Habib N. Najm, Laurent Capolungo, Cosmin Safta
Abstract: Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For such liquid-metal dealloying (LMD) process, phase field models have been developed. However, the governing equations often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, stiffness in the PDEs requires an extremely small time steps (e.g. $10^{-12}$ or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose U-Shaped Adaptive Fourier Neural Operators (U-AFNO), a machine learning (ML) model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g. the deformation of the liquid-metal interface) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in-spite of the chaotic nature of LMD. Our model reproduces the key micro-structure statistics and QoIs with a level of accuracy on-par with the high-fidelity numerical solver. We also investigate the opportunity of using hybrid simulations, in which we alternate forward leap in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.
Authors: Anurag Chowdhury, Abhinav Misra, Mark C. Fuhs, Monika Woszczyna
Abstract: Speaker diarization systems segment a conversation recording based on the speakers' identity. Such systems can misclassify the speaker of a portion of audio due to a variety of factors, such as speech pattern variation, background noise, and overlapping speech. These errors propagate to, and can adversely affect, downstream systems that rely on the speaker's identity, such as speaker-adapted speech recognition. One of the ways to mitigate these errors is to provide segment-level diarization confidence scores to downstream systems. In this work, we investigate multiple methods for generating diarization confidence scores, including those derived from the original diarization system and those derived from an external model. Our experiments across multiple datasets and diarization systems demonstrate that the most competitive confidence score methods can isolate ~30% of the diarization errors within segments with the lowest ~10% of confidence scores.
Authors: Piotr Tempczyk, {\L}ukasz Garncarek, Dominik Filipiak, Adam Kurpisz
Abstract: Local intrinsic dimension (LID) estimation methods have received a lot of attention in recent years thanks to the progress in deep neural networks and generative modeling. In opposition to old non-parametric methods, new methods use generative models to approximate diffused dataset density and scale the methods to high-dimensional datasets like images. In this paper, we investigate the recent state-of-the-art parametric LID estimation methods from the perspective of the Wiener process. We explore how these methods behave when their assumptions are not met. We give an extended mathematical description of those methods and their error as a function of the probability density of the data.
Authors: Wenqian Ye, Guangtao Zheng, Yunsheng Ma, Xu Cao, Bolin Lai, James M. Rehg, Aidong Zhang
Abstract: Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe robustness pitfall in deep learning models trained on single modality data. Multimodal Large Language Models (MLLMs), which integrate both vision and language models, have demonstrated strong capability in joint vision-language understanding. However, whether spurious biases are prevalent in MLLMs remains under-explored. We mitigate this gap by analyzing the spurious biases in a multimodal setting, uncovering the specific test data patterns that can manifest this problem when biases in the vision model cascade into the alignment between visual and text tokens in MLLMs. To better understand this problem, we introduce MM-SpuBench, a comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on nine distinct categories of spurious correlations from five open-source image datasets. The VQA dataset is built from human-understandable concept information (attributes). Leveraging this benchmark, we conduct a thorough evaluation of current state-of-the-art MLLMs. Our findings illuminate the persistence of the reliance on spurious correlations from these models and underscore the urge for new methodologies to mitigate spurious biases. To support the MLLM robustness research, we release our VQA benchmark at https://huggingface.co/datasets/mmbench/MM-SpuBench.
Authors: Federica Zoe Ricci, Erik B. Sudderth, Jaylen Lee, Megan A. K. Peters, Marina Vannucci, Michele Guindani
Abstract: We consider the problem of analyzing multivariate time series collected on multiple subjects, with the goal of identifying groups of subjects exhibiting similar trends in their recorded measurements over time as well as time-varying groups of associated measurements. To this end, we propose a Bayesian model for temporal biclustering featuring nested partitions, where a time-invariant partition of subjects induces a time-varying partition of measurements. Our approach allows for data-driven determination of the number of subject and measurement clusters as well as estimation of the number and location of changepoints in measurement partitions. To efficiently perform model fitting and posterior estimation with Markov Chain Monte Carlo, we derive a blocked update of measurements' cluster-assignment sequences. We illustrate the performance of our model in two applications to functional magnetic resonance imaging data and to an electroencephalogram dataset. The results indicate that the proposed model can combine information from potentially many subjects to discover a set of interpretable, dynamic patterns. Experiments on simulated data compare the estimation performance of the proposed model against ground-truth values and other statistical methods, showing that it performs well at identifying ground-truth subject and measurement clusters even when no subject or time dependence is present.
Authors: Byungsoo Jeon, Mengdi Wu, Shiyi Cao, Sunghyun Kim, Sunghyun Park, Neeraj Aggarwal, Colin Unger, Daiyaan Arfeen, Peiyuan Liao, Xupeng Miao, Mohammad Alizadeh, Gregory R. Ganger, Tianqi Chen, Zhihao Jia
Abstract: Deep neural networks (DNNs) continue to grow rapidly in size, making them infeasible to train on a single device. Pipeline parallelism is commonly used in existing DNN systems to support large-scale DNN training by partitioning a DNN into multiple stages, which concurrently perform DNN training for different micro-batches in a pipeline fashion. However, existing pipeline-parallel approaches only consider sequential pipeline stages and thus ignore the topology of a DNN, resulting in missed model-parallel opportunities. This paper presents graph pipeline parallelism (GPP), a new pipeline-parallel scheme that partitions a DNN into pipeline stages whose dependencies are identified by a directed acyclic graph. GPP generalizes existing sequential pipeline parallelism and preserves the inherent topology of a DNN to enable concurrent execution of computationally-independent operators, resulting in reduced memory requirement and improved GPU performance. In addition, we develop GraphPipe, a distributed system that exploits GPP strategies to enable performant and scalable DNN training. GraphPipe partitions a DNN into a graph of stages, optimizes micro-batch schedules for these stages, and parallelizes DNN training using the discovered GPP strategies. Evaluation on a variety of DNNs shows that GraphPipe outperforms existing pipeline-parallel systems such as PipeDream and Piper by up to 1.6X. GraphPipe also reduces the search time by 9-21X compared to PipeDream and Piper.
Authors: Muhammad Mohsin, Stefano Rovetta, Francesco Masulli, Alberto Cabri
Abstract: This contribution gives an overview of an ongoing project using machine learning and computer vision components for improving the electronic waste recycling process. In circular economy, the "virtual mines" concept refers to production cycles where interesting raw materials are reclaimed in an efficient and cost-effective manner from end-of-life items. In particular, the growth of e-waste, due to the increasingly shorter life cycle of hi-tech goods, is a global problem. In this paper, we describe a pipeline based on deep learning model to recycle printed circuit boards at the component level. A pre-trained YOLOv5 model is used to analyze the results of the locally developed dataset. With a different distribution of class instances, YOLOv5 managed to achieve satisfactory precision and recall, with the ability to optimize with large component instances.
Authors: Vikas Yadav, Zheng Tang, Vijay Srinivasan
Abstract: Large language models (LLM) have achieved remarkable success in natural language generation but lesser focus has been given to their applicability in decision making tasks such as classification. We show that LLMs like LLaMa can achieve high performance on large multi-class classification tasks but still make classification errors and worse, generate out-of-vocabulary class labels. To address these critical issues, we introduce Paraphrase and AGgregate (PAG)-LLM approach wherein an LLM generates multiple paraphrases of the input query (parallel queries), performs multi-class classification for the original query and each paraphrase, and at the end aggregate all the classification labels based on their confidence scores. We evaluate PAG-LLM on two large multi-class classication datasets: CLINC, and Banking and show 22.7% and 15.1% error reduction. We show that PAG-LLM is especially effective for hard examples where LLM is uncertain, and reduces the critical misclassification and hallucinated label generation errors
Authors: Shiva Raj Pokhrel, Luxing Yang, Sutharshan Rajasegarar, Gang Li
Abstract: This paper introduces a robust zero-trust architecture (ZTA) tailored for the decentralized system that empowers efficient remote work and collaboration within IoT networks. Using blockchain-based federated learning principles, our proposed framework includes a robust aggregation mechanism designed to counteract malicious updates from compromised clients, enhancing the security of the global learning process. Moreover, secure and reliable trust computation is essential for remote work and collaboration. The robust ZTA framework integrates anomaly detection and trust computation, ensuring secure and reliable device collaboration in a decentralized fashion. We introduce an adaptive algorithm that dynamically adjusts to varying user contexts, using unsupervised clustering to detect novel anomalies, like zero-day attacks. To ensure a reliable and scalable trust computation, we develop an algorithm that dynamically adapts to varying user contexts by employing incremental anomaly detection and clustering techniques to identify and share local and global anomalies between nodes. Future directions include scalability improvements, Dirichlet process for advanced anomaly detection, privacy-preserving techniques, and the integration of post-quantum cryptographic methods to safeguard against emerging quantum threats.
Authors: Zihao Jin, Yingying Fang, Jiahao Huang, Caiwen Xu, Simon Walsh, Guang Yang
Abstract: The manifestation of symptoms associated with lung diseases can vary in different depths for individual patients, highlighting the significance of 3D information in CT scans for medical image classification. While Vision Transformer has shown superior performance over convolutional neural networks in image classification tasks, their effectiveness is often demonstrated on sufficiently large 2D datasets and they easily encounter overfitting issues on small medical image datasets. To address this limitation, we propose a Diffusion-based 3D Vision Transformer (Diff3Dformer), which utilizes the latent space of the Diffusion model to form the slice sequence for 3D analysis and incorporates clustering attention into ViT to aggregate repetitive information within 3D CT scans, thereby harnessing the power of the advanced transformer in 3D classification tasks on small datasets. Our method exhibits improved performance on two different scales of small datasets of 3D lung CT scans, surpassing the state of the art 3D methods and other transformer-based approaches that emerged during the COVID-19 pandemic, demonstrating its robust and superior performance across different scales of data. Experimental results underscore the superiority of our proposed method, indicating its potential for enhancing medical image classification tasks in real-world scenarios.
Authors: Haoxuan Li, Chunyuan Zheng, Wenjie Wang, Hao Wang, Fuli Feng, Xiao-Hua Zhou
Abstract: Ratings of a user to most items in recommender systems are usually missing not at random (MNAR), largely because users are free to choose which items to rate. To achieve unbiased learning of the prediction model under MNAR data, three typical solutions have been proposed, including error-imputation-based (EIB), inverse-propensity-scoring (IPS), and doubly robust (DR) methods. However, these methods ignore an alternative form of bias caused by the inconsistency between the observed ratings and the users' true preferences, also known as noisy feedback or outcome measurement errors (OME), e.g., due to public opinion or low-quality data collection process. In this work, we study intersectional threats to the unbiased learning of the prediction model from data MNAR and OME in the collected data. First, we design OME-EIB, OME-IPS, and OME-DR estimators, which largely extend the existing estimators to combat OME in real-world recommendation scenarios. Next, we theoretically prove the unbiasedness and generalization bound of the proposed estimators. We further propose an alternate denoising training approach to achieve unbiased learning of the prediction model under MNAR data with OME. Extensive experiments are conducted on three real-world datasets and one semi-synthetic dataset to show the effectiveness of our proposed approaches. The code is available at https://github.com/haoxuanli-pku/KDD24-OME-DR.
Authors: Mohammad Nur Hossain Khan, Jialu Li, Nancy L. McElwain, Mark Hasegawa-Johnson, Bashima Islam
Abstract: Certain environmental noises have been associated with negative developmental outcomes for infants and young children. Though classifying or tagging sound events in a domestic environment is an active research area, previous studies focused on data collected from a non-stationary microphone placed in the environment or from the perspective of adults. Further, many of these works ignore infants or young children in the environment or have data collected from only a single family where noise from the fixed sound source can be moderate at the infant's position or vice versa. Thus, despite the recent success of large pre-trained models for noise event detection, the performance of these models on infant-centric noise soundscapes in the home is yet to be explored. To bridge this gap, we have collected and labeled noises in home soundscapes from 22 families in an unobtrusive manner, where the data are collected through an infant-worn recording device. In this paper, we explore the performance of a large pre-trained model (Audio Spectrogram Transformer [AST]) on our noise-conditioned infant-centric environmental data as well as publicly available home environmental datasets. Utilizing different training strategies such as resampling, utilizing public datasets, mixing public and infant-centric training sets, and data augmentation using noise and masking, we evaluate the performance of a large pre-trained model on sparse and imbalanced infant-centric data. Our results show that fine-tuning the large pre-trained model by combining our collected dataset with public datasets increases the F1-score from 0.11 (public datasets) and 0.76 (collected datasets) to 0.84 (combined datasets) and Cohen's Kappa from 0.013 (public datasets) and 0.77 (collected datasets) to 0.83 (combined datasets) compared to only training with public or collected datasets, respectively.
Authors: Ruochen Wang, Si Si, Felix Yu, Dorothea Wiesmann, Cho-Jui Hsieh, Inderjit Dhillon
Abstract: The trade-off between expressiveness and interpretability remains a core challenge when building human-centric predictive models for classification and decision-making. While symbolic rules offer interpretability, they often lack expressiveness, whereas neural networks excel in performance but are known for being black boxes. In this paper, we show a combination of Large Language Models (LLMs) and symbolic programs can bridge this gap. In the proposed LLM-based Symbolic Programs (LSPs), the pretrained LLM with natural language prompts provides a massive set of interpretable modules that can transform raw input into natural language concepts. Symbolic programs then integrate these modules into an interpretable decision rule. To train LSPs, we develop a divide-and-conquer approach to incrementally build the program from scratch, where the learning process of each step is guided by LLMs. To evaluate the effectiveness of LSPs in extracting interpretable and accurate knowledge from data, we introduce IL-Bench, a collection of diverse tasks, including both synthetic and real-world scenarios across different modalities. Empirical results demonstrate LSP's superior performance compared to traditional neurosymbolic programs and vanilla automatic prompt tuning methods. Moreover, as the knowledge learned by LSP is a combination of natural language descriptions and symbolic rules, it is easily transferable to humans (interpretable), and other LLMs, and generalizes well to out-of-distribution samples.
Authors: Bryon Aragam
Abstract: One of the hallmark achievements of the theory of graphical models and Bayesian model selection is the celebrated greedy equivalence search (GES) algorithm due to Chickering and Meek. GES is known to consistently estimate the structure of directed acyclic graph (DAG) models in various special cases including Gaussian and discrete models, which are in particular curved exponential families. A general theory that covers general nonparametric DAG models, however, is missing. Here, we establish the consistency of greedy equivalence search for general families of DAG models that satisfy smoothness conditions on the Markov factorization, and hence may not be curved exponential families, or even parametric. The proof leverages recent advances in nonparametric Bayes to construct a test for comparing misspecified DAG models that avoids arguments based on the Laplace approximation. Nonetheless, when the Laplace approximation is valid and a consistent scoring function exists, we recover the classical result. As a result, we obtain a general consistency theorem for GES applied to general DAG models.
Authors: Sri Harsha Dumpala, Katerina Dikaios, Abraham Nunes, Frank Rudzicz, Rudolf Uher, Sageev Oore
Abstract: Depression, a prevalent mental health disorder impacting millions globally, demands reliable assessment systems. Unlike previous studies that focus solely on either detecting depression or predicting its severity, our work identifies individual symptoms of depression while also predicting its severity using speech input. We leverage self-supervised learning (SSL)-based speech models to better utilize the small-sized datasets that are frequently encountered in this task. Our study demonstrates notable performance improvements by utilizing SSL embeddings compared to conventional speech features. We compare various types of SSL pretrained models to elucidate the type of speech information (semantic, speaker, or prosodic) that contributes the most in identifying different symptoms. Additionally, we evaluate the impact of combining multiple SSL embeddings on performance. Furthermore, we show the significance of multi-task learning for identifying depressive symptoms effectively.
Authors: Rohit Paturi, Xiang Li, Sundararajan Srinivasan
Abstract: Speaker Diarization (SD) systems are typically audio-based and operate independently of the ASR system in traditional speech transcription pipelines and can have speaker errors due to SD and/or ASR reconciliation, especially around speaker turns and regions of speech overlap. To reduce these errors, a Lexical Speaker Error Correction (LSEC), in which an external language model provides lexical information to correct the speaker errors, was recently proposed. Though the approach achieves good Word Diarization error rate (WDER) improvements, it does not use any additional acoustic information and is prone to miscorrections. In this paper, we propose to enhance and acoustically ground the LSEC system with speaker scores directly derived from the existing SD pipeline. This approach achieves significant relative WDER reductions in the range of 25-40% over the audio-based SD, ASR system and beats the LSEC system by 15-25% relative on RT03-CTS, Callhome American English and Fisher datasets.
Authors: Jianfeng He, Runing Yang, Linlin Yu, Changbin Li, Ruoxi Jia, Feng Chen, Ming Jin, Chang-Tien Lu
Abstract: Text summarization, a key natural language generation (NLG) task, is vital in various domains. However, the high cost of inaccurate summaries in risk-critical applications, particularly those involving human-in-the-loop decision-making, raises concerns about the reliability of uncertainty estimation on text summarization (UE-TS) evaluation methods. This concern stems from the dependency of uncertainty model metrics on diverse and potentially conflicting NLG metrics. To address this issue, we introduce a comprehensive UE-TS benchmark incorporating 31 NLG metrics across four dimensions. The benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with human-annotation analysis incorporated where applicable. We also assess the performance of 14 common uncertainty estimation methods within this benchmark. Our findings emphasize the importance of considering multiple uncorrelated NLG metrics and diverse uncertainty estimation methods to ensure reliable and efficient evaluation of UE-TS techniques.
Authors: Alexandra Dobrita (Imec Netherlands, Delft University of Technology), Amirreza Yousefzadeh (Imec Netherlands), Simon Thorpe (University of Toulouse), Kanishkan Vadivel (Imec Netherlands), Paul Detterer (Imec Netherlands), Guangzhi Tang (Imec Netherlands), Gert-Jan van Schaik (Imec Netherlands), Mario Konijnenburg (Imec Netherlands), Anteneh Gebregiorgis (Delft University of Technology), Said Hamdioui (Delft University of Technology), Manolis Sifalakis (Imec Netherlands)
Abstract: For Edge AI applications, deploying online learning and adaptation on resource-constrained embedded devices can deal with fast sensor-generated streams of data in changing environments. However, since maintaining low-latency and power-efficient inference is paramount at the Edge, online learning and adaptation on the device should impose minimal additional overhead for inference. With this goal in mind, we explore energy-efficient learning and adaptation on-device for streaming-data Edge AI applications using Spiking Neural Networks (SNNs), which follow the principles of brain-inspired computing, such as high-parallelism, neuron co-located memory and compute, and event-driven processing. We propose EON-1, a brain-inspired processor for near-sensor extreme edge online feature extraction, that integrates a fast online learning and adaptation algorithm. We report results of only 1% energy overhead for learning, by far the lowest overhead when compared to other SoTA solutions, while attaining comparable inference accuracy. Furthermore, we demonstrate that EON-1 is up for the challenge of low-latency processing of HD and UHD streaming video in real-time, with learning enabled.
Authors: Nawaf Alampara, Santiago Miret, Kevin Maik Jablonka
Abstract: Effectively representing materials as text has the potential to leverage the vast advancements of large language models (LLMs) for discovering new materials. While LLMs have shown remarkable success in various domains, their application to materials science remains underexplored. A fundamental challenge is the lack of understanding of how to best utilize text-based representations for materials modeling. This challenge is further compounded by the absence of a comprehensive benchmark to rigorously evaluate the capabilities and limitations of these text representations in capturing the complexity of material systems. To address this gap, we propose MatText, a suite of benchmarking tools and datasets designed to systematically evaluate the performance of language models in modeling materials. MatText encompasses nine distinct text-based representations for material systems, including several novel representations. Each representation incorporates unique inductive biases that capture relevant information and integrate prior physical knowledge about materials. Additionally, MatText provides essential tools for training and benchmarking the performance of language models in the context of materials science. These tools include standardized dataset splits for each representation, probes for evaluating sensitivity to geometric factors, and tools for seamlessly converting crystal structures into text. Using MatText, we conduct an extensive analysis of the capabilities of language models in modeling materials. Our findings reveal that current language models consistently struggle to capture the geometric information crucial for materials modeling across all representations. Instead, these models tend to leverage local information, which is emphasized in some of our novel representations. Our analysis underscores MatText's ability to reveal shortcomings of text-based methods for materials design.
Authors: Zuzanna Kostecka, Robert \'Slepaczuk
Abstract: The scope for the accurate calculation of the Loss Given Default (LGD) parameter is comprehensive in terms of financial data. In this research, we aim to explore methods for improving the approximation of realized LGD in conditions of limited access to the cash-flow data. We enhance the performance of the method which relies on the differences between exposure values (delta outstanding approach) by employing machine learning (ML) techniques. The research utilizes the data from the mortgage portfolio of one of the European countries and assumes a close resemblance to similar economic contexts. It incorporates non-financial variables and macroeconomic data related to the housing market, improving the accuracy of loss severity approximation. The proposed methodology attempts to mitigate the country-specific (related to the local legal) or portfolio-specific factors in aim to show the general advantage of applying ML techniques, rather than case-specific relation. We developed an XGBoost model that does not rely on cash-flow data yet enhances the accuracy of realized LGD estimation compared to results obtained with the delta outstanding approach. A novel aspect of our work is the detailed exploration of the delta outstanding approach and the methodology for addressing conditions of limited access to cash-flow data through machine learning models.
Authors: Sotiria Fotopoulou (University of Bristol)
Abstract: This review summarizes popular unsupervised learning methods, and gives an overview of their past, current, and future uses in astronomy. Unsupervised learning aims to organise the information content of a dataset, in such a way that knowledge can be extracted. Traditionally this has been achieved through dimensionality reduction techniques that aid the ranking of a dataset, for example through principal component analysis or by using auto-encoders, or simpler visualisation of a high dimensional space, for example through the use of a self organising map. Other desirable properties of unsupervised learning include the identification of clusters, i.e. groups of similar objects, which has traditionally been achieved by the k-means algorithm and more recently through density-based clustering such as HDBSCAN. More recently, complex frameworks have emerged, that chain together dimensionality reduction and clustering methods. However, no dataset is fully unknown. Thus, nowadays a lot of research has been directed towards self-supervised and semi-supervised methods that stand to gain from both supervised and unsupervised learning.
Authors: Elisabeta-Iulia Dima, Pablo G\'omez, Sandor Kruk, Peter Kretschmar, Simon Rosen, C\u{a}lin-Adrian Popa
Abstract: Reflected or scattered light produce artefacts in astronomical observations that can negatively impact the scientific study. Hence, automated detection of these artefacts is highly beneficial, especially with the increasing amounts of data gathered. Machine learning methods are well-suited to this problem, but currently there is a lack of annotated data to train such approaches to detect artefacts in astronomical observations. In this work, we present a dataset of images from the XMM-Newton space telescope Optical Monitoring camera showing different types of artefacts. We hand-annotated a sample of 1000 images with artefacts which we use to train automated ML methods. We further demonstrate techniques tailored for accurate detection and masking of artefacts using instance segmentation. We adopt a hybrid approach, combining knowledge from both convolutional neural networks (CNNs) and transformer-based models and use their advantages in segmentation. The presented method and dataset will advance artefact detection in astronomical observations by providing a reproducible baseline. All code and data are made available (https://github.com/ESA-Datalabs/XAMI-model and https://github.com/ESA-Datalabs/XAMI-dataset).
URLs: https://github.com/ESA-Datalabs/XAMI-model, https://github.com/ESA-Datalabs/XAMI-dataset).
Authors: Hung Vinh Tran, Tong Chen, Quoc Viet Hung Nguyen, Zi Huang, Lizhen Cui, Hongzhi Yin
Abstract: Since the creation of the Web, recommender systems (RSs) have been an indispensable mechanism in information filtering. State-of-the-art RSs primarily depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables. To prevent over-parameterized embedding tables from harming scalability, both academia and industry have seen increasing efforts in compressing RS embeddings. However, despite the prosperity of lightweight embedding-based RSs (LERSs), a wide diversity is seen in evaluation protocols, resulting in obstacles when relating LERS performance to real-world usability. Moreover, despite the common goal of lightweight embeddings, LERSs are evaluated with a single choice between the two main recommendation tasks -- collaborative filtering and content-based recommendation. This lack of discussions on cross-task transferability hinders the development of unified, more scalable solutions. Motivated by these issues, this study investigates various LERSs' performance, efficiency, and cross-task transferability via a thorough benchmarking process. Additionally, we propose an efficient embedding compression method using magnitude pruning, which is an easy-to-deploy yet highly competitive baseline that outperforms various complex LERSs. Our study reveals the distinct performance of LERSs across the two tasks, shedding light on their effectiveness and generalizability. To support edge-based recommendations, we tested all LERSs on a Raspberry Pi 4, where the efficiency bottleneck is exposed. Finally, we conclude this paper with critical summaries of LERS performance, model selection suggestions, and underexplored challenges around LERSs for future research. To encourage future research, we publish source codes and artifacts at \href{this link}{https://github.com/chenxing1999/recsys-benchmark}.
Authors: Peng Huang, Shu Hu, Bo Peng, Jiashu Zhang, Xi Wu, Xin Wang
Abstract: Current medical image classification efforts mainly aim for higher average performance, often neglecting the balance between different classes. This can lead to significant differences in recognition accuracy between classes and obvious recognition weaknesses. Without the support of massive data, deep learning faces challenges in fine-grained classification of fatty liver. In this paper, we propose an innovative deep learning framework that combines feature decoupling and adaptive adversarial training. Firstly, we employ two iteratively compressed decouplers to supervised decouple common features and specific features related to fatty liver in abdominal ultrasound images. Subsequently, the decoupled features are concatenated with the original image after transforming the color space and are fed into the classifier. During adversarial training, we adaptively adjust the perturbation and balance the adversarial strength by the accuracy of each class. The model will eliminate recognition weaknesses by correctly classifying adversarial samples, thus improving recognition robustness. Finally, the accuracy of our method improved by 4.16%, achieving 82.95%. As demonstrated by extensive experiments, our method is a generalized learning framework that can be directly used to eliminate the recognition weaknesses of any classifier while improving its average performance. Code is available at https://github.com/HP-ML/MICCAI2024.
Authors: Oshana Dissanayake (UCD), Sarah E. Mcpherson (Teagasc, WUR), Joseph Allyndr\'ee (UCD), Emer Kennedy (Teagasc), P\'adraig Cunningham (UCD), Lucile Riaboff (GenPhySE, INRAE)
Abstract: Automatic monitoring of calf behaviour is a promising way of assessing animal welfare from their first week on farms. This study aims to (i) develop machine learning models from accelerometer data to classify the main behaviours of pre-weaned calves and (ii) set up a digital tool for monitoring the behaviour of pre-weaned calves from the models' prediction. Thirty pre-weaned calves were equipped with a 3-D accelerometer attached to a neck-collar for two months and filmed simultaneously. The behaviours were annotated, resulting in 27.4 hours of observation aligned with the accelerometer data. The time-series were then split into 3 seconds windows. Two machine learning models were tuned using data from 80% of the calves: (i) a Random Forest model to classify between active and inactive behaviours using a set of 11 hand-craft features [model 1] and (ii) a RidgeClassifierCV model to classify between lying, running, drinking milk and other behaviours using ROCKET features [model 2]. The performance of the models was tested using data from the remaining 20% of the calves. Model 1 achieved a balanced accuracy of 0.92. Model 2 achieved a balanced accuracy of 0.84. Behavioural metrics such as daily activity ratio and episodes of running, lying, drinking milk, and other behaviours expressed over time were deduced from the predictions. All the development was finally embedded into a Python dashboard so that the individual calf metrics could be displayed directly from the raw accelerometer files.
Authors: Wanli Shi, Yi Chang, Bin Gu
Abstract: Bilevel optimization (BO) has recently gained prominence in many machine learning applications due to its ability to capture the nested structure inherent in these problems. Recently, many hypergradient methods have been proposed as effective solutions for solving large-scale problems. However, current hypergradient methods for the lower-level constrained bilevel optimization (LCBO) problems need very restrictive assumptions, namely, where optimality conditions satisfy the differentiability and invertibility conditions and lack a solid analysis of the convergence rate. What's worse, existing methods require either double-loop updates, which are sometimes less efficient. To solve this problem, in this paper, we propose a new hypergradient of LCBO leveraging the theory of nonsmooth implicit function theorem instead of using the restrive assumptions. In addition, we propose a \textit{single-loop single-timescale} algorithm based on the double-momentum method and adaptive step size method and prove it can return a $(\delta, \epsilon)$-stationary point with $\tilde{\mathcal{O}}(d_2^2\epsilon^{-4})$ iterations. Experiments on two applications demonstrate the effectiveness of our proposed method.
Authors: Yixuan Wang, Xianzhen Luo, Fuxuan Wei, Yijun Liu, Qingfu Zhu, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che
Abstract: Existing speculative decoding methods typically require additional model structure and training processes to assist the model for draft token generation. This makes the migration of acceleration methods to the new model more costly and more demanding on device memory. To address this problem, we propose the Make Some Noise (MSN) training framework as a replacement for the supervised fine-tuning stage of the large language model. The training method simply introduces some noise at the input for the model to learn the denoising task. It significantly enhances the parallel decoding capability of the model without affecting the original task capability. In addition, we propose a tree-based retrieval-augmented Jacobi (TR-Jacobi) decoding strategy to further improve the inference speed of MSN models. Experiments in both the general and code domains have shown that MSN can improve inference speed by 2.3-2.7x times without compromising model performance. The MSN model also achieves comparable acceleration ratios to the SOTA model with additional model structure on Spec-Bench.
Authors: Razvan-Gabriel Dumitru, Vikas Yadav, Rishabh Maheshwary, Paul-Ioan Clotan, Sathwik Tejaswi Madhusudhan, Mihai Surdeanu
Abstract: We present a simple variable quantization approach that quantizes different layers of a large language model (LLM) at different bit levels. Specifically, we quantize the most important layers to higher bit precision and less important layers to lower bits to achieve floating point quantization levels. We propose two effective strategies to measure the importance of layers within LLMs: the first measures the importance of a layer based on how different its output embeddings are from the input embeddings (the higher the better); the second estimates the importance of a layer using the number of layer weights that are much larger than average (the smaller the better). We show that quantizing different layers at varying bits according to our importance scores results in minimal performance drop with a far more compressed model size. Finally, we present several practical key takeaways from our variable layer-wise quantization experiments: (a) LLM performance under variable quantization remains close to the original model until 25-50% of layers are moved in lower quantization using our proposed ordering but only until 5-10% if moved using no specific ordering; (b) Quantizing LLMs to lower bits performs substantially better than pruning unless extreme quantization (2-bit) is used; and (c) Layer-wise quantization to lower bits works better in the case of larger LLMs with more layers compared to smaller LLMs with fewer layers. The code used to run the experiments is available at: https://github.com/RazvanDu/LayerwiseQuant.
Authors: Zhichen Xiang, Hongke Zhao, Chuang Zhao, Ming He, Jianping Fan
Abstract: Data bias, e.g., popularity impairs the dynamics of two-sided markets within recommender systems. This overshadows the less visible but potentially intriguing long-tail items that could capture user interest. Despite the abundance of research surrounding this issue, it still poses challenges and remains a hot topic in academic circles. Along this line, in this paper, we developed a re-ranking approach in dynamic settings with fair-exposure optimization driven by strategic agents. Designed for the producer side, the execution of agents assumes content creators can modify item features based on strategic incentives to maximize their exposure. This iterative process entails an end-to-end optimization, employing differentiable ranking operators that simultaneously target accuracy and fairness. Joint objectives ensure the performance of recommendations while enhancing the visibility of tail items. We also leveraged the performativity nature of predictions to illustrate how strategic learning influences content creators to shift towards fairness efficiently, thereby incentivizing features of tail items. Through comprehensive experiments on both public and industrial datasets, we have substantiated the effectiveness and dominance of the proposed method especially on unveiling the potential of tail items.
Authors: Yuji Byun, Jaeho Lee
Abstract: Low-rank adaptation (LoRA) is an attractive alternative of adapting full weights for the federated fine-tuning of large pretrained models, which can significantly reduce the memory and communication burden. In principle, federated LoRA can provide an effective mean to allocate different resources to each client by tuning ranks for each client, which can be useful in achieving a better communication-performance tradeoff. We find, however, that the empirical performance of LoRA is highly unstable with respect to such rank-heterogeneity, severely limiting the applicability to the scenarios where it is desirable or even required to allocate nonuniform communication bandwidth to each client due to constrained total bandwidth. Our investigation reveals that the root cause of this instability is the zero-padding-based aggregation strategy adopted in conventional federated LoRA frameworks, which causes the information from high rank clients to get diluted during the aggregation process. To address this issue, we propose a new replication-based padding strategy, which allows us to better leverage the information from clients with high-quality datasets. This method ensures that valuable information from high rank clients is retained during the aggregation process, accelerating the convergence speed and enhancing the overall prediction quality of the global model.
Authors: Sebastian Dittert, Vincent Moens, Gianni De Fabritiis
Abstract: We present BricksRL, a platform designed to democratize access to robotics for reinforcement learning research and education. BricksRL facilitates the creation, design, and training of custom LEGO robots in the real world by interfacing them with the TorchRL library for reinforcement learning agents. The integration of TorchRL with the LEGO hubs, via Bluetooth bidirectional communication, enables state-of-the-art reinforcement learning training on GPUs for a wide variety of LEGO builds. This offers a flexible and cost-efficient approach for scaling and also provides a robust infrastructure for robot-environment-algorithm communication. We present various experiments across tasks and robot configurations, providing built plans and training results. Furthermore, we demonstrate that inexpensive LEGO robots can be trained end-to-end in the real world to achieve simple tasks, with training times typically under 120 minutes on a normal laptop. Moreover, we show how users can extend the capabilities, exemplified by the successful integration of non-LEGO sensors. By enhancing accessibility to both robotics and reinforcement learning, BricksRL establishes a strong foundation for democratized robotic learning in research and educational settings.
Authors: Francesco Di Salvo, Sebastian Doerrich, Christian Ledig
Abstract: The integration of neural-network-based systems into clinical practice is limited by challenges related to domain generalization and robustness. The computer vision community established benchmarks such as ImageNet-C as a fundamental prerequisite to measure progress towards those challenges. Similar datasets are largely absent in the medical imaging community which lacks a comprehensive benchmark that spans across imaging modalities and applications. To address this gap, we create and open-source MedMNIST-C, a benchmark dataset based on the MedMNIST+ collection covering 12 datasets and 9 imaging modalities. We simulate task and modality-specific image corruptions of varying severity to comprehensively evaluate the robustness of established algorithms against real-world artifacts and distribution shifts. We further provide quantitative evidence that our simple-to-use artificial corruptions allow for highly performant, lightweight data augmentation to enhance model robustness. Unlike traditional, generic augmentation strategies, our approach leverages domain knowledge, exhibiting significantly higher robustness when compared to widely adopted methods. By introducing MedMNIST-C and open-sourcing the corresponding library allowing for targeted data augmentations, we contribute to the development of increasingly robust methods tailored to the challenges of medical imaging. The code is available at https://github.com/francescodisalvo05/medmnistc-api}{github.com/francescodisalvo05/medmnistc-api.
Authors: Bogumi{\l} Kami\'nski, Pawe{\l} Misiorek, Pawe{\l} Pra{\l}at, Fran\c{c}ois Th\'eberge
Abstract: In this paper, we propose a scalable community detection algorithm using hypergraph modularity function, h-Louvain. It is an adaptation of the classical Louvain algorithm in the context of hypergraphs. We observe that a direct application of the Louvain algorithm to optimize the hypergraph modularity function often fails to find meaningful communities. We propose a solution to this issue by adjusting the initial stage of the algorithm via carefully and dynamically tuned linear combination of the graph modularity function of the corresponding two-section graph and the desired hypergraph modularity function. The process is guided by Bayesian optimization of the hyper-parameters of the proposed procedure. Various experiments on synthetic as well as real-world networks are performed showing that this process yields improved results in various regimes.
Authors: Daniel Scalena, Gabriele Sarti, Malvina Nissim
Abstract: Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations. However, the evaluation of these techniques has so far been limited to single conditioning properties and synthetic settings. In this work, we conduct a comprehensive evaluation of various activation steering strategies, highlighting the property-dependent nature of optimal parameters to ensure a robust effect throughout generation. To address this issue, we propose Dynamic Activation Composition, an information-theoretic approach to modulate the steering intensity of one or more properties throughout generation. Our experiments on multi-property steering show that our method successfully maintains high conditioning while minimizing the impact of conditioning on generation fluency.
Authors: Cheng Wang, Christopher Redino, Ryan Clark, Abdul Rahman, Sal Aguinaga, Sathvik Murli, Dhruv Nandakumar, Roland Rao, Lanxiao Huang, Daniel Radke, Edward Bowen
Abstract: Ransomware presents a significant and increasing threat to individuals and organizations by encrypting their systems and not releasing them until a large fee has been extracted. To bolster preparedness against potential attacks, organizations commonly conduct red teaming exercises, which involve simulated attacks to assess existing security measures. This paper proposes a novel approach utilizing reinforcement learning (RL) to simulate ransomware attacks. By training an RL agent in a simulated environment mirroring real-world networks, effective attack strategies can be learned quickly, significantly streamlining traditional, manual penetration testing processes. The attack pathways revealed by the RL agent can provide valuable insights to the defense team, helping them identify network weak points and develop more resilient defensive measures. Experimental results on a 152-host example network confirm the effectiveness of the proposed approach, demonstrating the RL agent's capability to discover and orchestrate attacks on high-value targets while evading honeyfiles (decoy files strategically placed to detect unauthorized access).
Authors: Sean Tull, Robin Lorenz, Stephen Clark, Ilyas Khan, Bob Coecke
Abstract: Artificial intelligence (AI) is currently based largely on black-box machine learning models which lack interpretability. The field of eXplainable AI (XAI) strives to address this major concern, being critical in high-stakes areas such as the finance, legal and health sectors. We present an approach to defining AI models and their interpretability based on category theory. For this we employ the notion of a compositional model, which sees a model in terms of formal string diagrams which capture its abstract structure together with its concrete implementation. This comprehensive view incorporates deterministic, probabilistic and quantum models. We compare a wide range of AI models as compositional models, including linear and rule-based models, (recurrent) neural networks, transformers, VAEs, and causal and DisCoCirc models. Next we give a definition of interpretation of a model in terms of its compositional structure, demonstrating how to analyse the interpretability of a model, and using this to clarify common themes in XAI. We find that what makes the standard 'intrinsically interpretable' models so transparent is brought out most clearly diagrammatically. This leads us to the more general notion of compositionally-interpretable (CI) models, which additionally include, for instance, causal, conceptual space, and DisCoCirc models. We next demonstrate the explainability benefits of CI models. Firstly, their compositional structure may allow the computation of other quantities of interest, and may facilitate inference from the model to the modelled phenomenon by matching its structure. Secondly, they allow for diagrammatic explanations for their behaviour, based on influence constraints, diagram surgery and rewrite explanations. Finally, we discuss many future directions for the approach, raising the question of how to learn such meaningfully structured models in practice.
Authors: Kim Batselier
Abstract: Specifying a prior distribution is an essential part of solving Bayesian inverse problems. The prior encodes a belief on the nature of the solution and this regularizes the problem. In this article we completely characterize a Gaussian prior that encodes the belief that the solution is a structured tensor. We first define the notion of (A,b)-constrained tensors and show that they describe a large variety of different structures such as Hankel, circulant, triangular, symmetric, and so on. Then we completely characterize the Gaussian probability distribution of such tensors by specifying its mean vector and covariance matrix. Furthermore, explicit expressions are proved for the covariance matrix of tensors whose entries are invariant under a permutation. These results unlock a whole new class of priors for Bayesian inverse problems. We illustrate how new kernel functions can be designed and efficiently computed and apply our results on two particular Bayesian inverse problems: completing a Hankel matrix from a few noisy measurements and learning an image classifier of handwritten digits. The effectiveness of the proposed priors is demonstrated for both problems. All applications have been implemented as reactive Pluto notebooks in Julia.
Authors: Mohamed Amine Merzouk, Erwan Beurier, Reda Yaich, Nora Boulahia-Cuppens, Fr\'ed\'eric Cuppens
Abstract: The escalating sophistication of cyberattacks has encouraged the integration of machine learning techniques in intrusion detection systems, but the rise of adversarial examples presents a significant challenge. These crafted perturbations mislead ML models, enabling attackers to evade detection or trigger false alerts. As a reaction, adversarial purification has emerged as a compelling solution, particularly with diffusion models showing promising results. However, their purification potential remains unexplored in the context of intrusion detection. This paper demonstrates the effectiveness of diffusion models in purifying adversarial examples in network intrusion detection. Through a comprehensive analysis of the diffusion parameters, we identify optimal configurations maximizing adversarial robustness with minimal impact on normal performance. Importantly, this study reveals insights into the relationship between diffusion noise and diffusion steps, representing a novel contribution to the field. Our experiments are carried out on two datasets and against 5 adversarial attacks. The implementation code is publicly available.
Authors: Partha Chakraborty, Venkatraman Arumugam, Meiyappan Nagappan
Abstract: Bug localization refers to the identification of source code files which is in a programming language and also responsible for the unexpected behavior of software using the bug report, which is a natural language. As bug localization is labor-intensive, bug localization models are employed to assist software developers. Due to the domain difference between source code files and bug reports, modern bug-localization systems, based on deep learning models, rely heavily on embedding techniques that project bug reports and source code files into a shared vector space. The creation of an embedding involves several design choices, but the impact of these choices on the quality of embedding and the performance of bug localization models remains unexplained in current research. To address this gap, our study evaluated 14 distinct embedding models to gain insights into the effects of various design choices. Subsequently, we developed bug localization models utilizing these embedding models to assess the influence of these choices on the performance of the localization models. Our findings indicate that the pre-training strategies significantly affect the quality of the embedding. Moreover, we discovered that the familiarity of the embedding models with the data has a notable impact on the bug localization model's performance. Notably, when the training and testing data are collected from different projects, the performance of the bug localization models exhibits substantial fluctuations.
Authors: Devan Shanker
Abstract: In order to ensure autonomous vehicles are safe for on-road deployment, simulation-based testing has become an integral complement to on-road testing. The rise in simulation testing and validation reflects a growing need to verify that AV behavior is consistent with desired outcomes even in edge case scenarios $-$ which may seldom or never appear in on-road testing data. This raises a critical question: to what extent are AV failures in simulation consistent with data collected from real-world testing? As a result of the gap between simulated and real sensor data (sim-to-real gap), failures in simulation can either be spurious (simulation- or simulator-specific issues) or relevant (safety-critical AV system issues). One possible method for validating if simulated time series failures are consistent with real world time series sensor data could involve retrieving instances of the failure scenario from a real-world time series dataset, in order to understand AV performance in these scenarios. Adopting this strategy, we propose a formal definition of what constitutes a match between a real-world labeled time series data item and a simulated scenario written from a fragment of the Scenic probabilistic programming language for simulation generation. With this definition of a match, we develop a querying algorithm that identifies the subset of a labeled time series dataset matching a given scenario. To allow this approach to be used to verify the safety of other cyber-physical systems (CPS), we present a definition and algorithm for matching scalable beyond the autonomous vehicles domain. Experiments demonstrate the precision and scalability of the algorithm for a set of challenging and uncommon time series scenarios identified from the nuScenes autonomous driving dataset. We include a full system implementation of the querying algorithm freely available for use across a wide range of CPS.
Authors: Akash Kundu, Aritra Sarkar, Abhishek Sadhu
Abstract: Quantum architecture search~(QAS) is a promising direction for optimization and automated design of quantum circuits towards quantum advantage. Recent techniques in QAS focus on machine learning-based approaches from reinforcement learning, like deep Q-network. While multi-layer perceptron-based deep Q-networks have been applied for QAS, their interpretability remains challenging due to the high number of parameters. In this work, we evaluate the practicality of KANs in quantum architecture search problems, analyzing their efficiency in terms of the probability of success, frequency of optimal solutions and their dependencies on various degrees of freedom of the network. In a noiseless scenario, the probability of success and the number of optimal quantum circuit configurations to generate the multi-qubit maximally entangled states are significantly higher than MLPs. Moreover in noisy scenarios, KAN can achieve a better fidelity in approximating maximally entangled state than MLPs, where the performance of the MLP significantly depends on the choice of activation function. Further investigation reveals that KAN requires a very small number of learnable parameters compared to MLPs, however, the average time of executing each episode for KAN is much higher.
Authors: Nicholas Pangakis, Samuel Wolken
Abstract: Computational social science (CSS) practitioners often rely on human-labeled data to fine-tune supervised text classifiers. We assess the potential for researchers to augment or replace human-generated training data with surrogate training labels from generative large language models (LLMs). We introduce a recommended workflow and test this LLM application by replicating 14 classification tasks and measuring performance. We employ a novel corpus of English-language text classification data sets from recent CSS articles in high-impact journals. Because these data sets are stored in password-protected archives, our analyses are less prone to issues of contamination. For each task, we compare supervised classifiers fine-tuned using GPT-4 labels against classifiers fine-tuned with human annotations and against labels from GPT-4 and Mistral-7B with few-shot in-context learning. Our findings indicate that supervised classification models fine-tuned on LLM-generated labels perform comparably to models fine-tuned with labels from human annotators. Fine-tuning models using LLM-generated labels can be a fast, efficient and cost-effective method of building supervised text classifiers.
Authors: Sedigheh Eslami, Gerard de Melo
Abstract: Contrastive Language--Image Pre-training (CLIP) has manifested remarkable improvements in zero-shot classification and cross-modal vision-language tasks. Yet, from a geometrical point of view, the CLIP embedding space has been found to have a pronounced modality gap. This gap renders the embedding space overly sparse and disconnected, with different modalities being densely distributed in distinct subregions of the hypersphere. In this work, we aim at answering two main questions: 1. Does sharing the parameter space between the multi-modal encoders reduce the modality gap? 2. Can the gap be mitigated by pushing apart the uni-modal embeddings via intra-modality separation? We design AlignCLIP, in order to answer these questions and show that answers to both questions are positive. Through extensive experiments, we show that AlignCLIP achieves noticeable enhancements in the cross-modal alignment of the embeddings, and thereby, reduces the modality gap, while maintaining the performance across several downstream evaluations, such as zero-shot image classification, zero-shot multi-modal retrieval and zero-shot semantic text similarity.
Authors: Zeinab Sherkatghanad, Moloud Abdar, Mohammadreza Bakhtyari, Vladimir Makarenkov
Abstract: Test-time augmentation (TTA) is a well-known technique employed during the testing phase of computer vision tasks. It involves aggregating multiple augmented versions of input data. Combining predictions using a simple average formulation is a common and straightforward approach after performing TTA. This paper introduces a novel framework for optimizing TTA, called BayTTA (Bayesian-based TTA), which is based on Bayesian Model Averaging (BMA). First, we generate a model list associated with different variations of the input data created through TTA. Then, we use BMA to combine model predictions weighted by their respective posterior probabilities. Such an approach allows one to take into account model uncertainty, and thus to enhance the predictive performance of the related machine learning or deep learning model. We evaluate the performance of BayTTA on various public data, including three medical image datasets comprising skin cancer, breast cancer, and chest X-ray images and two well-known gene editing datasets, CRISPOR and GUIDE-seq. Our experimental results indicate that BayTTA can be effectively integrated into state-of-the-art deep learning models used in medical image analysis as well as into some popular pre-trained CNN models such as VGG-16, MobileNetV2, DenseNet201, ResNet152V2, and InceptionRes-NetV2, leading to the enhancement in their accuracy and robustness performance.
Authors: Thom Lake, Eunsol Choi, Greg Durrett
Abstract: The alignment process changes several properties of a large language model's (LLM's) output distribution. We analyze two aspects of post-alignment distributional shift of LLM responses. First, we re-examine previously reported reductions in response diversity post-alignment. Our analysis suggests that an apparent drop in the diversity of responses is largely explained by quality control and information aggregation. Alignment suppresses irrelevant and unhelpful content while shifting the output distribution toward longer responses that cover information spanning several responses from the base LLM, essentially presenting diverse information in a single response. Finding little evidence that alignment suppresses useful information, it is natural to ask the opposite question: do aligned models surface information that cannot be recovered from base models? Our second investigation shows this is not the case and the behavior of aligned models is recoverable from base models without fine-tuning. A combination of in-context examples and lower-resolution semantic hints about response content can elicit responses from base LLMs that are as similar to alignment-tuned LLM responses as alignment-tuned LLM responses are to each other. Taken together, these results indicate that current alignment techniques capture but do not extend the useful subset of assistant-like base LLM behavior, providing further evidence for the Superficial Alignment Hypothesis. They also show that in-context alignment can go surprisingly far as a strategy for imitating aligned LLMs without fine-tuning. Our code and data is available at https://github.com/thomlake/investigating-alignment.
Authors: Carles Balsells-Rodas, Yixin Wang, Pedro A. M. Mediano, Yingzhen Li
Abstract: Causal discovery in time series is a rapidly evolving field with a wide variety of applications in other areas such as climate science and neuroscience. Traditional approaches assume a stationary causal graph, which can be adapted to nonstationary time series with time-dependent effects or heterogeneous noise. In this work we address nonstationarity via regime-dependent causal structures. We first establish identifiability for high-order Markov Switching Models, which provide the foundations for identifiable regime-dependent causal discovery. Our empirical studies demonstrate the scalability of our proposed approach for high-order regime-dependent structure estimation, and we illustrate its applicability on brain activity data.
Authors: Siran Liu, Petros Dellaportas, Michalis K. Titsias
Abstract: Assume that we would like to estimate the expected value of a function $F$ with respect to a density $\pi$. We prove that if $\pi$ is close enough under KL divergence to another density $q$, an independent Metropolis sampler estimator that obtains samples from $\pi$ with proposal density $q$, enriched with a variance reduction computational strategy based on control variates, achieves smaller asymptotic variance than that of the crude Monte Carlo estimator. The control variates construction requires no extra computational effort but assumes that the expected value of $F$ under $q$ is analytically available. We illustrate this result by calculating the marginal likelihood in a linear regression model with prior-likelihood conflict and a non-conjugate prior. Furthermore, we propose an adaptive independent Metropolis algorithm that adapts the proposal density such that its KL divergence with the target is being reduced. We demonstrate its applicability in a Bayesian logistic and Gaussian process regression problems and we rigorously justify our asymptotic arguments under easily verifiable and essentially minimal conditions.
Authors: Purva Pruthi, David Jensen
Abstract: Many real-world systems can be represented as sets of interacting components. Examples of such systems include computational systems such as query processors, natural systems such as cells, and social systems such as families. Many approaches have been proposed in traditional (associational) machine learning to model such structured systems, including statistical relational models and graph neural networks. Despite this prior work, existing approaches to estimating causal effects typically treat such systems as single units, represent them with a fixed set of variables and assume a homogeneous data-generating process. We study a compositional approach for estimating individual treatment effects (ITE) in structured systems, where each unit is represented by the composition of multiple heterogeneous components. This approach uses a modular architecture to model potential outcomes at each component and aggregates component-level potential outcomes to obtain the unit-level potential outcomes. We discover novel benefits of the compositional approach in causal inference - systematic generalization to estimate counterfactual outcomes of unseen combinations of components and improved overlap guarantees between treatment and control groups compared to the classical methods for causal effect estimation. We also introduce a set of novel environments for empirically evaluating the compositional approach and demonstrate the effectiveness of our approach using both simulated and real-world data.
Authors: Myungsoo Yoo, Giri Gopalan, Matthew J. Hoffman, Sophie Coulson, Holly Kyeore Han, Christopher K. Wikle, Trevor Hillebrand
Abstract: Projecting sea-level change in various climate-change scenarios typically involves running forward simulations of the Earth's gravitational, rotational and deformational (GRD) response to ice mass change, which requires high computational cost and time. Here we build neural-network emulators of sea-level change at 27 coastal locations, due to the GRD effects associated with future Antarctic Ice Sheet mass change over the 21st century. The emulators are based on datasets produced using a numerical solver for the static sea-level equation and published ISMIP6-2100 ice-sheet model simulations referenced in the IPCC AR6 report. We show that the neural-network emulators have an accuracy that is competitive with baseline machine learning emulators. In order to quantify uncertainty, we derive well-calibrated prediction intervals for simulated sea-level change via a linear regression postprocessing technique that uses (nonlinear) machine learning model outputs, a technique that has previously been applied to numerical climate models. We also demonstrate substantial gains in computational efficiency: a feedforward neural-network emulator exhibits on the order of 100 times speedup in comparison to the numerical sea-level equation solver that is used for training.
Authors: Elinor Poole-Dayan, Deb Roy, Jad Kabbara
Abstract: While state-of-the-art Large Language Models (LLMs) have shown impressive performance on many tasks, there has been extensive research on undesirable model behavior such as hallucinations and bias. In this work, we investigate how the quality of LLM responses changes in terms of information accuracy, truthfulness, and refusals depending on three user traits: English proficiency, education level, and country of origin. We present extensive experimentation on three state-of-the-art LLMs and two different datasets targeting truthfulness and factuality. Our findings suggest that undesirable behaviors in state-of-the-art LLMs occur disproportionately more for users with lower English proficiency, of lower education status, and originating from outside the US, rendering these models unreliable sources of information towards their most vulnerable users.
Authors: Pai Peng, Quanxiang Jia, Ziqiang Zhou, Shuang Hong, Zichong Xiao
Abstract: Click-through-rate (CTR) prediction has an essential impact on improving user experience and revenue in e-commerce search. With the development of deep learning, graph-based methods are well exploited to utilize graph structure extracted from user behaviors and other information to help embedding learning. However, most of the previous graph-based methods mainly focus on recommendation scenarios, and therefore their graph structures highly depend on item's sequential information from user behaviors, ignoring query's sequential signal and query-item correlation. In this paper, we propose a new approach named Light-weight End-to-End Graph Interest Network (EGIN) to effectively mine users' search interests and tackle previous challenges. (i) EGIN utilizes query and item's correlation and sequential information from the search system to build a heterogeneous graph for better CTR prediction in e-commerce search. (ii) EGIN's graph embedding learning shares the same training input and is jointly trained with CTR prediction, making the end-to-end framework effortless to deploy in large-scale search systems. The proposed EGIN is composed of three parts: query-item heterogeneous graph, light-weight graph sampling, and multi-interest network. The query-item heterogeneous graph captures correlation and sequential information of query and item efficiently by the proposed light-weight graph sampling. The multi-interest network is well designed to utilize graph embedding to capture various similarity relationships between query and item to enhance the final CTR prediction. We conduct extensive experiments on both public and industrial datasets to demonstrate the effectiveness of the proposed EGIN. At the same time, the training cost of graph learning is relatively low compared with the main CTR prediction task, ensuring efficiency in practical applications.
Authors: Marcel F. Langer, Sergey N. Pozdnyakov, Michele Ceriotti
Abstract: Symmetry is one of the most central concepts in physics, and it is no surprise that it has also been widely adopted as an inductive bias for machine-learning models applied to the physical sciences. This is especially true for models targeting the properties of matter at the atomic scale. Both established and state-of-the-art approaches, with almost no exceptions, are built to be exactly equivariant to translations, permutations, and rotations of the atoms. Incorporating symmetries -- rotations in particular -- constrains the model design space and implies more complicated architectures that are often also computationally demanding. There are indications that non-symmetric models can easily learn symmetries from data, and that doing so can even be beneficial for the accuracy of the model. We put a model that obeys rotational invariance only approximately to the test, in realistic scenarios involving simulations of gas-phase, liquid, and solid water. We focus specifically on physical observables that are likely to be affected -- directly or indirectly -- by symmetry breaking, finding negligible consequences when the model is used in an interpolative, bulk, regime. Even for extrapolative gas-phase predictions, the model remains very stable, even though symmetry artifacts are noticeable. We also discuss strategies that can be used to systematically reduce the magnitude of symmetry breaking when it occurs, and assess their impact on the convergence of observables.
Authors: Tushar Prasanna Swaminathan, Christopher Silver, Thangarajah Akilan
Abstract: The proliferation of complex deep learning (DL) models has revolutionized various applications, including computer vision-based solutions, prompting their integration into real-time systems. However, the resource-intensive nature of these models poses challenges for deployment on low-computational power and low-memory devices, like embedded and edge devices. This work empirically investigates the optimization of such complex DL models to analyze their functionality on an embedded device, particularly on the NVIDIA Jetson Nano. It evaluates the effectiveness of the optimized models in terms of their inference speed for image classification and video action detection. The experimental results reveal that, on average, optimized models exhibit a 16.11% speed improvement over their non-optimized counterparts. This not only emphasizes the critical need to consider hardware constraints and environmental sustainability in model development and deployment but also underscores the pivotal role of model optimization in enabling the widespread deployment of AI-assisted technologies on resource-constrained computational systems. It also serves as proof that prioritizing hardware-specific model optimization leads to efficient and scalable solutions that substantially decrease energy consumption and carbon footprint.
Authors: Shane Arora, Marzena Karpinska, Hung-Ting Chen, Ipsita Bhattacharjee, Mohit Iyyer, Eunsol Choi
Abstract: Large language models (LLMs) are commonly used for long-form question answering, which requires them to generate paragraph-length answers to complex questions. While long-form QA has been well-studied in English via many different datasets and evaluation metrics, this research has not been extended to cover most other languages. To bridge this gap, we introduce CaLMQA, a collection of 2.6K complex questions spanning 23 languages, including under-resourced, rarely-studied languages such as Fijian and Kirundi. Our dataset includes both naturally-occurring questions collected from community web forums as well as questions written by native speakers, whom we hire for this purpose. Our process yields diverse, complex questions that reflect cultural topics (e.g. traditions, laws, news) and the language usage of native speakers. We conduct automatic evaluation across a suite of open- and closed-source models using our novel metric CaLMScore, which detects incorrect language and token repetitions in answers, and observe that the quality of LLM-generated answers degrades significantly for some low-resource languages. We perform human evaluation on a subset of models and see that model performance is significantly worse for culturally specific questions than for culturally agnostic questions. Our findings highlight the need for further research in LLM multilingual capabilities and non-English LFQA evaluation.
Authors: Jan Jakub\r{u}v, Mikol\'a\v{s} Janota, Josef Urban
Abstract: In this work, we prove over 3000 previously ATP-unproved Mizar/MPTP problems by using several ATP and AI methods, raising the number of ATP-solved Mizar problems from 75\% to above 80\%. First, we start to experiment with the cvc5 SMT solver which uses several instantiation-based heuristics that differ from the superposition-based systems, that were previously applied to Mizar,and add many new solutions. Then we use automated strategy invention to develop cvc5 strategies that largely improve cvc5's performance on the hard problems. In particular, the best invented strategy solves over 14\% more problems than the best previously available cvc5 strategy. We also show that different clausification methods have a high impact on such instantiation-based methods, again producing many new solutions. In total, the methods solve 3021 (21.3\%) of the 14163 previously unsolved hard Mizar problems. This is a new milestone over the Mizar large-theory benchmark and a large strengthening of the hammer methods for Mizar.
Authors: Jesse Zhang, Minho Heo, Zuxin Liu, Erdem Biyik, Joseph J Lim, Yao Liu, Rasool Fakoor
Abstract: Most reinforcement learning (RL) methods focus on learning optimal policies over low-level action spaces. While these methods can perform well in their training environments, they lack the flexibility to transfer to new tasks. Instead, RL agents that can act over useful, temporally extended skills rather than low-level actions can learn new tasks more easily. Prior work in skill-based RL either requires expert supervision to define useful skills, which is hard to scale, or learns a skill-space from offline data with heuristics that limit the adaptability of the skills, making them difficult to transfer during downstream RL. Our approach, EXTRACT, instead utilizes pre-trained vision language models to extract a discrete set of semantically meaningful skills from offline data, each of which is parameterized by continuous arguments, without human supervision. This skill parameterization allows robots to learn new tasks by only needing to learn when to select a specific skill and how to modify its arguments for the specific task. We demonstrate through experiments in sparse-reward, image-based, robot manipulation environments that EXTRACT can more quickly learn new tasks than prior works, with major gains in sample efficiency and performance over prior skill-based RL. Website at https://www.jessezhang.net/projects/extract/.
Authors: Li Meng, Anis Yazidi, Morten Goodwin, Paal Engelstad
Abstract: In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning through splitting Q-values into state values and action advantages. We require that an offline expert assesses the value of a state in a coarse manner using three discrete values. An expert network is designed in addition to the Q-network, which updates each time following the regular offline minibatch update whenever the expert example buffer is not empty. Using the board game Othello, we compare our algorithm with the baseline Q-learning algorithm, which is a combination of Double Q-learning and Dueling Q-learning. Our results show that Expert Q-learning is indeed useful and more resistant to the overestimation bias. The baseline Q-learning algorithm exhibits unstable and suboptimal behavior in non-deterministic settings, whereas Expert Q-learning demonstrates more robust performance with higher scores, illustrating that our algorithm is indeed suitable to integrate state values from expert examples into Q-learning.
Authors: Sungmin Cha, Jihwan Kwak, Dongsub Shim, Hyunwoo Kim, Moontae Lee, Honglak Lee, Taesup Moon
Abstract: Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average test accuracy across all classes learned so far -- however, we argue that solely focusing on maximizing the test accuracy may not necessarily lead to developing a CIL algorithm that also continually learns and updates the representations, which may be transferred to the downstream tasks. To that end, we experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning and propose new analysis methods. Our experiments show that most state-of-the-art algorithms prioritize high stability and do not significantly change the learned representation, and sometimes even learn a representation of lower quality than a naive baseline. However, we observe that these algorithms can still achieve high test accuracy because they enable a model to learn a classifier that closely resembles an estimated linear classifier trained for linear probing. Furthermore, the base model learned in the first task, which involves single-task learning, exhibits varying levels of representation quality across different algorithms, and this variance impacts the final performance of CIL algorithms. Therefore, we suggest that the representation-level evaluation should be considered as an additional recipe for more diverse evaluation for CIL algorithms.
Authors: Xinyu Chen, Zhanhong Cheng, HanQin Cai, Nicolas Saunier, Lijun Sun
Abstract: Spatiotemporal traffic data imputation is of great significance in intelligent transportation systems and data-driven decision-making processes. To perform efficient learning and accurate reconstruction from partially observed traffic data, we assert the importance of characterizing both global and local trends in time series. In the literature, substantial works have demonstrated the effectiveness of utilizing the low-rank property of traffic data by matrix/tensor completion models. In this study, we first introduce a Laplacian kernel to temporal regularization for characterizing local trends in traffic time series, which can be formulated as a circular convolution. Then, we develop a low-rank Laplacian convolutional representation (LCR) model by putting the circulant matrix nuclear norm and the Laplacian kernelized temporal regularization together, which is proved to meet a unified framework that has a fast Fourier transform (FFT) solution in log-linear time complexity. Through extensive experiments on several traffic datasets, we demonstrate the superiority of LCR over several baseline models for imputing traffic time series of various time series behaviors (e.g., data noises and strong/weak periodicity) and reconstructing sparse speed fields of vehicular traffic flow. The proposed LCR model is also an efficient solution to large-scale traffic data imputation over the existing imputation models.
Authors: Mimoun Mohamed (QARMA, I2M), Fran\c{c}ois Malgouyres (IMT), Valentin Emiya (QARMA), Caroline Chaux (IPAL)
Abstract: The {\it straight-through estimator} (STE) is commonly used to optimize quantized neural networks, yet its contexts of effective performance are still unclear despite empirical successes.To make a step forward in this comprehension, we apply STE to a well-understood problem: {\it sparse support recovery}. We introduce the {\it Support Exploration Algorithm} (SEA), a novel algorithm promoting sparsity, and we analyze its performance in support recovery (a.k.a. model selection) problems. SEA explores more supports than the state-of-the-art, leading to superior performance in experiments, especially when the columns of $A$ are strongly coherent.The theoretical analysis considers recovery guarantees when the linear measurements matrix $A$ satisfies the {\it Restricted Isometry Property} (RIP).The sufficient conditions of recovery are comparable but more stringent than those of the state-of-the-art in sparse support recovery. Their significance lies mainly in their applicability to an instance of the STE.
Authors: Saba Ahmadi, Avrim Blum, Kunhe Yang
Abstract: We study the problem of online binary classification where strategic agents can manipulate their observable features in predefined ways, modeled by a manipulation graph, in order to receive a positive classification. We show this setting differs in fundamental ways from non-strategic online classification. For instance, whereas in the non-strategic case, a mistake bound of $\ln|H|$ is achievable via the halving algorithm when the target function belongs to a known class $H$, we show that no deterministic algorithm can achieve a mistake bound $o(\Delta)$ in the strategic setting, where $\Delta$ is the maximum degree of the manipulation graph (even when $|H|=O(\Delta)$). We obtain an algorithm achieving mistake bound $O(\Delta\ln|H|)$. We also extend this to the agnostic setting and obtain an algorithm with a $\Delta$ multiplicative regret, and we show no deterministic algorithm can achieve $o(\Delta)$ multiplicative regret. Next, we study two randomized models based on whether the random choices are made before or after agents respond, and show they exhibit fundamental differences. In the first model, at each round the learner deterministically chooses a probability distribution over classifiers inducing expected values on each vertex (probabilities of being classified as positive), which the strategic agents respond to. We show that any learner in this model has to suffer linear regret. On the other hand, in the second model, while the adversary who selects the next agent must respond to the learner's probability distribution over classifiers, the agent then responds to the actual hypothesis classifier drawn from this distribution. Surprisingly, we show this model is more advantageous to the learner, and we design randomized algorithms that achieve sublinear regret bounds against both oblivious and adaptive adversaries.
Authors: Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri
Abstract: We introduce a novel method for training machine learning models in the presence of noisy labels, which are prevalent in domains such as medical diagnosis and autonomous driving and have the potential to degrade a model's generalization performance. Inspired by established literature that highlights how deep learning models are prone to overfitting to noisy samples in the later epochs of training, we propose a strategic approach. This strategy leverages the distance to class centroids in the latent space and incorporates a discounting mechanism, aiming to diminish the influence of samples that lie distant from all class centroids. By doing so, we effectively counteract the adverse effects of noisy labels. The foundational premise of our approach is the assumption that samples situated further from their respective class centroid in the initial stages of training are more likely to be associated with noise. Our methodology is grounded in robust theoretical principles and has been validated empirically through extensive experiments on several benchmark datasets. Our results show that our method consistently outperforms the existing state-of-the-art techniques, achieving significant improvements in classification accuracy in the presence of noisy labels. The code for our proposed loss function and supplementary materials is available at https://github.com/wanifarooq/NCOD
Authors: Cheng Wang, Jacek Golebiowski
Abstract: Model miscalibration has been frequently identified in modern deep neural networks. Recent work aims to improve model calibration directly through a differentiable calibration proxy. However, the calibration produced is often biased due to the binning mechanism. In this work, we propose to learn better-calibrated models via meta-regularization, which has two components: (1) gamma network (gamma-net), a meta learner that outputs sample-wise gamma values (continuous variable) for Focal loss for regularizing the backbone network; (2) smooth expected calibration error (SECE), a Gaussian-kernel based, unbiased, and differentiable surrogate to ECE that enables the smooth optimization of gamma-Net. We evaluate the effectiveness of the proposed approach in regularizing neural networks towards improved and unbiased calibration on three computer vision datasets. We empirically demonstrate that: (a) learning sample-wise gamma as continuous variables can effectively improve calibration; (b) SECE smoothly optimizes gamma-net towards unbiased and robust calibration with respect to the binning schemes; and (c) the combination of gamma-net and SECE achieves the best calibration performance across various calibration metrics while retaining very competitive predictive performance as compared to multiple recently proposed methods.
Authors: Tommaso Marzi, Arshjot Khehra, Andrea Cini, Cesare Alippi
Abstract: Graph-based representations and message-passing modular policies constitute prominent approaches to tackling composable control problems in Reinforcement Learning (RL). However, as shown by recent graph deep learning literature, such local message-passing operators can create information bottlenecks and hinder global coordination. The issue becomes more serious in tasks requiring high-level planning. In this work, we propose a novel methodology, named Feudal Graph Reinforcement Learning (FGRL), that addresses such challenges by relying on hierarchical RL and a pyramidal message-passing architecture. In particular, FGRL defines a hierarchy of policies where high-level commands are propagated from the top of the hierarchy down through a layered graph structure. The bottom layers mimic the morphology of the physical system, while the upper layers correspond to higher-order sub-modules. The resulting agents are then characterized by a committee of policies where actions at a certain level set goals for the level below, thus implementing a hierarchical decision-making structure that can naturally implement task decomposition. We evaluate the proposed framework on a graph clustering problem and MuJoCo locomotion tasks; simulation results show that FGRL compares favorably against relevant baselines. Furthermore, an in-depth analysis of the command propagation mechanism provides evidence that the introduced message-passing scheme favors learning hierarchical decision-making policies.
Authors: Max Staats, Matthias Thamm, Bernd Rosenow
Abstract: Large annotated datasets inevitably contain noisy labels, which poses a major challenge for training deep neural networks as they easily memorize the labels. Noise-robust loss functions have emerged as a notable strategy to counteract this issue, but it remains challenging to create a robust loss function which is not susceptible to underfitting. Through a quantitative approach, this paper explores the limited overlap between the network output at initialization and regions of non-vanishing gradients of bounded loss functions in the initial learning phase. Using these insights, we address underfitting of the MAE loss with a novel method denoted as logit bias, which adds a real number $\epsilon$ to the logit at the position of the correct class. This method enables bounded losses to learn, even on datasets like WebVision, consisting of over a million images from 1000 classes. Extensive numerical experiments show that the logit bias enables MAE to compete with state-of-the-art noise robust loss functions. In addition, we demonstrate that our method can be used to determine optimal parameters for other loss functions -- without having to train networks. Remarkably, our method determines the hyperparameters based on the number of classes, resulting in loss functions which require zero dataset or noise-dependent parameters.
Authors: Akansha Kalra, Daniel S. Brown
Abstract: Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for capturing human intent to alleviate the challenges of hand-crafting the reward values. Despite the increasing interest in RLHF, most works learn black box reward functions that while expressive are difficult to interpret and often require running the whole costly process of RL before we can even decipher if these frameworks are actually aligned with human preferences. We propose and evaluate a novel approach for learning expressive and interpretable reward functions from preferences using Differentiable Decision Trees (DDTs). Our experiments across several domains, including CartPole, Visual Gridworld environments and Atari games, provide evidence that the tree structure of our learned reward function is useful in determining the extent to which the reward function is aligned with human preferences. We also provide experimental evidence that not only shows that reward DDTs can often achieve competitive RL performance when compared with larger capacity deep neural network reward functions but also demonstrates the diagnostic utility of our framework in checking alignment of learned reward functions. We also observe that the choice between soft and hard (argmax) output of reward DDT reveals a tension between wanting highly shaped rewards to ensure good RL performance, while also wanting simpler, more interpretable rewards. Videos and code, are available at: https://sites.google.com/view/ddt-rlhf
Authors: Ziqin Chen, Yongqiang Wang
Abstract: Distributed online learning is gaining increased traction due to its unique ability to process large-scale datasets and streaming data. To address the growing public awareness and concern on privacy protection, plenty of algorithms have been proposed to enable differential privacy in distributed online optimization and learning. However, these algorithms often face the dilemma of trading learning accuracy for privacy. By exploiting the unique characteristics of online learning, this paper proposes an approach that tackles the dilemma and ensures both differential privacy and learning accuracy in distributed online learning. More specifically, while ensuring a diminishing expected instantaneous regret, the approach can simultaneously ensure a finite cumulative privacy budget, even in the infinite time horizon. To cater for the fully distributed setting, we adopt the local differential-privacy framework, which avoids the reliance on a trusted data curator, and, hence, provides stronger protection than the classic "centralized" (global) differential privacy. To the best of our knowledge, this is the first algorithm that successfully ensures both rigorous local differential privacy and learning accuracy. The effectiveness of the proposed algorithm is evaluated using machine learning tasks, including logistic regression on the the "mushrooms" datasets and CNN-based image classification on the "MNIST" and "CIFAR-10" datasets.
Authors: Charlie Hou, Kiran Koshy Thekumparampil, Michael Shavlovsky, Giulia Fanti, Yesh Dattatreya, Sujay Sanghavi
Abstract: On tabular data, a significant body of literature has shown that current deep learning (DL) models perform at best similarly to Gradient Boosted Decision Trees (GBDTs), while significantly underperforming them on outlier data. However, these works often study idealized problem settings which may fail to capture complexities of real-world scenarios. We identify a natural tabular data setting where DL models can outperform GBDTs: tabular Learning-to-Rank (LTR) under label scarcity. Tabular LTR applications, including search and recommendation, often have an abundance of unlabeled data, and scarce labeled data. We show that DL rankers can utilize unsupervised pretraining to exploit this unlabeled data. In extensive experiments over both public and proprietary datasets, we show that pretrained DL rankers consistently outperform GBDT rankers on ranking metrics -- sometimes by as much as 38% -- both overall and on outliers.
Authors: Haokun Chen, Denis Krompass, Jindong Gu, Volker Tresp
Abstract: Federated Learning (FL) is a distributed machine learning (ML) paradigm, in which multiple clients collaboratively train ML models without centralizing their local data. Similar to conventional ML pipelines, the client local optimization and server aggregation procedure in FL are sensitive to the hyperparameter (HP) selection. Despite extensive research on tuning HPs for centralized ML, these methods yield suboptimal results when employed in FL. This is mainly because their "training-after-tuning" framework is unsuitable for FL with limited client computation power. While some approaches have been proposed for HP-Tuning in FL, they are limited to the HPs for client local updates. In this work, we propose a novel HP-tuning algorithm, called Federated Population-based Hyperparameter Tuning (FedPop), to address this vital yet challenging problem. FedPop employs population-based evolutionary algorithms to optimize the HPs, which accommodates various HP types at both client and server sides. Compared with prior tuning methods, FedPop employs an online "tuning-while-training" framework, offering computational efficiency and enabling the exploration of a broader HP search space. Our empirical validation on the common FL benchmarks and complex real-world FL datasets demonstrates the effectiveness of the proposed method, which substantially outperforms the concurrent state-of-the-art HP tuning methods for FL.
Authors: Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, Tao Jiang
Abstract: Membership Inference Attack (MIA) identifies whether a record exists in a machine learning model's training set by querying the model. MIAs on the classic classification models have been well-studied, and recent works have started to explore how to transplant MIA onto generative models. Our investigation indicates that existing MIAs designed for generative models mainly depend on the overfitting in target models. However, overfitting can be avoided by employing various regularization techniques, whereas existing MIAs demonstrate poor performance in practice. Unlike overfitting, memorization is essential for deep learning models to attain optimal performance, making it a more prevalent phenomenon. Memorization in generative models leads to an increasing trend in the probability distribution of generating records around the member record. Therefore, we propose a Probabilistic Fluctuation Assessing Membership Inference Attack (PFAMI), a black-box MIA that infers memberships by detecting these trends via analyzing the overall probabilistic fluctuations around given records. We conduct extensive experiments across multiple generative models and datasets, which demonstrate PFAMI can improve the attack success rate (ASR) by about 27.9% when compared with the best baseline.
Authors: Mattie Fellows, Brandon Kaplowitz, Christian Schroeder de Witt, Shimon Whiteson
Abstract: Bayesian reinforcement learning (RL) offers a principled and elegant approach for sequential decision making under uncertainty. Most notably, Bayesian agents do not face an exploration/exploitation dilemma, a major pathology of frequentist methods. However theoretical understanding of model-free approaches is lacking. In this paper, we introduce a novel Bayesian model-free formulation and the first analysis showing that model-free approaches can yield Bayes-optimal policies. We show all existing model-free approaches make approximations that yield policies that can be arbitrarily Bayes-suboptimal. As a first step towards model-free Bayes optimality, we introduce the Bayesian exploration network (BEN) which uses normalising flows to model both the aleatoric uncertainty (via density estimation) and epistemic uncertainty (via variational inference) in the Bellman operator. In the limit of complete optimisation, BEN learns true Bayes-optimal policies, but like in variational expectation-maximisation, partial optimisation renders our approach tractable. Empirical results demonstrate that BEN can learn true Bayes-optimal policies in tasks where existing model-free approaches fail.
Authors: Sepehr Assadi, Chen Wang
Abstract: We give a near-optimal sample-pass trade-off for pure exploration in multi-armed bandits (MABs) via multi-pass streaming algorithms: any streaming algorithm with sublinear memory that uses the optimal sample complexity of $O(\frac{n}{\Delta^2})$ requires $\Omega(\frac{\log{(1/\Delta)}}{\log\log{(1/\Delta)}})$ passes. Here, $n$ is the number of arms and $\Delta$ is the reward gap between the best and the second-best arms. Our result matches the $O(\log(\frac{1}{\Delta}))$-pass algorithm of Jin et al. [ICML'21] (up to lower order terms) that only uses $O(1)$ memory and answers an open question posed by Assadi and Wang [STOC'20].
Authors: Julian Asilis, Siddartha Devic, Shaddin Dughmi, Vatsal Sharan, Shang-Hua Teng
Abstract: The quintessential learning algorithm of empirical risk minimization (ERM) is known to fail in various settings for which uniform convergence does not characterize learning. It is therefore unsurprising that the practice of machine learning is rife with considerably richer algorithmic techniques for successfully controlling model capacity. Nevertheless, no such technique or principle has broken away from the pack to characterize optimal learning in these more general settings. The purpose of this work is to characterize the role of regularization in perhaps the simplest setting for which ERM fails: multiclass learning with arbitrary label sets. Using one-inclusion graphs (OIGs), we exhibit optimal learning algorithms that dovetail with tried-and-true algorithmic principles: Occam's Razor as embodied by structural risk minimization (SRM), the principle of maximum entropy, and Bayesian reasoning. Most notably, we introduce an optimal learner which relaxes structural risk minimization on two dimensions: it allows the regularization function to be "local" to datapoints, and uses an unsupervised learning stage to learn this regularizer at the outset. We justify these relaxations by showing that they are necessary: removing either dimension fails to yield a near-optimal learner. We also extract from OIGs a combinatorial sequence we term the Hall complexity, which is the first to characterize a problem's transductive error rate exactly. Lastly, we introduce a generalization of OIGs and the transductive learning setting to the agnostic case, where we show that optimal orientations of Hamming graphs -- judged using nodes' outdegrees minus a system of node-dependent credits -- characterize optimal learners exactly. We demonstrate that an agnostic version of the Hall complexity again characterizes error rates exactly, and exhibit an optimal learner using maximum entropy programs.
Authors: Cat P. Le, Chris Cannella, Ali Hasan, Yuting Ng, Vahid Tarokh
Abstract: Transformers have demonstrated remarkable efficacy in forecasting time series data. However, their extensive dependence on self-attention mechanisms demands significant computational resources, thereby limiting their practical applicability across diverse tasks, especially in multimodal problems. In this work, we propose a new architecture, called perceiver-CDF, for modeling cumulative distribution functions (CDF) of time series data. Our approach combines the perceiver architecture with a copula-based attention mechanism tailored for multimodal time series prediction. By leveraging the perceiver, our model efficiently transforms high-dimensional and multimodal data into a compact latent space, thereby significantly reducing computational demands. Subsequently, we implement a copula-based attention mechanism to construct the joint distribution of missing data for prediction. Further, we propose an output variance testing mechanism to effectively mitigate error propagation during prediction. To enhance efficiency and reduce complexity, we introduce midpoint inference for the local attention mechanism. This enables the model to efficiently capture dependencies within nearby imputed samples without considering all previous samples. The experiments on the unimodal and multimodal benchmarks consistently demonstrate a 20% improvement over state-of-the-art methods while utilizing less than half of the computational resources.
Authors: Juncai He, Xinliang Liu, Jinchao Xu
Abstract: In this work, we propose a concise neural operator architecture for operator learning. Drawing an analogy with a conventional fully connected neural network, we define the neural operator as follows: the output of the $i$-th neuron in a nonlinear operator layer is defined by $\mathcal O_i(u) = \sigma\left( \sum_j \mathcal W_{ij} u + \mathcal B_{ij}\right)$. Here, $\mathcal W_{ij}$ denotes the bounded linear operator connecting $j$-th input neuron to $i$-th output neuron, and the bias $\mathcal B_{ij}$ takes the form of a function rather than a scalar. Given its new universal approximation property, the efficient parameterization of the bounded linear operators between two neurons (Banach spaces) plays a critical role. As a result, we introduce MgNO, utilizing multigrid structures to parameterize these linear operators between neurons. This approach offers both mathematical rigor and practical expressivity. Additionally, MgNO obviates the need for conventional lifting and projecting operators typically required in previous neural operators. Moreover, it seamlessly accommodates diverse boundary conditions. Our empirical observations reveal that MgNO exhibits superior ease of training compared to other CNN-based models, while also displaying a reduced susceptibility to overfitting when contrasted with spectral-type neural operators. We demonstrate the efficiency and accuracy of our method with consistently state-of-the-art performance on different types of partial differential equations (PDEs).
Authors: Jiaqi Li, Yuanhao Lai, Rui Wang, Changjian Shui, Sabyasachi Sahoo, Charles X. Ling, Shichun Yang, Boyu Wang, Christian Gagn\'e, Fan Zhou
Abstract: Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling the parameter transitions along the sequential tasks with the weight matrix transformation, we propose to apply the low-rank approximation on the task-adaptive parameters in each layer of the neural networks. Specifically, we theoretically demonstrate the quantitative relationship between the Hessian and the proposed low-rank approximation. The approximation ranks are then globally determined according to the marginal increment of the empirical loss estimated by the layer-specific gradient and low-rank approximation error. Furthermore, we control the model capacity by pruning less important parameters to diminish the parameter growth. We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method. Empirical results show that our method performs better on different benchmarks, especially in achieving task order robustness and handling the forgetting issue. The source code is at https://github.com/lijiaqi/HALRP.
Authors: Xingtong Yu, Zhenghao Liu, Yuan Fang, Zemin Liu, Sihong Chen, Xinming Zhang
Abstract: Graph neural networks have emerged as a powerful tool for graph representation learning, but their performance heavily relies on abundant task-specific supervision. To reduce labeling requirement, the "pre-train, prompt" paradigms have become increasingly common. However, existing study of prompting on graphs is limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. To further enhance GraphPrompt in these two stages, we extend it into GraphPrompt+ with two major enhancements. First, we generalize several popular graph pre-training tasks beyond simple link prediction to broaden the compatibility with our task template. Second, we propose a more generalized prompt design that incorporates a series of prompt vectors within every layer of the pre-trained graph encoder, in order to capitalize on the hierarchical information across different layers beyond just the readout layer. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt and GraphPrompt+.
Authors: Renukanandan Tumu, Matthew Cleaveland, Rahul Mangharam, George J. Pappas, Lars Lindemann
Abstract: Conformal prediction is a statistical tool for producing prediction regions for machine learning models that are valid with high probability. A key component of conformal prediction algorithms is a \emph{non-conformity score function} that quantifies how different a model's prediction is from the unknown ground truth value. Essentially, these functions determine the shape and the size of the conformal prediction regions. While prior work has gone into creating score functions that produce multi-model prediction regions, such regions are generally too complex for use in downstream planning and control problems. We propose a method that optimizes parameterized \emph{shape template functions} over calibration data, which results in non-conformity score functions that produce prediction regions with minimum volume. Our approach results in prediction regions that are \emph{multi-modal}, so they can properly capture residuals of distributions that have multiple modes, and \emph{practical}, so each region is convex and can be easily incorporated into downstream tasks, such as a motion planner using conformal prediction regions. Our method applies to general supervised learning tasks, while we illustrate its use in time-series prediction. We provide a toolbox and present illustrative case studies of F16 fighter jets and autonomous vehicles, showing an up to $68\%$ reduction in prediction region area compared to a circular baseline region.
Authors: Ikumi Okubo, Keisuke Sugiura, Hiroki Matsutani
Abstract: Transformer has been adopted to a wide range of tasks and shown to outperform CNNs and RNNs while it suffers from high training cost and computational complexity. To address these issues, a hybrid approach has become a recent research trend, which replaces a part of ResNet with an MHSA (Multi-Head Self-Attention). In this paper, we propose a lightweight hybrid model which uses Neural ODE (Ordinary Differential Equation) as a backbone instead of ResNet for 12.1$\times$ parameter reduction. For the STL10 dataset, the proposed model achieves 80.15% top-1 accuracy which is comparable to ResNet50. Then, the proposed model is deployed on a modest-sized FPGA device for edge computing. To further reduce FPGA resource utilization, the model is quantized following QAT (Quantization Aware Training) scheme instead of PTQ (Post Training Quantization) to suppress the accuracy loss. As a result, an extremely lightweight Transformer-based model can be implemented on resource-limited FPGAs. The weights of the feature extraction network are stored on-chip to minimize the memory transfer overhead, allowing faster inference. By eliminating the overhead of memory transfers, inference can be executed seamlessly, leading to accelerated inference. The proposed FPGA implementation achieves a 34.01$\times$ speedup for the backbone and MHSA parts, and it achieves an overall 9.85$\times$ speedup when taking into account software pre- and post-processing. It also achieves an overall 7.10$\times$ higher energy efficiency compared to the ARM Cortex-A53 CPU.
Authors: Ryan Boustany (TSE-R)
Abstract: This paper considers the reliability of automatic differentiation (AD) for neural networks involving the nonsmooth MaxPool operation. We investigate the behavior of AD across different precision levels (16, 32, 64 bits) and convolutional architectures (LeNet, VGG, and ResNet) on various datasets (MNIST, CIFAR10, SVHN, and ImageNet). Although AD can be incorrect, recent research has shown that it coincides with the derivative almost everywhere, even in the presence of nonsmooth operations (such as MaxPool and ReLU). On the other hand, in practice, AD operates with floating-point numbers (not real numbers), and there is, therefore, a need to explore subsets on which AD can be numerically incorrect. These subsets include a bifurcation zone (where AD is incorrect over reals) and a compensation zone (where AD is incorrect over floating-point numbers but correct over reals). Using SGD for the training process, we study the impact of different choices of the nonsmooth Jacobian for the MaxPool function on the precision of 16 and 32 bits. These findings suggest that nonsmooth MaxPool Jacobians with lower norms help maintain stable and efficient test accuracy, whereas those with higher norms can result in instability and decreased performance. We also observe that the influence of MaxPool's nonsmooth Jacobians on learning can be reduced by using batch normalization, Adam-like optimizers, or increasing the precision level.
Authors: Md Atik Ahamed, Qiang Cheng
Abstract: Despite the prevalence of images and texts in machine learning, tabular data remains widely used across various domains. Existing deep learning models, such as convolutional neural networks and transformers, perform well however demand extensive preprocessing and tuning limiting accessibility and scalability. This work introduces an innovative approach based on a structured state-space model (SSM), MambaTab, for tabular data. SSMs have strong capabilities for efficiently extracting effective representations from data with long-range dependencies. MambaTab leverages Mamba, an emerging SSM variant, for end-to-end supervised learning on tables. Compared to state-of-the-art baselines, MambaTab delivers superior performance while requiring significantly fewer parameters, as empirically validated on diverse benchmark datasets. MambaTab's efficiency, scalability, generalizability, and predictive gains signify it as a lightweight, "plug-and-play" solution for diverse tabular data with promise for enabling wider practical applications.
Authors: Leon Frischauf, Otmar Scherzer, Cong Shi
Abstract: Neural networks with quadratic decision functions have been introduced as alternatives to standard neural networks with affine linear ones. They are advantageous when the objects or classes to be identified are compact and of basic geometries like circles, ellipses etc. In this paper we investigate the use of such ansatz functions for classification. In particular we test and compare the algorithm on the MNIST dataset for classification of handwritten digits and for classification of subspecies. We also show, that the implementation can be based on the neural network structure in the software Tensorflow and Keras, respectively.
Authors: Adrian Pekar, Richard Jozsa
Abstract: Cybersecurity remains a critical challenge in the digital age, with network traffic flow anomaly detection being a key pivotal instrument in the fight against cyber threats. In this study, we address the prevalent issue of data integrity in network traffic datasets, which are instrumental in developing machine learning (ML) models for anomaly detection. We introduce two refined versions of the CICIDS-2017 dataset, NFS-2023-nTE and NFS-2023-TE, processed using NFStream to ensure methodologically sound flow expiration and labeling. Our research contrasts the performance of the Random Forest (RF) algorithm across the original CICIDS-2017, its refined counterparts WTMC-2021 and CRiSIS-2022, and our NFStream-generated datasets, in both binary and multi-class classification contexts. We observe that the RF model exhibits exceptional robustness, achieving consistent high-performance metrics irrespective of the underlying dataset quality, which prompts a critical discussion on the actual impact of data integrity on ML efficacy. Our study underscores the importance of continual refinement and methodological rigor in dataset generation for network security research. As the landscape of network threats evolves, so must the tools and techniques used to detect and analyze them.
Authors: Haozhi Gao, Qianqian Ren, Jinbao Li
Abstract: Contrastive representation learning is crucial in time series analysis as it alleviates the issue of data noise and incompleteness as well as sparsity of supervision signal. However, existing constrastive learning frameworks usually focus on intral-temporal features, which fails to fully exploit the intricate nature of time series data. To address this issue, we propose DE-TSMCL, an innovative distillation enhanced framework for long sequence time series forecasting. Specifically, we design a learnable data augmentation mechanism which adaptively learns whether to mask a timestamp to obtain optimized sub-sequences. Then, we propose a contrastive learning task with momentum update to explore inter-sample and intra-temporal correlations of time series to learn the underlying structure feature on the unlabeled time series. Meanwhile, we design a supervised task to learn more robust representations and facilitate the contrastive learning process. Finally, we jointly optimize the above two tasks. By developing model loss from multiple tasks, we can learn effective representations for downstream forecasting task. Extensive experiments, in comparison with state-of-the-arts, well demonstrate the effectiveness of DE-TSMCL, where the maximum improvement can reach to 27.3%.
Authors: Shashwat Singh, Shauli Ravfogel, Jonathan Herzig, Roee Aharoni, Ryan Cotterell, Ponnurangam Kumaraguru
Abstract: Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model's representations. Thus, one natural (and common) approach to prevent the model from exhibiting undesirable behavior is to steer the model's representations in a manner that reduces the probability of it generating undesirable text. This paper investigates the formal and empirical properties of steering functions, i.e., transformation of the neural language model's representations that alter its behavior. First, we derive two optimal, in the least-squares sense, affine steering functions under different constraints. Our theory provides justification for existing approaches and offers a novel, improved steering approach. Second, we offer a series of experiments that demonstrate the empirical effectiveness of the methods in mitigating bias and reducing toxic generation.
Authors: Sangkyu Lee, Sungdong Kim, Ashkan Yousefpour, Minjoon Seo, Kang Min Yoo, Youngjae Yu
Abstract: Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we present a novel alignment framework, SELF-JUDGE that (1) does on-policy learning and 2) is parameter efficient, as it does not require an additional RM for evaluating the samples for on-policy learning. To this end, we propose Judge-augmented Supervised Fine-Tuning (JSFT) to train a single model to act as both a policy and a judge. Specifically, we view the pairwise judgment task, choosing the better response from a response pair, as a special case of the instruction-following task. The resulting model can judge preferences of on-the-fly responses from current policy initialized from itself. Experimental results show the efficacy of SELF-JUDGE, outperforming baselines in preference benchmarks. We also show that the rejecting sampling by itself can improve performance further without an additional evaluator.
Authors: Johan Obando-Ceron, Aaron Courville, Pablo Samuel Castro
Abstract: Recent work has shown that deep reinforcement learning agents have difficulty in effectively using their network parameters. We leverage prior insights into the advantages of sparse training techniques and demonstrate that gradual magnitude pruning enables value-based agents to maximize parameter effectiveness. This results in networks that yield dramatic performance improvements over traditional networks, using only a small fraction of the full network parameters.
Authors: Zhiqiang Zhong, Kuangyu Zhou, Davide Mottin
Abstract: As Machine Learning (ML) models grow in size and demand higher-quality training data, the expenses associated with re-training and fine-tuning these models are escalating rapidly. Inspired by recent impressive achievements of Large Language Models (LLMs) in different fields, this paper delves into the question: can LLMs efficiently improve an ML's performance at a minimal cost? We show that, through our proposed training-free framework LlmCorr, an LLM can work as a post-hoc corrector to propose corrections for the predictions of an arbitrary ML model. In particular, we form a contextual knowledge database by incorporating the dataset's label information and the ML model's predictions on the validation dataset. Leveraging the in-context learning capability of LLMs, we ask the LLM to summarise the instances in which the ML model makes mistakes and the correlation between primary predictions and true labels. Following this, the LLM can transfer its acquired knowledge to suggest corrections for the ML model's predictions. Our experimental results on text analysis and the challenging molecular predictions show that \model improves the performance of a number of models by up to 39%.
Authors: Zhiqiang Zhong, Davide Mottin
Abstract: Predicting protein properties is paramount for biological and medical advancements. Current protein engineering mutates on a typical protein, called the wild-type, to construct a family of homologous proteins and study their properties. Yet, existing methods easily neglect subtle mutations, failing to capture the effect on the protein properties. To this end, we propose EvolMPNN, Evolution-aware Message Passing Neural Network, an efficient model to learn evolution-aware protein embeddings. EvolMPNN samples sets of anchor proteins, computes evolutionary information by means of residues and employs a differentiable evolution-aware aggregation scheme over these sampled anchors. This way, EvolMPNN can efficiently utilise a novel message-passing method to capture the mutation effect on proteins with respect to the anchor proteins. Afterwards, the aggregated evolution-aware embeddings are integrated with sequence embeddings to generate final comprehensive protein embeddings. Our model shows up to 6.4% better than state-of-the-art methods and attains 36X inference speedup in comparison with large pre-trained models. Code and models are available at https://github.com/zhiqiangzhongddu/EvolMPNN.
Authors: Rares-Darius Buhai, Jingqiu Ding, Stefan Tiegel
Abstract: We study computational-statistical gaps for improper learning in sparse linear regression. More specifically, given $n$ samples from a $k$-sparse linear model in dimension $d$, we ask what is the minimum sample complexity to efficiently (in time polynomial in $d$, $k$, and $n$) find a potentially dense estimate for the regression vector that achieves non-trivial prediction error on the $n$ samples. Information-theoretically this can be achieved using $\Theta(k \log (d/k))$ samples. Yet, despite its prominence in the literature, there is no polynomial-time algorithm known to achieve the same guarantees using less than $\Theta(d)$ samples without additional restrictions on the model. Similarly, existing hardness results are either restricted to the proper setting, in which the estimate must be sparse as well, or only apply to specific algorithms. We give evidence that efficient algorithms for this task require at least (roughly) $\Omega(k^2)$ samples. In particular, we show that an improper learning algorithm for sparse linear regression can be used to solve sparse PCA problems (with a negative spike) in their Wishart form, in regimes in which efficient algorithms are widely believed to require at least $\Omega(k^2)$ samples. We complement our reduction with low-degree and statistical query lower bounds for the sparse PCA problems from which we reduce. Our hardness results apply to the (correlated) random design setting in which the covariates are drawn i.i.d. from a mean-zero Gaussian distribution with unknown covariance.
Authors: Omer Nivron, Damon J. Wischik, Mathieu Vrac, Emily Shuckburgh, Alex T. Archibald
Abstract: Climate models are biased with respect to real-world observations. They usually need to be adjusted before being used in impact studies. The suite of statistical methods that enable such adjustments is called bias correction (BC). However, BC methods currently struggle to adjust temporal biases. Because they mostly disregard the dependence between consecutive time points. As a result, climate statistics with long-range temporal properties, such as heatwave duration and frequency, cannot be corrected accurately. This makes it more difficult to produce reliable impact studies on such climate statistics. This paper offers a novel BC methodology to correct temporal biases. This is made possible by rethinking the philosophy behind BC. We will introduce BC as a time-indexed regression task with stochastic outputs. Rethinking BC enables us to adapt state-of-the-art machine learning (ML) attention models and thereby learn different types of biases, including temporal asynchronicities. With a case study of heatwave duration statistics in Abuja, Nigeria, and Tokyo, Japan, we show more accurate results than current climate model outputs and alternative BC methods.
Authors: Stefan Balauca, Mark Niklas M\"uller, Yuhao Mao, Maximilian Baader, Marc Fischer, Martin Vechev
Abstract: Training neural networks with high certified accuracy against adversarial examples remains an open problem despite significant efforts. While certification methods can effectively leverage tight convex relaxations for bound computation, in training, these methods perform worse than looser relaxations. Prior work hypothesized that this is caused by the discontinuity and perturbation sensitivity of the loss surface induced by these tighter relaxations. In this work, we show theoretically that Gaussian Loss Smoothing can alleviate both issues. We confirm this empirically by proposing a certified training method combining PGPE, an algorithm computing gradients of a smoothed loss, with different convex relaxations. When using this training method, we observe that tighter bounds indeed lead to strictly better networks. While scaling PGPE training remains challenging due to high computational cost, we show that by using a not theoretically sound, yet much cheaper smoothing approximation, we obtain better certified accuracies than state-of-the-art methods when training on the same network architecture. Our results clearly demonstrate the promise of Gaussian Loss Smoothing for training certifiably robust neural networks.
Authors: Sayan Biswas, Davide Frey, Romaric Gaudel, Anne-Marie Kermarrec, Dimitri Ler\'ev\'erend, Rafael Pires, Rishi Sharma, Fran\c{c}ois Ta\"iani
Abstract: This paper introduces ZIP-DL, a novel privacy-aware decentralized learning (DL) algorithm that exploits correlated noise to provide strong privacy protection against a local adversary while yielding efficient convergence guarantees for a low communication cost. The progressive neutralization of the added noise during the distributed aggregation process results in ZIP-DL fostering a high model accuracy under privacy guarantees. ZIP-DL further uses a single communication round between each gradient descent, thus minimizing communication overhead. We provide theoretical guarantees for both convergence speed and privacy guarantees, thereby making ZIP-DL applicable to practical scenarios. Our extensive experimental study shows that ZIP-DL significantly outperforms the state-of-the-art in terms of vulnerability/accuracy trade-off. In particular, ZIP-DL (i) reduces the efficacy of linkability attacks by up to 52 percentage points compared to baseline DL, (ii) improves accuracy by up to 37 percent w.r.t. the state-of-the-art privacy-preserving mechanism operating under the same threat model as ours, when configured to provide the same protection against membership inference attacks, and (iii) reduces communication by up to 10.5x against the same competitor for the same level of protection.
Authors: Tausifa Jan Saleem, Ramanjit Ahuja, Surendra Prasad, Brejesh Lall
Abstract: Lottery ticket hypothesis for deep neural networks emphasizes the importance of initialization used to re-train the sparser networks obtained using the iterative magnitude pruning process. An explanation for why the specific initialization proposed by the lottery ticket hypothesis tends to work better in terms of generalization (and training) performance has been lacking. Moreover, the underlying principles in iterative magnitude pruning, like the pruning of smaller magnitude weights and the role of the iterative process, lack full understanding and explanation. In this work, we attempt to provide insights into these phenomena by empirically studying the volume/geometry and loss landscape characteristics of the solutions obtained at various stages of the iterative magnitude pruning process.
Authors: Van Khoa Nguyen, Yoann Boget, Frantzeska Lavda, Alexandros Kalousis
Abstract: Exploring the graph latent structures has not garnered much attention in the graph generative research field. Yet, exploiting the latent space is as crucial as working on the data space for discrete data such as graphs. However, previous methods either failed to preserve the permutation symmetry of graphs or lacked an effective approaches to model appropriately within the latent space. To mitigate those issues, we propose a simple, yet effective discrete latent graph diffusion generative model. Our model, namely GLAD, not only overcomes the drawbacks of existing latent approaches, but also alleviates inherent issues present in diffusion methods applied on the graph space. We validate our generative model on the molecular benchmark datasets, on which it demonstrates competitive performance compared with the state-of-the-art baselines.
Authors: Shwai He, Ang Li, Tianlong Chen
Abstract: Vision-Language Models (VLMs) integrate information from multiple modalities and have shown remarkable success across various tasks. However, deploying large-scale VLMs in resource-constrained scenarios is challenging. Pruning followed by finetuning offers a potential solution but remains underexplored for VLMs. This study addresses two key questions: how to distribute sparsity across different modality-specific models, and how to restore the performance of pruned sparse VLMs. Our preliminary studies identified two effective pruning settings: applying the same sparsity to both vision and language models, and pruning only the language models. While LoRA finetuning aims to restore sparse models, it faces challenges due to incompatibility with sparse models, disrupting the pruned sparsity. To overcome these issues, we propose SparseLoRA, which applies sparsity directly to LoRA weights. Our experimental results demonstrate significant improvements, including an 11.3\% boost under 2:4 sparsity and a 47.6\% enhancement under unstructured 70\% sparsity. Code is released at: \url{https://github.com/Shwai-He/VLM-Compression}.
Authors: Daniele Meli
Abstract: Online unsupervised detection of anomalies is crucial to guarantee the correct operation of cyber-physical systems and the safety of humans interacting with them. State-of-the-art approaches based on deep learning via neural networks achieve outstanding performance at anomaly recognition, evaluating the discrepancy between a normal model of the system (with no anomalies) and the real-time stream of sensor time series. However, large training data and time are typically required, and explainability is still a challenge to identify the root of the anomaly and implement predictive maintainance. In this paper, we use causal discovery to learn a normal causal graph of the system, and we evaluate the persistency of causal links during real-time acquisition of sensor data to promptly detect anomalies. On two benchmark anomaly detection datasets, we show that our method has higher training efficiency, outperforms the accuracy of state-of-the-art neural architectures and correctly identifies the sources of >10 different anomalies. The code is at https://github.com/Isla-lab/causal_anomaly_detection.
Authors: Mohamed Rashad, Zilong Zhao, Jeremie Decouchant, Lydia Y. Chen
Abstract: Autoencoders are popular neural networks that are able to compress high dimensional data to extract relevant latent information. TabNet is a state-of-the-art neural network model designed for tabular data that utilizes an autoencoder architecture for training. Vertical Federated Learning (VFL) is an emerging distributed machine learning paradigm that allows multiple parties to train a model collaboratively on vertically partitioned data while maintaining data privacy. The existing design of training autoencoders in VFL is to train a separate autoencoder in each participant and aggregate the latent representation later. This design could potentially break important correlations between feature data of participating parties, as each autoencoder is trained on locally available features while disregarding the features of others. In addition, traditional autoencoders are not specifically designed for tabular data, which is ubiquitous in VFL settings. Moreover, the impact of client failures during training on the model robustness is under-researched in the VFL scene. In this paper, we propose TabVFL, a distributed framework designed to improve latent representation learning using the joint features of participants. The framework (i) preserves privacy by mitigating potential data leakage with the addition of a fully-connected layer, (ii) conserves feature correlations by learning one latent representation vector, and (iii) provides enhanced robustness against client failures during training phase. Extensive experiments on five classification datasets show that TabVFL can outperform the prior work design, with 26.12% of improvement on f1-score.
Authors: Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu
Abstract: Large Language Models (LLMs) have highlighted the necessity of effective unlearning mechanisms to comply with data regulations and ethical AI practices. LLM unlearning aims at removing undesired data influences and associated model capabilities without compromising utility beyond the scope of unlearning. While interest in studying LLM unlearning is growing, the impact of the optimizer choice for LLM unlearning remains unexplored. In this work, we shed light on the significance of optimizer selection in LLM unlearning for the first time, establishing a clear connection between second-order optimization and influence unlearning (a classical approach using influence functions to update the model for data influence removal). This insight propels us to develop a second-order optimization-based LLM unlearning framework, termed Second-Order UnLearning (SOUL), which extends the static, one-shot model update using influence unlearning to a dynamic, iterative unlearning process. Our extensive experiments show that SOUL consistently outperforms conventional first-order methods across various unlearning tasks, models, and metrics, indicating that second-order optimization offers an effective and broadly applicable solution for LLM unlearning. Codes are available at https://github.com/OPTML-Group/SOUL.
Authors: Shashata Sawmya, Linghao Kong, Ilia Markov, Dan Alistarh, Nir Shavit
Abstract: We show how to improve the inference efficiency of an LLM by expanding it into a mixture of sparse experts, where each expert is a copy of the original weights, one-shot pruned for a specific cluster of input values. We call this approach $\textit{Sparse Expansion}$. We show that, for models such as Llama 2 70B, as we increase the number of sparse experts, Sparse Expansion outperforms all other one-shot sparsification approaches for the same inference FLOP budget per token, and that this gap grows as sparsity increases, leading to inference speedups. But why? To answer this, we provide strong evidence that the mixture of sparse experts is effectively $\textit{disentangling}$ the input-output relationship of every individual neuron across clusters of inputs. Specifically, sparse experts approximate the dense neuron output distribution with fewer weights by decomposing the distribution into a collection of simpler ones, each with a separate sparse dot product covering it. Interestingly, we show that the Wasserstein distance between a neuron's output distribution and a Gaussian distribution is an indicator of its entanglement level and contribution to the accuracy of the model. Every layer of an LLM has a fraction of highly entangled Wasserstein neurons, and model performance suffers more when these are sparsified as opposed to others. The code for Sparse Expansion is available at: https://github.com/Shavit-Lab/Sparse-Expansion .
Authors: Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Ling Liu
Abstract: Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we show that the jail-broken effect can be mitigated by separating states in the finetuning stage to optimize the alignment and user datasets. Unfortunately, our subsequent study shows that this simple Bi-State Optimization (BSO) solution experiences convergence instability when steps invested in its alignment state is too small, leading to downgraded alignment performance. By statistical analysis, we show that the \textit{excess drift} towards consensus could be a probable reason for the instability. To remedy this issue, we propose \textbf{L}azy(\textbf{i}) \textbf{s}afety \textbf{a}lignment (\textbf{Lisa}), which introduces a proximal term to constraint the drift of each state. Theoretically, the benefit of the proximal term is supported by the convergence analysis, wherein we show that a sufficient large proximal factor is necessary to guarantee Lisa's convergence. Empirically, our results on four downstream finetuning tasks show that Lisa with a proximal term can significantly increase alignment performance while maintaining the LLM's accuracy on the user tasks. Code is available at \url{https://github.com/git-disl/Lisa}.
Authors: Shwai He, Daize Dong, Liang Ding, Ang Li
Abstract: Scaling large language models has revolutionized the performance across diverse domains, yet the continual growth in model size poses significant challenges for real-world deployment. The Mixture of Experts (MoE) approach addresses this by dynamically selecting and activating only a subset of experts, significantly reducing computational costs while maintaining high performance. However, MoE introduces potential redundancy (e.g., parameters) and extra costs (e.g., communication overhead). Despite numerous compression techniques developed for mitigating the redundancy in dense models, the compression of MoE remains under-explored. We first bridge this gap with a cutting-edge unified framework that not only seamlessly integrates mainstream compression methods but also helps systematically understand MoE compression. This framework approaches compression from two perspectives: Expert Slimming which compresses individual experts and Expert Trimming which removes structured modules. Within this framework, we explore the optimization space unexplored by existing methods,and further introduce aggressive Expert Trimming techniques, i.e., Layer Drop and Block Drop, to eliminate redundancy at larger scales. Based on these insights,we present a comprehensive recipe to guide practitioners in compressing MoE effectively. Extensive experimental results demonstrate the effectiveness of the compression methods under our framework and the proposed recipe, achieving a 6.05x speedup and only 20.0GB memory usage while maintaining over 92% of performance on Mixtral-8x7B. Code is released at \url{https://github.com/DaizeDong/Unified-MoE-Compression}.
Authors: Sloan Nietert, Ziv Goldfeld, Soroosh Shafiee
Abstract: We consider learning in an adversarial environment, where an $\varepsilon$-fraction of samples from a distribution $P$ are arbitrarily modified (global corruptions) and the remaining perturbations have average magnitude bounded by $\rho$ (local corruptions). Given access to $n$ such corrupted samples, we seek a computationally efficient estimator $\hat{P}_n$ that minimizes the Wasserstein distance $\mathsf{W}_1(\hat{P}_n,P)$. In fact, we attack the fine-grained task of minimizing $\mathsf{W}_1(\Pi_\# \hat{P}_n, \Pi_\# P)$ for all orthogonal projections $\Pi \in \mathbb{R}^{d \times d}$, with performance scaling with $\mathrm{rank}(\Pi) = k$. This allows us to account simultaneously for mean estimation ($k=1$), distribution estimation ($k=d$), as well as the settings interpolating between these two extremes. We characterize the optimal population-limit risk for this task and then develop an efficient finite-sample algorithm with error bounded by $\sqrt{\varepsilon k} + \rho + \tilde{O}(d\sqrt{k}n^{-1/(k \lor 2)})$ when $P$ has bounded covariance. This guarantee holds uniformly in $k$ and is minimax optimal up to the sub-optimality of the plug-in estimator when $\rho = \varepsilon = 0$. Our efficient procedure relies on a novel trace norm approximation of an ideal yet intractable 2-Wasserstein projection estimator. We apply this algorithm to robust stochastic optimization, and, in the process, uncover a new method for overcoming the curse of dimensionality in Wasserstein distributionally robust optimization.
Authors: Jianhua Pei, Cheng Feng, Ping Wang, Hina Tabassum, Dongyuan Shi
Abstract: Semantic communication (SemCom) has emerged as a new paradigm for 6G communication, with deep learning (DL) models being one of the key drives to shift from the accuracy of bit/symbol to the semantics and pragmatics of data. Nevertheless, DL-based SemCom systems often face performance bottlenecks due to overfitting, poor generalization, and sensitivity to outliers. Furthermore, the varying-fading gains and noises with uncertain signal-to-noise ratios (SNRs) commonly present in wireless channels usually restrict the accuracy of semantic information transmission. Consequently, this paper constructs a latent diffusion model-enabled SemCom system, and proposes three improvements compared to existing works: i) To handle potential outliers in the source data, semantic errors obtained by projected gradient descent based on the vulnerabilities of DL models, are utilized to update the parameters and obtain an outlier-robust encoder. ii) A lightweight single-layer latent space transformation adapter completes one-shot learning at the transmitter and is placed before the decoder at the receiver, enabling adaptation for out-of-distribution data and enhancing human-perceptual quality. iii) An end-to-end consistency distillation (EECD) strategy is used to distill the diffusion models trained in latent space, enabling deterministic single or few-step real-time denoising in various noisy channels while maintaining high semantic quality. Extensive numerical experiments across different datasets demonstrate the superiority of the proposed SemCom system, consistently proving its robustness to outliers, the capability to transmit data with unknown distributions, and the ability to perform real-time channel denoising tasks while preserving high human perceptual quality, outperforming the existing denoising approaches in semantic metrics.
Authors: Ross Irwin, Alessandro Tibo, Jon Paul Janet, Simon Olsson
Abstract: Generative models for 3D drug design have gained prominence recently for their potential to design ligands directly within protein pockets. Current approaches, however, often suffer from very slow sampling times or generate molecules with poor chemical validity. Addressing these limitations, we propose Semla, a scalable E(3)-equivariant message passing architecture. We further introduce a molecular generation model, SemlaFlow, which is trained using flow matching along with scale optimal transport, a novel extension of equivariant optimal transport. Our model produces state-of-the-art results on benchmark datasets with just 100 sampling steps. Crucially, SemlaFlow samples high quality molecules with as few as 20 steps, corresponding to a two order-of-magnitude speed-up compared to state-of-the-art, without sacrificing performance. Furthermore, we highlight limitations of current evaluation methods for 3D generation and propose new benchmark metrics for unconditional molecular generators. Finally, using these new metrics, we compare our model's ability to generate high quality samples against current approaches and further demonstrate SemlaFlow's strong performance.
Authors: \'Alvaro Ciudad, Adri\'an Morales-Pastor, Laura Malo, Isaac Filella-Merc\`e, Victor Guallar, Alexis Molina
Abstract: In this study, we present ScoreFormer, a novel graph transformer model designed to accurately predict molecular docking scores, thereby optimizing high-throughput virtual screening (HTVS) in drug discovery. The architecture integrates Principal Neighborhood Aggregation (PNA) and Learnable Random Walk Positional Encodings (LRWPE), enhancing the model's ability to understand complex molecular structures and their relationship with their respective docking scores. This approach significantly surpasses traditional HTVS methods and recent Graph Neural Network (GNN) models in both recovery and efficiency due to a wider coverage of the chemical space and enhanced performance. Our results demonstrate that ScoreFormer achieves competitive performance in docking score prediction and offers a substantial 1.65-fold reduction in inference time compared to existing models. We evaluated ScoreFormer across multiple datasets under various conditions, confirming its robustness and reliability in identifying potential drug candidates rapidly.
Authors: Bhrij Patel, Vishnu Sashank Dorbala, Dinesh Manocha, Amrit Singh Bedi
Abstract: Embodied Question Answering (EQA) is an important problem, which involves an agent exploring the environment to answer user queries. In the existing literature, EQA has exclusively been studied in single-agent scenarios, where exploration can be time-consuming and costly. In this work, we consider EQA in a multi-agent framework involving multiple large language models (LLM) based agents independently answering queries about a household environment. To generate one answer for each query, we use the individual responses to train a Central Answer Model (CAM) that aggregates responses for a robust answer. Using CAM, we observe a $50\%$ higher EQA accuracy when compared against aggregation methods for ensemble LLM, such as voting schemes and debates. CAM does not require any form of agent communication, alleviating it from the associated costs. We ablate CAM with various nonlinear (neural network, random forest, decision tree, XGBoost) and linear (logistic regression classifier, SVM) algorithms. Finally, we present a feature importance analysis for CAM via permutation feature importance (PFI), quantifying CAMs reliance on each independent agent and query context.
Authors: Yanyong Huang, Li Yang, Dongjie Wang, Ke Li, Xiuwen Yi, Fengmao Lv, Tianrui Li
Abstract: Semi-supervised multi-label feature selection has recently been developed to solve the curse of dimensionality problem in high-dimensional multi-label data with certain samples missing labels. Although many efforts have been made, most existing methods use a predefined graph approach to capture the sample similarity or the label correlation. In this manner, the presence of noise and outliers within the original feature space can undermine the reliability of the resulting sample similarity graph. It also fails to precisely depict the label correlation due to the existence of unknown labels. Besides, these methods only consider the discriminative power of selected features, while neglecting their redundancy. In this paper, we propose an Adaptive Collaborative Correlation lEarning-based Semi-Supervised Multi-label Feature Selection (Access-MFS) method to address these issues. Specifically, a generalized regression model equipped with an extended uncorrelated constraint is introduced to select discriminative yet irrelevant features and maintain consistency between predicted and ground-truth labels in labeled data, simultaneously. Then, the instance correlation and label correlation are integrated into the proposed regression model to adaptively learn both the sample similarity graph and the label similarity graph, which mutually enhance feature selection performance. Extensive experimental results demonstrate the superiority of the proposed Access-MFS over other state-of-the-art methods.
Authors: Zahra Gharaee, Scott C. Lowe, ZeMing Gong, Pablo Millan Arias, Nicholas Pellegrino, Austin T. Wang, Joakim Bruslund Haurum, Iuliia Zarubiieva, Lila Kari, Dirk Steinke, Graham W. Taylor, Paul Fieguth, Angel X. Chang
Abstract: As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, this paper presents the BIOSCAN-5M Insect dataset to the machine learning community and establish several benchmark tasks. BIOSCAN-5M is a comprehensive dataset containing multi-modal information for over 5 million insect specimens, and it significantly expands existing image-based biological datasets by including taxonomic labels, raw nucleotide barcode sequences, assigned barcode index numbers, and geographical information. We propose three benchmark experiments to demonstrate the impact of the multi-modal data types on the classification and clustering accuracy. First, we pretrain a masked language model on the DNA barcode sequences of the BIOSCAN-5M dataset, and demonstrate the impact of using this large reference library on species- and genus-level classification performance. Second, we propose a zero-shot transfer learning task applied to images and DNA barcodes to cluster feature embeddings obtained from self-supervised learning, to investigate whether meaningful clusters can be derived from these representation embeddings. Third, we benchmark multi-modality by performing contrastive learning on DNA barcodes, image data, and taxonomic information. This yields a general shared embedding space enabling taxonomic classification using multiple types of information and modalities. The code repository of the BIOSCAN-5M Insect dataset is available at https://github.com/zahrag/BIOSCAN-5M.
Authors: Ajan Subramanian, Zhongqi Yang, Iman Azimi, Amir M. Rahmani
Abstract: Health monitoring systems have revolutionized modern healthcare by enabling the continuous capture of physiological and behavioral data, essential for preventive measures and early health intervention. While integrating this data with Large Language Models (LLMs) has shown promise in delivering interactive health advice, traditional methods like Retrieval-Augmented Generation (RAG) and fine-tuning often fail to fully utilize the complex, multi-dimensional, and temporally relevant data from wearable devices. These conventional approaches typically provide limited actionable and personalized health insights due to their inadequate capacity to dynamically integrate and interpret diverse health data streams. In response, this paper introduces a graph-augmented LLM framework designed to significantly enhance the personalization and clarity of health insights. Utilizing a hierarchical graph structure, the framework captures inter and intra-patient relationships, enriching LLM prompts with dynamic feature importance scores derived from a Random Forest Model. The effectiveness of this approach is demonstrated through a sleep analysis case study involving 20 college students during the COVID-19 lockdown, highlighting the potential of our model to generate actionable and personalized health insights efficiently. We leverage another LLM to evaluate the insights for relevance, comprehensiveness, actionability, and personalization, addressing the critical need for models that process and interpret complex health data effectively. Our findings show that augmenting prompts with our framework yields significant improvements in all 4 criteria. Through our framework, we can elicit well-crafted, more thoughtful responses tailored to a specific patient.
Authors: Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding, Chenwei Wu, Yinyu Ye, Zhi-Quan Luo, Ruoyu Sun
Abstract: We propose Adam-mini, an optimizer that achieves on-par or better performance than AdamW with 45% to 50% less memory footprint. Adam-mini reduces memory by cutting down the number of learning rates in Adam: Instead of assigning an individual learning rate for each parameter using $1/\sqrt{v}$, Adam-mini uses the average of $v$ within a pre-defined parameter block as the learning rate for that block. Such a design is inspired by two empirical findings. First, the Hessian of Transformers exhibits a near-block diagonal structure with different sizes of dense sub-blocks. Second, for each of these dense sub-blocks, there exists a single high-quality learning rate that can outperform Adam, provided that sufficient resources are available to search it out. Adam-mini provides one cost-effective way to find these good learning rates and manage to cut down $\geq$ 90% $v$ in Adam. Empirically, we verify that Adam-mini performs on par or better than AdamW on various language models sized from 125M to 7B for pre-training, supervised fine-tuning, and RLHF. The reduced memory footprint of Adam-mini also alleviates communication overheads among GPUs and CPUs, thereby increasing throughput. For instance, Adam-mini achieves 49.6% higher throughput than AdamW when pre-training Llama2-7B on 2x A800-80GB GPUs, which saves 33% wall-clock time for pre-training.
Authors: Mazen Ali, Anthony Nouy
Abstract: We study the approximation of multivariate functions with tensor networks (TNs). The main conclusion of this work is an answer to the following two questions: ``What are the approximation capabilities of TNs?" and "What is an appropriate model class of functions that can be approximated with TNs?" To answer the former, we show that TNs can (near to) optimally replicate $h$-uniform and $h$-adaptive approximation, for any smoothness order of the target function. Tensor networks thus exhibit universal expressivity w.r.t. isotropic, anisotropic and mixed smoothness spaces that is comparable with more general neural networks families such as deep rectified linear unit (ReLU) networks. Put differently, TNs have the capacity to (near to) optimally approximate many function classes -- without being adapted to the particular class in question. To answer the latter, as a candidate model class we consider approximation classes of TNs and show that these are (quasi-)Banach spaces, that many types of classical smoothness spaces are continuously embedded into said approximation classes and that TN approximation classes are themselves not embedded in any classical smoothness space.
Authors: Giulio Ortali, Alessandro Corbetta, Gianluigi Rozza, Federico Toschi
Abstract: The development of turbulence closure models, parametrizing the influence of small non-resolved scales on the dynamics of large resolved ones, is an outstanding theoretical challenge with vast applicative relevance. We present a closure, based on deep recurrent neural networks, that quantitatively reproduces, within statistical errors, Eulerian and Lagrangian structure functions and the intermittent statistics of the energy cascade, including those of subgrid fluxes. To achieve high-order statistical accuracy, and thus a stringent statistical test, we employ shell models of turbulence. Our results encourage the development of similar approaches for 3D Navier-Stokes turbulence.
Authors: Aida Kostikova, Benjamin Paassen, Dominik Beese, Ole P\"utz, Gregor Wiedemann, Steffen Eger
Abstract: Solidarity is a crucial concept to understand social relations in societies. In this paper, we explore fine-grained solidarity frames to study solidarity towards women and migrants in German parliamentary debates between 1867 and 2022. Using 2,864 manually annotated text snippets (with a cost exceeding 18k Euro), we evaluate large language models (LLMs) like Llama 3, GPT-3.5, and GPT-4. We find that GPT-4 outperforms other LLMs, approaching human annotation quality. Using GPT-4, we automatically annotate more than 18k further instances (with a cost of around 500 Euro) across 155 years and find that solidarity with migrants outweighs anti-solidarity but that frequencies and solidarity types shift over time. Most importantly, group-based notions of (anti-)solidarity fade in favor of compassionate solidarity, focusing on the vulnerability of migrant groups, and exchange-based anti-solidarity, focusing on the lack of (economic) contribution. Our study highlights the interplay of historical events, socio-economic needs, and political ideologies in shaping migration discourse and social cohesion. We also show that powerful LLMs, if carefully prompted, can be cost-effective alternatives to human annotation for hard social scientific tasks.
Authors: Heishiro Kanagawa, Alessandro Barp, Arthur Gretton, Lester Mackey
Abstract: Kernel Stein discrepancies (KSDs) measure the quality of a distributional approximation and can be computed even when the target density has an intractable normalizing constant. Notable applications include the diagnosis of approximate MCMC samplers and goodness-of-fit tests for unnormalized statistical models. The present work analyzes the convergence control properties of KSDs. We first show that standard KSDs used for weak convergence control fail to control moment convergence. To address this limitation, we next provide sufficient conditions under which alternative diffusion KSDs control both moment and weak convergence. As an immediate consequence we develop, for each $q > 0$, the first KSDs known to exactly characterize $q$-Wasserstein convergence.
Authors: Hongseok Namkoong, Yuanzhe Ma, Peter W. Glynn
Abstract: The performance of decision policies and prediction models often deteriorates when applied to environments different from the ones seen during training. To ensure reliable operation, we analyze the stability of a system under distribution shift, which is defined as the smallest change in the underlying environment that causes the system's performance to deteriorate beyond a permissible threshold. In contrast to standard tail risk measures and distributionally robust losses that require the specification of a plausible magnitude of distribution shift, the stability measure is defined in terms of a more intuitive quantity: the level of acceptable performance degradation. We develop a minimax optimal estimator of stability and analyze its convergence rate, which exhibits a fundamental phase shift behavior. Our characterization of the minimax convergence rate shows that evaluating stability against large performance degradation incurs a statistical cost. Empirically, we demonstrate the practical utility of our stability framework by using it to compare system designs on problems where robustness to distribution shift is critical.
Authors: Zihan Zhang, Philip Rodgers, Peter Kilpatrick, Ivor Spence, Blesson Varghese
Abstract: Collaborative machine learning (CML) techniques, such as federated learning, have been proposed to train deep learning models across multiple mobile devices and a server. CML techniques are privacy-preserving as a local model that is trained on each device instead of the raw data from the device is shared with the server. However, CML training is inefficient due to low resource utilization. We identify idling resources on the server and devices due to sequential computation and communication as the principal cause of low resource utilization. A novel framework PiPar that leverages pipeline parallelism for CML techniques is developed to substantially improve resource utilization. A new training pipeline is designed to parallelize the computations on different hardware resources and communication on different bandwidth resources, thereby accelerating the training process in CML. A low overhead automated parameter selection method is proposed to optimize the pipeline, maximizing the utilization of available resources. The experimental results confirm the validity of the underlying approach of PiPar and highlight that when compared to federated learning: (i) the idle time of the server can be reduced by up to 64.1x, and (ii) the overall training time can be accelerated by up to 34.6x under varying network conditions for a collection of six small and large popular deep neural networks and four datasets without sacrificing accuracy. It is also experimentally demonstrated that PiPar achieves performance benefits when incorporating differential privacy methods and operating in environments with heterogeneous devices and changing bandwidths.
Authors: Rafael S. Oyamada, Gabriel M. Tavares, Sylvio Barbon Junior, Paolo Ceravolo
Abstract: Process simulation is gaining attention for its ability to assess potential performance improvements and risks associated with business process changes. The existing literature presents various techniques, generally grounded in process models discovered from event log data or built upon deep learning algorithms. These techniques have specific strengths and limitations. Traditional data-driven approaches offer increased interpretability, while deep learning-based excel at generalizing changes across large event logs. However, the practical application of deep learning faces challenges related to managing stochasticity and integrating information for what-if analysis. This paper introduces a novel recurrent neural architecture tailored to discover COnditioned process Simulation MOdels (CoSMo) based on user-based constraints or any other nature of a-priori knowledge. This architecture facilitates the simulation of event logs that adhere to specific constraints by incorporating declarative-based rules into the learning phase as an attempt to fill the gap of incorporating information into deep learning models to perform what-if analysis. Experimental validation illustrates CoSMo's efficacy in simulating event logs while adhering to predefined declarative conditions, emphasizing both control-flow and data-flow perspectives.
Authors: Xinlei Niu, Christian Walder, Jing Zhang, Charles Patrick Martin
Abstract: We propose the stochastic optimal path which solves the classical optimal path problem by a probability-softening solution. This unified approach transforms a wide range of DP problems into directed acyclic graphs in which all paths follow a Gibbs distribution. We show the equivalence of the Gibbs distribution to a message-passing algorithm by the properties of the Gumbel distribution and give all the ingredients required for variational Bayesian inference of a latent path, namely Bayesian dynamic programming (BDP). We demonstrate the usage of BDP in the latent space of variational autoencoders (VAEs) and propose the BDP-VAE which captures structured sparse optimal paths as latent variables. This enables end-to-end training for generative tasks in which models rely on unobserved structural information. At last, we validate the behavior of our approach and showcase its applicability in two real-world applications: text-to-speech and singing voice synthesis. Our implementation code is available at \url{https://github.com/XinleiNIU/LatentOptimalPathsBayesianDP}.
URLs: https://github.com/XinleiNIU/LatentOptimalPathsBayesianDP
Authors: Mehdi Rezaie, Ashley J. Ross, Hee-Jong Seo, Hui Kong, Anna Porredon, Lado Samushia, Edmond Chaussidon, Alex Krolewski, Arnaud de Mattia, Florian Beutler, Jessica Nicole Aguilar, Steven Ahlen, Shadab Alam, Santiago Avila, Benedict Bahr-Kalus, Jose Bermejo-Climent, David Brooks, Todd Claybaugh, Shaun Cole, Kyle Dawson, Axel de la Macorra, Peter Doel, Andreu Font-Ribera, Jaime E. Forero-Romero, Satya Gontcho A Gontcho, Julien Guy, Klaus Honscheid, Dragan Huterer, Theodore Kisner, Martin Landriau, Michael Levi, Marc Manera, Aaron Meisner, Ramon Miquel, Eva-Maria Mueller, Adam Myers, Jeffrey A. Newman, Jundan Nie, Nathalie Palanque-Delabrouille, Will Percival, Claire Poppett, Graziano Rossi, Eusebio Sanchez, Michael Schubnell, Gregory Tarl\'e, Benjamin Alan Weaver, Christophe Y\`eche, Zhimin Zhou, Hu Zou
Abstract: We use angular clustering of luminous red galaxies from the Dark Energy Spectroscopic Instrument (DESI) imaging surveys to constrain the local primordial non-Gaussianity parameter $\fnl$. Our sample comprises over 12 million targets, covering 14,000 square degrees of the sky, with redshifts in the range $0.2< z < 1.35$. We identify Galactic extinction, survey depth, and astronomical seeing as the primary sources of systematic error, and employ linear regression and artificial neural networks to alleviate non-cosmological excess clustering on large scales. Our methods are tested against simulations with and without $\fnl$ and systematics, showing superior performance of the neural network treatment. The neural network with a set of nine imaging property maps passes our systematic null test criteria, and is chosen as the fiducial treatment. Assuming the universality relation, we find $\fnl = 34^{+24(+50)}_{-44(-73)}$ at 68\%(95\%) confidence. We apply a series of robustness tests (e.g., cuts on imaging, declination, or scales used) that show consistency in the obtained constraints. We study how the regression method biases the measured angular power-spectrum and degrades the $\fnl$ constraining power. The use of the nine maps more than doubles the uncertainty compared to using only the three primary maps in the regression. Our results thus motivate the development of more efficient methods that avoid over-correction, protect large-scale clustering information, and preserve constraining power. Additionally, our results encourage further studies of $\fnl$ with DESI spectroscopic samples, where the inclusion of 3D clustering modes should help separate imaging systematics and lessen the degradation in the $\fnl$ uncertainty.
Authors: Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, Tat-Seng Chua
Abstract: While recently Multimodal Large Language Models (MM-LLMs) have made exciting strides, they mostly fall prey to the limitation of only input-side multimodal understanding, without the ability to produce content in multiple modalities. As we humans always perceive the world and communicate with people through various modalities, developing any-to-any MM-LLMs capable of accepting and delivering content in any modality becomes essential to human-level AI. To fill the gap, we present an end-to-end general-purpose any-to-any MM-LLM system, NExT-GPT. We connect an LLM with multimodal adaptors and different diffusion decoders, enabling NExT-GPT to perceive inputs and generate outputs in arbitrary combinations of text, images, videos, and audio. By leveraging the existing well-trained highly-performing encoders and decoders, NExT-GPT is tuned with only a small amount of parameter (1%) of certain projection layers, which not only benefits low-cost training and also facilitates convenient expansion to more potential modalities. Moreover, we introduce a modality-switching instruction tuning (MosIT) and manually curate a high-quality dataset for MosIT, based on which NExT-GPT is empowered with complex cross-modal semantic understanding and content generation. Overall, our research showcases the promising possibility of building an AI agent capable of modeling universal modalities, paving the way for more human-like AI research in the community. Project page: https://next-gpt.github.io/
Authors: Hugo Cui, Florent Krzakala, Eric Vanden-Eijnden, Lenka Zdeborov\'a
Abstract: We study the problem of training a flow-based generative model, parametrized by a two-layer autoencoder, to sample from a high-dimensional Gaussian mixture. We provide a sharp end-to-end analysis of the problem. First, we provide a tight closed-form characterization of the learnt velocity field, when parametrized by a shallow denoising auto-encoder trained on a finite number $n$ of samples from the target distribution. Building on this analysis, we provide a sharp description of the corresponding generative flow, which pushes the base Gaussian density forward to an approximation of the target density. In particular, we provide closed-form formulae for the distance between the mean of the generated mixture and the mean of the target mixture, which we show decays as $\Theta_n(\frac{1}{n})$. Finally, this rate is shown to be in fact Bayes-optimal.
Authors: Yihan Wu, Zhengmian Hu, Junfeng Guo, Hongyang Zhang, Heng Huang
Abstract: Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge in the domain lies in preserving the distribution of original generated content after watermarking. Our research extends and improves upon existing watermarking framework, placing emphasis on the importance of a \textbf{Di}stribution-\textbf{P}reserving (DiP) watermark. Contrary to the current strategies, our proposed DiPmark simultaneously preserves the original token distribution during watermarking (distribution-preserving), is detectable without access to the language model API and prompts (accessible), and is provably robust to moderate changes of tokens (resilient). DiPmark operates by selecting a random set of tokens prior to the generation of a word, then modifying the token distribution through a distribution-preserving reweight function to enhance the probability of these selected tokens during the sampling process. Extensive empirical evaluation on various language models and tasks demonstrates our approach's distribution-preserving property, accessibility, and resilience, making it a effective solution for watermarking tasks that demand impeccable quality preservation.
Authors: David Chuan-En Lin, Nikolas Martelaro
Abstract: Recent advancements in AI foundation models have made it possible for them to be utilized off-the-shelf for creative tasks, including ideating design concepts or generating visual prototypes. However, integrating these models into the creative process can be challenging as they often exist as standalone applications tailored to specific tasks. To address this challenge, we introduce Jigsaw, a prototype system that employs puzzle pieces as metaphors to represent foundation models. Jigsaw allows designers to combine different foundation model capabilities across various modalities by assembling compatible puzzle pieces. To inform the design of Jigsaw, we interviewed ten designers and distilled design goals. In a user study, we showed that Jigsaw enhanced designers' understanding of available foundation model capabilities, provided guidance on combining capabilities across different modalities and tasks, and served as a canvas to support design exploration, prototyping, and documentation.
Authors: Logan Ward, Ben Blaiszik, Cheng-Wei Lee, Troy Martin, Ian Foster, Andr\'e Schleife
Abstract: Knowing the rate at which particle radiation releases energy in a material, the stopping power, is key to designing nuclear reactors, medical treatments, semiconductor and quantum materials, and many other technologies. While the nuclear contribution to stopping power, i.e., elastic scattering between atoms, is well understood in the literature, the route for gathering data on the electronic contribution has for decades remained costly and reliant on many simplifying assumptions, including that materials are isotropic. We establish a method that combines time-dependent density functional theory (TDDFT) and machine learning to reduce the time to assess new materials to mere hours on a supercomputer and provides valuable data on how atomic details influence electronic stopping. Our approach uses TDDFT to compute the electronic stopping contributions to stopping power from first principles in several directions and then machine learning to interpolate to other directions at a cost of 10 million times fewer core-hours. We demonstrate the combined approach in a study of proton irradiation in aluminum and employ it to predict how the depth of maximum energy deposition, the "Bragg Peak," varies depending on incident angle -- a quantity otherwise inaccessible to modelers. The lack of any experimental information requirement makes our method applicable to most materials, and its speed makes it a prime candidate for enabling quantum-to-continuum models of radiation damage. The prospect of reusing valuable TDDFT data for training the model make our approach appealing for applications in the age of materials data science.
Authors: Ravil Mussabayev, Rustam Mussabayev
Abstract: This paper introduces a novel formulation of the clustering problem, namely the Minimum Sum-of-Squares Clustering of Infinitely Tall Data (MSSC-ITD), and presents HPClust, an innovative set of hybrid parallel approaches for its effective solution. By utilizing modern high-performance computing techniques, HPClust enhances key clustering metrics: effectiveness, computational efficiency, and scalability. In contrast to vanilla data parallelism, which only accelerates processing time through the MapReduce framework, our approach unlocks superior performance by leveraging the multi-strategy competitive-cooperative parallelism and intricate properties of the objective function landscape. Unlike other available algorithms that struggle to scale, our algorithm is inherently parallel in nature, improving solution quality through increased scalability and parallelism, and outperforming even advanced algorithms designed for small and medium-sized datasets. Our evaluation of HPClust, featuring four parallel strategies, demonstrates its superiority over traditional and cutting-edge methods by offering better performance in the key metrics. These results also show that parallel processing not only enhances the clustering efficiency, but the accuracy as well. Additionally, we explore the balance between computational efficiency and clustering quality, providing insights into optimal parallel strategies based on dataset specifics and resource availability. This research advances our understanding of parallelism in clustering algorithms, demonstrating that a judicious hybridization of advanced parallel approaches yields optimal results for MSSC-ITD. Experiments on synthetic data further confirm HPClust's exceptional scalability and robustness to noise.
Authors: Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, Tao Jiang
Abstract: Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Prior attempts have quantified the privacy risks of language models (LMs) via MIAs, but there is still no consensus on whether existing MIA algorithms can cause remarkable privacy leakage on practical Large Language Models (LLMs). Existing MIAs designed for LMs can be classified into two categories: reference-free and reference-based attacks. They are both based on the hypothesis that training records consistently strike a higher probability of being sampled. Nevertheless, this hypothesis heavily relies on the overfitting of target models, which will be mitigated by multiple regularization methods and the generalization of LLMs. The reference-based attack seems to achieve promising effectiveness in LLMs, which measures a more reliable membership signal by comparing the probability discrepancy between the target model and the reference model. However, the performance of reference-based attack is highly dependent on a reference dataset that closely resembles the training dataset, which is usually inaccessible in the practical scenario. Overall, existing MIAs are unable to effectively unveil privacy leakage over practical fine-tuned LLMs that are overfitting-free and private. We propose a Membership Inference Attack based on Self-calibrated Probabilistic Variation (SPV-MIA). Specifically, since memorization in LLMs is inevitable during the training process and occurs before overfitting, we introduce a more reliable membership signal, probabilistic variation, which is based on memorization rather than overfitting. Furthermore, we introduce a self-prompt approach, which constructs the dataset to fine-tune the reference model by prompting the target LLM itself. In this manner, the adversary can collect a dataset with a similar distribution from public APIs.
Authors: Xuanchi Ren, Jiahui Huang, Xiaohui Zeng, Ken Museth, Sanja Fidler, Francis Williams
Abstract: We present XCube (abbreviated as $\mathcal{X}^3$), a novel generative model for high-resolution sparse 3D voxel grids with arbitrary attributes. Our model can generate millions of voxels with a finest effective resolution of up to $1024^3$ in a feed-forward fashion without time-consuming test-time optimization. To achieve this, we employ a hierarchical voxel latent diffusion model which generates progressively higher resolution grids in a coarse-to-fine manner using a custom framework built on the highly efficient VDB data structure. Apart from generating high-resolution objects, we demonstrate the effectiveness of XCube on large outdoor scenes at scales of 100m$\times$100m with a voxel size as small as 10cm. We observe clear qualitative and quantitative improvements over past approaches. In addition to unconditional generation, we show that our model can be used to solve a variety of tasks such as user-guided editing, scene completion from a single scan, and text-to-3D. The source code and more results can be found at https://research.nvidia.com/labs/toronto-ai/xcube/.
Authors: Kaustubh Shivdikar
Abstract: The advent of Graph Neural Networks (GNNs) has revolutionized the field of machine learning, offering a novel paradigm for learning on graph-structured data. Unlike traditional neural networks, GNNs are capable of capturing complex relationships and dependencies inherent in graph data, making them particularly suited for a wide range of applications including social network analysis, molecular chemistry, and network security. GNNs, with their unique structure and operation, present new computational challenges compared to conventional neural networks. This requires comprehensive benchmarking and a thorough characterization of GNNs to obtain insight into their computational requirements and to identify potential performance bottlenecks. In this thesis, we aim to develop a better understanding of how GNNs interact with the underlying hardware and will leverage this knowledge as we design specialized accelerators and develop new optimizations, leading to more efficient and faster GNN computations. A pivotal component within GNNs is the Sparse General Matrix-Matrix Multiplication (SpGEMM) kernel, known for its computational intensity and irregular memory access patterns. In this thesis, we address the challenges posed by SpGEMM by implementing a highly optimized hashing-based SpGEMM kernel tailored for a custom accelerator. Synthesizing these insights and optimizations, we design state-of-the-art hardware accelerators capable of efficiently handling various GNN workloads. Our accelerator architectures are built on our characterization of GNN computational demands, providing clear motivation for our approaches. This exploration into novel models underlines our comprehensive approach, as we strive to enable accelerators that are not just performant, but also versatile, able to adapt to the evolving landscape of graph computing.
Authors: Guy Katz, Natan Levy, Idan Refaeli, Raz Yerushalmi
Abstract: Software development in the aerospace domain requires adhering to strict, high-quality standards. While there exist regulatory guidelines for commercial software in this domain (e.g., ARP-4754 and DO-178), these do not apply to software with deep neural network (DNN) components. Consequently, it is unclear how to allow aerospace systems to benefit from the deep learning revolution. Our work here seeks to address this challenge with a novel, output-centric approach for DNN certification. Our method employs statistical verification techniques, and has the key advantage of being able to flag specific inputs for which the DNN's output may be unreliable - so that they may be later inspected by a human expert. To achieve this, our method conducts a statistical analysis of the DNN's predictions for other, nearby inputs, in order to detect inconsistencies. This is in contrast to existing techniques, which typically attempt to certify the entire DNN, as opposed to individual outputs. Our method uses the DNN as a black-box, and makes no assumptions about its topology. We hope that this work constitutes another step towards integrating DNNs in safety-critical applications - especially in the aerospace domain, where high standards of quality and reliability are crucial.
Authors: Binh M. Le, Jiwon Kim, Shahroz Tariq, Kristen Moore, Alsharif Abuadbba, Simon S. Woo
Abstract: Deepfakes have rapidly emerged as a profound and serious threat to society, primarily due to their ease of creation and dissemination. This situation has triggered an accelerated development of deepfake detection technologies. However, many existing detectors rely heavily on lab-generated datasets for validation, which may not effectively prepare them for novel, emerging, and real-world deepfake techniques. In this paper, we conduct an extensive and comprehensive review and analysis of the latest state-of-the-art deepfake detectors, evaluating them against several critical criteria. These criteria facilitate the categorization of these detectors into 4 high-level groups and 13 fine-grained sub-groups, all aligned with a unified standard conceptual framework. This classification and framework offer deep and practical insights into the factors that affect detector efficacy. We assess the generalizability of 16 leading detectors across various standard attack scenarios, including black-box, white-box, and gray-box settings. Our systematized analysis and experimentation lay the groundwork for a deeper understanding of deepfake detectors and their generalizability, paving the way for future research focused on creating detectors adept at countering various attack scenarios. Additionally, this work offers insights for developing more proactive defenses against deepfakes.
Authors: Yanran Guan, Oliver van Kaick
Abstract: Methods that use neural networks for synthesizing 3D shapes in the form of a part-based representation have been introduced over the last few years. These methods represent shapes as a graph or hierarchy of parts and enable a variety of applications such as shape sampling and reconstruction. However, current methods do not allow easily regenerating individual shape parts according to user preferences. In this paper, we investigate techniques that allow the user to generate multiple, diverse suggestions for individual parts. Specifically, we experiment with multimodal deep generative models that allow sampling diverse suggestions for shape parts and focus on models which have not been considered in previous work on shape synthesis. To provide a comparative study of these techniques, we introduce a method for synthesizing 3D shapes in a part-based representation and evaluate all the part suggestion techniques within this synthesis method. In our method, which is inspired by previous work, shapes are represented as a set of parts in the form of implicit functions which are then positioned in space to form the final shape. Synthesis in this representation is enabled by a neural network architecture based on an implicit decoder and a spatial transformer. We compare the various multimodal generative models by evaluating their performance in generating part suggestions. Our contribution is to show with qualitative and quantitative evaluations which of the new techniques for multimodal part generation perform the best and that a synthesis method based on the top-performing techniques allows the user to more finely control the parts that are generated in the 3D shapes while maintaining high shape fidelity when reconstructing shapes.
Authors: Nikita Pospelov, Andrei Chertkov, Maxim Beketov, Ivan Oseledets, Konstantin Anokhin
Abstract: Elements of neural networks, both biological and artificial, can be described by their selectivity for specific cognitive features. Understanding these features is important for understanding the inner workings of neural networks. For a living system, such as a neuron, whose response to a stimulus is unknown and not differentiable, the only way to reveal these features is through a feedback loop that exposes it to a large set of different stimuli. The properties of these stimuli should be varied iteratively in order to maximize the neuronal response. To utilize this feedback loop for a biological neural network, it is important to run it quickly and efficiently in order to reach the stimuli that maximizes certain neurons' activation with the least number of iterations possible. Here we present a framework with an efficient design for such a loop. We successfully tested it on an artificial spiking neural network (SNN), which is a model that simulates the asynchronous spiking activity of neurons in living brains. Our optimization method for activation maximization is based on the low-rank Tensor Train decomposition of the discrete activation function. The optimization space is the latent parameter space of images generated by SN-GAN or VQ-VAE generative models. To our knowledge, this is the first time that effective AM has been applied to SNNs. We track changes in the optimal stimuli for artificial neurons during training and show that highly selective neurons can form already in the early epochs of training and in the early layers of a convolutional spiking network. This formation of refined optimal stimuli is associated with an increase in classification accuracy. Some neurons, especially in the deeper layers, may gradually change the concepts they are selective for during learning, potentially explaining their importance for model performance.
Authors: Sanket Rajan Gupte, Josiah Aklilu, Jeffrey J. Nirschl, Serena Yeung-Levy
Abstract: Foundation vision or vision-language models are trained on large unlabeled or noisy data and learn robust representations that can achieve impressive zero- or few-shot performance on diverse tasks. Given these properties, they are a natural fit for active learning (AL), which aims to maximize labeling efficiency. However, the full potential of foundation models has not been explored in the context of AL, specifically in the low-budget regime. In this work, we evaluate how foundation models influence three critical components of effective AL, namely, 1) initial labeled pool selection, 2) ensuring diverse sampling, and 3) the trade-off between representative and uncertainty sampling. We systematically study how the robust representations of foundation models (DINOv2, OpenCLIP) challenge existing findings in active learning. Our observations inform the principled construction of a new simple and elegant AL strategy that balances uncertainty estimated via dropout with sample diversity. We extensively test our strategy on many challenging image classification benchmarks, including natural images as well as out-of-domain biomedical images that are relatively understudied in the AL literature. We also provide a highly performant and efficient implementation of modern AL strategies (including our method) at https://github.com/sanketx/AL-foundation-models.
Authors: Sahab Zandi, Kamesh Korangi, Mar\'ia \'Oskarsd\'ottir, Christophe Mues, Cristi\'an Bravo
Abstract: Whereas traditional credit scoring tends to employ only individual borrower- or loan-level predictors, it has been acknowledged for some time that connections between borrowers may result in default risk propagating over a network. In this paper, we present a model for credit risk assessment leveraging a dynamic multilayer network built from a Graph Neural Network and a Recurrent Neural Network, each layer reflecting a different source of network connection. We test our methodology in a behavioural credit scoring context using a dataset provided by U.S. mortgage financier Freddie Mac, in which different types of connections arise from the geographical location of the borrower and their choice of mortgage provider. The proposed model considers both types of connections and the evolution of these connections over time. We enhance the model by using a custom attention mechanism that weights the different time snapshots according to their importance. After testing multiple configurations, a model with GAT, LSTM, and the attention mechanism provides the best results. Empirical results demonstrate that, when it comes to predicting probability of default for the borrowers, our proposed model brings both better results and novel insights for the analysis of the importance of connections and timestamps, compared to traditional methods.
Authors: Shangda Yang, Vitaly Zankin, Maximilian Balandat, Stefan Scherer, Kevin Carlberg, Neil Walton, Kody J. H. Law
Abstract: We leverage multilevel Monte Carlo (MLMC) to improve the performance of multi-step look-ahead Bayesian optimization (BO) methods that involve nested expectations and maximizations. Often these expectations must be computed by Monte Carlo (MC). The complexity rate of naive MC degrades for nested operations, whereas MLMC is capable of achieving the canonical MC convergence rate for this type of problem, independently of dimension and without any smoothness assumptions. Our theoretical study focuses on the approximation improvements for twoand three-step look-ahead acquisition functions, but, as we discuss, the approach is generalizable in various ways, including beyond the context of BO. Our findings are verified numerically and the benefits of MLMC for BO are illustrated on several benchmark examples. Code is available at https://github.com/Shangda-Yang/MLMCBO .
Authors: Jiaming Ji, Boyuan Chen, Hantao Lou, Donghai Hong, Borong Zhang, Xuehai Pan, Juntao Dai, Tianyi Qiu, Yaodong Yang
Abstract: With the rapid development of large language models (LLMs) and ever-evolving practical requirements, finding an efficient and effective alignment method has never been more critical. However, the tension between the complexity of current alignment methods and the need for rapid iteration in deployment scenarios necessitates the development of a model-agnostic alignment approach that can operate under these constraints. In this paper, we introduce Aligner, a novel and simple alignment paradigm that learns the correctional residuals between preferred and dispreferred answers using a small model. Designed as a model-agnostic, plug-and-play module, Aligner can be directly applied to various open-source and API-based models with only one-off training, making it suitable for rapid iteration. Notably, Aligner can be applied to any powerful, large-scale upstream models. Moreover, it can even iteratively bootstrap the upstream models using corrected responses as synthetic human preference data, breaking through the model's performance ceiling. Our experiments demonstrate performance improvements by deploying the same Aligner model across 11 different LLMs, evaluated on the 3H dimensions (helpfulness, harmlessness, and honesty). Specifically, Aligner-7B has achieved an average improvement of 68.9% in helpfulness and 23.8% in harmlessness across the tested LLMs while also effectively reducing hallucination. In the Alpaca-Eval leaderboard, stacking Aligner-2B on GPT-4 Turbo improved its LC Win Rate from 55.0% to 58.3%, surpassing GPT-4 Omni's 57.5% Win Rate (community report).
Authors: Andr\'e V. Duarte, Xuandong Zhao, Arlindo L. Oliveira, Lei Li
Abstract: How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the premise that a language model is likely to identify verbatim excerpts from its training text. We propose DE-COP, a method to determine whether a piece of copyrighted content was included in training. DE-COP's core approach is to probe an LLM with multiple-choice questions, whose options include both verbatim text and their paraphrases. We construct BookTection, a benchmark with excerpts from 165 books published prior and subsequent to a model's training cutoff, along with their paraphrases. Our experiments show that DE-COP surpasses the prior best method by 9.6% in detection performance (AUC) on models with logits available. Moreover, DE-COP also achieves an average accuracy of 72% for detecting suspect books on fully black-box models where prior methods give approximately 4% accuracy. The code and datasets are available at https://github.com/LeiLiLab/DE-COP.
Authors: Alex Havrilla, Sharath Raparthy, Christoforus Nalmpantis, Jane Dwivedi-Yu, Maksym Zhuravinskyi, Eric Hambro, Roberta Raileanu
Abstract: State-of-the-art language models can exhibit impressive reasoning refinement capabilities on math, science or coding tasks. However, recent work demonstrates that even the best models struggle to identify \textit{when and where to refine} without access to external feedback. Outcome-based Reward Models (\textbf{ORMs}), trained to predict correctness of the final answer indicating when to refine, offer one convenient solution for deciding when to refine. Process Based Reward Models (\textbf{PRMs}), trained to predict correctness of intermediate steps, can then be used to indicate where to refine. But they are expensive to train, requiring extensive human annotations. In this paper, we propose Stepwise ORMs (\textbf{SORMs}) which are trained, only on synthetic data, to approximate the expected future reward of the optimal policy or $V^{\star}$. More specifically, SORMs are trained to predict the correctness of the final answer when sampling the current policy many times (rather than only once as in the case of ORMs). Our experiments show that SORMs can more accurately detect incorrect reasoning steps compared to ORMs, thus improving downstream accuracy when doing refinements. We then train \textit{global} refinement models, which take only the question and a draft solution as input and predict a corrected solution, and \textit{local} refinement models which also take as input a critique indicating the location of the first reasoning error. We generate training data for both models synthetically by reusing data used to train the SORM. We find combining global and local refinements, using the ORM as a reranker, significantly outperforms either one individually, as well as a best of three sample baseline. With this strategy we can improve the accuracy of a LLaMA-2 13B model (already fine-tuned with RL) on GSM8K from 53\% to 65\% when greedily sampled.
Authors: Danyang Li, Roberto Tron
Abstract: Time-series data can represent the behaviors of autonomous systems, such as drones and self-driving cars. The task of binary and multi-class classification for time-series data has become a prominent area of research. Neural networks represent a popular approach to classifying data; However, they lack interpretability, which poses a significant challenge in extracting meaningful information from them. Signal Temporal Logic (STL) is a formalism that describes the properties of timed behaviors. We propose a method that combines all of the above: neural networks that represent STL specifications for multi-class classification of time-series data. We offer two key contributions: 1) We introduce a notion of margin for multi-class classification, and 2) we introduce STL-based attributes for enhancing the interpretability of the results. We evaluate our method on two datasets and compare it with state-of-the-art baselines.
Authors: Stefan Hegselmann, Shannon Zejiang Shen, Florian Gierse, Monica Agrawal, David Sontag, Xiaoyi Jiang
Abstract: Patients often face difficulties in understanding their hospitalizations, while healthcare workers have limited resources to provide explanations. In this work, we investigate the potential of large language models to generate patient summaries based on doctors' notes and study the effect of training data on the faithfulness and quality of the generated summaries. To this end, we release (i) a rigorous labeling protocol for errors in medical texts and (ii) a publicly available dataset of annotated hallucinations in 100 doctor-written and 100 generated summaries. We show that fine-tuning on hallucination-free data effectively reduces hallucinations from 2.60 to 1.55 per summary for Llama 2, while preserving relevant information. We observe a similar effect on GPT-4 (0.70 to 0.40), when the few-shot examples are hallucination-free. We also conduct a qualitative evaluation using hallucination-free and improved training data. We find that common quantitative metrics do not correlate well with faithfulness and quality. Finally, we test GPT-4 for automatic hallucination detection, which clearly outperforms common baselines.
Authors: Nicola Piovesan, Antonio De Domenico, Fadhel Ayed
Abstract: The increasing interest in Large Language Models (LLMs) within the telecommunications sector underscores their potential to revolutionize operational efficiency. However, the deployment of these sophisticated models is often hampered by their substantial size and computational demands, raising concerns about their viability in resource-constrained environments. Addressing this challenge, recent advancements have seen the emergence of small language models that surprisingly exhibit performance comparable to their larger counterparts in many tasks, such as coding and common-sense reasoning. Phi-2, a compact yet powerful model, exemplifies this new wave of efficient small language models. This paper conducts a comprehensive evaluation of Phi-2's intrinsic understanding of the telecommunications domain. Recognizing the scale-related limitations, we enhance Phi-2's capabilities through a Retrieval-Augmented Generation approach, meticulously integrating an extensive knowledge base specifically curated with telecom standard specifications. The enhanced Phi-2 model demonstrates a profound improvement in accuracy, answering questions about telecom standards with a precision that closely rivals the more resource-intensive GPT-3.5. The paper further explores the refined capabilities of Phi-2 in addressing problem-solving scenarios within the telecom sector, highlighting its potential and limitations.
Authors: Gianluca Barone, Aashrit Cunchala, Rudy Nunez
Abstract: Standard classification theory assumes that the distribution of images in the test and training sets are identical. Unfortunately, real-life scenarios typically feature unseen data ("out-of-distribution data") which is different from data in the training distribution("in-distribution"). This issue is most prevalent in social justice problems where data from under-represented groups may appear in the test data without representing an equal proportion of the training data. This may result in a model returning confidently wrong decisions and predictions. We are interested in the following question: Can the performance of a neural network improve on facial images of out-of-distribution data when it is trained simultaneously on multiple datasets of in-distribution data? We approach this problem by incorporating the Outlier Exposure model and investigate how the model's performance changes when other datasets of facial images were implemented. We observe that the accuracy and other metrics of the model can be increased by applying Outlier Exposure, incorporating a trainable weight parameter to increase the machine's emphasis on outlier images, and by re-weighting the importance of different class labels. We also experimented with whether sorting the images and determining outliers via image features would have more of an effect on the metrics than sorting by average pixel value. Our goal was to make models not only more accurate but also more fair by scanning a more expanded range of images. We also tested the datasets in reverse order to see whether a more fair dataset with balanced features has an effect on the model's accuracy.
Authors: David Pogorzelski, Peter Arlinghaus, Wenyan Zhang
Abstract: In this paper, we introduce a novel method designed to enhance label efficiency in satellite imagery analysis by integrating semi-supervised learning (SSL) with active learning strategies. Our approach utilizes contrastive learning together with uncertainty estimations via Monte Carlo Dropout (MC Dropout), with a particular focus on Sentinel-2 imagery analyzed using the Eurosat dataset. We explore the effectiveness of our method in scenarios featuring both balanced and unbalanced class distributions. Our results show that the proposed method performs better than several other popular methods in this field, enabling significant savings in labeling effort while maintaining high classification accuracy. These findings highlight the potential of our approach to facilitate scalable and cost-effective satellite image analysis, particularly advantageous for extensive environmental monitoring and land use classification tasks.
Authors: Malia L. Kao, Keith Hawkins, Laura K. Rogers, Amy Bonsor, Bart H. Dunlap, Jason L. Sanders, M. H. Montgomery, D. E. Winget
Abstract: White dwarfs (WDs) polluted by exoplanetary material provide the unprecedented opportunity to directly observe the interiors of exoplanets. However, spectroscopic surveys are often limited by brightness constraints, and WDs tend to be very faint, making detections of large populations of polluted WDs difficult. In this paper, we aim to increase considerably the number of WDs with multiple metals in their atmospheres. Using 96,134 WDs with Gaia DR3 BP/RP (XP) spectra, we constructed a 2D map using an unsupervised machine learning technique called Uniform Manifold Approximation and Projection (UMAP) to organize the WDs into identifiable spectral regions. The polluted WDs are among the distinct spectral groups identified in our map. We have shown that this selection method could potentially increase the number of known WDs with 5 or more metal species in their atmospheres by an order of magnitude. Such systems are essential for characterizing exoplanet diversity and geology.
Authors: Ethan Shen, Alan Fan, Sarah M. Pratt, Jae Sung Park, Matthew Wallingford, Sham M. Kakade, Ari Holtzman, Ranjay Krishna, Ali Farhadi, Aditya Kusupati
Abstract: Many applications today provide users with multiple auto-complete drafts as they type, including GitHub's code completion, Gmail's smart compose, and Apple's messaging auto-suggestions. Under the hood, language models support this by running an autoregressive inference pass to provide a draft. Consequently, providing $k$ drafts to the user requires running an expensive language model $k$ times. To alleviate the computation cost of running $k$ inference passes, we propose Superposed Decoding, a new decoding algorithm that generates $k$ drafts at the computation cost of one autoregressive inference pass. We achieve this by feeding a superposition of the most recent token embeddings from the $k$ drafts as input to the next decoding step of the language model. At every inference step we combine the $k$ drafts with the top-$k$ tokens to get $k^2$ new drafts and cache the $k$ most likely options, using an n-gram interpolation with minimal compute overhead to filter out incoherent generations. Our experiments show that $k$ drafts from Superposed Decoding are at least as coherent and factual as Nucleus Sampling and Greedy Decoding respectively, while being at least $2.44\times$ faster for $k\ge3$. In a compute-normalized setting, user evaluations demonstrably favor text generated by Superposed Decoding over Nucleus Sampling. Code and more examples open-sourced at https://github.com/RAIVNLab/SuperposedDecoding.
Authors: Johannes M\"uller, Semih Cayci
Abstract: We study the error introduced by entropy regularization of infinite-horizon discrete discounted Markov decision processes. We show that this error decreases exponentially in the inverse regularization strength both in a weighted KL-divergence and in value with a problem-specific exponent. We provide a lower bound matching our upper bound up to a polynomial factor. Our proof relies on the correspondence of the solutions of entropy-regularized Markov decision processes with gradient flows of the unregularized reward with respect to a Riemannian metric common in natural policy gradient methods. Further, this correspondence allows us to identify the limit of the gradient flow as the generalized maximum entropy optimal policy, thereby characterizing the implicit bias of the Kakade gradient flow which corresponds to a time-continuous version of the natural policy gradient method. We use this to show that for entropy-regularized natural policy gradient methods the overall error decays exponentially in the square root of the number of iterations improving existing sublinear guarantees.
Authors: Viet Anh Trinh, Rosy Southwell, Yiwen Guan, Xinlu He, Zhiyong Wang, Jacob Whitehill
Abstract: Recent work on discrete speech tokenization has paved the way for models that can seamlessly perform multiple tasks across modalities, e.g., speech recognition, text to speech, speech to speech translation. Moreover, large language models (LLMs) pretrained from vast text corpora contain rich linguistic information that can improve accuracy in a variety of tasks. In this paper, we present a decoder-only Discrete Multimodal Language Model (DMLM), which can be flexibly applied to multiple tasks (ASR, T2S, S2TT, etc.) and modalities (text, speech, vision). We explore several critical aspects of discrete multi-modal models, including the loss function, weight initialization, mixed training supervision, and codebook. Our results show that DMLM benefits significantly, across multiple tasks and datasets, from a combination of supervised and unsupervised training. Moreover, for ASR, it benefits from initializing DMLM from a pretrained LLM, and from a codebook derived from Whisper activations.
Authors: Federico Spagnolo, Nataliia Molchanova, Roger Schaer, Meritxell Bach Cuadra, Mario Ocampo Pineda, Lester Melie-Garcia, Cristina Granziera, Vincent Andrearczyk, Adrien Depeursinge
Abstract: In recent years, explainable methods for artificial intelligence (XAI) have tried to reveal and describe models' decision mechanisms in the case of classification tasks. However, XAI for semantic segmentation and in particular for single instances has been little studied to date. Understanding the process underlying automatic segmentation of single instances is crucial to reveal what information was used to detect and segment a given object of interest. In this study, we proposed two instance-level explanation maps for semantic segmentation based on SmoothGrad and Grad-CAM++ methods. Then, we investigated their relevance for the detection and segmentation of white matter lesions (WML), a magnetic resonance imaging (MRI) biomarker in multiple sclerosis (MS). 687 patients diagnosed with MS for a total of 4043 FLAIR and MPRAGE MRI scans were collected at the University Hospital of Basel, Switzerland. Data were randomly split into training, validation and test sets to train a 3D U-Net for MS lesion segmentation. We observed 3050 true positive (TP), 1818 false positive (FP), and 789 false negative (FN) cases. We generated instance-level explanation maps for semantic segmentation, by developing two XAI methods based on SmoothGrad and Grad-CAM++. We investigated: 1) the distribution of gradients in saliency maps with respect to both input MRI sequences; 2) the model's response in the case of synthetic lesions; 3) the amount of perilesional tissue needed by the model to segment a lesion. Saliency maps (based on SmoothGrad) in FLAIR showed positive values inside a lesion and negative in its neighborhood. Peak values of saliency maps generated for these four groups of volumes presented distributions that differ significantly from one another, suggesting a quantitative nature of the proposed saliency. Contextual information of 7mm around the lesion border was required for their segmentation.
Authors: Gayane Ghazaryan, Erik Arakelyan, Pasquale Minervini, Isabelle Augenstein
Abstract: Question Answering (QA) datasets have been instrumental in developing and evaluating Large Language Model (LLM) capabilities. However, such datasets are scarce for languages other than English due to the cost and difficulties of collection and manual annotation. This means that producing novel models and measuring the performance of multilingual LLMs in low-resource languages is challenging. To mitigate this, we propose $\textbf{S}$yn$\textbf{DAR}$in, a method for generating and validating QA datasets for low-resource languages. We utilize parallel content mining to obtain $\textit{human-curated}$ paragraphs between English and the target language. We use the English data as context to $\textit{generate}$ synthetic multiple-choice (MC) question-answer pairs, which are automatically translated and further validated for quality. Combining these with their designated non-English $\textit{human-curated}$ paragraphs form the final QA dataset. The method allows to maintain the content quality, reduces the likelihood of factual errors, and circumvents the need for costly annotation. To test the method, we created a QA dataset with $1.2$K samples for the Armenian language. The human evaluation shows that $98\%$ of the generated English data maintains quality and diversity in the question types and topics, while the translation validation pipeline can filter out $\sim70\%$ of data with poor quality. We use the dataset to benchmark state-of-the-art LLMs, showing their inability to achieve human accuracy with some model performances closer to random chance. This shows that the generated dataset is non-trivial and can be used to evaluate reasoning capabilities in low-resource language.
Authors: Wentao Shi, Mengqi Yuan, Junkang Wu, Qifan Wang, Fuli Feng
Abstract: Adapting Large Language Models (LLMs) for agent tasks is critical in developing language agents. Direct Preference Optimization (DPO) is a promising technique for this adaptation with the alleviation of compounding errors, offering a means to directly optimize Reinforcement Learning (RL) objectives. However, applying DPO to multi-turn tasks presents challenges due to the inability to cancel the partition function. Overcoming this obstacle involves making the partition function independent of the current state and addressing length disparities between preferred and dis-preferred trajectories. In this light, we replace the policy constraint with the state-action occupancy measure constraint in the RL objective and add length normalization to the Bradley-Terry model, yielding a novel loss function named DMPO for multi-turn agent tasks with theoretical explanations. Extensive experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the DMPO loss.
Authors: Jiawen Wang, Pei Cai, Ziyan Wang, Huabin Zhang, Jianpan Huang
Abstract: Purpose: This study aims to propose and investigate the feasibility of using Kolmogorov-Arnold Network (KAN) for CEST MRI data analysis (CEST-KAN). Methods: CEST MRI data were acquired from twelve healthy volunteers at 3T. Data from ten subjects were used for training, while the remaining two were reserved for testing. The performance of multi-layer perceptron (MLP) and KAN models with the same network settings were evaluated and compared to the conventional multi-pool Lorentzian fitting (MPLF) method in generating water and multiple CEST contrasts, including amide, relayed nuclear Overhauser effect (rNOE), and magnetization transfer (MT). Results: The water and CEST maps generated by both MLP and KAN were visually comparable to the MPLF results. However, the KAN model demonstrated higher accuracy in extrapolating the CEST fitting metrics, as evidenced by the smaller validation loss during training and smaller absolute error during testing. Voxel-wise correlation analysis showed that all four CEST fitting metrics generated by KAN consistently exhibited higher Pearson coefficients than the MLP results, indicating superior performance. Moreover, the KAN models consistently outperformed the MLP models in varying hidden layer numbers despite longer training time. Conclusion: In this study, we demonstrated for the first time the feasibility of utilizing KAN for CEST MRI data analysis, highlighting its superiority over MLP in this task. The findings suggest that CEST-KAN has the potential to be a robust and reliable post-analysis tool for CEST MRI in clinical settings.