Authors: Kacy Zhou, Jiawen Wen, Nan Yang, Dong Yuan, Qinghua Lu, Huaming Chen
Abstract: While deep learning has become a core functional module of most software systems, concerns regarding the fairness of ML predictions have emerged as a significant issue that affects prediction results due to discrimination. Intersectional bias, which disproportionately affects members of subgroups, is a prime example of this. For instance, a machine learning model might exhibit bias against darker-skinned women, while not showing bias against individuals with darker skin or women. This problem calls for effective fairness testing before the deployment of such deep learning models in real-world scenarios. However, research into detecting such bias is currently limited compared to research on individual and group fairness. Existing tools to investigate intersectional bias lack important features such as support for multiple fairness metrics, fast and efficient computation, and user-friendly interpretation. This paper introduces Fairpriori, a novel biased subgroup discovery method, which aims to address these limitations. Fairpriori incorporates the frequent itemset generation algorithm to facilitate effective and efficient investigation of intersectional bias by producing fast fairness metric calculations on subgroups of a dataset. Through comparison with the state-of-the-art methods (e.g., Themis, FairFictPlay, and TestSGD) under similar conditions, Fairpriori demonstrates superior effectiveness and efficiency when identifying intersectional bias. Specifically, Fairpriori is easier to use and interpret, supports a wider range of use cases by accommodating multiple fairness metrics, and exhibits higher efficiency in computing fairness metrics. These findings showcase Fairpriori's potential for effectively uncovering subgroups affected by intersectional bias, supported by its open-source tooling at https://anonymous.4open.science/r/Fairpriori-0320.
Authors: Kalpana Ranasinghe, H. P. Madushanka, Rafaela Scaciota, Sumudu Samarakoon, Mehdi Bennis
Abstract: This work presents a use case of federated learning (FL) applied to discovering a maze with LiDAR sensors-equipped robots. Goal here is to train classification models to accurately identify the shapes of grid areas within two different square mazes made up with irregular shaped walls. Due to the use of different shapes for the walls, a classification model trained in one maze that captures its structure does not generalize for the other. This issue is resolved by adopting FL framework between the robots that explore only one maze so that the collective knowledge allows them to operate accurately in the unseen maze. This illustrates the effectiveness of FL in real-world applications in terms of enhancing classification accuracy and robustness in maze discovery tasks.
Authors: Yifan Hu, Fukang Yin, Weimin Zhang, Kaijun Ren, Junqiang Song, Kefeng Deng, Di Zhang
Abstract: Long-term stability stands as a crucial requirement in data-driven medium-range global weather forecasting. Spectral bias is recognized as the primary contributor to instabilities, as data-driven methods difficult to learn small-scale dynamics. In this paper, we reveal that the universal mechanism for these instabilities is not only related to spectral bias but also to distortions brought by processing spherical data using conventional convolution. These distortions lead to a rapid amplification of errors over successive long-term iterations, resulting in a significant decline in forecast accuracy. To address this issue, a universal neural operator called the Spherical Harmonic Neural Operator (SHNO) is introduced to improve long-term iterative forecasts. SHNO uses the spherical harmonic basis to mitigate distortions for spherical data and uses gated residual spectral attention (GRSA) to correct spectral bias caused by spurious correlations across different scales. The effectiveness and merit of the proposed method have been validated through its application for spherical Shallow Water Equations (SWEs) and medium-range global weather forecasting. Our findings highlight the benefits and potential of SHNO to improve the accuracy of long-term prediction.
Authors: Ruiqing Yan, Xingbo Du, Haoyu Deng, Linghan Zheng, Qiuzhuang Sun, Jifang Hu, Yuhang Shao, Penghao Jiang, Jinrong Jiang, Lian Zhao
Abstract: With the advent of large models based on the Transformer architecture, researchers have observed an anomalous phenomenon in the Attention mechanism--there is a very high attention on the first element, which is prevalent across Transformer-based models. It is crucial to understand it for the development of techniques focusing on attention distribution, such as Key-Value (KV) Cache compression and infinite extrapolation; however, the latent cause leaves to be unknown. In this paper, we analyze such a phenomenon from the perspective of waiver phenomenon, which involves reducing the internal values of certain elements in the Softmax function, allowing them to absorb excess attention without affecting their contribution to information. In specific models, due to differences in positional encoding and attention patterns, we have found that the selection of waiver elements by the model can be categorized into two methods: positional-encoding-based and feature-distribution-within-elements-based.
Authors: Mayk Caldas Ramos, Christopher J. Collison, Andrew D. White
Abstract: Large language models (LLMs) are emerging as a powerful tool in chemistry across multiple domains. In chemistry, LLMs are able to accurately predict properties, design new molecules, optimize synthesis pathways, and accelerate drug and material discovery. A core emerging idea is combining LLMs with chemistry-specific tools like synthesis planners and databases, leading to so-called "agents." This review covers LLMs' recent history, current capabilities, design, challenges specific to chemistry, and future directions. Particular attention is given to agents and their emergence as a cross-chemistry paradigm. Agents have proven effective in diverse domains of chemistry, but challenges remain. It is unclear if creating domain-specific versus generalist agents and developing autonomous pipelines versus "co-pilot" systems will accelerate chemistry. An emerging direction is the development of multi-agent systems using a human-in-the-loop approach. Due to the incredibly fast development of this field, a repository has been built to keep track of the latest studies: https://github.com/ur-whitelab/LLMs-in-science.
Authors: Ruochen Wang, Ting Liu, Cho-Jui Hsieh, Boqing Gong
Abstract: This paper introduces the first gradient-based framework for prompt optimization in text-to-image diffusion models. We formulate prompt engineering as a discrete optimization problem over the language space. Two major challenges arise in efficiently finding a solution to this problem: (1) Enormous Domain Space: Setting the domain to the entire language space poses significant difficulty to the optimization process. (2) Text Gradient: Efficiently computing the text gradient is challenging, as it requires backpropagating through the inference steps of the diffusion model and a non-differentiable embedding lookup table. Beyond the problem formulation, our main technical contributions lie in solving the above challenges. First, we design a family of dynamically generated compact subspaces comprised of only the most relevant words to user input, substantially restricting the domain space. Second, we introduce "Shortcut Text Gradient" -- an effective replacement for the text gradient that can be obtained with constant memory and runtime. Empirical evaluation on prompts collected from diverse sources (DiffusionDB, ChatGPT, COCO) suggests that our method can discover prompts that substantially improve (prompt enhancement) or destroy (adversarial attack) the faithfulness of images generated by the text-to-image diffusion model.
Authors: Zhongxiang Fan, Zhaocheng Liu, Jian Liang, Dongying Kong, Han Li, Peng Jiang, Shuang Li, Kun Gai
Abstract: This paper investigates the one-epoch overfitting phenomenon in Click-Through Rate (CTR) models, where performance notably declines at the start of the second epoch. Despite extensive research, the efficacy of multi-epoch training over the conventional one-epoch approach remains unclear. We identify the overfitting of the embedding layer, caused by high-dimensional data sparsity, as the primary issue. To address this, we introduce a novel and simple Multi-Epoch learning with Data Augmentation (MEDA) framework, suitable for both non-continual and continual learning scenarios, which can be seamlessly integrated into existing deep CTR models and may have potential applications to handle the "forgetting or overfitting" dilemma in the retraining and the well-known catastrophic forgetting problems. MEDA minimizes overfitting by reducing the dependency of the embedding layer on subsequent training data or the Multi-Layer Perceptron (MLP) layers, and achieves data augmentation through training the MLP with varied embedding spaces. Our findings confirm that pre-trained MLP layers can adapt to new embedding spaces, enhancing performance without overfitting. This adaptability underscores the MLP layers' role in learning a matching function focused on the relative relationships among embeddings rather than their absolute positions. To our knowledge, MEDA represents the first multi-epoch training strategy tailored for deep CTR prediction models. We conduct extensive experiments on several public and business datasets, and the effectiveness of data augmentation and superiority over conventional single-epoch training are fully demonstrated. Besides, MEDA has exhibited significant benefits in a real-world online advertising system.
Authors: Zhiwei Li, Carl Kesselman, Mike D'Arch, Michael Pazzani, Benjamin Yizing Xu
Abstract: Increasingly, artificial intelligence (AI) and machine learning (ML) are used in eScience applications [9]. While these approaches have great potential, the literature has shown that ML-based approaches frequently suffer from results that are either incorrect or unreproducible due to mismanagement or misuse of data used for training and validating the models [12, 15]. Recognition of the necessity of high-quality data for correct ML results has led to data-centric ML approaches that shift the central focus from model development to creation of high-quality data sets to train and validate the models [14, 20]. However, there are limited tools and methods available for data-centric approaches to explore and evaluate ML solutions for eScience problems which often require collaborative multidisciplinary teams working with models and data that will rapidly evolve as an investigation unfolds [1]. In this paper, we show how data management tools based on the principle that all of the data for ML should be findable, accessible, interoperable and reusable (i.e. FAIR [26]) can significantly improve the quality of data that is used for ML applications. When combined with best practices that apply these tools to the entire life cycle of an ML-based eScience investigation, we can significantly improve the ability of an eScience team to create correct and reproducible ML solutions. We propose an architecture and implementation of such tools and demonstrate through two use cases how they can be used to improve ML-based eScience investigations.
Authors: Wenqian Chen, Amanda A. Howard, Panos Stinis
Abstract: Physics-informed deep learning has emerged as a promising alternative for solving partial differential equations. However, for complex problems, training these networks can still be challenging, often resulting in unsatisfactory accuracy and efficiency. In this work, we demonstrate that the failure of plain physics-informed neural networks arises from the significant discrepancy in the convergence speed of residuals at different training points, where the slowest convergence speed dominates the overall solution convergence. Based on these observations, we propose a point-wise adaptive weighting method that balances the residual decay rate across different training points. The performance of our proposed adaptive weighting method is compared with current state-of-the-art adaptive weighting methods on benchmark problems for both physics-informed neural networks and physics-informed deep operator networks. Through extensive numerical results we demonstrate that our proposed approach of balanced residual decay rates offers several advantages, including bounded weights, high prediction accuracy, fast convergence speed, low training uncertainty, low computational cost and ease of hyperparameter tuning.
Authors: Yun Dai, Tejas Dharamsi, Byron Hsu, Tao Song, Hamed Firooz
Abstract: Training extremely large language models with billions of parameters is a computationally intensive task that pushes the limits of current data parallel training systems. While techniques like ZeRO++ have enabled efficient distributed training of such giant models on inexpensive low-bandwidth clusters, they can suffer from convergence issues due to potential race conditions in the hierarchical partitioning (hpZ) scheme employed to reduce cross-machine communication. In this work, we first show how these race conditions cause instability when training models with billions of parameters. We then propose a modification to the partitioning algorithm that addresses these convergence challenges while maintaining competitive training efficiency. Empirical evaluation on training the multi-billion parameters Falcon Models and Llama-2 models demonstrates the updated algorithm's ability to achieve reliable convergence on these massive models, where stock ZeRO++ hpZ fails to converge. The updated algorithm enables robust training of larger models with 98\% throughput and model training speed improvement without sacrificing the quality of convergence.
Authors: Arash Mozhdehi, Mahdi Mohammadizadeh, Xin Wang
Abstract: In response to carbon-neutral policies in developed countries, electric vehicles route optimization has gained importance for logistics companies. With the increasing focus on customer expectations and the shift towards more customer-oriented business models, the integration of delivery time-windows has become essential in logistics operations. Recognizing the critical nature of these developments, this article studies the heterogeneous electric vehicle routing problem with time-window constraints (HEVRPTW). To solve this variant of vehicle routing problem (VRP), we propose a DRL-based approach, named Edge-enhanced Dual attentIon encoderR and feature-EnhanCed dual aTtention decoder (Edge-DIRECT). Edge-DIRECT features an extra graph representation, the node connectivity of which is based on the overlap of customer time-windows. Edge-DIRECT's self-attention encoding mechanism is enhanced by exploiting the energy consumption and travel time between the locations. To effectively account for the heterogeneity of the EVs' fleet, a dual attention decoder has been introduced. Experimental results based on two real-world datasets reveal that Edge-DIRECT outperforms a state-of-the-art DRL-based method and a well-established heuristic approach in solution quality and execution time. Furthermore, it exhibits competitive performance when compared to another leading heuristic method.
Authors: Aamod Khatiwada, Harsha Kokel, Ibrahim Abdelaziz, Subhajit Chaudhury, Julian Dolby, Oktie Hassanzadeh, Zhenhan Huang, Tejaswini Pedapati, Horst Samulowitz, Kavitha Srinivas
Abstract: Enterprises have a growing need to identify relevant tables in data lakes; e.g. tables that are unionable, joinable, or subsets of each other. Tabular neural models can be helpful for such data discovery tasks. In this paper, we present TabSketchFM, a neural tabular model for data discovery over data lakes. First, we propose a novel pre-training sketch-based approach to enhance the effectiveness of data discovery techniques in neural tabular models. Second, to further finetune the pretrained model for several downstream tasks, we develop LakeBench, a collection of 8 benchmarks to help with different data discovery tasks such as finding tasks that are unionable, joinable, or subsets of each other. We then show on these finetuning tasks that TabSketchFM achieves state-of-the art performance compared to existing neural models. Third, we use these finetuned models to search for tables that are unionable, joinable, or can be subsets of each other. Our results demonstrate improvements in F1 scores for search compared to state-of-the-art techniques (even up to 70% improvement in a joinable search benchmark). Finally, we show significant transfer across datasets and tasks establishing that our model can generalize across different tasks over different data lakes
Authors: Jifan Shi, Yang Li, Juan Zhao, Siyang Leng, Kazuyuki Aihara, Luonan Chen, Wei Lin
Abstract: Detecting and quantifying causality is a focal topic in the fields of science, engineering, and interdisciplinary studies. However, causal studies on non-intervention systems attract much attention but remain extremely challenging. To address this challenge, we propose a framework named Interventional Dynamical Causality (IntDC) for such non-intervention systems, along with its computational criterion, Interventional Embedding Entropy (IEE), to quantify causality. The IEE criterion theoretically and numerically enables the deciphering of IntDC solely from observational (non-interventional) time-series data, without requiring any knowledge of dynamical models or real interventions in the considered system. Demonstrations of performance showed the accuracy and robustness of IEE on benchmark simulated systems as well as real-world systems, including the neural connectomes of C. elegans, COVID-19 transmission networks in Japan, and regulatory networks surrounding key circadian genes.
Authors: Sheo Yon Jhin, Seojin Kim, Noseong Park
Abstract: Time series forecasting has been an essential field in many different application areas, including economic analysis, meteorology, and so forth. The majority of time series forecasting models are trained using the mean squared error (MSE). However, this training based on MSE causes a limitation known as prediction delay. The prediction delay, which implies the ground-truth precedes the prediction, can cause serious problems in a variety of fields, e.g., finance and weather forecasting -- as a matter of fact, predictions succeeding ground-truth observations are not practically meaningful although their MSEs can be low. This paper proposes a new perspective on traditional time series forecasting tasks and introduces a new solution to mitigate the prediction delay. We introduce a continuous-time gated recurrent unit (GRU) based on the neural ordinary differential equation (NODE) which can supervise explicit time-derivatives. We generalize the GRU architecture in a continuous-time manner and minimize the prediction delay through our time-derivative regularization. Our method outperforms in metrics such as MSE, Dynamic Time Warping (DTW) and Time Distortion Index (TDI). In addition, we demonstrate the low prediction delay of our method in a variety of datasets.
Authors: Georgia Papacharalampous, Hristos Tyralis, Nikolaos Doulamis, Anastasios Doulamis
Abstract: To facilitate effective decision-making, gridded satellite precipitation products should include uncertainty estimates. Machine learning has been proposed for issuing such estimates. However, most existing algorithms for this purpose rely on quantile regression. Distributional regression offers distinct advantages over quantile regression, including the ability to model intermittency as well as a stronger ability to extrapolate beyond the training data, which is critical for predicting extreme precipitation. In this work, we introduce the concept of distributional regression for the engineering task of creating precipitation datasets through data merging. Building upon this concept, we propose new ensemble learning methods that can be valuable not only for spatial prediction but also for prediction problems in general. These methods exploit conditional zero-adjusted probability distributions estimated with generalized additive models for location, scale, and shape (GAMLSS), spline-based GAMLSS and distributional regression forests as well as their ensembles (stacking based on quantile regression, and equal-weight averaging). To identify the most effective methods for our specific problem, we compared them to benchmarks using a large, multi-source precipitation dataset. Stacking emerged as the most successful strategy. Three specific stacking methods achieved the best performance based on the quantile scoring rule, although the ranking of these methods varied across quantile levels. This suggests that a task-specific combination of multiple algorithms could yield significant benefits.
Authors: Taeyoung Yun, Sujin Yun, Jaewoo Lee, Jinkyoo Park
Abstract: Optimizing complex and high-dimensional black-box functions is ubiquitous in science and engineering fields. Unfortunately, the online evaluation of these functions is restricted due to time and safety constraints in most cases. In offline model-based optimization (MBO), we aim to find a design that maximizes the target function using only a pre-existing offline dataset. While prior methods consider forward or inverse approaches to address the problem, these approaches are limited by conservatism and the difficulty of learning highly multi-modal mappings. Recently, there has been an emerging paradigm of learning to improve solutions with synthetic trajectories constructed from the offline dataset. In this paper, we introduce a novel conditional generative modeling approach to produce trajectories toward high-scoring regions. First, we construct synthetic trajectories toward high-scoring regions using the dataset while injecting locality bias for consistent improvement directions. Then, we train a conditional diffusion model to generate trajectories conditioned on their scores. Lastly, we sample multiple trajectories from the trained model with guidance to explore high-scoring regions beyond the dataset and select high-fidelity designs among generated trajectories with the proxy function. Extensive experiment results demonstrate that our method outperforms competitive baselines on Design-Bench and its practical variants. The code is publicly available in \texttt{https://github.com/dbsxodud-11/GTG}.
Authors: Wei Zhuo, Guang Tan
Abstract: Graph Neural Networks (GNNs) have shown remarkable success in learning from graph-structured data. However, their application to directed graphs (digraphs) presents unique challenges, primarily due to the inherent asymmetry in node relationships. Traditional GNNs are adept at capturing unidirectional relations but fall short in encoding the mutual path dependencies between nodes, such as asymmetrical shortest paths typically found in digraphs. Recognizing this gap, we introduce Commute Graph Neural Networks (CGNN), an approach that seamlessly integrates node-wise commute time into the message passing scheme. The cornerstone of CGNN is an efficient method for computing commute time using a newly formulated digraph Laplacian. Commute time information is then integrated into the neighborhood aggregation process, with neighbor contributions weighted according to their respective commute time to the central node in each layer. It enables CGNN to directly capture the mutual, asymmetric relationships in digraphs.
Authors: Tianhao Wei, Luca Marzari, Kai S. Yun, Hanjiang Hu, Peizhi Niu, Xusheng Luo, Changliu Liu
Abstract: Deep Neural Networks (DNN) are crucial in approximating nonlinear functions across diverse applications, ranging from image classification to control. Verifying specific input-output properties can be a highly challenging task due to the lack of a single, self-contained framework that allows a complete range of verification types. To this end, we present \texttt{ModelVerification.jl (MV)}, the first comprehensive, cutting-edge toolbox that contains a suite of state-of-the-art methods for verifying different types of DNNs and safety specifications. This versatile toolbox is designed to empower developers and machine learning practitioners with robust tools for verifying and ensuring the trustworthiness of their DNN models.
Authors: Ouya Wang, Shenglong Zhou, Geoffrey Ye Li
Abstract: Stochastic gradient descent-based algorithms are widely used for training deep neural networks but often suffer from slow convergence. To address the challenge, we leverage the framework of the alternating direction method of multipliers (ADMM) to develop a novel data-driven algorithm, called batch ADMM (BADM). The fundamental idea of the proposed algorithm is to split the training data into batches, which is further divided into sub-batches where primal and dual variables are updated to generate global parameters through aggregation. We evaluate the performance of BADM across various deep learning tasks, including graph modelling, computer vision, image generation, and natural language processing. Extensive numerical experiments demonstrate that BADM achieves faster convergence and superior testing accuracy compared to other state-of-the-art optimizers.
Authors: Xiao Qian, Utkarsh Gangwal, Shangjia Dong, Rachel Davidson
Abstract: Household and individual-level sociodemographic data are essential for understanding human-infrastructure interaction and policymaking. However, the Public Use Microdata Sample (PUMS) offers only a sample at the state level, while census tract data only provides the marginal distributions of variables without correlations. Therefore, we need an accurate synthetic population dataset that maintains consistent variable correlations observed in microdata, preserves household-individual and individual-individual relationships, adheres to state-level statistics, and accurately represents the geographic distribution of the population. We propose a deep generative framework leveraging the variational autoencoder (VAE) to generate a synthetic population with the aforementioned features. The methodological contributions include (1) a new data structure for capturing household-individual and individual-individual relationships, (2) a transfer learning process with pre-training and fine-tuning steps to generate households and individuals whose aggregated distributions align with the census tract marginal distribution, and (3) decoupled binary cross-entropy (D-BCE) loss function enabling distribution shift and out-of-sample records generation. Model results for an application in Delaware, USA demonstrate the ability to ensure the realism of generated household-individual records and accurately describe population statistics at the census tract level compared to existing methods. Furthermore, testing in North Carolina, USA yielded promising results, supporting the transferability of our method.
Authors: Nawazish Ali, Rachael Shaw, Karl Mason
Abstract: Dairy farms consume a significant amount of electricity for their operations, and this research focuses on enhancing energy efficiency and minimizing the impact on the environment in the sector by maximizing the utilization of renewable energy sources. This research investigates the application of Proximal Policy Optimization (PPO), a deep reinforcement learning algorithm (DRL), to enhance dairy farming battery management. We evaluate the algorithm's effectiveness based on its ability to reduce reliance on the electricity grid, highlighting the potential of DRL to enhance energy management in dairy farming. Using real-world data our results demonstrate how the PPO approach outperforms Q-learning by 1.62% for reducing electricity import from the grid. This significant improvement highlights the potential of the Deep Reinforcement Learning algorithm for improving energy efficiency and sustainability in dairy farms.
Authors: Carlo Orientale Caputo, Matteo Marsili
Abstract: We study how abstract representations emerge in a Deep Belief Network (DBN) trained on benchmark datasets. Our analysis targets the principles of learning in the early stages of information processing, starting from the "primordial soup" of the under-sampling regime. As the data is processed by deeper and deeper layers, features are detected and removed, transferring more and more "context-invariant" information to deeper layers. We show that the representation approaches an universal model -- the Hierarchical Feature Model (HFM) -- determined by the principle of maximal relevance. Relevance quantifies the uncertainty on the model of the data, thus suggesting that "meaning" -- i.e. syntactic information -- is that part of the data which is not yet captured by a model. Our analysis shows that shallow layers are well described by pairwise Ising models, which provide a representation of the data in terms of generic, low order features. We also show that plasticity increases with depth, in a similar way as it does in the brain. These findings suggest that DBNs are capable of extracting a hierarchy of features from the data which is consistent with the principle of maximal relevance.
Authors: Mohamed Elsayed, Qingfeng Lan, Clare Lyle, A. Rupam Mahmood
Abstract: Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they often change the optimizer or the architecture, a complexity that hinders widespread adoption in various systems. In this paper, we focus on learning failures that are associated with increasing weight norm and we propose a simple technique that can be easily added on top of existing learning systems: clipping neural network weights to limit them to a specific range. We study the effectiveness of weight clipping in a series of supervised and reinforcement learning experiments. Our empirical results highlight the benefits of weight clipping for generalization, addressing loss of plasticity and policy collapse, and facilitating learning with a large replay ratio.
Authors: Gaojie Jin, Ronghui Mu, Xinping Yi, Xiaowei Huang, Lijun Zhang
Abstract: The Invariant Risk Minimization (IRM) approach aims to address the challenge of domain generalization by training a feature representation that remains invariant across multiple environments. However, in noisy environments, IRM-related techniques such as IRMv1 and VREx may be unable to achieve the optimal IRM solution, primarily due to erroneous optimization directions. To address this issue, we introduce ICorr (an abbreviation for \textbf{I}nvariant \textbf{Corr}elation), a novel approach designed to surmount the above challenge in noisy settings. Additionally, we dig into a case study to analyze why previous methods may lose ground while ICorr can succeed. Through a theoretical lens, particularly from a causality perspective, we illustrate that the invariant correlation of representation with label is a necessary condition for the optimal invariant predictor in noisy environments, whereas the optimization motivations for other methods may not be. Furthermore, we empirically demonstrate the effectiveness of ICorr by comparing it with other domain generalization methods on various noisy datasets.
Authors: Amirhossein Parsi, Melina Jafari, Sina Sabzekar, Zahra Amini
Abstract: Accurate classification of mode choice datasets is crucial for transportation planning and decision-making processes. However, conventional classification models often struggle to adequately capture the nuanced patterns of minority classes within these datasets, leading to sub-optimal accuracy. In response to this challenge, we present Ensemble Synthesizer (ENSY) which leverages probability distribution for data augmentation, a novel data model tailored specifically for enhancing classification accuracy in mode choice datasets. In our study, ENSY demonstrates remarkable efficacy by nearly quadrupling the F1 score of minority classes and improving overall classification accuracy by nearly 3%. To assess its performance comprehensively, we compare ENSY against various augmentation techniques including Random Oversampling, SMOTE-NC, and CTGAN. Through experimentation, ENSY consistently outperforms these methods across various scenarios, underscoring its robustness and effectiveness
Authors: Sebastian Dalleiger, Jilles Vreeken, Michael Kamp
Abstract: Identifying informative components in binary data is an essential task in many research areas, including life sciences, social sciences, and recommendation systems. Boolean matrix factorization (BMF) is a family of methods that performs this task by efficiently factorizing the data. In real-world settings, the data is often distributed across stakeholders and required to stay private, prohibiting the straightforward application of BMF. To adapt BMF to this context, we approach the problem from a federated-learning perspective, while building on a state-of-the-art continuous binary matrix factorization relaxation to BMF that enables efficient gradient-based optimization. We propose to only share the relaxed component matrices, which are aggregated centrally using a proximal operator that regularizes for binary outcomes. We show the convergence of our federated proximal gradient descent algorithm and provide differential privacy guarantees. Our extensive empirical evaluation demonstrates that our algorithm outperforms, in terms of quality and efficacy, federation schemes of state-of-the-art BMF methods on a diverse set of real-world and synthetic data.
Authors: Clare Lyle, Zeyu Zheng, Khimya Khetarpal, James Martens, Hado van Hasselt, Razvan Pascanu, Will Dabney
Abstract: Normalization layers have recently experienced a renaissance in the deep reinforcement learning and continual learning literature, with several works highlighting diverse benefits such as improving loss landscape conditioning and combatting overestimation bias. However, normalization brings with it a subtle but important side effect: an equivalence between growth in the norm of the network parameters and decay in the effective learning rate. This becomes problematic in continual learning settings, where the resulting effective learning rate schedule may decay to near zero too quickly relative to the timescale of the learning problem. We propose to make the learning rate schedule explicit with a simple re-parameterization which we call Normalize-and-Project (NaP), which couples the insertion of normalization layers with weight projection, ensuring that the effective learning rate remains constant throughout training. This technique reveals itself as a powerful analytical tool to better understand learning rate schedules in deep reinforcement learning, and as a means of improving robustness to nonstationarity in synthetic plasticity loss benchmarks along with both the single-task and sequential variants of the Arcade Learning Environment. We also show that our approach can be easily applied to popular architectures such as ResNets and transformers while recovering and in some cases even slightly improving the performance of the base model in common stationary benchmarks.
Authors: Inbal Mishal, Daphna Weinshall
Abstract: Deep Active Learning (AL) techniques can be effective in reducing annotation costs for training deep models. However, their effectiveness in low- and high-budget scenarios seems to require different strategies, and achieving optimal results across varying budget scenarios remains a challenge. In this study, we introduce Dynamic Coverage & Margin mix (DCoM), a novel active learning approach designed to bridge this gap. Unlike existing strategies, DCoM dynamically adjusts its strategy, considering the competence of the current model. Through theoretical analysis and empirical evaluations on diverse datasets, including challenging computer vision tasks, we demonstrate DCoM's ability to overcome the cold start problem and consistently improve results across different budgetary constraints. Thus DCoM achieves state-of-the-art performance in both low- and high-budget regimes.
Authors: Hoang Tran, Qinzi Zhang, Ashok Cutkosky
Abstract: There is a significant gap between our theoretical understanding of optimization algorithms used in deep learning and their practical performance. Theoretical development usually focuses on proving convergence guarantees under a variety of different assumptions, which are themselves often chosen based on a rough combination of intuitive match to practice and analytical convenience. The theory/practice gap may then arise because of the failure to prove a theorem under such assumptions, or because the assumptions do not reflect reality. In this paper, we carefully measure the degree to which these assumptions are capable of explaining modern optimization algorithms by developing new empirical metrics that closely track the key quantities that must be controlled in theoretical analysis. All of our tested assumptions (including typical modern assumptions based on bounds on the Hessian) fail to reliably capture optimization performance. This highlights a need for new empirical verification of analytical assumptions used in theoretical analysis.
Authors: Milad Saadat, Deepak Mangal, Safa Jamali
Abstract: The development of data-driven approaches for solving differential equations has been followed by a plethora of applications in science and engineering across a multitude of disciplines and remains a central focus of active scientific inquiry. However, a large body of natural phenomena incorporates memory effects that are best described via fractional integro-differential equations (FIDEs), in which the integral or differential operators accept non-integer orders. Addressing the challenges posed by nonlinear FIDEs is a recognized difficulty, necessitating the application of generic methods with immediate practical relevance. This work introduces the Universal Fractional Integro-Differential Equation Solvers (UniFIDES), a comprehensive machine learning platform designed to expeditiously solve a variety of FIDEs in both forward and inverse directions, without the need for ad hoc manipulation of the equations. The effectiveness of UniFIDES is demonstrated through a collection of integer-order and fractional problems in science and engineering. Our results highlight UniFIDES' ability to accurately solve a wide spectrum of integro-differential equations and offer the prospect of using machine learning platforms universally for discovering and describing dynamical and complex systems.
Authors: Xinxing Shi, Thomas Baldwin-McDonald, Mauricio A. \'Alvarez
Abstract: Deep Gaussian Processes (DGPs) leverage a compositional structure to model non-stationary processes. DGPs typically rely on local inducing point approximations across intermediate GP layers. Recent advances in DGP inference have shown that incorporating global Fourier features from Reproducing Kernel Hilbert Space (RKHS) can enhance the DGPs' capability to capture complex non-stationary patterns. This paper extends the use of these features to compositional GPs involving linear transformations. In particular, we introduce Ordinary Differential Equation (ODE) -based RKHS Fourier features that allow for adaptive amplitude and phase modulation through convolution operations. This convolutional formulation relates our work to recently proposed deep latent force models, a multi-layer structure designed for modelling nonlinear dynamical systems. By embedding these adjustable RKHS Fourier features within a doubly stochastic variational inference framework, our model exhibits improved predictive performance across various regression tasks.
Authors: Christopher Michael Ormerod, Alexander Kwako
Abstract: Current research on generative language models (GLMs) for automated text scoring (ATS) has focused almost exclusively on querying proprietary models via Application Programming Interfaces (APIs). Yet such practices raise issues around transparency and security, and these methods offer little in the way of efficiency or customizability. With the recent proliferation of smaller, open-source models, there is the option to explore GLMs with computers equipped with modest, consumer-grade hardware, that is, for the "GPU poor." In this study, we analyze the performance and efficiency of open-source, small-scale GLMs for ATS. Results show that GLMs can be fine-tuned to achieve adequate, though not state-of-the-art, performance. In addition to ATS, we take small steps towards analyzing models' capacity for generating feedback by prompting GLMs to explain their scores. Model-generated feedback shows promise, but requires more rigorous evaluation focused on targeted use cases.
Authors: Bowen Zhang, Zhichao Huang, Genan Dai, Guangning Xu, Xiaomao Fan, Hu Huang
Abstract: Graph classification is a pivotal challenge in machine learning, especially within the realm of graph-based data, given its importance in numerous real-world applications such as social network analysis, recommendation systems, and bioinformatics. Despite its significance, graph classification faces several hurdles, including adapting to diverse prediction tasks, training across multiple target domains, and handling small-sample prediction scenarios. Current methods often tackle these challenges individually, leading to fragmented solutions that lack a holistic approach to the overarching problem. In this paper, we propose an algorithm aimed at addressing the aforementioned challenges. By incorporating insights from various types of tasks, our method aims to enhance adaptability, scalability, and generalizability in graph classification. Motivated by the recognition that the underlying subgraph plays a crucial role in GNN prediction, while the remainder is task-irrelevant, we introduce the Core Knowledge Learning (\method{}) framework for graph adaptation and scalability learning. \method{} comprises several key modules, including the core subgraph knowledge submodule, graph domain adaptation module, and few-shot learning module for downstream tasks. Each module is tailored to tackle specific challenges in graph classification, such as domain shift, label inconsistencies, and data scarcity. By learning the core subgraph of the entire graph, we focus on the most pertinent features for task relevance. Consequently, our method offers benefits such as improved model performance, increased domain adaptability, and enhanced robustness to domain variations. Experimental results demonstrate significant performance enhancements achieved by our method compared to state-of-the-art approaches.
Authors: Fanzeng Xia, Hao Liu, Yisong Yue, Tongxin Li
Abstract: In-context decision-making is an important capability of artificial general intelligence, which Large Language Models (LLMs) have effectively demonstrated in various scenarios. However, LLMs often face challenges when dealing with numerical contexts, and limited attention has been paid to evaluating their performance through preference feedback generated by the environment. This paper investigates the performance of LLMs as decision-makers in the context of Dueling Bandits (DB). We first evaluate the performance of LLMs by comparing GPT-3.5-Turbo, GPT-4, and GPT-4-Turbo against established DB algorithms. Our results reveal that LLMs, particularly GPT-4 Turbo, quickly identify the Condorcet winner, thus outperforming existing state-of-the-art algorithms in terms of weak regret. Nevertheless, LLMs struggle to converge even when explicitly prompted to do so, and are sensitive to prompt variations. To overcome these issues, we introduce an LLM-augmented algorithm, IF-Enhanced LLM, which takes advantage of both in-context decision-making capabilities of LLMs and theoretical guarantees inherited from classic DB algorithms. The design of such an algorithm sheds light on how to enhance trustworthiness for LLMs used in decision-making tasks where performance robustness matters. We show that IF-Enhanced LLM has theoretical guarantees on both weak and strong regret. Our experimental results validate that IF-Enhanced LLM is robust even with noisy and adversarial prompts.
Authors: Calvin Luo, Mandy He, Zilai Zeng, Chen Sun
Abstract: Training an agent to achieve particular goals or perform desired behaviors is often accomplished through reinforcement learning, especially in the absence of expert demonstrations. However, supporting novel goals or behaviors through reinforcement learning requires the ad-hoc design of appropriate reward functions, which quickly becomes intractable. To address this challenge, we propose Text-Aware Diffusion for Policy Learning (TADPoLe), which uses a pretrained, frozen text-conditioned diffusion model to compute dense zero-shot reward signals for text-aligned policy learning. We hypothesize that large-scale pretrained generative models encode rich priors that can supervise a policy to behave not only in a text-aligned manner, but also in alignment with a notion of naturalness summarized from internet-scale training data. In our experiments, we demonstrate that TADPoLe is able to learn policies for novel goal-achievement and continuous locomotion behaviors specified by natural language, in both Humanoid and Dog environments. The behaviors are learned zero-shot without ground-truth rewards or expert demonstrations, and are qualitatively more natural according to human evaluation. We further show that TADPoLe performs competitively when applied to robotic manipulation tasks in the Meta-World environment.
Authors: Yongan Zhang (Celine), Zhongzhi Yu (Celine), Yonggan Fu (Celine), Cheng Wan (Celine), Yingyan (Celine), Lin
Abstract: Large Language Models (LLMs) have recently shown promise in streamlining hardware design processes by encapsulating vast amounts of domain-specific data. In addition, they allow users to interact with the design processes through natural language instructions, thus making hardware design more accessible to developers. However, effectively leveraging LLMs in hardware design necessitates providing domain-specific data during inference (e.g., through in-context learning), fine-tuning, or pre-training. Unfortunately, existing publicly available hardware datasets are often limited in size, complexity, or detail, which hinders the effectiveness of LLMs in hardware design tasks. To address this issue, we first propose a set of criteria for creating high-quality hardware datasets that can effectively enhance LLM-assisted hardware design. Based on these criteria, we propose a Multi-Grained-Verilog (MG-Verilog) dataset, which encompasses descriptions at various levels of detail and corresponding code samples. To benefit the broader hardware design community, we have developed an open-source infrastructure that facilitates easy access, integration, and extension of the dataset to meet specific project needs. Furthermore, to fully exploit the potential of the MG-Verilog dataset, which varies in complexity and detail, we introduce a balanced fine-tuning scheme. This scheme serves as a unique use case to leverage the diverse levels of detail provided by the dataset. Extensive experiments demonstrate that the proposed dataset and fine-tuning scheme consistently improve the performance of LLMs in hardware design tasks.
Authors: Yuwen Wang, Shunyu Liu, Tongya Zheng, Kaixuan Chen, Mingli Song
Abstract: Graph Neural Networks (GNNs) have emerged as a prominent framework for graph mining, leading to significant advances across various domains. Stemmed from the node-wise representations of GNNs, existing explanation studies have embraced the subgraph-specific viewpoint that attributes the decision results to the salient features and local structures of nodes. However, graph-level tasks necessitate long-range dependencies and global interactions for advanced GNNs, deviating significantly from subgraph-specific explanations. To bridge this gap, this paper proposes a novel intrinsically interpretable scheme for graph classification, termed as Global Interactive Pattern (GIP) learning, which introduces learnable global interactive patterns to explicitly interpret decisions. GIP first tackles the complexity of interpretation by clustering numerous nodes using a constrained graph clustering module. Then, it matches the coarsened global interactive instance with a batch of self-interpretable graph prototypes, thereby facilitating a transparent graph-level reasoning process. Extensive experiments conducted on both synthetic and real-world benchmarks demonstrate that the proposed GIP yields significantly superior interpretability and competitive performance to~the state-of-the-art counterparts. Our code will be made publicly available.
Authors: Kazumi Kasaura
Abstract: To find the shortest paths for all pairs on continuous manifolds with infinitesimally defined metrics, we propose to generate them by predicting midpoints recursively and an actor-critic method to learn midpoint prediction. We prove the soundness of our approach and show experimentally that the proposed method outperforms existing methods on both local and global path planning tasks.
Authors: Krishna Sri Ipsit Mantri, Xinzhi Wang, Carola-Bibiane Sch\"onlieb, Bruno Ribeiro, Beatrice Bevilacqua, Moshe Eliasof
Abstract: In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs). Motivated by the need for graph-adaptive and flexible activation functions, we introduce DiGRAF, leveraging Continuous Piecewise-Affine Based (CPAB) transformations, which we augment with an additional GNN to learn a graph-adaptive diffeomorphic activation function in an end-to-end manner. In addition to its graph-adaptivity and flexibility, DiGRAF also possesses properties that are widely recognized as desirable for activation functions, such as differentiability, boundness within the domain and computational efficiency. We conduct an extensive set of experiments across diverse datasets and tasks, demonstrating a consistent and superior performance of DiGRAF compared to traditional and graph-specific activation functions, highlighting its effectiveness as an activation function for GNNs.
Authors: Yonatan Sverdlov, Nadav Dym
Abstract: Motivated by applications in chemistry and other sciences, we study the expressive power of message-passing neural networks for geometric graphs, whose node features correspond to 3-dimensional positions. Recent work has shown that such models can separate generic pairs of non-equivalent geometric graphs, though they may fail to separate some rare and complicated instances. However, these results assume a fully connected graph, where each node possesses complete knowledge of all other nodes. In contrast, often, in application, every node only possesses knowledge of a small number of nearest neighbors. This paper shows that generic pairs of non-equivalent geometric graphs can be separated by message-passing networks with rotation equivariant features as long as the underlying graph is connected. When only invariant intermediate features are allowed, generic separation is guaranteed for generically globally rigid graphs. We introduce a simple architecture, EGENNET, which achieves our theoretical guarantees and compares favorably with alternative architecture on synthetic and chemical benchmarks.
Authors: Yali Fu, Jindong Li, Jiahong Liu, Qianli Xing, Qi Wang, Irwin King
Abstract: Unsupervised graph-level anomaly detection (UGAD) has garnered increasing attention in recent years due to its significance. However, most existing methods only rely on traditional graph neural networks to explore pairwise relationships but such kind of pairwise edges are not enough to describe multifaceted relationships involving anomaly. There is an emergency need to exploit node group information which plays a crucial role in UGAD. In addition, most previous works ignore the global underlying properties (e.g., hierarchy and power-law structure) which are common in real-world graph datasets and therefore are indispensable factors on UGAD task. In this paper, we propose a novel Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detection (HC-GLAD in short). To exploit node group connections, we construct hypergraphs based on gold motifs and subsequently perform hypergraph convolution. Furthermore, to preserve the hierarchy of real-world graphs, we introduce hyperbolic geometry into this field and conduct both graph and hypergraph embedding learning in hyperbolic space with hyperboloid model. To the best of our knowledge, this is the first work to simultaneously apply hypergraph with node group connections and hyperbolic geometry into this field. Extensive experiments on several real world datasets of different fields demonstrate the superiority of HC-GLAD on UGAD task. The code is available at https://github.com/Yali-F/HC-GLAD.
Authors: Jonathan Thomm, Michael Hersche, Giacomo Camposampiero, Aleksandar Terzi\'c, Bernhard Sch\"olkopf, Abbas Rahimi
Abstract: We advance the recently proposed neuro-symbolic Differentiable Tree Machine, which learns tree operations using a combination of transformers and Tensor Product Representations. We investigate the architecture and propose two key components. We first remove a series of different transformer layers that are used in every step by introducing a mixture of experts. This results in a Differentiable Tree Experts model with a constant number of parameters for any arbitrary number of steps in the computation, compared to the previous method in the Differentiable Tree Machine with a linear growth. Given this flexibility in the number of steps, we additionally propose a new termination algorithm to provide the model the power to choose how many steps to make automatically. The resulting Terminating Differentiable Tree Experts model sluggishly learns to predict the number of steps without an oracle. It can do so while maintaining the learning capabilities of the model, converging to the optimal amount of steps.
Authors: Johannes Meuer, Maximilian Witte, Claudia Timmreck, Thomas Ludwig, Christopher Kadow
Abstract: Obtaining accurate estimates of uncertainty in climate scenarios often requires generating large ensembles of high-resolution climate simulations, a computationally expensive and memory intensive process. To address this challenge, we train a novel generative deep learning approach on extensive sets of climate simulations. The model consists of two components: a variational autoencoder for dimensionality reduction and a denoising diffusion probabilistic model that generates multiple ensemble members. We validate our model on the Max Planck Institute Grand Ensemble and show that it achieves good agreement with the original ensemble in terms of variability. By leveraging the latent space representation, our model can rapidly generate large ensembles on-the-fly with minimal memory requirements, which can significantly improve the efficiency of uncertainty quantification in climate simulations.
Authors: Qi Guo, Minghao Yao, Zhen Tian, Saiyu Qi, Yong Qi, Yun Lin, Jin Song Dong
Abstract: Contribution evaluation in federated learning (FL) has become a pivotal research area due to its applicability across various domains, such as detecting low-quality datasets, enhancing model robustness, and designing incentive mechanisms. Existing contribution evaluation methods, which primarily rely on data volume, model similarity, and auxiliary test datasets, have shown success in diverse scenarios. However, their effectiveness often diminishes due to the heterogeneity of data distributions, presenting a significant challenge to their applicability. In response, this paper explores contribution evaluation in FL from an entirely new perspective of representation. In this work, we propose a new method for the contribution evaluation of heterogeneous participants in federated learning (FLCE), which introduces a novel indicator \emph{class contribution momentum} to conduct refined contribution evaluation. Our core idea is the construction and application of the class contribution momentum indicator from individual, relative, and holistic perspectives, thereby achieving an effective and efficient contribution evaluation of heterogeneous participants without relying on an auxiliary test dataset. Extensive experimental results demonstrate the superiority of our method in terms of fidelity, effectiveness, efficiency, and heterogeneity across various scenarios.
Authors: Gabriele Franch, Elena Tomasi, Rishabh Wanjari, Virginia Poli, Chiara Cardinali, Pier Paolo Alberoni, Marco Cristoforetti
Abstract: This work introduces GPTCast, a generative deep-learning method for ensemble nowcast of radar-based precipitation, inspired by advancements in large language models (LLMs). We employ a GPT model as a forecaster to learn spatiotemporal precipitation dynamics using tokenized radar images. The tokenizer is based on a Quantized Variational Autoencoder featuring a novel reconstruction loss tailored for the skewed distribution of precipitation that promotes faithful reconstruction of high rainfall rates. The approach produces realistic ensemble forecasts and provides probabilistic outputs with accurate uncertainty estimation. The model is trained without resorting to randomness, all variability is learned solely from the data and exposed by model at inference for ensemble generation. We train and test GPTCast using a 6-year radar dataset over the Emilia-Romagna region in Northern Italy, showing superior results compared to state-of-the-art ensemble extrapolation methods.
Authors: Shota Koshikawa, Aruto Hosaka, Tsuyoshi Yoshida
Abstract: To efficiently find an optimum parameter combination in a large-scale problem, it is a key to convert the parameters into available variables in actual machines. Specifically, quadratic unconstrained binary optimization problems are solved with the help of machine learning, e.g., factorization machines with annealing, which convert a raw parameter to binary variables. This work investigates the dependence of the convergence speed and the accuracy on binary labeling method, which can influence the cost function shape and thus the probability of being captured at a local minimum solution. By exemplifying traveling salesman problem, we propose and evaluate Gray labeling, which correlates the Hamming distance in binary labels with the traveling distance. Through numerical simulation of traveling salesman problem up to 15 cities at a limited number of iterations, the Gray labeling shows less local minima percentages and shorter traveling distances compared with natural labeling.
Authors: Lolitta Ammann, Jorge Martinez-Gil, Michael Mayr, Georgios C. Chasparis
Abstract: Industrial processes generate vast amounts of time series data, yet extracting meaningful relationships and insights remains challenging. This paper introduces a framework for automated knowledge graph learning from time series data, specifically tailored for industrial applications. Our framework addresses the complexities inherent in industrial datasets, transforming them into knowledge graphs that improve decision-making, process optimization, and knowledge discovery. Additionally, it employs Granger causality to identify key attributes that can inform the design of predictive models. To illustrate the practical utility of our approach, we also present a motivating use case demonstrating the benefits of our framework in a real-world industrial scenario. Further, we demonstrate how the automated conversion of time series data into knowledge graphs can identify causal influences or dependencies between important process parameters.
Authors: Andrej Tschalzev, Sascha Marton, Stefan L\"udtke, Christian Bartelt, Heiner Stuckenschmidt
Abstract: Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of model-centric evaluation setups with overly standardized data preprocessing. This paper demonstrates that such model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. Therefore, we propose a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. We conduct experiments with different preprocessing pipelines and hyperparameter optimization (HPO) regimes to quantify the impact of model selection, HPO, feature engineering, and test-time adaptation. Our main findings are: 1. After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces. 2. Recent models, despite their measurable progress, still significantly benefit from manual feature engineering. This holds true for both tree-based models and neural networks. 3. While tabular data is typically considered static, samples are often collected over time, and adapting to distribution shifts can be important even in supposedly static data. These insights suggest that research efforts should be directed toward a data-centric perspective, acknowledging that tabular data requires feature engineering and often exhibits temporal characteristics.
Authors: Yifang Chen, Shuohang Wang, Ziyi Yang, Hiteshi Sharma, Nikos Karampatziakis, Donghan Yu, Kevin Jamieson, Simon Shaolei Du, Yelong Shen
Abstract: Reinforcement learning with human feedback (RLHF), as a widely adopted approach in current large language model pipelines, is \textit{bottlenecked by the size of human preference data}. While traditional methods rely on offline preference dataset constructions, recent approaches have shifted towards online settings, where a learner uses a small amount of labeled seed data and a large pool of unlabeled prompts to iteratively construct new preference data through self-generated responses and high-quality reward/preference feedback. However, most current online algorithms still focus on preference labeling during policy model updating with given feedback oracles, which incurs significant expert query costs. \textit{We are the first to explore cost-effective proxy reward oracles construction strategies for further labeling preferences or rewards with extremely limited labeled data and expert query budgets}. Our approach introduces two key innovations: (1) on-policy query to avoid OOD and imbalance issues in seed data, and (2) active learning to select the most informative data for preference queries. Using these methods, we train a evaluation model with minimal expert-labeled data, which then effectively labels nine times more preference pairs for further RLHF training. For instance, our model using Direct Preference Optimization (DPO) gains around over 1% average improvement on AlpacaEval2, MMLU-5shot and MMLU-0shot, with only 1.7K query cost. Our methodology is orthogonal to other direct expert query-based strategies and therefore might be integrated with them to further reduce query costs.
Authors: Chunjing Xiao, Shikang Pang, Xovee Xu, Xuan Li, Goce Trajcevski, Fan Zhou
Abstract: A critical aspect of Graph Neural Networks (GNNs) is to enhance the node representations by aggregating node neighborhood information. However, when detecting anomalies, the representations of abnormal nodes are prone to be averaged by normal neighbors, making the learned anomaly representations less distinguishable. To tackle this issue, we propose CAGAD -- an unsupervised Counterfactual data Augmentation method for Graph Anomaly Detection -- which introduces a graph pointer neural network as the heterophilic node detector to identify potential anomalies whose neighborhoods are normal-node-dominant. For each identified potential anomaly, we design a graph-specific diffusion model to translate a part of its neighbors, which are probably normal, into anomalous ones. At last, we involve these translated neighbors in GNN neighborhood aggregation to produce counterfactual representations of anomalies. Through aggregating the translated anomalous neighbors, counterfactual representations become more distinguishable and further advocate detection performance. The experimental results on four datasets demonstrate that CAGAD significantly outperforms strong baselines, with an average improvement of 2.35% on F1, 2.53% on AUC-ROC, and 2.79% on AUC-PR.
Authors: Simone Appella, Simon Arridge, Chris Budd, Teo Deveney, Lisa Maria Kreusser
Abstract: We consider the problem of one-dimensional function approximation using shallow neural networks (NN) with a rectified linear unit (ReLU) activation function and compare their training with traditional methods such as univariate Free Knot Splines (FKS). ReLU NNs and FKS span the same function space, and thus have the same theoretical expressivity. In the case of ReLU NNs, we show that their ill-conditioning degrades rapidly as the width of the network increases. This often leads to significantly poorer approximation in contrast to the FKS representation, which remains well-conditioned as the number of knots increases. We leverage the theory of optimal piecewise linear interpolants to improve the training procedure for a ReLU NN. Using the equidistribution principle, we propose a two-level procedure for training the FKS by first solving the nonlinear problem of finding the optimal knot locations of the interpolating FKS. Determining the optimal knots then acts as a good starting point for training the weights of the FKS. The training of the FKS gives insights into how we can train a ReLU NN effectively to give an equally accurate approximation. More precisely, we combine the training of the ReLU NN with an equidistribution based loss to find the breakpoints of the ReLU functions, combined with preconditioning the ReLU NN approximation (to take an FKS form) to find the scalings of the ReLU functions, leads to a well-conditioned and reliable method of finding an accurate ReLU NN approximation to a target function. We test this method on a series or regular, singular, and rapidly varying target functions and obtain good results realising the expressivity of the network in this case.
Authors: Shuaike Xu, Xiaolin Zhang, Peng Zhang, Kun Zhan
Abstract: Graph node classification with few labeled nodes presents significant challenges due to limited supervision. Conventional methods often exploit the graph in a transductive learning manner. They fail to effectively utilize the abundant unlabeled data and the structural information inherent in graphs. To address these issues, we introduce a Structure-Aware Consensus Network (SACN) from three perspectives. Firstly, SACN leverages a novel structure-aware consensus learning strategy between two strongly augmented views. The proposed strategy can fully exploit the potentially useful information of the unlabeled nodes and the structural information of the entire graph. Secondly, SACN uniquely integrates the graph's structural information to achieve strong-to-strong consensus learning, improving the utilization of unlabeled data while maintaining multiview learning. Thirdly, unlike two-branch graph neural network-based methods, SACN is designed for multiview feature learning within a single-branch architecture. Furthermore, a class-aware pseudolabel selection strategy helps address class imbalance and achieve effective weak-to-strong supervision. Extensive experiments on three benchmark datasets demonstrate SACN's superior performance in node classification tasks, particularly at very low label rates, outperforming state-of-the-art methods while maintaining computational simplicity.The source code is available at https://github.com/kunzhan/SACN
Authors: Bogdan Kulynych, Juan Felipe Gomez, Georgios Kaissis, Flavio du Pin Calmon, Carmela Troncoso
Abstract: Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the added noise is critical, as it determines the trade-off between privacy and utility. The standard practice is to select the noise scale in terms of a privacy budget parameter $\epsilon$. This parameter is in turn interpreted in terms of operational attack risk, such as accuracy, or sensitivity and specificity of inference attacks against the privacy of the data. We demonstrate that this two-step procedure of first calibrating the noise scale to a privacy budget $\epsilon$, and then translating $\epsilon$ to attack risk leads to overly conservative risk assessments and unnecessarily low utility. We propose methods to directly calibrate the noise scale to a desired attack risk level, bypassing the intermediate step of choosing $\epsilon$. For a target attack risk, our approach significantly decreases noise scale, leading to increased utility at the same level of privacy. We empirically demonstrate that calibrating noise to attack sensitivity/specificity, rather than $\epsilon$, when training privacy-preserving ML models substantially improves model accuracy for the same risk level. Our work provides a principled and practical way to improve the utility of privacy-preserving ML without compromising on privacy.
Authors: Zakariae El Asri, Olivier Sigaud, Nicolas Thome
Abstract: Applying reinforcement learning (RL) to real-world applications requires addressing a trade-off between asymptotic performance, sample efficiency, and inference time. In this work, we demonstrate how to address this triple challenge by leveraging partial physical knowledge about the system dynamics. Our approach involves learning a physics-informed model to boost sample efficiency and generating imaginary trajectories from this model to learn a model-free policy and Q-function. Furthermore, we propose a hybrid planning strategy, combining the learned policy and Q-function with the learned model to enhance time efficiency in planning. Through practical demonstrations, we illustrate that our method improves the compromise between sample efficiency, time efficiency, and performance over state-of-the-art methods.
Authors: Odelia Melamed, Gilad Yehudai, Adi Shamir
Abstract: Current adversarial attacks for multi-class classifiers choose the target class for a given input naively, based on the classifier's confidence levels for various target classes. We present a novel adversarial targeting method, \textit{MALT - Mesoscopic Almost Linearity Targeting}, based on medium-scale almost linearity assumptions. Our attack wins over the current state of the art AutoAttack on the standard benchmark datasets CIFAR-100 and ImageNet and for a variety of robust models. In particular, our attack is \emph{five times faster} than AutoAttack, while successfully matching all of AutoAttack's successes and attacking additional samples that were previously out of reach. We then prove formally and demonstrate empirically that our targeting method, although inspired by linear predictors, also applies to standard non-linear models.
Authors: Jiaxu Tian, Fan Lyu
Abstract: Continual Test-Time Adaptation (CTTA) aims to adapt a pretrained model to ever-changing environments during the test time under continuous domain shifts. Most existing CTTA approaches are based on the Mean Teacher (MT) structure, which contains a student and a teacher model, where the student is updated using the pseudo-labels from the teacher model, and the teacher is then updated by exponential moving average strategy. However, these methods update the MT model indiscriminately on all parameters of the model. That is, some critical parameters involving sharing knowledge across different domains may be erased, intensifying error accumulation and catastrophic forgetting. In this paper, we introduce Parameter-Selective Mean Teacher (PSMT) method, which is capable of effectively updating the critical parameters within the MT network under domain shifts. First, we introduce a selective distillation mechanism in the student model, which utilizes past knowledge to regularize novel knowledge, thereby mitigating the impact of error accumulation. Second, to avoid catastrophic forgetting, in the teacher model, we create a mask through Fisher information to selectively update parameters via exponential moving average, with preservation measures applied to crucial parameters. Extensive experimental results verify that PSMT outperforms state-of-the-art methods across multiple benchmark datasets. Our code is available at \url{https://github.com/JiaxuTian/PSMT}.
Authors: Simen Kristoffersen, Peter Skaar Nordby, Sara Malacarne, Massimiliano Ruocco, Pablo Ortiz
Abstract: We introduce SiamTST, a novel representation learning framework for multivariate time series. SiamTST integrates a Siamese network with attention, channel-independent patching, and normalization techniques to achieve superior performance. Evaluated on a real-world industrial telecommunication dataset, SiamTST demonstrates significant improvements in forecasting accuracy over existing methods. Notably, a simple linear network also shows competitive performance, achieving the second-best results, just behind SiamTST. The code is available at https://github.com/simenkristoff/SiamTST.
Authors: Shihao Shao, Haoran Geng, Qinghua Cui
Abstract: The Clebsch-Gordan Transform (CG transform) effectively encodes many-body interactions. Many studies have proven its accuracy in depicting atomic environments, although this comes with high computational needs. The computational burden of this challenge is hard to reduce due to the need for permutation equivariance, which limits the design space of the CG transform layer. We show that, implementing the CG transform layer on permutation-invariant inputs allows complete freedom in the design of this layer without affecting symmetry. Developing further on this premise, our idea is to create a CG transform layer that operates on permutation-invariant abstract edges generated from real edge information. We bring in group CG transform with sparse path, abstract edges shuffling, and attention enhancer to form a powerful and efficient CG transform layer. Our method, known as FreeCG, achieves State-of-The-Art (SoTA) results in force prediction for MD17, rMD17, MD22, and property prediction in QM9 datasets with notable enhancement. It introduces a novel paradigm for carrying out efficient and expressive CG transform in future geometric neural network designs.
Authors: Yingzhou Lu, Yaojun Hu, Chenhao Li
Abstract: Bringing a novel drug from the original idea to market typically requires more than ten years and billions of dollars. To alleviate the heavy burden, a natural idea is to reuse the approved drug to treat new diseases. The process is also known as drug repurposing or drug repositioning. Machine learning methods exhibited huge potential in automating drug repurposing. However, it still encounter some challenges, such as lack of labels and multimodal feature representation. To address these issues, we design DrugCLIP, a cutting-edge contrastive learning method, to learn drug and disease's interaction without negative labels. Additionally, we have curated a drug repurposing dataset based on real-world clinical trial records. Thorough empirical studies are conducted to validate the effectiveness of the proposed DrugCLIP method.
Authors: Hilarie Sit, Brendan Keith, Karianne Bergen
Abstract: We propose a prototype-based approach for improving explainability of softmax classifiers that provides an understandable prediction confidence, generated through stochastic sampling of prototypes, and demonstrates potential for out of distribution detection (OOD). By modifying the model architecture and training to make predictions using similarities to any set of class examples from the training dataset, we acquire the ability to sample for prototypical examples that contributed to the prediction, which provide an instance-based explanation for the model's decision. Furthermore, by learning relationships between images from the training dataset through relative distances within the model's latent space, we obtain a metric for uncertainty that is better able to detect out of distribution data than softmax confidence.
Authors: Michael Mayr, Georgios C. Chasparis, Josef K\"ung
Abstract: Central to the digital transformation of the process industry are Digital Twins (DTs), virtual replicas of physical manufacturing systems that combine sensor data with sophisticated data-based or physics-based models, or a combination thereof, to tackle a variety of industrial-relevant tasks like process monitoring, predictive control or decision support. The backbone of a DT, i.e. the concrete modelling methodologies and architectural frameworks supporting these models, are complex, diverse and evolve fast, necessitating a thorough understanding of the latest state-of-the-art methods and trends to stay on top of a highly competitive market. From a research perspective, despite the high research interest in reviewing various aspects of DTs, structured literature reports specifically focusing on unravelling the utilized learning paradigms (e.g. self-supervised learning) for DT-creation in the process industry are a novel contribution in this field. This study aims to address these gaps by (1) systematically analyzing the modelling methodologies (e.g. Convolutional Neural Network, Encoder-Decoder, Hidden Markov Model) and paradigms (e.g. data-driven, physics-based, hybrid) used for DT-creation; (2) assessing the utilized learning strategies (e.g. supervised, unsupervised, self-supervised); (3) analyzing the type of modelling task (e.g. regression, classification, clustering); and (4) identifying the challenges and research gaps, as well as, discuss potential resolutions provided.
Authors: Richard Nock, Yishay Mansour
Abstract: Boosting is a highly successful ML-born optimization setting in which one is required to computationally efficiently learn arbitrarily good models based on the access to a weak learner oracle, providing classifiers performing at least slightly differently from random guessing. A key difference with gradient-based optimization is that boosting's original model does not requires access to first order information about a loss, yet the decades long history of boosting has quickly evolved it into a first order optimization setting -- sometimes even wrongfully \textit{defining} it as such. Owing to recent progress extending gradient-based optimization to use only a loss' zeroth ($0^{th}$) order information to learn, this begs the question: what loss functions can be efficiently optimized with boosting and what is the information really needed for boosting to meet the \textit{original} boosting blueprint's requirements? We provide a constructive formal answer essentially showing that \textit{any} loss function can be optimized with boosting and thus boosting can achieve a feat not yet known to be possible in the classical $0^{th}$ order setting, since loss functions are not required to be be convex, nor differentiable or Lipschitz -- and in fact not required to be continuous either. Some tools we use are rooted in quantum calculus, the mathematical field -- not to be confounded with quantum computation -- that studies calculus without passing to the limit, and thus without using first order information.
Authors: Adrien Schertzer, Loucas Pillaud-Vivien
Abstract: We study the dynamics of a continuous-time model of the Stochastic Gradient Descent (SGD) for the least-square problem. Indeed, pursuing the work of Li et al. (2019), we analyze Stochastic Differential Equations (SDEs) that model SGD either in the case of the training loss (finite samples) or the population one (online setting). A key qualitative feature of the dynamics is the existence of a perfect interpolator of the data, irrespective of the sample size. In both scenarios, we provide precise, non-asymptotic rates of convergence to the (possibly degenerate) stationary distribution. Additionally, we describe this asymptotic distribution, offering estimates of its mean, deviations from it, and a proof of the emergence of heavy-tails related to the step-size magnitude. Numerical simulations supporting our findings are also presented.
Authors: Juntao Zhao, Borui Wan, Yanghua Peng, Haibin Lin, Yibo Zhu, Chuan Wu
Abstract: A number of production deep learning clusters have attempted to explore inference hardware for DNN training, at the off-peak serving hours with many inference GPUs idling. Conducting DNN training with a combination of heterogeneous training and inference GPUs, known as hybrid device training, presents considerable challenges due to disparities in compute capability and significant differences in memory capacity. We propose QSync, a training system that enables efficient synchronous data-parallel DNN training over hybrid devices by strategically exploiting quantized operators. According to each device's available resource capacity, QSync selects a quantization-minimized setting for operators in the distributed DNN training graph, minimizing model accuracy degradation but keeping the training efficiency brought by quantization. We carefully design a predictor with a bi-directional mixed-precision indicator to reflect the sensitivity of DNN layers on fixed-point and floating-point low-precision operators, a replayer with a neighborhood-aware cost mapper to accurately estimate the latency of distributed hybrid mixed-precision training, and then an allocator that efficiently synchronizes workers with minimized model accuracy degradation. QSync bridges the computational graph on PyTorch to an optimized backend for quantization kernel performance and flexible support for various GPU architectures. Extensive experiments show that QSync's predictor can accurately simulate distributed mixed-precision training with <5% error, with a consistent 0.27-1.03% accuracy improvement over the from-scratch training tasks compared to uniform precision.
Authors: Lorenzo S. Querol, Hajime Nagahara, Hideaki Hayashi
Abstract: The growing use of deep learning in safety-critical applications, such as medical imaging, has raised concerns about limited labeled data, where this demand is amplified as model complexity increases, posing hurdles for domain experts to annotate data. In response to this, active learning (AL) is used to efficiently train models with limited annotation costs. In the context of deep neural networks (DNNs), AL often uses confidence or probability outputs as a score for selecting the most informative samples. However, modern DNNs exhibit unreliable confidence outputs, making calibration essential. We propose an AL framework that self-calibrates the confidence used for sample selection during the training process, referred to as Confident Active Learning with Integrated CalibratiOn (CALICO). CALICO incorporates the joint training of a classifier and an energy-based model, instead of the standard softmax-based classifier. This approach allows for simultaneous estimation of the input data distribution and the class probabilities during training, improving calibration without needing an additional labeled dataset. Experimental results showcase improved classification performance compared to a softmax-based classifier with fewer labeled samples. Furthermore, the calibration stability of the model is observed to depend on the prior class distribution of the data.
Authors: Wenhua Wang, Qiong Wu, Pingyi Fan, Nan Cheng, Wen Chen, Jiangzhou Wang, Khaled B. Letaief
Abstract: With the rapid development of intelligent vehicles and Intelligent Transport Systems (ITS), the sensors such as cameras and LiDAR installed on intelligent vehicles provides higher capacity of executing computation-intensive and delay-sensitive tasks, thereby raising deployment costs. To address this issue, Vehicular Edge Computing (VEC) has been proposed to process data through Road Side Units (RSUs) to support real-time applications. This paper focuses on the Age of Information (AoI) as a key metric for data freshness and explores task offloading issues for vehicles under RSU communication resource constraints. We adopt a Multi-agent Deep Reinforcement Learning (MADRL) approach, allowing vehicles to autonomously make optimal data offloading decisions. However, MADRL poses risks of vehicle information leakage during communication learning and centralized training. To mitigate this, we employ a Federated Learning (FL) framework that shares model parameters instead of raw data to protect the privacy of vehicle users. Building on this, we propose an innovative distributed federated learning framework combining Graph Neural Networks (GNN), named Federated Graph Neural Network Multi-Agent Reinforcement Learning (FGNN-MADRL), to optimize AoI across the system. For the first time, road scenarios are constructed as graph data structures, and a GNN-based federated learning framework is proposed, effectively combining distributed and centralized federated aggregation. Furthermore, we propose a new MADRL algorithm that simplifies decision making and enhances offloading efficiency, further reducing the decision complexity. Simulation results demonstrate the superiority of our proposed approach to other methods through simulations.
Authors: Steven Kolawole, Don Dennis, Ameet Talwalkar, Virginia Smith
Abstract: A common approach to make machine learning inference more efficient is to use example-specific adaptive schemes, which route or select models for each example at inference time. In this work we study a simple scheme for adaptive inference. We build a cascade of ensembles (CoE), beginning with resource-efficient models and growing to larger, more expressive models, where ensemble agreement serves as a data-dependent routing criterion. This scheme is easy to incorporate into existing inference pipelines, requires no additional training, and can be used to place models across multiple resource tiers--for instance, serving efficient models at the edge and invoking larger models in the cloud only when necessary. In cases where parallel inference is feasible, we show that CoE can improve accuracy relative to the single best model while reducing the average cost of inference by up to 7x, and provides Pareto-dominate solutions in accuracy and efficiency relative to existing adaptive inference baselines. These savings translate to an over 3x-reduction in total monetary cost when performing inference using a heterogeneous cluster of GPUs. Finally, for edge inference scenarios where portions of the cascade reside at the edge vs. in the cloud, CoE can provide a 14x reduction in communication cost and inference latency without sacrificing accuracy.
Authors: Antony Vijesh, Shreyas S R
Abstract: Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical advantages over existing methods. This paper proposes a novel off-policy two-step Q-learning algorithms, without importance sampling. With suitable assumption it was shown that, iterates in the proposed two-step Q-learning is bounded and converges almost surely to the optimal Q-values. This study also address the convergence analysis of the smooth version of two-step Q-learning, i.e., by replacing max function with the log-sum-exp function. The proposed algorithms are robust and easy to implement. Finally, we test the proposed algorithms on benchmark problems such as the roulette problem, maximization bias problem, and randomly generated Markov decision processes and compare it with the existing methods available in literature. Numerical experiments demonstrate the superior performance of both the two-step Q-learning and its smooth variants.
Authors: Nikhil Khatri, Tuomas Laakkonen, Jonathon Liu, Vincent Wang-Ma\'scianica
Abstract: We introduce a category-theoretic diagrammatic formalism in order to systematically relate and reason about machine learning models. Our diagrams present architectures intuitively but without loss of essential detail, where natural relationships between models are captured by graphical transformations, and important differences and similarities can be identified at a glance. In this paper, we focus on attention mechanisms: translating folklore into mathematical derivations, and constructing a taxonomy of attention variants in the literature. As a first example of an empirical investigation underpinned by our formalism, we identify recurring anatomical components of attention, which we exhaustively recombine to explore a space of variations on the attention mechanism.
Authors: Benjamin Rodatz, Ian Fan, Tuomas Laakkonen, Neil John Ortega, Thomas Hoffman, Vincent Wang-Mascianica
Abstract: Idealised as universal approximators, learners such as neural networks can be viewed as "variable functions" that may become one of a range of concrete functions after training. In the same way that equations constrain the possible values of variables in algebra, we may view objective functions as constraints on the behaviour of learners. We extract the equivalences perfectly optimised objective functions impose, calling them "tasks". For these tasks, we develop a formal graphical language that allows us to: (1) separate the core tasks of a behaviour from its implementation details; (2) reason about and design behaviours model-agnostically; and (3) simply describe and unify approaches in machine learning across domains. As proof-of-concept, we design a novel task that enables converting classifiers into generative models we call "manipulators", which we implement by directly translating task specifications into code. The resulting models exhibit capabilities such as style transfer and interpretable latent-space editing, without the need for custom architectures, adversarial training or random sampling. We formally relate the behaviour of manipulators to GANs, and empirically demonstrate their competitive performance with VAEs. We report on experiments across vision and language domains aiming to characterise manipulators as approximate Bayesian inversions of discriminative classifiers.
Authors: Yuxuan Zhu, Michael Mandulak, Kerui Wu, George Slota, Yuseok Jeon, Ka-Ho Chow, Lei Yu
Abstract: Graph Neural Networks (GNNs) are gaining popularity across various domains due to their effectiveness in learning graph-structured data. Nevertheless, they have been shown to be susceptible to backdoor poisoning attacks, which pose serious threats to real-world applications. Meanwhile, graph reduction techniques, including coarsening and sparsification, which have long been employed to improve the scalability of large graph computational tasks, have recently emerged as effective methods for accelerating GNN training on large-scale graphs. However, the current development and deployment of graph reduction techniques for large graphs overlook the potential risks of data poisoning attacks against GNNs. It is not yet clear how graph reduction interacts with existing backdoor attacks. This paper conducts a thorough examination of the robustness of graph reduction methods in scalable GNN training in the presence of state-of-the-art backdoor attacks. We performed a comprehensive robustness analysis across six coarsening methods and six sparsification methods for graph reduction, under three GNN backdoor attacks against three GNN architectures. Our findings indicate that the effectiveness of graph reduction methods in mitigating attack success rates varies significantly, with some methods even exacerbating the attacks. Through detailed analyses of triggers and poisoned nodes, we interpret our findings and enhance our understanding of how graph reduction interacts with backdoor attacks. These results highlight the critical need for incorporating robustness considerations in graph reduction for GNN training, ensuring that enhancements in computational efficiency do not compromise the security of GNN systems.
Authors: Yu Zhe, Jun Sakuma
Abstract: The widespread use of personal data for training machine learning models raises significant privacy concerns, as individuals have limited control over how their public data is subsequently utilized. Availability attacks have emerged as a means for data owners to safeguard their data by desning imperceptible perturbations that degrade model performance when incorporated into training datasets. However, existing availability attacks exhibit limitations in practical applicability, particularly when only a portion of the data can be perturbed. To address this challenge, we propose a novel availability attack approach termed Parameter Matching Attack (PMA). PMA is the first availability attack that works when only a portion of data can be perturbed. PMA optimizes perturbations so that when the model is trained on a mixture of clean and perturbed data, the resulting model will approach a model designed to perform poorly. Experimental results across four datasets demonstrate that PMA outperforms existing methods, achieving significant model performance degradation when a part of the training data is perturbed. Our code is available in the supplementary.
Authors: Anshul Nasery, Jonathan Hayase, Pang Wei Koh, Sewoong Oh
Abstract: The democratization of machine learning systems has made the process of fine-tuning accessible to a large number of practitioners, leading to a wide range of open-source models fine-tuned on specialized tasks and datasets. Recent work has proposed to merge such models to combine their functionalities. However, prior approaches are restricted to models that are fine-tuned from the same base model. Furthermore, the final merged model is typically restricted to be of the same size as the original models. In this work, we propose a new two-step algorithm to merge models-termed PLeaS-which relaxes these constraints. First, leveraging the Permutation symmetries inherent in the two models, PLeaS partially matches nodes in each layer by maximizing alignment. Next, PLeaS computes the weights of the merged model as a layer-wise Least Squares solution to minimize the approximation error between the features of the merged model and the permuted features of the original models. into a single model of a desired size, even when the two original models are fine-tuned from different base models. We also present a variant of our method which can merge models without using data from the fine-tuning domains. We demonstrate our method to merge ResNet models trained with shared and different label spaces, and show that we can perform better than the state-of-the-art merging methods by 8 to 15 percentage points for the same target compute while merging models trained on DomainNet and on fine-grained classification tasks.
Authors: Ignat Georgiev, Varun Giridhar, Nicklas Hansen, Animesh Garg
Abstract: Reinforcement Learning (RL) has achieved impressive results on complex tasks but struggles in multi-task settings with different embodiments. World models offer scalability by learning a simulation of the environment, yet they often rely on inefficient gradient-free optimization methods. We introduce Policy learning with large World Models (PWM), a novel model-based RL algorithm that learns continuous control policies from large multi-task world models. By pre-training the world model on offline data and using it for first-order gradient policy learning, PWM effectively solves tasks with up to 152 action dimensions and outperforms methods using ground-truth dynamics. Additionally, PWM scales to an 80-task setting, achieving up to 27% higher rewards than existing baselines without the need for expensive online planning. Visualizations and code available at https://policy-world-model.github.io
Authors: Xiaoyu Jiang, Sokratia Georgaka, Magnus Rattray, Mauricio A. Alvarez
Abstract: The Multi-Output Gaussian Process is is a popular tool for modelling data from multiple sources. A typical choice to build a covariance function for a MOGP is the Linear Model of Coregionalization (LMC) which parametrically models the covariance between outputs. The Latent Variable MOGP (LV-MOGP) generalises this idea by modelling the covariance between outputs using a kernel applied to latent variables, one per output, leading to a flexible MOGP model that allows efficient generalization to new outputs with few data points. Computational complexity in LV-MOGP grows linearly with the number of outputs, which makes it unsuitable for problems with a large number of outputs. In this paper, we propose a stochastic variational inference approach for the LV-MOGP that allows mini-batches for both inputs and outputs, making computational complexity per training iteration independent of the number of outputs.
Authors: Jingyun Yang, Congyue Deng, Jimmy Wu, Rika Antonova, Leonidas Guibas, Jeannette Bohg
Abstract: If a robot masters folding a kitchen towel, we would expect it to master folding a large beach towel. However, existing policy learning methods that rely on data augmentation still don't guarantee such generalization. Our insight is to add equivariance to both the visual object representation and policy architecture. We propose EquivAct which utilizes SIM(3)-equivariant network structures that guarantee generalization across all possible object translations, 3D rotations, and scales by construction. EquivAct is trained in two phases. We first pre-train a SIM(3)-equivariant visual representation on simulated scene point clouds. Then, we learn a SIM(3)-equivariant visuomotor policy using a small amount of source task demonstrations. We show that the learned policy directly transfers to objects that substantially differ from demonstrations in scale, position, and orientation. We evaluate our method in three manipulation tasks involving deformable and articulated objects, going beyond typical rigid object manipulation tasks considered in prior work. We conduct experiments both in simulation and in reality. For real robot experiments, our method uses 20 human demonstrations of a tabletop task and transfers zero-shot to a mobile manipulation task in a much larger setup. Experiments confirm that our contrastive pre-training procedure and equivariant architecture offer significant improvements over prior work. Project website: https://equivact.github.io
Authors: Jingyun Yang, Zi-ang Cao, Congyue Deng, Rika Antonova, Shuran Song, Jeannette Bohg
Abstract: Building effective imitation learning methods that enable robots to learn from limited data and still generalize across diverse real-world environments is a long-standing problem in robot learning. We propose EquiBot, a robust, data-efficient, and generalizable approach for robot manipulation task learning. Our approach combines SIM(3)-equivariant neural network architectures with diffusion models. This ensures that our learned policies are invariant to changes in scale, rotation, and translation, enhancing their applicability to unseen environments while retaining the benefits of diffusion-based policy learning such as multi-modality and robustness. We show in a suite of 6 simulation tasks that our proposed method reduces the data requirements and improves generalization to novel scenarios. In the real world, we show with in total 10 variations of 6 mobile manipulation tasks that our method can easily generalize to novel objects and scenes after learning from just 5 minutes of human demonstrations in each task.
Authors: Hongjie Xu, Yunzhuang Shen, Yuan Sun, Xiaodong Li
Abstract: Column generation (CG) is a powerful technique for solving optimization problems that involve a large number of variables or columns. This technique begins by solving a smaller problem with a subset of columns and gradually generates additional columns as needed. However, the generation of columns often requires solving difficult subproblems repeatedly, which can be a bottleneck for CG. To address this challenge, we propose a novel method called machine learning enhanced ant colony optimization (MLACO), to efficiently generate multiple high-quality columns from a subproblem. Specifically, we train a ML model to predict the optimal solution of a subproblem, and then integrate this ML prediction into the probabilistic model of ACO to sample multiple high-quality columns. Our experimental results on the bin packing problem with conflicts show that the MLACO method significantly improves the performance of CG compared to several state-of-the-art methods. Furthermore, when our method is incorporated into a Branch-and-Price method, it leads to a significant reduction in solution time.
Authors: Minglu Zhao, Dehong Xu, Tao Gao
Abstract: Attention is a cornerstone of human cognition that facilitates the efficient extraction of information in everyday life. Recent developments in artificial intelligence like the Transformer architecture also incorporate the idea of attention in model designs. However, despite the shared fundamental principle of selectively attending to information, human attention and the Transformer model display notable differences, particularly in their capacity constraints, attention pathways, and intentional mechanisms. Our review aims to provide a comparative analysis of these mechanisms from a cognitive-functional perspective, thereby shedding light on several open research questions. The exploration encourages interdisciplinary efforts to derive insights from human attention mechanisms in the pursuit of developing more generalized artificial intelligence.
Authors: Alexander Denker, Zeljko Kereta, Imraj Singh, Tom Freudenberg, Tobias Kluth, Peter Maass, Simon Arridge
Abstract: Electrical impedance tomography (EIT) plays a crucial role in non-invasive imaging, with both medical and industrial applications. In this paper, we present three data-driven reconstruction methods for EIT imaging. These three approaches were originally submitted to the Kuopio tomography challenge 2023 (KTC2023). First, we introduce a post-processing approach, which achieved first place at KTC2023. Further, we present a fully learned and a conditional diffusion approach. All three methods are based on a similar neural network as a backbone and were trained using a synthetically generated data set, providing with an opportunity for a fair comparison of these different data-driven reconstruction methods.
Authors: Tim Johnsen, Marco Levorato
Abstract: Small-scale autonomous airborne vehicles, such as micro-drones, are expected to be a central component of a broad spectrum of applications ranging from exploration to surveillance and delivery. This class of vehicles is characterized by severe constraints in computing power and energy reservoir, which impairs their ability to support the complex state-of-the-art neural models needed for autonomous operations. The main contribution of this paper is a new class of neural navigation models -- NaviSlim -- capable of adapting the amount of resources spent on computing and sensing in response to the current context (i.e., difficulty of the environment, current trajectory, and navigation goals). Specifically, NaviSlim is designed as a gated slimmable neural network architecture that, different from existing slimmable networks, can dynamically select a slimming factor to autonomously scale model complexity, which consequently optimizes execution time and energy consumption. Moreover, different from existing sensor fusion approaches, NaviSlim can dynamically select power levels of onboard sensors to autonomously reduce power and time spent during sensor acquisition, without the need to switch between different neural networks. By means of extensive training and testing on the robust simulation environment Microsoft AirSim, we evaluate our NaviSlim models on scenarios with varying difficulty and a test set that showed a dynamic reduced model complexity on average between 57-92%, and between 61-80% sensor utilization, as compared to static neural networks designed to match computing and sensing of that required by the most difficult scenario.
Authors: Fran\c{c}ois Bachoc, Tommaso Cesari, Roberto Colomboni
Abstract: We study the role of contextual information in the online learning problem of brokerage between traders. At each round, two traders arrive with secret valuations about an asset they wish to trade. The broker suggests a trading price based on contextual data about the asset. Then, the traders decide to buy or sell depending on whether their valuations are higher or lower than the brokerage price. We assume the market value of traded assets is an unknown linear function of a $d$-dimensional vector representing the contextual information available to the broker. Additionally, we model traders' valuations as independent bounded zero-mean perturbations of the asset's market value, allowing for potentially different unknown distributions across traders and time steps. Consistently with the existing online learning literature, we evaluate the performance of a learning algorithm with the regret with respect to the gain from trade. If the noise distributions admit densities bounded by some constant $L$, then, for any time horizon $T$: - If the agents' valuations are revealed after each interaction, we provide an algorithm achieving $O ( L d \ln T )$ regret, and show a corresponding matching lower bound of $\Omega( Ld \ln T )$. - If only their willingness to sell or buy at the proposed price is revealed after each interaction, we provide an algorithm achieving $O(\sqrt{LdT \ln T })$ regret, and show that this rate is optimal (up to logarithmic factors), via a lower bound of $\Omega(\sqrt{LdT})$. To complete the picture, we show that if the bounded density assumption is lifted, then the problem becomes unlearnable, even with full feedback.
Authors: Megan Tjandrasuwita, Jie Xu, Armando Solar-Lezama, Wojciech Matusik
Abstract: Robots are often built from standardized assemblies, (e.g. arms, legs, or fingers), but each robot must be trained from scratch to control all the actuators of all the parts together. In this paper we demonstrate a new approach that takes a single robot and its controller as input and produces a set of modular controllers for each of these assemblies such that when a new robot is built from the same parts, its control can be quickly learned by reusing the modular controllers. We achieve this with a framework called MeMo which learns (Me)aningful, (Mo)dular controllers. Specifically, we propose a novel modularity objective to learn an appropriate division of labor among the modules. We demonstrate that this objective can be optimized simultaneously with standard behavior cloning loss via noise injection. We benchmark our framework in locomotion and grasping environments on simple to complex robot morphology transfer. We also show that the modules help in task transfer. On both structure and task transfer, MeMo achieves improved training efficiency to graph neural network and Transformer baselines.
Authors: Haoran Han, Jian Cheng, Maolong Lv
Abstract: This paper proposes a three-layer unmanned combat aerial vehicle (UCAV) dogfight frame where Deep reinforcement learning (DRL) is responsible for high-level maneuver decision. A four-channel low-level control law is firstly constructed, followed by a library containing eight basic flight maneuvers (BFMs). Double deep Q network (DDQN) is applied for BFM selection in UCAV dogfight, where the opponent strategy during the training process is constructed with DT. Our simulation result shows that, the agent can achieve a win rate of 85.75% against the DT strategy, and positive results when facing various unseen opponents. Based on the proposed frame, interpretability of the DRL-based dogfight is significantly improved. The agent performs yo-yo to adjust its turn rate and gain higher maneuverability. Emergence of "Dive and Chase" behavior also indicates the agent can generate a novel tactic that utilizes the drawback of its opponent.
Authors: Jaydip Sen, Hetvi Waghela, Sneha Rakshit
Abstract: This paper explores using a deep learning Long Short-Term Memory (LSTM) model for accurate stock price prediction and its implications for portfolio design. Despite the efficient market hypothesis suggesting that predicting stock prices is impossible, recent research has shown the potential of advanced algorithms and predictive models. The study builds upon existing literature on stock price prediction methods, emphasizing the shift toward machine learning and deep learning approaches. Using historical stock prices of 180 stocks across 18 sectors listed on the NSE, India, the LSTM model predicts future prices. These predictions guide buy/sell decisions for each stock and analyze sector profitability. The study's main contributions are threefold: introducing an optimized LSTM model for robust portfolio design, utilizing LSTM predictions for buy/sell transactions, and insights into sector profitability and volatility. Results demonstrate the efficacy of the LSTM model in accurately predicting stock prices and informing investment decisions. By comparing sector profitability and prediction accuracy, the work provides valuable insights into the dynamics of the current financial markets in India.
Authors: Chaoyi Pan, Zeji Yi, Guanya Shi, Guannan Qu
Abstract: Recent advances in diffusion models have demonstrated their strong capabilities in generating high-fidelity samples from complex distributions through an iterative refinement process. Despite the empirical success of diffusion models in motion planning and control, the model-free nature of these methods does not leverage readily available model information and limits their generalization to new scenarios beyond the training data (e.g., new robots with different dynamics). In this work, we introduce Model-Based Diffusion (MBD), an optimization approach using the diffusion process to solve trajectory optimization (TO) problems without data. The key idea is to explicitly compute the score function by leveraging the model information in TO problems, which is why we refer to our approach as model-based diffusion. Moreover, although MBD does not require external data, it can be naturally integrated with data of diverse qualities to steer the diffusion process. We also reveal that MBD has interesting connections to sampling-based optimization. Empirical evaluations show that MBD outperforms state-of-the-art reinforcement learning and sampling-based TO methods in challenging contact-rich tasks. Additionally, MBD's ability to integrate with data enhances its versatility and practical applicability, even with imperfect and infeasible data (e.g., partial-state demonstrations for high-dimensional humanoids), beyond the scope of standard diffusion models.
Authors: Gabriel Ducrocq, Lukas Grunewald, Sebastian Westenhoff, Fredrik Lindsten
Abstract: The three-dimensional structure of a protein plays a key role in determining its function. Methods like AlphaFold have revolutionized protein structure prediction based only on the amino-acid sequence. However, proteins often appear in multiple different conformations, and it is highly relevant to resolve the full conformational distribution. Single-particle cryo-electron microscopy (cryo EM) is a powerful tool for capturing a large number of images of a given protein, frequently in different conformations (referred to as particles). The images are, however, very noisy projections of the protein, and traditional methods for cryo EM reconstruction are limited to recovering a single, or a few, conformations. In this paper, we introduce cryoSPHERE, a deep learning method that takes as input a nominal protein structure, e.g. from AlphaFold, learns how to divide it into segments, and how to move these as approximately rigid bodies to fit the different conformations present in the cryo EM dataset. This formulation is shown to provide enough constraints to recover meaningful reconstructions of single protein structures. This is illustrated in three examples where we show consistent improvements over the current state-of-the-art for heterogeneous reconstruction.
Authors: Xi Cheng, Jinghao Zhang, Yunan Zeng, Wenfang Xue
Abstract: Algorithmic trading refers to executing buy and sell orders for specific assets based on automatically identified trading opportunities. Strategies based on reinforcement learning (RL) have demonstrated remarkable capabilities in addressing algorithmic trading problems. However, the trading patterns differ among market conditions due to shifted distribution data. Ignoring multiple patterns in the data will undermine the performance of RL. In this paper, we propose MOT,which designs multiple actors with disentangled representation learning to model the different patterns of the market. Furthermore, we incorporate the Optimal Transport (OT) algorithm to allocate samples to the appropriate actor by introducing a regularization loss term. Additionally, we propose Pretrain Module to facilitate imitation learning by aligning the outputs of actors with expert strategy and better balance the exploration and exploitation of RL. Experimental results on real futures market data demonstrate that MOT exhibits excellent profit capabilities while balancing risks. Ablation studies validate the effectiveness of the components of MOT.
Authors: Yulong Dong, Jonathan A. Gross, Murphy Yuezhen Niu
Abstract: Quantum effects like entanglement and coherent amplification can be used to drastically enhance the accuracy of quantum parameter estimation beyond classical limits. However, challenges such as decoherence and time-dependent errors hinder Heisenberg-limited amplification. We introduce Quantum Signal-Processing Phase Estimation algorithms that are robust against these challenges and achieve optimal performance as dictated by the Cram\'{e}r-Rao bound. These algorithms use quantum signal transformation to decouple interdependent phase parameters into largely orthogonal ones, ensuring that time-dependent errors in one do not compromise the accuracy of learning the other. Combining provably optimal classical estimation with near-optimal quantum circuit design, our approach achieves an unprecedented standard deviation accuracy of $10^{-4}$ radians for estimating unwanted swap angles in superconducting two-qubit experiments, using low-depth ($<10$) circuits. This represents up to two orders of magnitude improvement over existing methods. Theoretically and numerically, we demonstrate the optimality of our algorithm against time-dependent phase errors, observing that the variance of the time-sensitive parameter $\varphi$ scales faster than the asymptotic Heisenberg scaling in the small-depth regime. Our results are rigorously validated against the quantum Fisher information, confirming our protocol's ability to achieve unmatched precision for two-qubit gate learning.
Authors: Sariah Mghames, Luca Castri, Marc Hanheide, Nicola Bellotto
Abstract: Autonomous mobile robots can rely on several human motion detection and prediction systems for safe and efficient navigation in human environments, but the underline model architectures can have different impacts on the trustworthiness of the robot in the real world. Among existing solutions for context-aware human motion prediction, some approaches have shown the benefit of integrating symbolic knowledge with state-of-the-art neural networks. In particular, a recent neuro-symbolic architecture (NeuroSyM) has successfully embedded context with a Qualitative Trajectory Calculus (QTC) for spatial interactions representation. This work achieved better performance than neural-only baseline architectures on offline datasets. In this paper, we extend the original architecture to provide neuROSym, a ROS package for robot deployment in real-world scenarios, which can run, visualise, and evaluate previous neural-only and neuro-symbolic models for motion prediction online. We evaluated these models, NeuroSyM and a baseline SGAN, on a TIAGo robot in two scenarios with different human motion patterns. We assessed accuracy and runtime performance of the prediction models, showing a general improvement in case our neuro-symbolic architecture is used. We make the neuROSym package1 publicly available to the robotics community.
Authors: Haibo Jin, Leyang Hu, Xinuo Li, Peiyan Zhang, Chonghan Chen, Jun Zhuang, Haohan Wang
Abstract: The rapid evolution of artificial intelligence (AI) through developments in Large Language Models (LLMs) and Vision-Language Models (VLMs) has brought significant advancements across various technological domains. While these models enhance capabilities in natural language processing and visual interactive tasks, their growing adoption raises critical concerns regarding security and ethical alignment. This survey provides an extensive review of the emerging field of jailbreaking--deliberately circumventing the ethical and operational boundaries of LLMs and VLMs--and the consequent development of defense mechanisms. Our study categorizes jailbreaks into seven distinct types and elaborates on defense strategies that address these vulnerabilities. Through this comprehensive examination, we identify research gaps and propose directions for future studies to enhance the security frameworks of LLMs and VLMs. Our findings underscore the necessity for a unified perspective that integrates both jailbreak strategies and defensive solutions to foster a robust, secure, and reliable environment for the next generation of language models. More details can be found on our website: \url{https://chonghan-chen.com/llm-jailbreak-zoo-survey/}.
Authors: Albert Alcalde, Giovanni Fantuzzi, Enrique Zuazua
Abstract: Transformers are extremely successful machine learning models whose mathematical properties remain poorly understood. Here, we rigorously characterize the behavior of transformers with hardmax self-attention and normalization sublayers as the number of layers tends to infinity. By viewing such transformers as discrete-time dynamical systems describing the evolution of points in a Euclidean space, and thanks to a geometric interpretation of the self-attention mechanism based on hyperplane separation, we show that the transformer inputs asymptotically converge to a clustered equilibrium determined by special points called leaders. We then leverage this theoretical understanding to solve sentiment analysis problems from language processing using a fully interpretable transformer model, which effectively captures `context' by clustering meaningless words around leader words carrying the most meaning. Finally, we outline remaining challenges to bridge the gap between the mathematical analysis of transformers and their real-life implementation.
Authors: Mouadh Yagoubi, David Danan, Milad Leyli-abadi, Jean-Patrick Brunet, Jocelyn Ahmed Mazari, Florent Bonnet, maroua gmati, Asma Farjallah, Paola Cinnella, Patrick Gallinari, Marc Schoenauer
Abstract: The integration of machine learning (ML) techniques for addressing intricate physics problems is increasingly recognized as a promising avenue for expediting simulations. However, assessing ML-derived physical models poses a significant challenge for their adoption within industrial contexts. This competition is designed to promote the development of innovative ML approaches for tackling physical challenges, leveraging our recently introduced unified evaluation framework known as Learning Industrial Physical Simulations (LIPS). Building upon the preliminary edition held from November 2023 to March 2024, this iteration centers on a task fundamental to a well-established physical application: airfoil design simulation, utilizing our proposed AirfRANS dataset. The competition evaluates solutions based on various criteria encompassing ML accuracy, computational efficiency, Out-Of-Distribution performance, and adherence to physical principles. Notably, this competition represents a pioneering effort in exploring ML-driven surrogate methods aimed at optimizing the trade-off between computational efficiency and accuracy in physical simulations. Hosted on the Codabench platform, the competition offers online training and evaluation for all participating solutions.
Authors: Chathurangi Shyalika, Ruwan Wickramarachchi, Fadi El Kalach, Ramy Harik, Amit Sheth
Abstract: Rare events are occurrences that take place with a significantly lower frequency than more common regular events. In manufacturing, predicting such events is particularly important, as they lead to unplanned downtime, shortening equipment lifespan, and high energy consumption. The occurrence of events is considered frequently-rare if observed in more than 10% of all instances, very-rare if it is 1-5%, moderately-rare if it is 5-10%, and extremely-rare if less than 1%. The rarity of events is inversely correlated with the maturity of a manufacturing industry. Typically, the rarity of events affects the multivariate data generated within a manufacturing process to be highly imbalanced, which leads to bias in predictive models. This paper evaluates the role of data enrichment techniques combined with supervised machine-learning techniques for rare event detection and prediction. To address the data scarcity, we use time series data augmentation and sampling methods to amplify the dataset with more multivariate features and data points while preserving the underlying time series patterns in the combined alterations. Imputation techniques are used in handling null values in datasets. Considering 15 learning models ranging from statistical learning to machine learning to deep learning methods, the best-performing model for the selected datasets is obtained and the efficacy of data enrichment is evaluated. Based on this evaluation, our results find that the enrichment procedure enhances up to 48% of F1 measure in rare failure event detection and prediction of supervised prediction models. We also conduct empirical and ablation experiments on the datasets to derive dataset-specific novel insights. Finally, we investigate the interpretability aspect of models for rare event prediction, considering multiple methods.
Authors: Hyunseok Oh, Youngki Lee
Abstract: Spiking neural network (SNN) is studied in multidisciplinary domains to (i) enable order-of-magnitudes energy-efficient AI inference and (ii) computationally simulate neuro-scientific mechanisms. The lack of discrete theory obstructs the practical application of SNN by limiting its performance and nonlinearity support. We present a new optimization-theoretic perspective of the discrete dynamics of spiking neurons. We prove that a discrete dynamical system of simple integrate-and-fire models approximates the sub-gradient method over unconstrained optimization problems. We practically extend our theory to introduce a novel sign gradient descent (signGD)-based neuronal dynamics that can (i) approximate diverse nonlinearities beyond ReLU and (ii) advance ANN-to-SNN conversion performance in low time steps. Experiments on large-scale datasets show that our technique achieves (i) state-of-the-art performance in ANN-to-SNN conversion and (ii) is the first to convert new DNN architectures, e.g., ConvNext, MLP-Mixer, and ResMLP. We publicly share our source code at https://github.com/snuhcs/snn_signgd .
Authors: Parviz Ghafariasl, Masoomeh Zeinalnezhad, Amir Ahmadishokooh
Abstract: Timely alerts about hazardous air pollutants are crucial for public health. However, existing forecasting models often overlook key factors like baseline parameters and missing data, limiting their accuracy. This study introduces a hybrid approach to address these issues, focusing on forecasting hourly PM2.5 concentrations using Support Vector Regression (SVR). Meta-heuristic algorithms, Grey Wolf Optimization (GWO) and Particle Swarm Optimization (PSO), optimize SVR Hyper-parameters "C" and "Gamma" to enhance prediction accuracy. Evaluation metrics include R-squared (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Results show significant improvements with PSO-SVR (R2: 0.9401, RMSE: 0.2390, MAE: 0.1368) and GWO-SVR (R2: 0.9408, RMSE: 0.2376, MAE: 0.1373), indicating robust and accurate models suitable for similar research applications.
Authors: Siyi Gu, Minkai Xu, Alexander Powers, Weili Nie, Tomas Geffner, Karsten Kreis, Jure Leskovec, Arash Vahdat, Stefano Ermon
Abstract: Generating ligand molecules for specific protein targets, known as structure-based drug design, is a fundamental problem in therapeutics development and biological discovery. Recently, target-aware generative models, especially diffusion models, have shown great promise in modeling protein-ligand interactions and generating candidate drugs. However, existing models primarily focus on learning the chemical distribution of all drug candidates, which lacks effective steerability on the chemical quality of model generations. In this paper, we propose a novel and general alignment framework to align pretrained target diffusion models with preferred functional properties, named AliDiff. AliDiff shifts the target-conditioned chemical distribution towards regions with higher binding affinity and structural rationality, specified by user-defined reward functions, via the preference optimization approach. To avoid the overfitting problem in common preference optimization objectives, we further develop an improved Exact Energy Preference Optimization method to yield an exact and efficient alignment of the diffusion models, and provide the closed-form expression for the converged distribution. Empirical studies on the CrossDocked2020 benchmark show that AliDiff can generate molecules with state-of-the-art binding energies with up to -7.07 Avg. Vina Score, while maintaining strong molecular properties.
Authors: Ruidong Wu, Ruihan Guo, Rui Wang, Shitong Luo, Yue Xu, Jiahan Li, Jianzhu Ma, Qiang Liu, Yunan Luo, Jian Peng
Abstract: Despite the striking success of general protein folding models such as AlphaFold2(AF2, Jumper et al. (2021)), the accurate computational modeling of antibody-antigen complexes remains a challenging task. In this paper, we first analyze AF2's primary loss function, known as the Frame Aligned Point Error (FAPE), and raise a previously overlooked issue that FAPE tends to face gradient vanishing problem on high-rotational-error targets. To address this fundamental limitation, we propose a novel geodesic loss called Frame Aligned Frame Error (FAFE, denoted as F2E to distinguish from FAPE), which enables the model to better optimize both the rotational and translational errors between two frames. We then prove that F2E can be reformulated as a group-aware geodesic loss, which translates the optimization of the residue-to-residue error to optimizing group-to-group geodesic frame distance. By fine-tuning AF2 with our proposed new loss function, we attain a correct rate of 52.3\% (DockQ $>$ 0.23) on an evaluation set and 43.8\% correct rate on a subset with low homology, with substantial improvement over AF2 by 182\% and 100\% respectively.
Authors: Marina Maciel Ansanelli, Elie Wolfe, Robert W. Spekkens
Abstract: What types of differences among causal structures with latent variables are impossible to distinguish by statistical data obtained by probing each visible variable? If the probing scheme is simply passive observation, then it is well-known that many different causal structures can realize the same joint probability distributions. Even for the simplest case of two visible variables, for instance, one cannot distinguish between one variable being a causal parent of the other and the two variables sharing a latent common cause. However, it is possible to distinguish between these two causal structures if we have recourse to more powerful probing schemes, such as the possibility of intervening on one of the variables and observing the other. Herein, we address the question of which causal structures remain indistinguishable even given the most informative types of probing schemes on the visible variables. We find that two causal structures remain indistinguishable if and only if they are both associated with the same mDAG structure (as defined by Evans (2016)). We also consider the question of when one causal structure dominates another in the sense that it can realize all of the joint probability distributions that can be realized by the other using a given probing scheme. (Equivalence of causal structures is the special case of mutual dominance.) Finally, we investigate to what extent one can weaken the probing schemes implemented on the visible variables and still have the same discrimination power as a maximally informative probing scheme.
Authors: Boris Landa, Yuval Kluger, Rong Ma
Abstract: Embedding high-dimensional data into a low-dimensional space is an indispensable component of data analysis. In numerous applications, it is necessary to align and jointly embed multiple datasets from different studies or experimental conditions. Such datasets may share underlying structures of interest but exhibit individual distortions, resulting in misaligned embeddings using traditional techniques. In this work, we propose \textit{Entropic Optimal Transport (EOT) eigenmaps}, a principled approach for aligning and jointly embedding a pair of datasets with theoretical guarantees. Our approach leverages the leading singular vectors of the EOT plan matrix between two datasets to extract their shared underlying structure and align the datasets accordingly in a common embedding space. We interpret our approach as an inter-data variant of the classical Laplacian eigenmaps and diffusion maps embeddings, showing that it enjoys many favorable analogous properties. We then analyze a data-generative model where two observed high-dimensional datasets share latent variables on a common low-dimensional manifold, but each dataset is subject to data-specific translation, scaling, nuisance structures, and noise. We show that in a high-dimensional asymptotic regime, the EOT plan recovers the shared manifold structure by approximating a kernel function evaluated at the locations of the latent variables. Subsequently, we provide a geometric interpretation of our embedding by relating it to the eigenfunctions of population-level operators encoding the density and geometry of the shared manifold. Finally, we showcase the performance of our approach for data integration and embedding through simulations and analyses of real-world biological data, demonstrating its advantages over alternative methods in challenging scenarios.
Authors: Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, Bhavana Dalvi Mishra, Abhijeetsingh Meena, Aryan Prakhar, Tirth Vora, Tushar Khot, Ashish Sabharwal, Peter Clark
Abstract: Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. The benchmark is designed to systematically assess current model capabilities in discovery tasks and provide a useful resource for improving them. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering, by manually deriving discovery workflows from published papers to approximate the real-world challenges faced by researchers, where each task is defined by a dataset, its metadata, and a discovery goal in natural language. We additionally provide 903 synthetic tasks to conduct controlled evaluations across task complexity. Furthermore, our structured formalism of data-driven discovery enables a facet-based evaluation that provides useful insights into different failure modes. We evaluate several popular LLM-based reasoning frameworks using both open and closed LLMs as baselines on DiscoveryBench and find that even the best system scores only 25%. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
Authors: Luke Bhan, Yuanyuan Shi, Miroslav Krstic
Abstract: Neural operator approximations of the gain kernels in PDE backstepping has emerged as a viable method for implementing controllers in real time. With such an approach, one approximates the gain kernel, which maps the plant coefficient into the solution of a PDE, with a neural operator. It is in adaptive control that the benefit of the neural operator is realized, as the kernel PDE solution needs to be computed online, for every updated estimate of the plant coefficient. We extend the neural operator methodology from adaptive control of a hyperbolic PDE to adaptive control of a benchmark parabolic PDE (a reaction-diffusion equation with a spatially-varying and unknown reaction coefficient). We prove global stability and asymptotic regulation of the plant state for a Lyapunov design of parameter adaptation. The key technical challenge of the result is handling the 2D nature of the gain kernels and proving that the target system with two distinct sources of perturbation terms, due to the parameter estimation error and due to the neural approximation error, is Lyapunov stable. To verify our theoretical result, we present simulations achieving calculation speedups up to 45x relative to the traditional finite difference solvers for every timestep in the simulation trajectory.
Authors: Francis Williams, Jiahui Huang, Jonathan Swartz, Gergely Kl\'ar, Vijay Thakkar, Matthew Cong, Xuanchi Ren, Ruilong Li, Clement Fuji-Tsang, Sanja Fidler, Eftychios Sifakis, Ken Museth
Abstract: We present fVDB, a novel GPU-optimized framework for deep learning on large-scale 3D data. fVDB provides a complete set of differentiable primitives to build deep learning architectures for common tasks in 3D learning such as convolution, pooling, attention, ray-tracing, meshing, etc. fVDB simultaneously provides a much larger feature set (primitives and operators) than established frameworks with no loss in efficiency: our operators match or exceed the performance of other frameworks with narrower scope. Furthermore, fVDB can process datasets with much larger footprint and spatial resolution than prior works, while providing a competitive memory footprint on small inputs. To achieve this combination of versatility and performance, fVDB relies on a single novel VDB index grid acceleration structure paired with several key innovations including GPU accelerated sparse grid construction, convolution using tensorcores, fast ray tracing kernels using a Hierarchical Digital Differential Analyzer algorithm (HDDA), and jagged tensors. Our framework is fully integrated with PyTorch enabling interoperability with existing pipelines, and we demonstrate its effectiveness on a number of representative tasks such as large-scale point-cloud segmentation, high resolution 3D generative modeling, unbounded scale Neural Radiance Fields, and large-scale point cloud reconstruction.
Authors: Kota Shamanth Ramanath Nayak, Leila Kosseim
Abstract: This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. Our model, developed as a part of the recent SemEval task, is based on fine-tuning individual language models (BERT, XLM-RoBERTa, and mBERT) and leveraging a mean-based ensemble model in addition to dataset augmentation through paraphrase generation from ChatGPT. The scope of the study encompasses enhancing model performance through innovative training techniques and data augmentation strategies. The problem addressed is the effective identification and classification of multiple persuasive techniques in meme texts, a task complicated by the diversity and complexity of such content. The objective of the paper is to improve detection accuracy by refining model training methods and examining the impact of balanced versus unbalanced training datasets. Novelty in the results and discussion lies in the finding that training with paraphrases enhances model performance, yet a balanced training set proves more advantageous than a larger unbalanced one. Additionally, the analysis reveals the potential pitfalls of indiscriminate incorporation of paraphrases from diverse distributions, which can introduce substantial noise. Results with the SemEval 2024 data confirm these insights, demonstrating improved model efficacy with the proposed methods.
Authors: Jiayi Wang, Kevin Alexander Laube, Yumeng Li, Jan Hendrik Metzen, Shin-I Cheng, Julio Borges, Anna Khoreva
Abstract: Recent work has shown great progress in integrating spatial conditioning to control large, pre-trained text-to-image diffusion models. Despite these advances, existing methods describe the spatial image content using hand-crafted conditioning inputs, which are either semantically ambiguous (e.g., edges) or require expensive manual annotations (e.g., semantic segmentation). To address these limitations, we propose a new label-free way of conditioning diffusion models to enable fine-grained spatial control. We introduce the concept of neural semantic image synthesis, which uses neural layouts extracted from pre-trained foundation models as conditioning. Neural layouts are advantageous as they provide rich descriptions of the desired image, containing both semantics and detailed geometry of the scene. We experimentally show that images synthesized via neural semantic image synthesis achieve similar or superior pixel-level alignment of semantic classes compared to those created using expensive semantic label maps. At the same time, they capture better semantics, instance separation, and object orientation than other label-free conditioning options, such as edges or depth. Moreover, we show that images generated by neural layout conditioning can effectively augment real data for training various perception tasks.
Authors: Vincent Plassier, Alexander Fishkov, Maxim Panov, Eric Moulines
Abstract: We develop a new method for creating prediction sets that combines the flexibility of conformal methods with an estimate of the conditional distribution $P_{Y \mid X}$. Most existing methods, such as conformalized quantile regression and probabilistic conformal prediction, only offer marginal coverage guarantees. Our approach extends these methods to achieve conditional coverage, which is essential for many practical applications. While exact conditional guarantees are impossible without assumptions on the data distribution, we provide non-asymptotic bounds that explicitly depend on the quality of the available estimate of the conditional distribution. Our confidence sets are highly adaptive to the local structure of the data, making them particularly useful in high heteroskedasticity situations. We demonstrate the effectiveness of our approach through extensive simulations, showing that it outperforms existing methods in terms of conditional coverage and improves the reliability of statistical inference in a wide range of applications.
Authors: Ariel D. Procaccia, Benjamin Schiffer, Shirley Zhang
Abstract: We consider the problem of online fair division of indivisible goods to players when there are a finite number of types of goods and player values are drawn from distributions with unknown means. Our goal is to maximize social welfare subject to allocating the goods fairly in expectation. When a player's value for an item is unknown at the time of allocation, we show that this problem reduces to a variant of (stochastic) multi-armed bandits, where there exists an arm for each player's value for each type of good. At each time step, we choose a distribution over arms which determines how the next item is allocated. We consider two sets of fairness constraints for this problem: envy-freeness in expectation and proportionality in expectation. Our main result is the design of an explore-then-commit algorithm that achieves $\tilde{O}(T^{2/3})$ regret while maintaining either fairness constraint. This result relies on unique properties fundamental to fair-division constraints that allow faster rates of learning, despite the restricted action space.
Authors: Dian Wang, Stephen Hart, David Surovik, Tarik Kelestemur, Haojie Huang, Haibo Zhao, Mark Yeatman, Jiuguang Wang, Robin Walters, Robert Platt
Abstract: Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning. However, a drawback of this approach is the need to learn a denoising function, which is significantly more complex than learning an explicit policy. In this work, we propose Equivariant Diffusion Policy, a novel diffusion policy learning method that leverages domain symmetries to obtain better sample efficiency and generalization in the denoising function. We theoretically analyze the $\mathrm{SO}(2)$ symmetry of full 6-DoF control and characterize when a diffusion model is $\mathrm{SO}(2)$-equivariant. We furthermore evaluate the method empirically on a set of 12 simulation tasks in MimicGen, and show that it obtains a success rate that is, on average, 21.9% higher than the baseline Diffusion Policy. We also evaluate the method on a real-world system to show that effective policies can be learned with relatively few training samples, whereas the baseline Diffusion Policy cannot.
Authors: Rafael Cerna Loli, Bruno Clerckx
Abstract: Optimization algorithms for wireless systems play a fundamental role in improving their performance and efficiency. However, it is known that the complexity of conventional optimization algorithms in the literature often exponentially increases with the number of transmit antennas and communication users in the wireless system. Therefore, in the large scale regime, the astronomically large complexity of these optimization algorithms prohibits their use and prevents assessing large scale wireless systems performance under optimized conditions. To overcome this limitation, this work proposes instead the use of an unsupervised meta-learning based approach to directly perform non-convex optimization at significantly reduced complexity. To demonstrate the effectiveness of the proposed meta-learning based solution, the sum-rate (SR) maximization problem for the following three emerging 6G technologies is contemplated: hierarchical rate-splitting multiple access (H-RSMA), integrated sensing and communication (ISAC), and beyond-diagonal reconfigurable intelligent surfaces (BD-RIS). Through numerical results, it is demonstrated that the proposed meta-learning based optimization framework is able to successfully optimize the performance and also reveal unknown aspects of the operation in the large scale regime for the considered three 6G technologies.
Authors: Tao Ma, Xuzhi Yang, Zoltan Szabo
Abstract: Reinforcement learning (RL) -- finding the optimal behaviour (also referred to as policy) maximizing the collected long-term cumulative reward -- is among the most influential approaches in machine learning with a large number of successful applications. In several decision problems, however, one faces the possibility of policy switching -- changing from the current policy to a new one -- which incurs a non-negligible cost (examples include the shifting of the currently applied educational technology, modernization of a computing cluster, and the introduction of a new webpage design), and in the decision one is limited to using historical data without the availability for further online interaction. Despite the inevitable importance of this offline learning scenario, to our best knowledge, very little effort has been made to tackle the key problem of balancing between the gain and the cost of switching in a flexible and principled way. Leveraging ideas from the area of optimal transport, we initialize the systematic study of policy switching in offline RL. We establish fundamental properties and design a Net Actor-Critic algorithm for the proposed novel switching formulation. Numerical experiments demonstrate the efficiency of our approach on multiple benchmarks of the Gymnasium.
Authors: Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta, Jun Chen, Mohamed Elhoseiny, Ruohan Gao, Dinesh Manocha
Abstract: Leveraging Large Language Models' remarkable proficiency in text-based tasks, recent works on Multi-modal LLMs (MLLMs) extend them to other modalities like vision and audio. However, the progress in these directions has been mostly focused on tasks that only require a coarse-grained understanding of the audio-visual semantics. We present Meerkat, an audio-visual LLM equipped with a fine-grained understanding of image and audio both spatially and temporally. With a new modality alignment module based on optimal transport and a cross-attention module that enforces audio-visual consistency, Meerkat can tackle challenging tasks such as audio referred image grounding, image guided audio temporal localization, and audio-visual fact-checking. Moreover, we carefully curate a large dataset AVFIT that comprises 3M instruction tuning samples collected from open-source datasets, and introduce MeerkatBench that unifies five challenging audio-visual tasks. We achieve state-of-the-art performance on all these downstream tasks with a relative improvement of up to 37.12%.
Authors: Sathish Reddy Indurthi, Wenxuan Zhou, Shamil Chollampatt, Ravi Agrawal, Kaiqiang Song, Lingxiao Zhao, Chenguang Zhu
Abstract: Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages. Traditional methods for creating multilingual IFT datasets such as translating existing English IFT datasets or converting existing NLP datasets into IFT datasets by templating, struggle to capture linguistic nuances and ensure prompt (instruction) diversity. To address this issue, we propose a novel method for collecting multilingual IFT datasets that preserves linguistic naturalness and ensures prompt diversity. This approach leverages English-focused LLMs, monolingual corpora, and a scoring function to create high-quality, diversified IFT datasets in multiple languages. Experiments demonstrate that LLMs finetuned using these IFT datasets show notable improvements in both generative and discriminative tasks, indicating enhanced language comprehension by LLMs in non-English contexts. Specifically, on the multilingual summarization task, LLMs using our IFT dataset achieved 17.57% and 15.23% improvements over LLMs fine-tuned with translation-based and template-based datasets, respectively.
Authors: Shiquan Shen, Zhizhong Wu, Pan Zhang
Abstract: With the development of deep learning technology, the detection and classification of distracted driving behaviour requires higher accuracy. Existing deep learning-based methods are computationally intensive and parameter redundant, limiting the efficiency and accuracy in practical applications. To solve this problem, this study proposes an improved YOLOv8 detection method based on the original YOLOv8 model by integrating the BoTNet module, GAM attention mechanism and EIoU loss function. By optimising the feature extraction and multi-scale feature fusion strategies, the training and inference processes are simplified, and the detection accuracy and efficiency are significantly improved. Experimental results show that the improved model performs well in both detection speed and accuracy, with an accuracy rate of 99.4%, and the model is smaller and easy to deploy, which is able to identify and classify distracted driving behaviours in real time, provide timely warnings, and enhance driving safety.
Authors: Wenyi Lian, Joakim Lindblad, Christina Runow Stark, Jan-Micha\'el Hirsch, Nata\v{s}a Sladoje
Abstract: Oral cancer is a global health challenge. It is treatable if detected early, but it is often fatal in late stages. There is a shift from the invasive and time-consuming tissue sampling and histological examination, toward non-invasive brush biopsies and cytological examination. Reliable computer-assisted methods are essential for cost-effective and accurate cytological analysis, but the lack of detailed cell-level annotations impairs model effectiveness. This study aims to improve AI-based oral cancer detection using multimodal imaging and deep fusion. We combine brightfield and fluorescence whole slide microscopy imaging to analyze Papanicolaou-stained liquid-based cytology slides of brush biopsies collected from both healthy and cancer patients. Due to limited cytological annotations, we utilize a weakly supervised deep learning approach using only patient-level labels. We evaluate various multimodal fusion strategies, including early, late, and three recent intermediate fusion methods. Our results show: (i) fluorescence imaging of Papanicolaou-stained samples provides substantial diagnostic information; (ii) multimodal fusion enhances classification and cancer detection accuracy over single-modality methods. Intermediate fusion is the leading method among the studied approaches. Specifically, the Co-Attention Fusion Network (CAFNet) model excels with an F1 score of 83.34% and accuracy of 91.79%, surpassing human performance on the task. Additional tests highlight the need for precise image registration to optimize multimodal analysis benefits. This study advances cytopathology by combining deep learning and multimodal imaging to enhance early, non-invasive detection of oral cancer, improving diagnostic accuracy and streamlining clinical workflows. The developed pipeline is also applicable in other cytological settings. Our codes and dataset are available online for further research.
Authors: Zihan Wang, Deli Chen, Damai Dai, Runxin Xu, Zhuoshu Li, Y. Wu
Abstract: Parameter-efficient fine-tuning (PEFT) is crucial for customizing Large Language Models (LLMs) with constrained resources. Although there have been various PEFT methods for dense-architecture LLMs, PEFT for sparse-architecture LLMs is still underexplored. In this work, we study the PEFT method for LLMs with the Mixture-of-Experts (MoE) architecture and the contents of this work are mainly threefold: (1) We investigate the dispersion degree of the activated experts in customized tasks, and found that the routing distribution for a specific task tends to be highly concentrated, while the distribution of activated experts varies significantly across different tasks. (2) We propose Expert-Specialized Fine-Tuning, or ESFT, which tunes the experts most relevant to downstream tasks while freezing the other experts and modules; experimental results demonstrate that our method not only improves the tuning efficiency, but also matches or even surpasses the performance of full-parameter fine-tuning. (3) We further analyze the impact of the MoE architecture on expert-specialized fine-tuning. We find that MoE models with finer-grained experts are more advantageous in selecting the combination of experts that are most relevant to downstream tasks, thereby enhancing both the training efficiency and effectiveness.
Authors: Hailiang Zhang, Dian Chao, Zhihao Guan, Yang Yang
Abstract: In this paper, we introduce a grounded video question-answering solution. Our research reveals that the fixed official baseline method for video question answering involves two main steps: visual grounding and object tracking. However, a significant challenge emerges during the initial step, where selected frames may lack clearly identifiable target objects. Furthermore, single images cannot address questions like "Track the container from which the person pours the first time." To tackle this issue, we propose an alternative two-stage approach:(1) First, we leverage the VALOR model to answer questions based on video information.(2) concatenate the answered questions with their respective answers. Finally, we employ TubeDETR to generate bounding boxes for the targets.
Authors: Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng, Qingbin Liu, Mengru Wang, Dianbo Sui, Xi Chen, Huajun Chen, Ningyu Zhang
Abstract: Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase specific knowledge. However, current unlearning paradigms are mired in vague forgetting boundaries, often erasing knowledge indiscriminately. In this work, we introduce KnowUnDo, a benchmark containing copyrighted content and user privacy domains to evaluate if the unlearning process inadvertently erases essential knowledge. Our findings indicate that existing unlearning methods often suffer from excessive unlearning. To address this, we propose a simple yet effective method, MemFlex, which utilizes gradient information to precisely target and unlearn sensitive parameters. Experimental results show that MemFlex is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs. Code and dataset will be released at https://github.com/zjunlp/KnowUnDo.
Authors: Pablo Messina, Ren\'e Vidal, Denis Parra, \'Alvaro Soto, Vladimir Araujo
Abstract: Advancing representation learning in specialized fields like medicine remains challenging due to the scarcity of expert annotations for text and images. To tackle this issue, we present a novel two-stage framework designed to extract high-quality factual statements from free-text radiology reports in order to improve the representations of text encoders and, consequently, their performance on various downstream tasks. In the first stage, we propose a \textit{Fact Extractor} that leverages large language models (LLMs) to identify factual statements from well-curated domain-specific datasets. In the second stage, we introduce a \textit{Fact Encoder} (CXRFE) based on a BERT model fine-tuned with objective functions designed to improve its representations using the extracted factual data. Our framework also includes a new embedding-based metric (CXRFEScore) for evaluating chest X-ray text generation systems, leveraging both stages of our approach. Extensive evaluations show that our fact extractor and encoder outperform current state-of-the-art methods in tasks such as sentence ranking, natural language inference, and label extraction from radiology reports. Additionally, our metric proves to be more robust and effective than existing metrics commonly used in the radiology report generation literature. The code of this project is available at \url{https://github.com/PabloMessina/CXR-Fact-Encoder}.
Authors: Yupeng Cao, Zhiyuan Yao, Zhi Chen, Zhiyang Deng
Abstract: The integration of Large Language Models (LLMs) into financial analysis has garnered significant attention in the NLP community. This paper presents our solution to IJCAI-2024 FinLLM challenge, investigating the capabilities of LLMs within three critical areas of financial tasks: financial classification, financial text summarization, and single stock trading. We adopted Llama3-8B and Mistral-7B as base models, fine-tuning them through Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA) approaches. To enhance model performance, we combine datasets from task 1 and task 2 for data fusion. Our approach aims to tackle these diverse tasks in a comprehensive and integrated manner, showcasing LLMs' capacity to address diverse and complex financial tasks with improved accuracy and decision-making capabilities.
Authors: Cong Cao, Huanjing Yue, Xin Liu, Jingyu Yang
Abstract: Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various image restoration and enhancement tasks without training. However, directly applying them to video restoration and enhancement results in severe temporal flickering artifacts. In this paper, we propose the first framework for zero-shot video restoration and enhancement based on a pre-trained image diffusion model. By replacing the self-attention layer with the proposed cross-previous-frame attention layer, the pre-trained image diffusion model can take advantage of the temporal correlation between neighboring frames. We further propose temporal consistency guidance, spatial-temporal noise sharing, and an early stopping sampling strategy for better temporally consistent sampling. Our method is a plug-and-play module that can be inserted into any diffusion-based zero-shot image restoration or enhancement methods to further improve their performance. Experimental results demonstrate the superiority of our proposed method in producing temporally consistent videos with better fidelity.
Authors: Zijie J. Wang, Duen Horng Chau
Abstract: Retrieval-augmented text generation (RAG) addresses the common limitations of large language models (LLMs), such as hallucination, by retrieving information from an updatable external knowledge base. However, existing approaches often require dedicated backend servers for data storage and retrieval, thereby limiting their applicability in use cases that require strict data privacy, such as personal finance, education, and medicine. To address the pressing need for client-side dense retrieval, we introduce MeMemo, the first open-source JavaScript toolkit that adapts the state-of-the-art approximate nearest neighbor search technique HNSW to browser environments. Developed with modern and native Web technologies, such as IndexedDB and Web Workers, our toolkit leverages client-side hardware capabilities to enable researchers and developers to efficiently search through millions of high-dimensional vectors in the browser. MeMemo enables exciting new design and research opportunities, such as private and personalized content creation and interactive prototyping, as demonstrated in our example application RAG Playground. Reflecting on our work, we discuss the opportunities and challenges for on-device dense retrieval. MeMemo is available at https://github.com/poloclub/mememo.
Authors: Mohammed Fellaji, Fr\'ed\'eric Pennerath
Abstract: Bayesian Deep Learning (BDL) gives access not only to aleatoric uncertainty, as standard neural networks already do, but also to epistemic uncertainty, a measure of confidence a model has in its own predictions. In this article, we show through experiments that the evolution of epistemic uncertainty metrics regarding the model size and the size of the training set, goes against theoretical expectations. More precisely, we observe that the epistemic uncertainty collapses literally in the presence of large models and sometimes also of little training data, while we expect the exact opposite behaviour. This phenomenon, which we call "epistemic uncertainty hole", is all the more problematic as it undermines the entire applicative potential of BDL, which is based precisely on the use of epistemic uncertainty. As an example, we evaluate the practical consequences of this uncertainty hole on one of the main applications of BDL, namely the detection of out-of-distribution samples
Authors: Jingyuan Li, Wei Liu
Abstract: The Feynman-Kac Operator Expectation Estimator (FKEE) is an innovative method for estimating the target Mathematical Expectation $\mathbb{E}_{X\sim P}[f(X)]$ without relying on a large number of samples, in contrast to the commonly used Markov Chain Monte Carlo (MCMC) Expectation Estimator. FKEE comprises diffusion bridge models and approximation of the Feynman-Kac operator. The key idea is to use the solution to the Feynmann-Kac equation at the initial time $u(x_0,0)=\mathbb{E}[f(X_T)|X_0=x_0]$. We use Physically Informed Neural Networks (PINN) to approximate the Feynman-Kac operator, which enables the incorporation of diffusion bridge models into the expectation estimator and significantly improves the efficiency of using data while substantially reducing the variance. Diffusion Bridge Model is a more general MCMC method. In order to incorporate extensive MCMC algorithms, we propose a new diffusion bridge model based on the Minimum Wasserstein distance. This diffusion bridge model is universal and reduces the training time of the PINN. FKEE also reduces the adverse impact of the curse of dimensionality and weakens the assumptions on the distribution of $X$ and performance function $f$ in the general MCMC expectation estimator. The theoretical properties of this universal diffusion bridge model are also shown. Finally, we demonstrate the advantages and potential applications of this method through various concrete experiments, including the challenging task of approximating the partition function in the random graph model such as the Ising model.
Authors: Xiang Li, Haoran Tang, Siyu Chen, Ziwei Wang, Ryan Chen, Marcin Abram
Abstract: We measure the performance of in-context learning as a function of task novelty and difficulty for open and closed questions. For that purpose, we created a novel benchmark consisting of hard scientific questions, each paired with a context of various relevancy. We show that counter-intuitively, a context that is more aligned with the topic does not always help more than a less relevant context. This effect is especially visible for open questions and questions of high difficulty or novelty. This result reveals a fundamental difference between the treatment of close-form and open-form questions by large-language models and shows a need for a more robust evaluation of in-context learning on the variety of different types of questions. It also poses a new question of how to optimally select a context for large language models, especially in the context of Retrieval Augmented Generation (RAG) systems. Our results suggest that the answer to this question can be highly application-dependent and might be contingent on factors including the format of the question, the perceived difficulty level of the questions, and the novelty or popularity of the information we seek.
Authors: Suyi Li, Lingyun Yang, Xiaoxiao Jiang, Hanfeng Lu, Zhipeng Di, Weiyi Lu, Jiawei Chen, Kan Liu, Yinghao Yu, Tao Lan, Guodong Yang, Lin Qu, Liping Zhang, Wei Wang
Abstract: This paper documents our characterization study and practices for serving text-to-image requests with stable diffusion models in production. We first comprehensively analyze inference request traces for commercial text-to-image applications. It commences with our observation that add-on modules, i.e., ControlNets and LoRAs, that augment the base stable diffusion models, are ubiquitous in generating images for commercial applications. Despite their efficacy, these add-on modules incur high loading overhead, prolong the serving latency, and swallow up expensive GPU resources. Driven by our characterization study, we present SwiftDiffusion, a system that efficiently generates high-quality images using stable diffusion models and add-on modules. To achieve this, SwiftDiffusion reconstructs the existing text-to-image serving workflow by identifying the opportunities for parallel computation and distributing ControlNet computations across multiple GPUs. Further, SwiftDiffusion thoroughly analyzes the dynamics of image generation and develops techniques to eliminate the overhead associated with LoRA loading and patching while preserving the image quality. Last, SwiftDiffusion proposes specialized optimizations in the backbone architecture of the stable diffusion models, which are also compatible with the efficient serving of add-on modules. Compared to state-of-the-art text-to-image serving systems, SwiftDiffusion reduces serving latency by up to 5x and improves serving throughput by up to 2x without compromising image quality.
Authors: Wataru Hashimoto, Hidetaka Kamigaito, Taro Watanabe
Abstract: This work investigates the impact of data augmentation on confidence calibration and uncertainty estimation in Named Entity Recognition (NER) tasks. For the future advance of NER in safety-critical fields like healthcare and finance, it is essential to achieve accurate predictions with calibrated confidence when applying Deep Neural Networks (DNNs), including Pre-trained Language Models (PLMs), as a real-world application. However, DNNs are prone to miscalibration, which limits their applicability. Moreover, existing methods for calibration and uncertainty estimation are computational expensive. Our investigation in NER found that data augmentation improves calibration and uncertainty in cross-genre and cross-lingual setting, especially in-domain setting. Furthermore, we showed that the calibration for NER tends to be more effective when the perplexity of the sentences generated by data augmentation is lower, and that increasing the size of the augmentation further improves calibration and uncertainty.
Authors: Romain Pic, Cl\'ement Dombry, Philippe Naveau, Maxime Taillardat
Abstract: Accurate precipitation forecasts have a high socio-economic value due to their role in decision-making in various fields such as transport networks and farming. We propose a global statistical postprocessing method for grid-based precipitation ensemble forecasts. This U-Net-based distributional regression method predicts marginal distributions in the form of parametric distributions inferred by scoring rule minimization. Distributional regression U-Nets are compared to state-of-the-art postprocessing methods for daily 21-h forecasts of 3-h accumulated precipitation over the South of France. Training data comes from the M\'et\'eo-France weather model AROME-EPS and spans 3 years. A practical challenge appears when consistent data or reforecasts are not available. Distributional regression U-Nets compete favorably with the raw ensemble. In terms of continuous ranked probability score, they reach a performance comparable to quantile regression forests (QRF). However, they are unable to provide calibrated forecasts in areas associated with high climatological precipitation. In terms of predictive power for heavy precipitation events, they outperform both QRF and semi-parametric QRF with tail extensions.
Authors: Wataru Hashimoto, Hidetaka Kamigaito, Taro Watanabe
Abstract: Trustworthy prediction in Deep Neural Networks (DNNs), including Pre-trained Language Models (PLMs) is important for safety-critical applications in the real world. However, DNNs often suffer from uncertainty estimation, such as miscalibration. In particular, approaches that require multiple stochastic inference can mitigate this problem, but the expensive cost of inference makes them impractical. In this study, we propose $k$-Nearest Neighbor Uncertainty Estimation ($k$NN-UE), which is an uncertainty estimation method that uses the distances from the neighbors and label-existence ratio of neighbors. Experiments on sentiment analysis, natural language inference, and named entity recognition show that our proposed method outperforms the baselines or recent density-based methods in confidence calibration, selective prediction, and out-of-distribution detection. Moreover, our analyses indicate that introducing dimension reduction or approximate nearest neighbor search inspired by recent $k$NN-LM studies reduces the inference overhead without significantly degrading estimation performance when combined them appropriately.
Authors: Nadine Kroher, Steven Manangu, Aggelos Pikrakis
Abstract: Most contemporary music tagging systems rely on large volumes of annotated data. As an alternative, we investigate the extent to which synthetically generated music excerpts can improve tagging systems when only small annotated collections are available. To this end, we release GTZAN-synth, a synthetic dataset that follows the taxonomy of the well-known GTZAN dataset while being ten times larger in data volume. We first observe that simply adding this synthetic dataset to the training split of GTZAN does not result into performance improvements. We then proceed to investigating domain adaptation, transfer learning and fine-tuning strategies for the task at hand and draw the conclusion that the last two options yield an increase in accuracy. Overall, the proposed approach can be considered as a first guide in a promising field for future research.
Authors: Jiaru Zou, Mengyu Zhou, Tao Li, Shi Han, Dongmei Zhang
Abstract: Large language models (LLMs) have played a fundamental role in various natural language processing tasks with powerful prompt techniques. However, in real-world applications, there are often similar prompt components for repeated queries, which causes significant computational burdens during inference. Existing prompt compression and direct fine-tuning methods aim to tackle these challenges, yet they frequently struggle to strike an optimal balance between cost-efficiency and performance effectiveness, especially in complex tasks such as NL2Code. In this paper, we propose a novel method namely PromptIntern to internalize the prompt knowledge into model parameters via progressive fine-tuning. Our method enables LLMs to emulate the human learning process for a new task, where detailed templates and examples in a prompt are gradually internalized and phased out progressively as the model grows accustomed to the task. Extensive experiments demonstrate that our method reduces inference tokens over 90%, speedups inference by 4.2 times, and saves 88.3% monetary cost.
Authors: Ammar N. Abbas, Shakra Mehak, Georgios C. Chasparis, John D. Kelleher, Michael Guilfoyle, Maria Chiara Leva, Aswin K Ramasubramanian
Abstract: This study presents a novel methodology incorporating safety constraints into a robotic simulation during the training of deep reinforcement learning (DRL). The framework integrates specific parts of the safety requirements, such as velocity constraints, as specified by ISO 10218, directly within the DRL model that becomes a part of the robot's learning algorithm. The study then evaluated the efficiency of these safety constraints by subjecting the DRL model to various scenarios, including grasping tasks with and without obstacle avoidance. The validation process involved comprehensive simulation-based testing of the DRL model's responses to potential hazards and its compliance. Also, the performance of the system is carried out by the functional safety standards IEC 61508 to determine the safety integrity level. The study indicated a significant improvement in the safety performance of the robotic system. The proposed DRL model anticipates and mitigates hazards while maintaining operational efficiency. This study was validated in a testbed with a collaborative robotic arm with safety sensors and assessed with metrics such as the average number of safety violations, obstacle avoidance, and the number of successful grasps. The proposed approach outperforms the conventional method by a 16.5% average success rate on the tested scenarios in the simulations and 2.5% in the testbed without safety violations. The project repository is available at https://github.com/ammar-n-abbas/sim2real-ur-gym-gazebo.
URLs: https://github.com/ammar-n-abbas/sim2real-ur-gym-gazebo.
Authors: Ian Wu, Sravan Jayanthi, Vijay Viswanathan, Simon Rosenberg, Sina Pakazad, Tongshuang Wu, Graham Neubig
Abstract: Multimodal Retrieval Augmented Generation (MMRAG) is a powerful approach to question-answering over multimodal documents. A key challenge with evaluating MMRAG is the paucity of high-quality datasets matching the question styles and modalities of interest. In light of this, we propose SMMQG, a synthetic data generation framework. SMMQG leverages interplay between a retriever, large language model (LLM) and large multimodal model (LMM) to generate question and answer pairs directly from multimodal documents, with the questions conforming to specified styles and modalities. We use SMMQG to generate an MMRAG dataset of 1024 questions over Wikipedia documents and evaluate state-of-the-art models using it, revealing insights into model performance that are attainable only through style- and modality-specific evaluation data. Next, we measure the quality of data produced by SMMQG via a human study. We find that the quality of our synthetic data is on par with the quality of the crowdsourced benchmark MMQA and that downstream evaluation results using both datasets strongly concur.
Authors: Akash Dutta, Ali Jannesari
Abstract: One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate Representations (IRs) for extracting features from source code. Most such works target specific tasks, or are designed with a pre-defined set of heuristics. So far, pre-trained models are rare in this domain, but the possibilities have been widely discussed. Especially approaches mimicking large-language models (LLMs) have been proposed. But these have prohibitively large training costs. In this paper, we propose MIREncoder, a M}ulti-modal IR-based Auto-Encoder that can be pre-trained to generate a learned embedding space to be used for downstream tasks by machine learning-based approaches. A multi-modal approach enables us to better extract features from compilable programs. It allows us to better model code syntax, semantics and structure. For code-based performance optimizations, these features are very important while making optimization decisions. A pre-trained model/embedding implicitly enables the usage of transfer learning, and helps move away from task-specific trained models. Additionally, a pre-trained model used for downstream performance optimization should itself have reduced overhead, and be easily usable. These considerations have led us to propose a modeling approach that i) understands code semantics and structure, ii) enables use of transfer learning, and iii) is small and simple enough to be easily re-purposed or reused even with low resource availability. Our evaluations will show that our proposed approach can outperform the state of the art while reducing overhead.
Authors: Kathryn McConkey, Talha Enes Ayranci, Mohamed Khamis, Jonathan Grizou
Abstract: Personalising an interface to the needs and preferences of a user often incurs additional interaction steps. In this paper, we demonstrate a novel method that enables the personalising of an interface without the need for explicit calibration procedures, via a process we call self-calibration. A second-order effect of self-calibration is that an outside observer cannot easily infer what a user is trying to achieve because they cannot interpret the user's actions. To explore this security angle, we developed IFTT-PIN (If This Then PIN) as the first self-calibrating PIN-entry method. When using IFTT-PIN, users are free to choose any button for any meaning without ever explicitly communicating their choice to the machine. IFTT-PIN infers both the user's PIN and their preferred button mapping at the same time. This paper presents the concept, implementation, and interactive demonstrations of IFTT-PIN, as well as an evaluation against shoulder surfing attacks. Our study (N=24) shows that by adding self-calibration to an existing PIN entry method, IFTT-PIN statistically significantly decreased PIN attack decoding rate by ca. 8.5 times (p=1.1e-9), while only decreasing the PIN entry encoding rate by ca. 1.4 times (p=0.02), leading to a positive security-usability trade-off. IFTT-PIN's entry rate significantly improved 21 days after first exposure (p=3.6e-6) to the method, suggesting self-calibrating interfaces are memorable despite using an initially undefined user interface. Self-calibration methods might lead to novel opportunities for interaction that are more inclusive and versatile, a potentially interesting challenge for the community. A short introductory video is available at https://youtu.be/pP5sfniNRns.
Authors: Anxhelo Diko, Danilo Avola, Bardh Prenkaj, Federico Fontana, Luigi Cinque
Abstract: Action anticipation is the task of forecasting future activity from a partially observed sequence of events. However, this task is exposed to intrinsic future uncertainty and the difficulty of reasoning upon interconnected actions. Unlike previous works that focus on extrapolating better visual and temporal information, we concentrate on learning action representations that are aware of their semantic interconnectivity based on prototypical action patterns and contextual co-occurrences. To this end, we propose the novel Semantically Guided Representation Learning (S-GEAR) framework. S-GEAR learns visual action prototypes and leverages language models to structure their relationship, inducing semanticity. To gather insights on S-GEAR's effectiveness, we test it on four action anticipation benchmarks, obtaining improved results compared to previous works: +3.5, +2.7, and +3.5 absolute points on Top-1 Accuracy on Epic-Kitchen 55, EGTEA Gaze+ and 50 Salads, respectively, and +0.8 on Top-5 Recall on Epic-Kitchens 100. We further observe that S-GEAR effectively transfers the geometric associations between actions from language to visual prototypes. Finally, S-GEAR opens new research frontiers in anticipation tasks by demonstrating the intricate impact of action semantic interconnectivity.
Authors: Yurui Huang, Yang Yang, Shou Chen, Xiangyu Wu, Qingguo Chen, Jianfeng Lu
Abstract: In this paper, we propose a solution for improving the quality of temporal sound localization. We employ a multimodal fusion approach to combine visual and audio features. High-quality visual features are extracted using a state-of-the-art self-supervised pre-training network, resulting in efficient video feature representations. At the same time, audio features serve as complementary information to help the model better localize the start and end of sounds. The fused features are trained in a multi-scale Transformer for training. In the final test dataset, we achieved a mean average precision (mAP) of 0.33, obtaining the second-best performance in this track.
Authors: Zhipeng Deng, Luyang Luo, Hao Chen
Abstract: The right to be forgotten, as stated in most data regulations, poses an underexplored challenge in federated learning (FL), leading to the development of federated unlearning (FU). However, current FU approaches often face trade-offs between efficiency, model performance, forgetting efficacy, and privacy preservation. In this paper, we delve into the paradigm of Federated Client Unlearning (FCU) to guarantee a client the right to erase the contribution or the influence, introducing the first FU framework in medical imaging. In the unlearning process of a client, the proposed model-contrastive unlearning marks a pioneering step towards feature-level unlearning, and frequency-guided memory preservation ensures smooth forgetting of local knowledge while maintaining the generalizability of the trained global model, thus avoiding performance compromises and guaranteeing rapid post-training. We evaluated our FCU framework on two public medical image datasets, including Intracranial hemorrhage diagnosis and skin lesion diagnosis, demonstrating that our framework outperformed other state-of-the-art FU frameworks, with an expected speed-up of 10-15 times compared with retraining from scratch. The code and the organized datasets can be found at: https://github.com/dzp2095/FCU.
Authors: Xuqi Zhu, Huaizhi Zhang, JunKyu Lee, Jiacheng Zhu, Chandrajit Pal, Sangeet Saha, Klaus D. McDonald-Maier, Xiaojun Zhai
Abstract: Modern Neural Network (NN) architectures heavily rely on vast numbers of multiply-accumulate arithmetic operations, constituting the predominant computational cost. Therefore, this paper proposes a high-throughput, scalable and energy efficient non-element-wise matrix multiplication unit on FPGAs as a basic component of the NNs. We firstly streamline inter-layer and intra-layer redundancies of MADDNESS algorithm, a LUT-based approximate matrix multiplication, to design a fast, efficient scalable approximate matrix multiplication module termed "Approximate Multiplication Unit (AMU)". The AMU optimizes LUT-based matrix multiplications further through dedicated memory management and access design, decoupling computational overhead from input resolution and boosting FPGA-based NN accelerator efficiency significantly. The experimental results show that using our AMU achieves up to 9x higher throughput and 112x higher energy efficiency over the state-of-the-art solutions for the FPGA-based Quantised Neural Network (QNN) accelerators.
Authors: Zhiqi Zhao, Chang Wu, Xiaotong Kong, Zejie Lv, Xiaoqi Du, Qiyan Li
Abstract: Simultaneous Localization and Mapping (SLAM) has become a critical technology for intelligent transportation systems and autonomous robots and is widely used in autonomous driving. However, traditional manual feature-based methods in challenging lighting environments make it difficult to ensure robustness and accuracy. Some deep learning-based methods show potential but still have significant drawbacks. To address this problem, we propose a novel hybrid system for visual SLAM based on the LightGlue deep learning network. It uses deep local feature descriptors to replace traditional hand-crafted features and a more efficient and accurate deep network to achieve fast and precise feature matching. Thus, we use the robustness of deep learning to improve the whole system. We have combined traditional geometry-based approaches to introduce a complete visual SLAM system for monocular, binocular, and RGB-D sensors. We thoroughly tested the proposed system on four public datasets: KITTI, EuRoC, TUM, and 4Season, as well as on actual campus scenes. The experimental results show that the proposed method exhibits better accuracy and robustness in adapting to low-light and strongly light-varying environments than traditional manual features and deep learning-based methods. It can also run on GPU in real time.
Authors: Sayan Nag, Koustava Goswami, Srikrishna Karanam
Abstract: Referring Expression Segmentation (RES) aims to provide a segmentation mask of the target object in an image referred to by the text (i.e., referring expression). Existing methods require large-scale mask annotations. Moreover, such approaches do not generalize well to unseen/zero-shot scenarios. To address the aforementioned issues, we propose a weakly-supervised bootstrapping architecture for RES with several new algorithmic innovations. To the best of our knowledge, ours is the first approach that considers only a fraction of both mask and box annotations (shown in Figure 1 and Table 1) for training. To enable principled training of models in such low-annotation settings, improve image-text region-level alignment, and further enhance spatial localization of the target object in the image, we propose Cross-modal Fusion with Attention Consistency module. For automatic pseudo-labeling of unlabeled samples, we introduce a novel Mask Validity Filtering routine based on a spatially aware zero-shot proposal scoring approach. Extensive experiments show that with just 30% annotations, our model SafaRi achieves 59.31 and 48.26 mIoUs as compared to 58.93 and 48.19 mIoUs obtained by the fully-supervised SOTA method SeqTR respectively on RefCOCO+@testA and RefCOCO+testB datasets. SafaRi also outperforms SeqTR by 11.7% (on RefCOCO+testA) and 19.6% (on RefCOCO+testB) in a fully-supervised setting and demonstrates strong generalization capabilities in unseen/zero-shot tasks.
Authors: Amy Li, Sihang Liu, Yi Ding
Abstract: This paper represents the first effort to quantify uncertainty in carbon intensity forecasting for datacenter decarbonization. We identify and analyze two types of uncertainty -- temporal and spatial -- and discuss their system implications. To address the temporal dynamics in quantifying uncertainty for carbon intensity forecasting, we introduce a conformal prediction-based framework. Evaluation results show that our technique robustly achieves target coverages in uncertainty quantification across various significance levels. We conduct two case studies using production power traces, focusing on temporal and spatial load shifting respectively. The results show that incorporating uncertainty into scheduling decisions can prevent a 5% and 14% increase in carbon emissions, respectively. These percentages translate to an absolute reduction of 2.1 and 10.4 tons of carbon emissions in a 20 MW datacenter cluster.
Authors: Lorenzo Lamberti, Vlad Niculescu, Micha{\l} Barcis, Lorenzo Bellone, Enrico Natalizio, Luca Benini, Daniele Palossi
Abstract: Pocket-sized autonomous nano-drones can revolutionize many robotic use cases, such as visual inspection in narrow, constrained spaces, and ensure safer human-robot interaction due to their tiny form factor and weight -- i.e., tens of grams. This compelling vision is challenged by the high level of intelligence needed aboard, which clashes against the limited computational and storage resources available on PULP (parallel-ultra-low-power) MCU class navigation and mission controllers that can be hosted aboard. This work moves from PULP-Dronet, a State-of-the-Art convolutional neural network for autonomous navigation on nano-drones. We introduce Tiny-PULP-Dronet: a novel methodology to squeeze by more than one order of magnitude model size (50x fewer parameters), and number of operations (27x less multiply-and-accumulate) required to run inference with similar flight performance as PULP-Dronet. This massive reduction paves the way towards affordable multi-tasking on nano-drones, a fundamental requirement for achieving high-level intelligence.
Authors: Song Wang, Peng Wang, Tong Zhou, Yushun Dong, Zhen Tan, Jundong Li
Abstract: As Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks, concerns regarding the potential negative societal impacts of LLM-generated content have also arisen. To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets. However, existing bias evaluation efforts often focus on only a particular type of bias and employ inconsistent evaluation metrics, leading to difficulties in comparison across different datasets and LLMs. To address these limitations, we collect a variety of datasets designed for the bias evaluation of LLMs, and further propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks. The curation of CEB is based on our newly proposed compositional taxonomy, which characterizes each dataset from three dimensions: bias types, social groups, and tasks. By combining the three dimensions, we develop a comprehensive evaluation strategy for the bias in LLMs. Our experiments demonstrate that the levels of bias vary across these dimensions, thereby providing guidance for the development of specific bias mitigation methods.
Authors: Quoc Hoan Tran, Yasuhiro Endo, Hirotaka Oshima
Abstract: Quantum machine learning (QML) requires significant quantum resources to achieve quantum advantage. Research should prioritize both the efficient design of quantum architectures and the development of learning strategies to optimize resource usage. We propose a framework called quantum curriculum learning (Q-CurL) for quantum data, where the curriculum introduces simpler tasks or data to the learning model before progressing to more challenging ones. We define the curriculum criteria based on the data density ratio between tasks to determine the curriculum order. We also implement a dynamic learning schedule to emphasize the significance of quantum data in optimizing the loss function. Empirical evidence shows that Q-CurL enhances the training convergence and the generalization for unitary learning tasks and improves the robustness of quantum phase recognition tasks. Our framework provides a general learning strategy, bringing QML closer to realizing practical advantages.
Authors: Raphael Bensadoun, Yanir Kleiman, Idan Azuri, Omri Harosh, Andrea Vedaldi, Natalia Neverova, Oran Gafni
Abstract: The recent availability and adaptability of text-to-image models has sparked a new era in many related domains that benefit from the learned text priors as well as high-quality and fast generation capabilities, one of which is texture generation for 3D objects. Although recent texture generation methods achieve impressive results by using text-to-image networks, the combination of global consistency, quality, and speed, which is crucial for advancing texture generation to real-world applications, remains elusive. To that end, we introduce Meta 3D TextureGen: a new feedforward method comprised of two sequential networks aimed at generating high-quality and globally consistent textures for arbitrary geometries of any complexity degree in less than 20 seconds. Our method achieves state-of-the-art results in quality and speed by conditioning a text-to-image model on 3D semantics in 2D space and fusing them into a complete and high-resolution UV texture map, as demonstrated by extensive qualitative and quantitative evaluations. In addition, we introduce a texture enhancement network that is capable of up-scaling any texture by an arbitrary ratio, producing 4k pixel resolution textures.
Authors: Dorothea MacPhail, David Harbecke, Lisa Raithel, Sebastian M\"oller
Abstract: An adverse drug effect (ADE) is any harmful event resulting from medical drug treatment. Despite their importance, ADEs are often under-reported in official channels. Some research has therefore turned to detecting discussions of ADEs in social media. Impressive results have been achieved in various attempts to detect ADEs. In a high-stakes domain such as medicine, however, an in-depth evaluation of a model's abilities is crucial. We address the issue of thorough performance evaluation in English-language ADE detection with hand-crafted templates for four capabilities: Temporal order, negation, sentiment, and beneficial effect. We find that models with similar performance on held-out test sets have varying results on these capabilities.
Authors: Abraham Nash
Abstract: Decentralized Intelligence Network (DIN) addresses the significant challenges of data sovereignty and AI utilization caused by the fragmentation and siloing of data across providers and institutions. This comprehensive framework overcomes access barriers to scalable data sources previously hindered by silos by leveraging: 1) personal data stores as a prerequisite for data sovereignty; 2) a scalable federated learning protocol implemented on a public blockchain for decentralized AI training, where data remains with participants and only model parameter updates are shared; and 3) a scalable, trustless rewards mechanism to incentivize participation and ensure fair reward distribution. This framework ensures that no entity can prevent or control access to training on data offered by participants or determine financial benefits, as these processes operate on a public blockchain with an immutable record and without a third party. It supports effective AI training, allowing participants to maintain control over their data, benefit financially, and contribute to a decentralized, scalable ecosystem that leverages collective AI to develop beneficial algorithms.
Authors: Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, Bryan Catanzaro
Abstract: Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel instruction fine-tuning framework RankRAG, which instruction-tunes a single LLM for the dual purpose of context ranking and answer generation in RAG. In particular, the instruction-tuned LLMs work surprisingly well by adding a small fraction of ranking data into the training blend, and outperform existing expert ranking models, including the same LLM exclusively fine-tuned on a large amount of ranking data. For generation, we compare our model with many strong baselines, including GPT-4-0613, GPT-4-turbo-2024-0409, and ChatQA-1.5, an open-sourced model with the state-of-the-art performance on RAG benchmarks. Specifically, our Llama3-RankRAG significantly outperforms Llama3-ChatQA-1.5 and GPT-4 models on nine knowledge-intensive benchmarks. In addition, it also performs comparably to GPT-4 on five RAG benchmarks in the biomedical domain without instruction fine-tuning on biomedical data, demonstrating its superb capability for generalization to new domains.
Authors: Ali Safaya, Deniz Yuret
Abstract: This paper introduces Neurocache, an approach to extend the effective context size of large language models (LLMs) using an external vector cache to store its past states. Like recent vector retrieval approaches, Neurocache uses an efficient k-nearest-neighbor (kNN) algorithm to retrieve relevant past states and incorporate them into the attention process. Neurocache improves upon previous methods by (1) storing compressed states, which reduces cache size; (2) performing a single retrieval operation per token which increases inference speed; and (3) extending the retrieval window to neighboring states, which improves both language modeling and downstream task accuracy. Our experiments show the effectiveness of Neurocache both for models trained from scratch and for pre-trained models such as Llama2-7B and Mistral-7B when enhanced with the cache mechanism. We also compare Neurocache with text retrieval methods and show improvements in single-document question-answering and few-shot learning tasks. We made the source code available under: https://github.com/alisafaya/neurocache
Authors: Nataniel Ruiz, Yuanzhen Li, Neal Wadhwa, Yael Pritch, Michael Rubinstein, David E. Jacobs, Shlomi Fruchter
Abstract: We present Magic Insert, a method for dragging-and-dropping subjects from a user-provided image into a target image of a different style in a physically plausible manner while matching the style of the target image. This work formalizes the problem of style-aware drag-and-drop and presents a method for tackling it by addressing two sub-problems: style-aware personalization and realistic object insertion in stylized images. For style-aware personalization, our method first fine-tunes a pretrained text-to-image diffusion model using LoRA and learned text tokens on the subject image, and then infuses it with a CLIP representation of the target style. For object insertion, we use Bootstrapped Domain Adaption to adapt a domain-specific photorealistic object insertion model to the domain of diverse artistic styles. Overall, the method significantly outperforms traditional approaches such as inpainting. Finally, we present a dataset, SubjectPlop, to facilitate evaluation and future progress in this area. Project page: https://magicinsert.github.io/
Authors: Huiqiang Jiang, Yucheng Li, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir H. Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu
Abstract: The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method designed to accelerate pre-filling of long-sequence processing. Specifically, we identify three unique patterns in long-context attention matrices-the A-shape, Vertical-Slash, and Block-Sparsethat can be leveraged for efficient sparse computation on GPUs. We determine the optimal pattern for each attention head offline and dynamically build sparse indices based on the assigned pattern during inference. With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs. Our proposed technique can be directly applied to existing LLMs without any modifications to the pre-training setup or additional fine-tuning. By evaluating on a wide range of downstream tasks, including InfiniteBench, RULER, PG-19, and Needle In A Haystack, and models including LLaMA-3-1M, GLM4-1M, Yi-200K, Phi-3-128K, and Qwen2-128K, we demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy. Our code is available at https://aka.ms/MInference.
Authors: Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey, Masahiro Ikeda, Sham Kakade, Yoshinobu Kawahara
Abstract: Most modern reinforcement learning algorithms optimize a cumulative single-step cost along a trajectory. The optimized motions are often 'unnatural', representing, for example, behaviors with sudden accelerations that waste energy and lack predictability. In this work, we present a novel paradigm of controlling nonlinear systems via the minimization of the Koopman spectrum cost: a cost over the Koopman operator of the controlled dynamics. This induces a broader class of dynamical behaviors that evolve over stable manifolds such as nonlinear oscillators, closed loops, and smooth movements. We demonstrate that some dynamics characterizations that are not possible with a cumulative cost are feasible in this paradigm, which generalizes the classical eigenstructure and pole assignments to nonlinear decision making. Moreover, we present a sample efficient online learning algorithm for our problem that enjoys a sub-linear regret bound under some structural assumptions.
Authors: XinYu Piao, DoangJoo Synn, JooYoung Park, Jong-Kook Kim
Abstract: Recent deep learning models are difficult to train using a large batch size, because commodity machines may not have enough memory to accommodate both the model and a large data batch size. The batch size is one of the hyper-parameters used in the training model, and it is dependent on and is limited by the target machine memory capacity because the batch size can only fit into the remaining memory after the model is uploaded. Moreover, the data item size is also an important factor because if each data item size is larger then the batch size that can fit into the remaining memory becomes smaller. This paper proposes a method called Micro-Batch Processing (MBP) to address this problem. This method helps deep learning models to train by providing a batch processing method that splits a batch into a size that can fit in the remaining memory and processes them sequentially. After processing the small batches individually, a loss normalization algorithm based on the gradient accumulation is used to maintain the performance. The purpose of our method is to allow deep learning models to train using larger batch sizes that exceed the memory capacity of a system without increasing the memory size or using multiple devices (GPUs).
Authors: Hilde Weerts, Lamb\`er Royakkers, Mykola Pechenizkiy
Abstract: Fairness-aware machine learning (fair-ml) techniques are algorithmic interventions designed to ensure that individuals who are affected by the predictions of a machine learning model are treated fairly. The problem is often posed as an optimization problem, where the objective is to achieve high predictive performance under a quantitative fairness constraint. However, any attempt to design a fair-ml algorithm must assume a world where Goodhart's law has an exception: when a fairness measure becomes an optimization constraint, it does not cease to be a good measure. In this paper, we argue that fairness measures are particularly sensitive to Goodhart's law. Our main contributions are as follows. First, we present a framework for moral reasoning about the justification of fairness metrics. In contrast to existing work, our framework incorporates the belief that whether a distribution of outcomes is fair, depends not only on the cause of inequalities but also on what moral claims decision subjects have to receive a particular benefit or avoid a burden. We use the framework to distil moral and empirical assumptions under which particular fairness metrics correspond to a fair distribution of outcomes. Second, we explore the extent to which employing fairness metrics as a constraint in a fair-ml algorithm is morally justifiable, exemplified by the fair-ml algorithm introduced by Hardt et al. (2016). We illustrate that enforcing a fairness metric through a fair-ml algorithm often does not result in the fair distribution of outcomes that motivated its use and can even harm the individuals the intervention was intended to protect.
Authors: Mantas Luko\v{s}evi\v{c}ius, Arnas Uselis
Abstract: Data are often sampled irregularly in time. Dealing with this using Recurrent Neural Networks (RNNs) traditionally involved ignoring the fact, feeding the time differences as additional inputs, or resampling the data. All these methods have their shortcomings. We propose an elegant straightforward alternative approach where instead the RNN is in effect resampled in time to match the time of the data or the task at hand. We use Echo State Network (ESN) and Gated Recurrent Unit (GRU) as the basis for our solution. Such RNNs can be seen as discretizations of continuous-time dynamical systems, which gives a solid theoretical ground to our approach. Our Task-Synchronized ESN (TSESN) and GRU (TSGRU) models allow for a direct model time setting and require no additional training, parameter tuning, or computation (solving differential equations or interpolating data) compared to their regular counterparts, thus retaining their original efficiency. We confirm empirically that our models can effectively compensate for the time-non-uniformity of the data and demonstrate that they compare favorably to data resampling, classical RNN methods, and alternative RNN models proposed to deal with time irregularities on several real-world nonuniform-time datasets. We open-source the code at https://github.com/oshapio/task-synchronized-RNNs .
Authors: Xuefeng Gao, Xun Yu Zhou
Abstract: We consider reinforcement learning for continuous-time Markov decision processes (MDPs) in the infinite-horizon, average-reward setting. In contrast to discrete-time MDPs, a continuous-time process moves to a state and stays there for a random holding time after an action is taken. With unknown transition probabilities and rates of exponential holding times, we derive instance-dependent regret lower bounds that are logarithmic in the time horizon. Moreover, we design a learning algorithm and establish a finite-time regret bound that achieves the logarithmic growth rate. Our analysis builds upon upper confidence reinforcement learning, a delicate estimation of the mean holding times, and stochastic comparison of point processes.
Authors: Hamza Keurti, Hsiao-Ru Pan, Michel Besserve, Benjamin F. Grewe, Bernhard Sch\"olkopf
Abstract: How can agents learn internal models that veridically represent interactions with the real world is a largely open question. As machine learning is moving towards representations containing not just observational but also interventional knowledge, we study this problem using tools from representation learning and group theory. We propose methods enabling an agent acting upon the world to learn internal representations of sensory information that are consistent with actions that modify it. We use an autoencoder equipped with a group representation acting on its latent space, trained using an equivariance-derived loss in order to enforce a suitable homomorphism property on the group representation. In contrast to existing work, our approach does not require prior knowledge of the group and does not restrict the set of actions the agent can perform. We motivate our method theoretically, and show empirically that it can learn a group representation of the actions, thereby capturing the structure of the set of transformations applied to the environment. We further show that this allows agents to predict the effect of sequences of future actions with improved accuracy.
Authors: Syed Asad Rizvi, Nazreen Pallikkavaliyaveetil, David Zhang, Zhuoyang Lyu, Nhi Nguyen, Haoran Lyu, Benjamin Christensen, Josue Ortega Caro, Antonio H. O. Fonseca, Emanuele Zappala, Maryam Bagherian, Christopher Averill, Chadi G. Abdallah, Amin Karbasi, Rex Ying, Maria Brbic, Rahul Madhav Dhodapkar, David van Dijk
Abstract: Foundation models have achieved remarkable success across many domains, relying on pretraining over vast amounts of data. Graph-structured data often lacks the same scale as unstructured data, making the development of graph foundation models challenging. In this work, we propose Foundation-Informed Message Passing (FIMP), a Graph Neural Network (GNN) message-passing framework that leverages pretrained non-textual foundation models in graph-based tasks. We show that the self-attention layers of foundation models can effectively be repurposed on graphs to perform cross-node attention-based message-passing. Our model is evaluated on a real-world image network dataset and two biological applications (single-cell RNA sequencing data and fMRI brain activity recordings) in both finetuned and zero-shot settings. FIMP outperforms strong baselines, demonstrating that it can effectively leverage state-of-the-art foundation models in graph tasks.
Authors: Jin-Zhu Yu, Hiba Baroud
Abstract: Hierarchical Bayesian Poisson regression models (HBPRMs) provide a flexible modeling approach of the relationship between predictors and count response variables. The applications of HBPRMs to large-scale datasets require efficient inference algorithms due to the high computational cost of inferring many model parameters based on random sampling. Although Markov Chain Monte Carlo (MCMC) algorithms have been widely used for Bayesian inference, sampling using this class of algorithms is time-consuming for applications with large-scale data and time-sensitive decision-making, partially due to the non-conjugacy of many models. To overcome this limitation, this research develops an approximate Gibbs sampler (AGS) to efficiently learn the HBPRMs while maintaining the inference accuracy. In the proposed sampler, the data likelihood is approximated with Gaussian distribution such that the conditional posterior of the coefficients has a closed-form solution. Numerical experiments using real and synthetic datasets with small and large counts demonstrate the superior performance of AGS in comparison to the state-of-the-art sampling algorithm, especially for large datasets.
Authors: Axel Klawonn, Martin Lanser, Janine Weber
Abstract: Deep neural networks (DNNs) and, in particular, convolutional neural networks (CNNs) have brought significant advances in a wide range of modern computer application problems. However, the increasing availability of large amounts of datasets as well as the increasing available computational power of modern computers lead to a steady growth in the complexity and size of DNN and CNN models, respectively, and thus, to longer training times. Hence, various methods and attempts have been developed to accelerate and parallelize the training of complex network architectures. In this work, a novel CNN-DNN architecture is proposed that naturally supports a model parallel training strategy and that is loosely inspired by two-level domain decomposition methods (DDM). First, local CNN models, that is, subnetworks, are defined that operate on overlapping or nonoverlapping parts of the input data, for example, sub-images. The subnetworks can be trained completely in parallel and independently of each other. Each subnetwork then outputs a local decision for the given machine learning problem which is exclusively based on the respective local input data. Subsequently, in a second step, an additional DNN model is trained which evaluates the local decisions of the local subnetworks and generates a final, global decision. In this paper, we apply the proposed architecture to image classification problems using CNNs. Experimental results for different 2D image classification problems are provided as well as a face recognition problem, and a classification problem for 3D computer tomography (CT) scans. Therefore, classical ResNet and VGG architectures are considered. The results show that the proposed approach can significantly accelerate the required training time compared to the global model and, additionally, can also help to improve the accuracy of the underlying classification problem.
Authors: Liu Ziyin, Botao Li, Tomer Galanti, Masahito Ueda
Abstract: Characterizing and understanding the dynamics of stochastic gradient descent (SGD) around saddle points remains an open problem. We first show that saddle points in neural networks can be divided into two types, among which the Type-II saddles are especially difficult to escape from because the gradient noise vanishes at the saddle. The dynamics of SGD around these saddles are thus to leading order described by a random matrix product process, and it is thus natural to study the dynamics of SGD around these saddles using the notion of probabilistic stability and the related Lyapunov exponent. Theoretically, we link the study of SGD dynamics to well-known concepts in ergodic theory, which we leverage to show that saddle points can be either attractive or repulsive for SGD, and its dynamics can be classified into four different phases, depending on the signal-to-noise ratio in the gradient close to the saddle.
Authors: Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
Abstract: Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are crucial to meet memory and inference time requirements, as well as to reduce inference costs. Building small, fast, and private domain-specific language models is a thriving area of research. In this work, we show that a careful pre-training on a \emph{subset} of the public dataset that is guided by the private dataset is crucial to train small language models with differential privacy. On standard benchmarks, small models trained with our new framework achieve state-of-the-art performance. In addition to performance improvements, our results demonstrate that smaller models, through careful pre-training and private fine-tuning, can match the performance of much larger models that do not have access to private data. This underscores the potential of private learning for model compression and enhanced efficiency.
Authors: Hejie Ying, Mengmeng Song, Yaohong Tang, Shungen Xiao, Zimin Xiao
Abstract: Deep neural networks (DNN) have achieved remarkable success in various fields, including computer vision and natural language processing. However, training an effective DNN model still poses challenges. This paper aims to propose a method to optimize the training effectiveness of DNN, with the goal of improving model performance. Firstly, based on the observation that the DNN parameters change in certain laws during training process, the potential of parameter prediction for improving model training efficiency and performance is discovered. Secondly, considering the magnitude of DNN model parameters, hardware limitations and characteristics of Stochastic Gradient Descent (SGD) for noise tolerance, a Parameter Linear Prediction (PLP) method is exploit to perform DNN parameter prediction. Finally, validations are carried out on some representative backbones. Experiment results show that compare to the normal training ways, under the same training conditions and epochs, by employing proposed PLP method, the optimal model is able to obtain average about 1% accuracy improvement and 0.01 top-1/top-5 error reduction for Vgg16, Resnet18 and GoogLeNet based on CIFAR-100 dataset, which shown the effectiveness of the proposed method on different DNN structures, and validated its capacity in enhancing DNN training efficiency and performance.
Authors: Emma Cramer, Jonas Reiher, Sebastian Trimpe
Abstract: Reinforcement learning (RL) for robot control typically requires a detailed representation of the environment state, including information about task-relevant objects not directly measurable. Keypoint detectors, such as spatial autoencoders (SAEs), are a common approach to extracting a low-dimensional representation from high-dimensional image data. SAEs aim at spatial features such as object positions, which are often useful representations in robotic RL. However, whether an SAE is actually able to track objects in the scene and thus yields a spatial state representation well suited for RL tasks has rarely been examined due to a lack of established metrics. In this paper, we propose to assess the performance of an SAE instance by measuring how well keypoints track ground truth objects in images. We present a computationally lightweight metric and use it to evaluate common baseline SAE architectures on image data from a simulated robot task. We find that common SAEs differ substantially in their spatial extraction capability. Furthermore, we validate that SAEs that perform well in our metric achieve superior performance when used in downstream RL. Thus, our metric is an effective and lightweight indicator of RL performance before executing expensive RL training. Building on these insights, we identify three key modifications of SAE architectures to improve tracking performance.
Authors: Tong Xia, Abhirup Ghosh, Xinchi Qiu, Cecilia Mascolo
Abstract: Federated Learning (FL) enables model development by leveraging data distributed across numerous edge devices without transferring local data to a central server. However, existing FL methods still face challenges when dealing with scarce and label-skewed data across devices, resulting in local model overfitting and drift, consequently hindering the performance of the global model. In response to these challenges, we propose a pioneering framework called \textit{FLea}, incorporating the following key components: \textit{i)} A global feature buffer that stores activation-target pairs shared from multiple clients to support local training. This design mitigates local model drift caused by the absence of certain classes; \textit{ii)} A feature augmentation approach based on local and global activation mix-ups for local training. This strategy enlarges the training samples, thereby reducing the risk of local overfitting; \textit{iii)} An obfuscation method to minimize the correlation between intermediate activations and the source data, enhancing the privacy of shared features. To verify the superiority of \textit{FLea}, we conduct extensive experiments using a wide range of data modalities, simulating different levels of local data scarcity and label skew. The results demonstrate that \textit{FLea} consistently outperforms state-of-the-art FL counterparts (among 13 of the experimented 18 settings, the improvement is over $5\%$) while concurrently mitigating the privacy vulnerabilities associated with shared features. Code is available at https://github.com/XTxiatong/FLea.git
Authors: Gleb Ryzhakov, Svetlana Pavlova, Egor Sevriugov, Ivan Oseledets
Abstract: This paper proposes a novel method, Explicit Flow Matching (ExFM), for training and analyzing flow-based generative models. ExFM leverages a theoretically grounded loss function, ExFM loss (a tractable form of Flow Matching (FM) loss), to demonstrably reduce variance during training, leading to faster convergence and more stable learning. Based on theoretical analysis of these formulas, we derived exact expressions for the vector field (and score in stochastic cases) for model examples (in particular, for separating multiple exponents), and in some simple cases, exact solutions for trajectories. In addition, we also investigated simple cases of diffusion generative models by adding a stochastic term and obtained an explicit form of the expression for score. While the paper emphasizes the theoretical underpinnings of ExFM, it also showcases its effectiveness through numerical experiments on various datasets, including high-dimensional ones. Compared to traditional FM methods, ExFM achieves superior performance in terms of both learning speed and final outcomes.
Authors: Sijia Liu, Yuanshun Yao, Jinghan Jia, Stephen Casper, Nathalie Baracaldo, Peter Hase, Yuguang Yao, Chris Yuhao Liu, Xiaojun Xu, Hang Li, Kush R. Varshney, Mohit Bansal, Sanmi Koyejo, Yang Liu
Abstract: We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning. This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities, while maintaining the integrity of essential knowledge generation and not affecting causally unrelated information. We envision LLM unlearning becoming a pivotal element in the life-cycle management of LLMs, potentially standing as an essential foundation for developing generative AI that is not only safe, secure, and trustworthy, but also resource-efficient without the need of full retraining. We navigate the unlearning landscape in LLMs from conceptual formulation, methodologies, metrics, and applications. In particular, we highlight the often-overlooked aspects of existing LLM unlearning research, e.g., unlearning scope, data-model interaction, and multifaceted efficacy assessment. We also draw connections between LLM unlearning and related areas such as model editing, influence functions, model explanation, adversarial training, and reinforcement learning. Furthermore, we outline an effective assessment framework for LLM unlearning and explore its applications in copyright and privacy safeguards and sociotechnical harm reduction.
Authors: Cuong Dang, Dung D. Le, Thai Le
Abstract: Existing works have shown that fine-tuned textual transformer models achieve state-of-the-art prediction performances but are also vulnerable to adversarial text perturbations. Traditional adversarial evaluation is often done \textit{only after} fine-tuning the models and ignoring the training data. In this paper, we want to prove that there is also a strong correlation between training data and model robustness. To this end, we extract 13 different features representing a wide range of input fine-tuning corpora properties and use them to predict the adversarial robustness of the fine-tuned models. Focusing mostly on encoder-only transformer models BERT and RoBERTa with additional results for BART, ELECTRA, and GPT2, we provide diverse evidence to support our argument. First, empirical analyses show that (a) extracted features can be used with a lightweight classifier such as Random Forest to predict the attack success rate effectively, and (b) features with the most influence on the model robustness have a clear correlation with the robustness. Second, our framework can be used as a fast and effective additional tool for robustness evaluation since it (a) saves 30x-193x runtime compared to the traditional technique, (b) is transferable across models, (c) can be used under adversarial training, and (d) robust to statistical randomness. Our code is publicly available at \url{https://github.com/CaptainCuong/RobustText_ACL2024}.
Authors: Hao Ban, Kaiyi Ji
Abstract: By jointly learning multiple tasks, multi-task learning (MTL) can leverage the shared knowledge across tasks, resulting in improved data efficiency and generalization performance. However, a major challenge in MTL lies in the presence of conflicting gradients, which can hinder the fair optimization of some tasks and subsequently impede MTL's ability to achieve better overall performance. Inspired by fair resource allocation in communication networks, we formulate the optimization of MTL as a utility maximization problem, where the loss decreases across tasks are maximized under different fairness measurements. To solve this problem, we propose FairGrad, a novel MTL optimization method. FairGrad not only enables flexible emphasis on certain tasks but also achieves a theoretical convergence guarantee. Extensive experiments demonstrate that our method can achieve state-of-the-art performance among gradient manipulation methods on a suite of multi-task benchmarks in supervised learning and reinforcement learning. Furthermore, we incorporate the idea of $\alpha$-fairness into loss functions of various MTL methods. Extensive empirical studies demonstrate that their performance can be significantly enhanced. Code is provided at \url{https://github.com/OptMN-Lab/fairgrad}.
Authors: Daniel Iong, Matthew McAnear, Yuezhou Qu, Shasha Zou, Gabor Toth, Yang Chen
Abstract: Gaussian Processes (GP) have become popular machine-learning methods for kernel-based learning on datasets with complicated covariance structures. In this paper, we present a novel extension to the GP framework using a contaminated normal likelihood function to better account for heteroscedastic variance and outlier noise. We propose a scalable inference algorithm based on the Sparse Variational Gaussian Process (SVGP) method for fitting sparse Gaussian process regression models with contaminated normal noise on large datasets. We examine an application to geomagnetic ground perturbations, where the state-of-the-art prediction model is based on neural networks. We show that our approach yields shorter prediction intervals for similar coverage and accuracy when compared to an artificial dense neural network baseline.
Authors: Sandeep Nagar, Ehsan Farahbakhsh, Joseph Awange, Rohitash Chandra
Abstract: Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionality reduction and clustering. Dimensionality reduction methods have the potential to play a crucial role in improving the accuracy of geological maps. Although conventional dimensionality reduction methods may struggle with nonlinear data, unsupervised deep learning models such as autoencoders can model non-linear relationships. Stacked autoencoders feature multiple interconnected layers to capture hierarchical data representations useful for remote sensing data. This study presents an unsupervised machine learning-based framework for processing remote sensing data using stacked autoencoders for dimensionality reduction and k-means clustering for mapping geological units. We use Landsat 8, ASTER, and Sentinel-2 datasets to evaluate the framework for geological mapping of the Mutawintji region in Western New South Wales, Australia. We also compare stacked autoencoders with principal component analysis and canonical autoencoders. Our results reveal that the framework produces accurate and interpretable geological maps, efficiently discriminating rock units. We find that the accuracy of stacked autoencoders ranges from 86.6 % to 90 %, depending on the remote sensing data type, which is superior to their counterparts. We also find that the generated maps align with prior geological knowledge of the study area while providing novel insights into geological structures.
Authors: Matt Y Cheung, Tucker J Netherton, Laurence E Court, Ashok Veeraraghavan, Guha Balakrishnan
Abstract: Recent advancements in machine learning have led to the development of novel medical imaging systems and algorithms that address ill-posed problems. Assessing their trustworthiness and understanding how to deploy them safely at test time remains an important and open problem. In this work, we propose using conformal prediction to compute valid and distribution-free bounds on downstream metrics given reconstructions generated by one algorithm, and retrieve upper/lower bounds and inlier/outlier reconstructions according to the adjusted bounds. Our work offers 1) test time image reconstruction evaluation without ground truth, 2) downstream performance guarantees, 3) meaningful upper/lower bound reconstructions, and 4) meaningful statistical inliers/outlier reconstructions. We demonstrate our method on post-mastectomy radiotherapy planning using 3D breast CT reconstructions, and show 1) that metric-guided bounds have valid coverage for downstream metrics while conventional pixel-wise bounds do not and 2) anatomical differences of upper/lower bounds between metric-guided and pixel-wise methods. Our work paves way for more meaningful and trustworthy test-time evaluation of medical image reconstructions. Code available at https://github.com/matthewyccheung/conformal-metric
Authors: Juri Opitz
Abstract: Classification systems are evaluated in a countless number of papers. However, we find that evaluation practice is often nebulous. Frequently, metrics are selected without arguments, and blurry terminology invites misconceptions. For instance, many works use so-called 'macro' metrics to rank systems (e.g., 'macro F1') but do not clearly specify what they would expect from such a `macro' metric. This is problematic, since picking a metric can affect research findings, and thus any clarity in the process should be maximized. Starting from the intuitive concepts of bias and prevalence, we perform an analysis of common evaluation metrics. The analysis helps us understand the metrics' underlying properties, and how they align with expectations as found expressed in papers. Then we reflect on the practical situation in the field, and survey evaluation practice in recent shared tasks. We find that metric selection is often not supported with convincing arguments, an issue that can make a system ranking seem arbitrary. Our work aims at providing overview and guidance for more informed and transparent metric selection, fostering meaningful evaluation.
Authors: Pedro O. Pinheiro, Arian Jamasb, Omar Mahmood, Vishnu Sresht, Saeed Saremi
Abstract: We present VoxBind, a new score-based generative model for 3D molecules conditioned on protein structures. Our approach represents molecules as 3D atomic density grids and leverages a 3D voxel-denoising network for learning and generation. We extend the neural empirical Bayes formalism (Saremi & Hyvarinen, 2019) to the conditional setting and generate structure-conditioned molecules with a two-step procedure: (i) sample noisy molecules from the Gaussian-smoothed conditional distribution with underdamped Langevin MCMC using the learned score function and (ii) estimate clean molecules from the noisy samples with single-step denoising. Compared to the current state of the art, our model is simpler to train, significantly faster to sample from, and achieves better results on extensive in silico benchmarks -- the generated molecules are more diverse, exhibit fewer steric clashes, and bind with higher affinity to protein pockets. The code is available at https://github.com/genentech/voxbind/.
Authors: Zhao Ding, Chenguang Duan, Yuling Jiao, Ruoxuan Li, Jerry Zhijian Yang, Pingwen Zhang
Abstract: We propose the characteristic generator, a novel one-step generative model that combines the efficiency of sampling in Generative Adversarial Networks (GANs) with the stable performance of flow-based models. Our model is driven by characteristics, along which the probability density transport can be described by ordinary differential equations (ODEs). Specifically, We estimate the velocity field through nonparametric regression and utilize Euler method to solve the probability flow ODE, generating a series of discrete approximations to the characteristics. We then use a deep neural network to fit these characteristics, ensuring a one-step mapping that effectively pushes the prior distribution towards the target distribution. In the theoretical aspect, we analyze the errors in velocity matching, Euler discretization, and characteristic fitting to establish a non-asymptotic convergence rate for the characteristic generator in 2-Wasserstein distance. To the best of our knowledge, this is the first thorough analysis for simulation-free one step generative models. Additionally, our analysis refines the error analysis of flow-based generative models in prior works. We apply our method on both synthetic and real datasets, and the results demonstrate that the characteristic generator achieves high generation quality with just a single evaluation of neural network.
Authors: Jiarui Fang, Shangchun Zhao
Abstract: Sequence parallelism (SP), which divides the sequence dimension of input tensors across multiple computational devices, is becoming key to unlocking the long-context capabilities of generative AI models. This paper investigates the state-of-the-art SP approaches, i.e. DeepSpeed-Ulysses and Ring-Attention, and proposes a unified SP approach, which is more robust to transformer model architectures and network hardware topology. This paper compares the communication and memory cost of SP and existing parallelism, including data/tensor/zero/pipeline parallelism, and discusses the best practices for designing hybrid 4D parallelism involving SP. We achieved 47% MFU on two 8xA800 nodes using SP for the LLAMA3-8B model training using sequence length 208K. Our code is publicly available at https://github.com/feifeibear/long-context-attention.
Authors: Yangjun Ruan, Chris J. Maddison, Tatsunori Hashimoto
Abstract: Understanding how language model performance varies with scale is critical to benchmark and algorithm development. Scaling laws are one approach to building this understanding, but the requirement of training models across many different scales has limited their use. We propose an alternative, observational approach that bypasses model training and instead builds scaling laws from ~80 publically available models. Building a single scaling law from multiple model families is challenging due to large variations in their training compute efficiencies and capabilities. However, we show that these variations are consistent with a simple, generalized scaling law where language model performance is a function of a low-dimensional capability space, and model families only vary in their efficiency in converting training compute to capabilities. Using this approach, we show the surprising predictability of complex scaling phenomena: we show that several emergent phenomena follow a smooth, sigmoidal behavior and are predictable from small models; we show that the agent performance of models such as GPT-4 can be precisely predicted from simpler non-agentic benchmarks; and we show how to predict the impact of post-training interventions like Chain-of-Thought and Self-Consistency as language model capabilities continue to improve.
Authors: Xingtong Yu, Zhenghao Liu, Yuan Fang, Xinming Zhang
Abstract: Dynamic graphs are pervasive in the real world, modeling dynamic relations between objects across various fields. For dynamic graph modeling, dynamic graph neural networks (DGNNs) have emerged as a mainstream technique, which are generally pre-trained on the link prediction task, leaving a significant gap from the objectives of downstream tasks such as node classification. To bridge the gap, prompt-based learning has gained traction on graphs. However, existing efforts focus on static graphs, neglecting the evolution of dynamic graphs. In this paper, we propose DyGPrompt, a novel pre-training and prompting framework for dynamic graph modeling. First, we design dual prompts to address the gap in both task objectives and dynamic variations across pre-training and downstream tasks. Second, we recognize that node and time features mutually characterize each other, and propose dual condition-nets to model the evolving node-time patterns in downstream tasks. Finally, we thoroughly evaluate and analyze DyGPrompt through extensive experiments on three public datasets.
Authors: Hamed Karimi, Reza Samavi
Abstract: In this paper, we propose Evidential Conformal Prediction (ECP) method for image classifiers to generate the conformal prediction sets. Our method is designed based on a non-conformity score function that has its roots in Evidential Deep Learning (EDL) as a method of quantifying model (epistemic) uncertainty in DNN classifiers. We use evidence that are derived from the logit values of target labels to compute the components of our non-conformity score function: the heuristic notion of uncertainty in CP, uncertainty surprisal, and expected utility. Our extensive experimental evaluation demonstrates that ECP outperforms three state-of-the-art methods for generating CP sets, in terms of their set sizes and adaptivity while maintaining the coverage of true labels.
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: Ivan Rubachev, Nikolay Kartashev, Yury Gorishniy, Artem Babenko
Abstract: Benchmarks that closely reflect downstream application scenarios are essential for the streamlined adoption of new research in tabular machine learning (ML). In this work, we examine existing tabular benchmarks and find two common characteristics of industry-grade tabular data that are underrepresented in the datasets available to the academic community. First, tabular data often changes over time in real-world deployment scenarios. This impacts model performance and requires time-based train and test splits for correct model evaluation. Yet, existing academic tabular datasets often lack timestamp metadata to enable such evaluation. Second, a considerable portion of datasets in production settings stem from extensive data acquisition and feature engineering pipelines. For each specific dataset, this can have a different impact on the absolute and relative number of predictive, uninformative, and correlated features, which in turn can affect model selection. To fill the aforementioned gaps in academic benchmarks, we introduce TabReD -- a collection of eight industry-grade tabular datasets covering a wide range of domains from finance to food delivery services. We assess a large number of tabular ML models in the feature-rich, temporally-evolving data setting facilitated by TabReD. We demonstrate that evaluation on time-based data splits leads to different methods ranking, compared to evaluation on random splits more common in academic benchmarks. Furthermore, on the TabReD datasets, MLP-like architectures and GBDT show the best results, while more sophisticated DL models are yet to prove their effectiveness.
Authors: Mahmoud Ibrahim, Yasmina Al Khalil, Sina Amirrajab, Chang Sun, Marcel Breeuwer, Josien Pluim, Bart Elen, Gokhan Ertaylan, Michel Dumontier
Abstract: This paper presents a comprehensive systematic review of generative models (GANs, VAEs, DMs, and LLMs) used to synthesize various medical data types, including imaging (dermoscopic, mammographic, ultrasound, CT, MRI, and X-ray), text, time-series, and tabular data (EHR). Unlike previous narrowly focused reviews, our study encompasses a broad array of medical data modalities and explores various generative models. Our search strategy queries databases such as Scopus, PubMed, and ArXiv, focusing on recent works from January 2021 to November 2023, excluding reviews and perspectives. This period emphasizes recent advancements beyond GANs, which have been extensively covered previously. The survey reveals insights from three key aspects: (1) Synthesis applications and purpose of synthesis, (2) generation techniques, and (3) evaluation methods. It highlights clinically valid synthesis applications, demonstrating the potential of synthetic data to tackle diverse clinical requirements. While conditional models incorporating class labels, segmentation masks and image translations are prevalent, there is a gap in utilizing prior clinical knowledge and patient-specific context, suggesting a need for more personalized synthesis approaches and emphasizing the importance of tailoring generative approaches to the unique characteristics of medical data. Additionally, there is a significant gap in using synthetic data beyond augmentation, such as for validation and evaluation of downstream medical AI models. The survey uncovers that the lack of standardized evaluation methodologies tailored to medical images is a barrier to clinical application, underscoring the need for in-depth evaluation approaches, benchmarking, and comparative studies to promote openness and collaboration.
Authors: Mirco Ravanelli, Titouan Parcollet, Adel Moumen, Sylvain de Langen, Cem Subakan, Peter Plantinga, Yingzhi Wang, Pooneh Mousavi, Luca Della Libera, Artem Ploujnikov, Francesco Paissan, Davide Borra, Salah Zaiem, Zeyu Zhao, Shucong Zhang, Georgios Karakasidis, Sung-Lin Yeh, Aku Rouhe, Rudolf Braun, Florian Mai, Juan Zuluaga-Gomez, Seyed Mahed Mousavi, Andreas Nautsch, Xuechen Liu, Sangeet Sagar, Jarod Duret, Salima Mdhaffar, Gaelle Laperriere, Renato De Mori, Yannick Esteve
Abstract: SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech recognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete "recipes" of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks
Authors: Dibyajyoti Chakraborty, Seung Whan Chung, Romit Maulik
Abstract: Forecasting high-dimensional dynamical systems is a fundamental challenge in various fields, such as the geosciences and engineering. Neural Ordinary Differential Equations (NODEs), which combine the power of neural networks and numerical solvers, have emerged as a promising algorithm for forecasting complex nonlinear dynamical systems. However, classical techniques used for NODE training are ineffective for learning chaotic dynamical systems. In this work, we propose a novel NODE-training approach that allows for robust learning of chaotic dynamical systems. Our method addresses the challenges of non-convexity and exploding gradients associated with underlying chaotic dynamics. Training data trajectories from such systems are split into multiple, non-overlapping time windows. In addition to the deviation from the training data, the optimization loss term further penalizes the discontinuities of the predicted trajectory between the time windows. The window size is selected based on the fastest Lyapunov time scale of the system. Multi-step penalty(MP) method is first demonstrated on Lorenz equation, to illustrate how it improves the loss landscape and thereby accelerating the optimization convergence. MP method can optimize chaotic systems in a manner similar to least-squares shadowing with significantly lower computational costs. Our proposed algorithm, denoted the Multistep Penalty NODE(MP-NODE), is applied to chaotic systems such as the Kuramoto-Sivashinsky equation and the two-dimensional Kolmogorov flow. It is observed that MP-NODE provide viable performance for such chaotic systems, not only for short-term trajectory predictions but also for invariant statistics that are hallmarks of the chaotic nature of these dynamics.
Authors: Youngmin Seo, Jinha Kim, Unsang Park
Abstract: We propose the Swish-T family, an enhancement of the existing non-monotonic activation function Swish. Swish-T is defined by adding a Tanh bias to the original Swish function. This modification creates a family of Swish-T variants, each designed to excel in different tasks, showcasing specific advantages depending on the application context. The Tanh bias allows for broader acceptance of negative values during initial training stages, offering a smoother non-monotonic curve than the original Swish. We ultimately propose the Swish-T$_{\textbf{C}}$ function, while Swish-T and Swish-T$_{\textbf{B}}$, byproducts of Swish-T$_{\textbf{C}}$, also demonstrate satisfactory performance. Furthermore, our ablation study shows that using Swish-T$_{\textbf{C}}$ as a non-parametric function can still achieve high performance. The superiority of the Swish-T family has been empirically demonstrated across various models and benchmark datasets, including MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. The code is publicly available at "https://github.com/ictseoyoungmin/Swish-T-pytorch".
Authors: Negin Yousefpour, Bo Wang
Abstract: This paper introduces scour physics-informed neural networks (SPINNs), a hybrid physics-data-driven framework for bridge scour prediction using deep learning. SPINNs are developed based on historical scour monitoring data and integrate physics-based empirical equations into neural networks as supplementary loss components. We incorporated three architectures: LSTM, CNN, and NLinear as the base data-driven model. Despite varying performance across different base models and bridges, SPINNs overall outperformed pure data-driven models. In some bridge cases, SPINN reduced forecasting errors by up to 50 percent. In this study, we also explored general models for bridge clusters, trained by aggregating datasets across multiple bridges in a region. The pure data-driven models mostly benefited from this approach, in particular bridges with limited data. However, bridge-specific SPINNs provided more accurate predictions than general SPINNs for almost all case studies. Also, the time-dependent empirical equations derived from SPINNs showed reasonable accuracy in estimating maximum scour depth, providing more accurate predictions compared to HEC-18. Comparing both SPINNs and pure deep learning models with traditional HEC-18 equation indicates substantial improvements in scour prediction accuracy. This study can pave the way for hybrid physics-machine learning methodologies to be implemented for bridge scour design and maintenance.
Authors: Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, Vincent Sitzmann
Abstract: This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens without fully diffusing past ones. Our approach is shown to combine the strengths of next-token prediction models, such as variable-length generation, with the strengths of full-sequence diffusion models, such as the ability to guide sampling to desirable trajectories. Our method offers a range of additional capabilities, such as (1) rolling-out sequences of continuous tokens, such as video, with lengths past the training horizon, where baselines diverge and (2) new sampling and guiding schemes that uniquely profit from Diffusion Forcing's variable-horizon and causal architecture, and which lead to marked performance gains in decision-making and planning tasks. In addition to its empirical success, our method is proven to optimize a variational lower bound on the likelihoods of all subsequences of tokens drawn from the true joint distribution. Project website: https://boyuan.space/diffusion-forcing/
Authors: Jibang Wu, Siyu Chen, Mengdi Wang, Huazheng Wang, Haifeng Xu
Abstract: The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. The problem, termed \emph{contractual reinforcement learning}, naturally arises from the classic model of Markov decision processes, where a learning principal seeks to optimally influence the agent's action policy for their common interests through a set of payment rules contingent on the realization of next state. For the planning problem, we design an efficient dynamic programming algorithm to determine the optimal contracts against the far-sighted agent. For the learning problem, we introduce a generic design of no-regret learning algorithms to untangle the challenges from robust design of contracts to the balance of exploration and exploitation, reducing the complexity analysis to the construction of efficient search algorithms. For several natural classes of problems, we design tailored search algorithms that provably achieve $\tilde{O}(\sqrt{T})$ regret. We also present an algorithm with $\tilde{O}(T^{2/3})$ for the general problem that improves the existing analysis in online contract design with mild technical assumptions.
Authors: Ian J. Costello, Abhinav Bhatele
Abstract: In recent years, several HPC facilities have started continuous monitoring of their systems and jobs to collect performance-related data for understanding performance and operational efficiency. Such data can be used to optimize the performance of individual jobs and the overall system by creating data-driven models that can predict the performance of jobs waiting in the scheduler queue. In this paper, we model the performance of representative control jobs using longitudinal system-wide monitoring data and machine learning to explore the causes of performance variability. We analyze these prediction models in great detail to identify the features that are dominant predictors of performance. We demonstrate that such models can be application-agnostic and can be used for predicting performance of applications that are not included in training.
Authors: Jiangyan Yi, Ruibo Fu, Jianhua Tao, Shuai Nie, Haoxin Ma, Chenglong Wang, Tao Wang, Zhengkun Tian, Xiaohui Zhang, Ye Bai, Cunhang Fan, Shan Liang, Shiming Wang, Shuai Zhang, Xinrui Yan, Le Xu, Zhengqi Wen, Haizhou Li, Zheng Lian, Bin Liu
Abstract: Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios. The first Audio Deep synthesis Detection challenge (ADD) was motivated to fill in the gap. The ADD 2022 includes three tracks: low-quality fake audio detection (LF), partially fake audio detection (PF) and audio fake game (FG). The LF track focuses on dealing with bona fide and fully fake utterances with various real-world noises etc. The PF track aims to distinguish the partially fake audio from the real. The FG track is a rivalry game, which includes two tasks: an audio generation task and an audio fake detection task. In this paper, we describe the datasets, evaluation metrics, and protocols. We also report major findings that reflect the recent advances in audio deepfake detection tasks.
Authors: Linus Bleistein, Agathe Guilloux
Abstract: Neural Controlled Differential Equations (NCDEs) are a state-of-the-art tool for supervised learning with irregularly sampled time series (Kidger, 2020). However, no theoretical analysis of their performance has been provided yet, and it remains unclear in particular how the irregularity of the time series affects their predictions. By merging the rich theory of controlled differential equations (CDE) and Lipschitz-based measures of the complexity of deep neural nets, we take a first step towards the theoretical understanding of NCDE. Our first result is a generalization bound for this class of predictors that depends on the regularity of the time series data. In a second time, we leverage the continuity of the flow of CDEs to provide a detailed analysis of both the sampling-induced bias and the approximation bias. Regarding this last result, we show how classical approximation results on neural nets may transfer to NCDEs. Our theoretical results are validated through a series of experiments.
Authors: Patrick Wagner, Temesgen Mehari, Wilhelm Haverkamp, Nils Strodthoff
Abstract: Deep neural networks have become increasingly popular for analyzing ECG data because of their ability to accurately identify cardiac conditions and hidden clinical factors. However, the lack of transparency due to the black box nature of these models is a common concern. To address this issue, explainable AI (XAI) methods can be employed. In this study, we present a comprehensive analysis of post-hoc XAI methods, investigating the local (attributions per sample) and global (based on domain expert concepts) perspectives. We have established a set of sanity checks to identify sensible attribution methods, and we provide quantitative evidence in accordance with expert rules. This dataset-wide analysis goes beyond anecdotal evidence by aggregating data across patient subgroups. Furthermore, we demonstrate how these XAI techniques can be utilized for knowledge discovery, such as identifying subtypes of myocardial infarction. We believe that these proposed methods can serve as building blocks for a complementary assessment of the internal validity during a certification process, as well as for knowledge discovery in the field of ECG analysis.
Authors: Anastasiia Klimashevskaia, Dietmar Jannach, Mehdi Elahi, Christoph Trattner
Abstract: Recommender systems help people find relevant content in a personalized way. One main promise of such systems is that they are able to increase the visibility of items in the long tail, i.e., the lesser-known items in a catalogue. Existing research, however, suggests that in many situations todays recommendation algorithms instead exhibit a popularity bias, meaning that they often focus on rather popular items in their recommendations. Such a bias may not only lead to the limited value of the recommendations for consumers and providers in the short run, but it may also cause undesired reinforcement effects over time. In this paper, we discuss the potential reasons for popularity bias and review existing approaches to detect, quantify and mitigate popularity bias in recommender systems. Our survey, therefore, includes both an overview of the computational metrics used in the literature as well as a review of the main technical approaches to reduce the bias. Furthermore, we critically discuss todays literature, where we observe that the research is almost entirely based on computational experiments and on certain assumptions regarding the practical effects of including long-tail items in the recommendations.
Authors: Lin Deng, Michael Stanley Smith, Worapree Maneesoonthorn
Abstract: Skew-t copula models are attractive for the modeling of financial data because they allow for asymmetric and extreme tail dependence. We show that the copula implicit in the skew-t distribution of Azzalini and Capitanio (2003) allows for a higher level of pairwise asymmetric dependence than two popular alternative skew-t copulas. Estimation of this copula in high dimensions is challenging, and we propose a fast and accurate Bayesian variational inference (VI) approach to do so. The method uses a generative representation of the skew-t distribution to define an augmented posterior that can be approximated accurately. A stochastic gradient ascent algorithm is used to solve the variational optimization. The methodology is used to estimate skew-t factor copula models with up to 15 factors for intraday returns from 2017 to 2021 on 93 U.S. equities. The copula captures substantial heterogeneity in asymmetric dependence over equity pairs, in addition to the variability in pairwise correlations. In a moving window study we show that the asymmetric dependencies also vary over time, and that intraday predictive densities from the skew-t copula are more accurate than those from benchmark copula models. Portfolio selection strategies based on the estimated pairwise asymmetric dependencies improve performance relative to the index.
Authors: Muhammad Abdul Rahman, Muhammad Aamir Basheer, Zubair Khalid, Muhammad Tahir, Momin Uppal
Abstract: Logistic hubs play a pivotal role in the last-mile delivery distance; even a slight increment in distance negatively impacts the business of the e-commerce industry while also increasing its carbon footprint. The growth of this industry, particularly after Covid-19, has further intensified the need for optimized allocation of resources in an urban environment. In this study, we use a hybrid approach to optimize the placement of logistic hubs. The approach sequentially employs different techniques. Initially, delivery points are clustered using K-Means in relation to their spatial locations. The clustering method utilizes road network distances as opposed to Euclidean distances. Non-road network-based approaches have been avoided since they lead to erroneous and misleading results. Finally, hubs are located using the P-Median method. The P-Median method also incorporates the number of deliveries and population as weights. Real-world delivery data from Muller and Phipps (M&P) is used to demonstrate the effectiveness of the approach. Serving deliveries from the optimal hub locations results in the saving of 815 (10%) meters per delivery.
Authors: Patrick Feeney, Michael C. Hughes
Abstract: The information noise-contrastive estimation (InfoNCE) loss function provides the basis of many self-supervised deep learning methods due to its strong empirical results and theoretic motivation. Previous work suggests a supervised contrastive (SupCon) loss to extend InfoNCE to learn from available class labels. This SupCon loss has been widely-used due to reports of good empirical performance. However, in this work we find that the prior SupCon loss formulation has questionable justification because it can encourage some images from the same class to repel one another in the learned embedding space. This problematic intra-class repulsion gets worse as the number of images sharing one class label increases. We propose the Supervised InfoNCE REvisited (SINCERE) loss as a theoretically-justified supervised extension of InfoNCE that eliminates intra-class repulsion. Experiments show that SINCERE leads to better separation of embeddings from different classes and improves transfer learning classification accuracy. We additionally utilize probabilistic modeling to derive an information-theoretic bound that relates SINCERE loss to the symmeterized KL divergence between data-generating distributions for a target class and all other classes.
Authors: Gilles Van De Vyver, Sarina Thomas, Guy Ben-Yosef, Sindre Hellum Olaisen, H\r{a}vard Dalen, Lasse L{\o}vstakken, Erik Smistad
Abstract: Fully automatic cardiac segmentation can be a fast and reproducible method to extract clinical measurements from an echocardiography examination. The U-Net architecture is the current state-of-the-art deep learning architecture for medical segmentation and can segment cardiac structures in real-time with average errors comparable to inter-observer variability. However, this architecture still generates large outliers that are often anatomically incorrect. This work uses the concept of graph convolutional neural networks that predict the contour points of the structures of interest instead of labeling each pixel. We propose a graph architecture that uses two convolutional rings based on cardiac anatomy and show that this eliminates anatomical incorrect multi-structure segmentations on the publicly available CAMUS dataset. Additionally, this work contributes with an ablation study on the graph convolutional architecture and an evaluation of clinical measurements on the clinical HUNT4 dataset. Finally, we propose to use the inter-model agreement of the U-Net and the graph network as a predictor of both the input and segmentation quality. We show this predictor can detect out-of-distribution and unsuitable input images in real-time. Source code is available online: https://github.com/gillesvntnu/GCN_multistructure
Authors: Vidya Sagar Sharma
Abstract: Causal DAGs (also known as Bayesian networks) are a popular tool for encoding conditional dependencies between random variables. In a causal DAG, the random variables are modeled as vertices in the DAG, and it is stipulated that every random variable is independent of its ancestors conditioned on its parents. It is possible, however, for two different causal DAGs on the same set of random variables to encode exactly the same set of conditional dependencies. Such causal DAGs are said to be Markov equivalent, and equivalence classes of Markov equivalent DAGs are known as Markov Equivalent Classes (MECs). Beautiful combinatorial characterizations of MECs have been developed in the past few decades, and it is known, in particular that all DAGs in the same MEC must have the same "skeleton" (underlying undirected graph) and v-structures (induced subgraph of the form $a\rightarrow b \leftarrow c$). These combinatorial characterizations also suggest several natural algorithmic questions. One of these is: given an undirected graph $G$ as input, how many distinct Markov equivalence classes have the skeleton $G$? Much work has been devoted in the last few years to this and other closely related problems. However, to the best of our knowledge, a polynomial time algorithm for the problem remains unknown. In this paper, we make progress towards this goal by giving a fixed parameter tractable algorithm for the above problem, with the parameters being the treewidth and the maximum degree of the input graph $G$. The main technical ingredient in our work is a construction we refer to as shadow, which lets us create a "local description" of long-range constraints imposed by the combinatorial characterizations of MECs.
Authors: Melanie Sclar, Yejin Choi, Yulia Tsvetkov, Alane Suhr
Abstract: As large language models (LLMs) are adopted as a fundamental component of language technologies, it is crucial to accurately characterize their performance. Because choices in prompt design can strongly influence model behavior, this design process is critical in effectively using any modern pre-trained generative language model. In this work, we focus on LLM sensitivity to a quintessential class of meaning-preserving design choices: prompt formatting. We find that several widely used open-source LLMs are extremely sensitive to subtle changes in prompt formatting in few-shot settings, with performance differences of up to 76 accuracy points when evaluated using LLaMA-2-13B. Sensitivity remains even when increasing model size, the number of few-shot examples, or performing instruction tuning. Our analysis suggests that work evaluating LLMs with prompting-based methods would benefit from reporting a range of performance across plausible prompt formats, instead of the currently-standard practice of reporting performance on a single format. We also show that format performance only weakly correlates between models, which puts into question the methodological validity of comparing models with an arbitrarily chosen, fixed prompt format. To facilitate systematic analysis we propose FormatSpread, an algorithm that rapidly evaluates a sampled set of plausible prompt formats for a given task, and reports the interval of expected performance without accessing model weights. Furthermore, we present a suite of analyses that characterize the nature of this sensitivity, including exploring the influence of particular atomic perturbations and the internal representation of particular formats.
Authors: Ananjan Nandi, Navdeep Kaur, Parag Singla, Mausam
Abstract: We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connectivity structure of the Knowledge Graph (KG). Preliminary experiments show that these approaches have complementary strengths: structure-based models perform exceptionally well when the gold answer is easily reachable from the query head in the KG, while textual models exploit descriptions to give good performance even when the gold answer is not easily reachable. In response, we propose DynaSemble, a novel method for learning query-dependent ensemble weights to combine these approaches by using the distributions of scores assigned by the models in the ensemble to all candidate entities. DynaSemble achieves state-of-the-art results on three standard KGC datasets, with up to 6.8 pt MRR and 8.3 pt Hits@1 gains over the best baseline model for the WN18RR dataset.
Authors: Kwanyoung Kim, Yujin Oh, Sangjoon Park, Hwa Kyung Byun, Joongyo Lee, Jin Sung Kim, Yong Bae Kim, Jong Chul Ye
Abstract: Recent advances in AI foundation models have significant potential for lightening the clinical workload by mimicking the comprehensive and multi-faceted approaches used by medical professionals. In the field of radiation oncology, the integration of multiple modalities holds great importance, so the opportunity of foundational model is abundant. Inspired by this, here we present RO-LMM, a multi-purpose, comprehensive large multimodal model (LMM) tailored for the field of radiation oncology. This model effectively manages a series of tasks within the clinical workflow, including clinical context summarization, radiation treatment plan suggestion, and plan-guided target volume segmentation by leveraging the capabilities of LMM. In particular, to perform consecutive clinical tasks without error accumulation, we present a novel Consistency Embedding Fine-Tuning (CEFTune) technique, which boosts LMM's robustness to noisy inputs while preserving the consistency of handling clean inputs. We further extend this concept to LMM-driven segmentation framework, leading to a novel Consistency Embedding Segmentation~(CESEG) techniques. Experimental results including multi-centre validation confirm that our RO-LMM with CEFTune and CESEG results in promising performance for multiple clinical tasks with generalization capabilities.
Authors: Raviteja Vemulapalli, Hadi Pouransari, Fartash Faghri, Sachin Mehta, Mehrdad Farajtabar, Mohammad Rastegari, Oncel Tuzel
Abstract: Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due to their high inference compute cost, these models cannot be deployed for many real-world applications. Motivated by this, we ask the following important question, "How can we leverage the knowledge from a large VFM to train a small task-specific model for a new target task with limited labeled training data?", and propose a simple task-oriented knowledge transfer approach as a highly effective solution to this problem. Our experimental results on five target tasks show that the proposed approach outperforms task-agnostic VFM distillation, web-scale CLIP pretraining, supervised ImageNet pretraining, and self-supervised DINO pretraining by up to 11.6%, 22.1%, 13.7%, and 29.8%, respectively. Furthermore, the proposed approach also demonstrates up to 9x, 4x and 15x reduction in pretraining compute cost when compared to task-agnostic VFM distillation, ImageNet pretraining and DINO pretraining, respectively, while outperforming them. We also show that the dataset used for transferring knowledge has a significant effect on the final target task performance, and introduce a retrieval-augmented knowledge transfer strategy that uses web-scale image retrieval to curate effective transfer sets.
Authors: Da Wu, Jingye Yang, Kai Wang
Abstract: The term "Reversal Curse" refers to the scenario where auto-regressive decoder large language models (LLMs), such as ChatGPT, trained on "A is B" fail to learn "B is A," assuming that B and A are distinct and can be uniquely identified from each other, demonstrating a basic failure of logical deduction. This raises a red flag in the use of GPT models for certain general tasks such as constructing knowledge graphs, considering their adherence to this symmetric principle. In our study, we examined a bidirectional LLM, BERT, and found that it is immune to the reversal curse. Driven by ongoing efforts to construct biomedical knowledge graphs with LLMs, we also embarked on evaluating more complex but essential deductive reasoning capabilities. This process included first training encoder and decoder language models to master the intersection and union operations on two sets and then moving on to assess their capability to infer different combinations of union and intersection operations on three newly created sets. The findings showed that while both encoder and decoder language models, trained for tasks involving two sets (union/intersection), were proficient in such scenarios, they encountered difficulties when dealing with operations that included three sets (various combinations of union and intersection). Our research highlights the distinct characteristics of encoder and decoder models in simple and complex logical reasoning. In practice, the choice between BERT and GPT should be guided by the specific requirements and nature of the task at hand, leveraging their respective strengths in bidirectional context comprehension and sequence prediction.
Authors: Val\'erian Jacques-Dumas, Ren\'e M. van Westen, Henk A. Dijkstra
Abstract: The Atlantic Meridional Overturning Circulation (AMOC) is an important component of the global climate, known to be a tipping element, as it could collapse under global warming. The main objective of this study is to compute the probability that the AMOC collapses within a specified time window, using a rare-event algorithm called Trajectory-Adaptive Multilevel Splitting (TAMS). However, the efficiency and accuracy of TAMS depend on the choice of the score function. Although the definition of the optimal score function, called ``committor function" is known, it is impossible in general to compute it a priori. Here, we combine TAMS with a Next-Generation Reservoir Computing technique that estimates the committor function from the data generated by the rare-event algorithm. We test this technique in a stochastic box model of the AMOC for which two types of transition exist, the so-called F(ast)-transitions and S(low)-transitions. Results for the F-transtions compare favorably with those in the literature where a physically-informed score function was used. We show that coupling a rare-event algorithm with machine learning allows for a correct estimation of transition probabilities, transition times, and even transition paths for a wide range of model parameters. We then extend these results to the more difficult problem of S-transitions in the same model. In both cases of F-transitions and S-transitions, we also show how the Next-Generation Reservoir Computing technique can be interpreted to retrieve an analytical estimate of the committor function.
Authors: Michael Ahn, Debidatta Dwibedi, Chelsea Finn, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Karol Hausman, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Sean Kirmani, Isabel Leal, Edward Lee, Sergey Levine, Yao Lu, Isabel Leal, Sharath Maddineni, Kanishka Rao, Dorsa Sadigh, Pannag Sanketi, Pierre Sermanet, Quan Vuong, Stefan Welker, Fei Xia, Ted Xiao, Peng Xu, Steve Xu, Zhuo Xu
Abstract: Foundation models that incorporate language, vision, and more recently actions have revolutionized the ability to harness internet scale data to reason about useful tasks. However, one of the key challenges of training embodied foundation models is the lack of data grounded in the physical world. In this paper, we propose AutoRT, a system that leverages existing foundation models to scale up the deployment of operational robots in completely unseen scenarios with minimal human supervision. AutoRT leverages vision-language models (VLMs) for scene understanding and grounding, and further uses large language models (LLMs) for proposing diverse and novel instructions to be performed by a fleet of robots. Guiding data collection by tapping into the knowledge of foundation models enables AutoRT to effectively reason about autonomy tradeoffs and safety while significantly scaling up data collection for robot learning. We demonstrate AutoRT proposing instructions to over 20 robots across multiple buildings and collecting 77k real robot episodes via both teleoperation and autonomous robot policies. We experimentally show that such "in-the-wild" data collected by AutoRT is significantly more diverse, and that AutoRT's use of LLMs allows for instruction following data collection robots that can align to human preferences.
Authors: Matthew Ho, Deaglan J. Bartlett, Nicolas Chartier, Carolina Cuesta-Lazaro, Simon Ding, Axel Lapel, Pablo Lemos, Christopher C. Lovell, T. Lucas Makinen, Chirag Modi, Viraj Pandya, Shivam Pandey, Lucia A. Perez, Benjamin Wandelt, Greg L. Bryan
Abstract: This paper presents the Learning the Universe Implicit Likelihood Inference (LtU-ILI) pipeline, a codebase for rapid, user-friendly, and cutting-edge machine learning (ML) inference in astrophysics and cosmology. The pipeline includes software for implementing various neural architectures, training schemata, priors, and density estimators in a manner easily adaptable to any research workflow. It includes comprehensive validation metrics to assess posterior estimate coverage, enhancing the reliability of inferred results. Additionally, the pipeline is easily parallelizable and is designed for efficient exploration of modeling hyperparameters. To demonstrate its capabilities, we present real applications across a range of astrophysics and cosmology problems, such as: estimating galaxy cluster masses from X-ray photometry; inferring cosmology from matter power spectra and halo point clouds; characterizing progenitors in gravitational wave signals; capturing physical dust parameters from galaxy colors and luminosities; and establishing properties of semi-analytic models of galaxy formation. We also include exhaustive benchmarking and comparisons of all implemented methods as well as discussions about the challenges and pitfalls of ML inference in astronomical sciences. All code and examples are made publicly available at https://github.com/maho3/ltu-ili.
Authors: Zijie J. Wang, Chinmay Kulkarni, Lauren Wilcox, Michael Terry, Michael Madaio
Abstract: Prompt-based interfaces for Large Language Models (LLMs) have made prototyping and building AI-powered applications easier than ever before. However, identifying potential harms that may arise from AI applications remains a challenge, particularly during prompt-based prototyping. To address this, we present Farsight, a novel in situ interactive tool that helps people identify potential harms from the AI applications they are prototyping. Based on a user's prompt, Farsight highlights news articles about relevant AI incidents and allows users to explore and edit LLM-generated use cases, stakeholders, and harms. We report design insights from a co-design study with 10 AI prototypers and findings from a user study with 42 AI prototypers. After using Farsight, AI prototypers in our user study are better able to independently identify potential harms associated with a prompt and find our tool more useful and usable than existing resources. Their qualitative feedback also highlights that Farsight encourages them to focus on end-users and think beyond immediate harms. We discuss these findings and reflect on their implications for designing AI prototyping experiences that meaningfully engage with AI harms. Farsight is publicly accessible at: https://PAIR-code.github.io/farsight.
Authors: Shuchen Xue, Zhaoqiang Liu, Fei Chen, Shifeng Zhang, Tianyang Hu, Enze Xie, Zhenguo Li
Abstract: Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis, but their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps. While this is a significant development, most sampling methods still employ uniform time steps, which is not optimal when using a small number of steps. To address this issue, we propose a general framework for designing an optimization problem that seeks more appropriate time steps for a specific numerical ODE solver for DPMs. This optimization problem aims to minimize the distance between the ground-truth solution to the ODE and an approximate solution corresponding to the numerical solver. It can be efficiently solved using the constrained trust region method, taking less than $15$ seconds. Our extensive experiments on both unconditional and conditional sampling using pixel- and latent-space DPMs demonstrate that, when combined with the state-of-the-art sampling method UniPC, our optimized time steps significantly improve image generation performance in terms of FID scores for datasets such as CIFAR-10 and ImageNet, compared to using uniform time steps.
Authors: Che Liu, Zhongwei Wan, Cheng Ouyang, Anand Shah, Wenjia Bai, Rossella Arcucci
Abstract: Electrocardiograms (ECGs) are non-invasive diagnostic tools crucial for detecting cardiac arrhythmic diseases in clinical practice. While ECG Self-supervised Learning (eSSL) methods show promise in representation learning from unannotated ECG data, they often overlook the clinical knowledge that can be found in reports. This oversight and the requirement for annotated samples for downstream tasks limit eSSL's versatility. In this work, we address these issues with the Multimodal ECG Representation Learning (MERL}) framework. Through multimodal learning on ECG records and associated reports, MERL is capable of performing zero-shot ECG classification with text prompts, eliminating the need for training data in downstream tasks. At test time, we propose the Clinical Knowledge Enhanced Prompt Engineering (CKEPE) approach, which uses Large Language Models (LLMs) to exploit external expert-verified clinical knowledge databases, generating more descriptive prompts and reducing hallucinations in LLM-generated content to boost zero-shot classification. Based on MERL, we perform the first benchmark across six public ECG datasets, showing the superior performance of MERL compared against eSSL methods. Notably, MERL achieves an average AUC score of 75.2% in zero-shot classification (without training data), 3.2% higher than linear probed eSSL methods with 10\% annotated training data, averaged across all six datasets. Code and models are available at https://github.com/cheliu-computation/MERL
Authors: Elizabeth Qian, Dayoung Kang, Vignesh Sella, Anirban Chaudhuri
Abstract: Machine learning (ML) methods, which fit to data the parameters of a given parameterized model class, have garnered significant interest as potential methods for learning surrogate models for complex engineering systems for which traditional simulation is expensive. However, in many scientific and engineering settings, generating high-fidelity data on which to train ML models is expensive, and the available budget for generating training data is limited, so that high-fidelity training data are scarce. ML models trained on scarce data have high variance, resulting in poor expected generalization performance. We propose a new multifidelity training approach for scientific machine learning via linear regression that exploits the scientific context where data of varying fidelities and costs are available: for example, high-fidelity data may be generated by an expensive fully resolved physics simulation whereas lower-fidelity data may arise from a cheaper model based on simplifying assumptions. We use the multifidelity data within an approximate control variate framework to define new multifidelity Monte Carlo estimators for linear regression models. We provide bias and variance analysis of our new estimators that guarantee the approach's accuracy and improved robustness to scarce high-fidelity data. Numerical results demonstrate that our multifidelity training approach achieves similar accuracy to the standard high-fidelity only approach with orders-of-magnitude reduced high-fidelity data requirements.
Authors: M Manvith Prabhu, Haricharana Srinivasa, Anand Kumar M
Abstract: This paper summarizes Team SCaLAR's work on SemEval-2024 Task 5: Legal Argument Reasoning in Civil Procedure. To address this Binary Classification task, which was daunting due to the complexity of the Legal Texts involved, we propose a simple yet novel similarity and distance-based unsupervised approach to generate labels. Further, we explore the Multi-level fusion of Legal-Bert embeddings using ensemble features, including CNN, GRU, and LSTM. To address the lengthy nature of Legal explanation in the dataset, we introduce T5-based segment-wise summarization, which successfully retained crucial information, enhancing the model's performance. Our unsupervised system witnessed a 20-point increase in macro F1-score on the development set and a 10-point increase on the test set, which is promising given its uncomplicated architecture.
Authors: Sayantan Kumar, Tom Earnest, Braden Yang, Deydeep Kothapalli, Andrew J. Aschenbrenner, Jason Hassenstab, Chengie Xiong, Beau Ances, John Morris, Tammie L. S. Benzinger, Brian A. Gordon, Philip Payne, Aristeidis Sotiras
Abstract: INTRODUCTION: Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer Disease (AD) heterogeneity. We employed a deep learning-based multimodal normative framework to analyze individual-level variation across ATN (amyloid-tau-neurodegeneration) imaging biomarkers. METHODS: We selected cross-sectional discovery (n = 665) and replication cohorts (n = 430) with available T1-weighted MRI, amyloid and tau PET. Normative modeling estimated individual-level abnormal deviations in amyloid-positive individuals compared to amyloid-negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra-group heterogeneity. An individual-level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN. RESULTS: Greater intra-group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression. DISCUSSION: Subject-specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain.
Authors: Julia Gonski, Aseem Gupta, Haoyi Jia, Hyunjoon Kim, Lorenzo Rota, Larry Ruckman, Angelo Dragone, Ryan Herbst
Abstract: Embedded field programmable gate array (eFPGA) technology allows the implementation of reconfigurable logic within the design of an application-specific integrated circuit (ASIC). This approach offers the low power and efficiency of an ASIC along with the ease of FPGA configuration, particularly beneficial for the use case of machine learning in the data pipeline of next-generation collider experiments. An open-source framework called "FABulous" was used to design eFPGAs using 130 nm and 28 nm CMOS technology nodes, which were subsequently fabricated and verified through testing. The capability of an eFPGA to act as a front-end readout chip was assessed using simulation of high energy particles passing through a silicon pixel sensor. A machine learning-based classifier, designed for reduction of sensor data at the source, was synthesized and configured onto the eFPGA. A successful proof-of-concept was demonstrated through reproduction of the expected algorithm result on the eFPGA with perfect accuracy. Further development of the eFPGA technology and its application to collider detector readout is discussed.
Authors: Rui Zhao, Bin Shi, Jianfei Ruan, Tianze Pan, Bo Dong
Abstract: In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically learn noisy class posteriors by training a classification model with noisy labels. However, when labels are incorrect, these models may be misled to overemphasize the feature parts that do not reflect the instance characteristics, resulting in significant errors in estimating noisy class posteriors. To address this issue, this paper proposes to augment the supervised information with part-level labels, encouraging the model to focus on and integrate richer information from various parts. Specifically, our method first partitions features into distinct parts by cropping instances, yielding part-level labels associated with these various parts. Subsequently, we introduce a novel single-to-multiple transition matrix to model the relationship between the noisy and part-level labels, which incorporates part-level labels into a classifier-consistent framework. Utilizing this framework with part-level labels, we can learn the noisy class posteriors more precisely by guiding the model to integrate information from various parts, ultimately improving the classification performance. Our method is theoretically sound, while experiments show that it is empirically effective in synthetic and real-world noisy benchmarks.
Authors: Emilian Postolache, Natalia Polouliakh, Hiroaki Kitano, Akima Connelly, Emanuele Rodol\`a, Luca Cosmo, Taketo Akama
Abstract: In this article, we explore the potential of using latent diffusion models, a family of powerful generative models, for the task of reconstructing naturalistic music from electroencephalogram (EEG) recordings. Unlike simpler music with limited timbres, such as MIDI-generated tunes or monophonic pieces, the focus here is on intricate music featuring a diverse array of instruments, voices, and effects, rich in harmonics and timbre. This study represents an initial foray into achieving general music reconstruction of high-quality using non-invasive EEG data, employing an end-to-end training approach directly on raw data without the need for manual pre-processing and channel selection. We train our models on the public NMED-T dataset and perform quantitative evaluation proposing neural embedding-based metrics. We additionally perform song classification based on the generated tracks. Our work contributes to the ongoing research in neural decoding and brain-computer interfaces, offering insights into the feasibility of using EEG data for complex auditory information reconstruction.
Authors: Albert Yu, Adeline Foote, Raymond Mooney, Roberto Mart\'in-Mart\'in
Abstract: The main challenge in learning image-conditioned robotic policies is acquiring a visual representation conducive to low-level control. Due to the high dimensionality of the image space, learning a good visual representation requires a considerable amount of visual data. However, when learning in the real world, data is expensive. Sim2Real is a promising paradigm for overcoming data scarcity in the real-world target domain by using a simulator to collect large amounts of cheap data closely related to the target task. However, it is difficult to transfer an image-conditioned policy from sim to real when the domains are very visually dissimilar. To bridge the sim2real visual gap, we propose using natural language descriptions of images as a unifying signal across domains that captures the underlying task-relevant semantics. Our key insight is that if two image observations from different domains are labeled with similar language, the policy should predict similar action distributions for both images. We demonstrate that training the image encoder to predict the language description or the distance between descriptions of a sim or real image serves as a useful, data-efficient pretraining step that helps learn a domain-invariant image representation. We can then use this image encoder as the backbone of an IL policy trained simultaneously on a large amount of simulated and a handful of real demonstrations. Our approach outperforms widely used prior sim2real methods and strong vision-language pretraining baselines like CLIP and R3M by 25 to 40%. See additional videos and materials at https://robin-lab.cs.utexas.edu/lang4sim2real/.
Authors: Ning Shi, Zijun Wu
Abstract: Recent studies have demonstrated the potential to control paraphrase generation, such as through syntax, which has broad applications in various downstream tasks. However, these methods often require detailed parse trees or syntactic exemplars, countering human-like paraphrasing behavior in language use. Furthermore, an inference gap exists, as control specifications are only available during training but not during inference. In this work, we propose a new setup for controlled paraphrase generation. Specifically, we represent user intent as action tokens, embedding and concatenating them with text embeddings, thus flowing together into a self-attention encoder for representation fusion. To address the inference gap, we introduce an optional action token as a placeholder that encourages the model to determine the appropriate action independently when users' intended actions are not provided. Experimental results show that our method successfully enables precise action-controlled paraphrasing and preserves or even enhances performance compared to conventional uncontrolled methods when actions are not given. Our findings promote the concept of action-controlled paraphrasing for a more user-centered design.
Authors: Andres Hernandez, Zhongqi Miao, Luisa Vargas, Rahul Dodhia, Pablo Arbelaez, Juan M. Lavista Ferres
Abstract: The alarming decline in global biodiversity, driven by various factors, underscores the urgent need for large-scale wildlife monitoring. In response, scientists have turned to automated deep learning methods for data processing in wildlife monitoring. However, applying these advanced methods in real-world scenarios is challenging due to their complexity and the need for specialized knowledge, primarily because of technical challenges and interdisciplinary barriers. To address these challenges, we introduce Pytorch-Wildlife, an open-source deep learning platform built on PyTorch. It is designed for creating, modifying, and sharing powerful AI models. This platform emphasizes usability and accessibility, making it accessible to individuals with limited or no technical background. It also offers a modular codebase to simplify feature expansion and further development. Pytorch-Wildlife offers an intuitive, user-friendly interface, accessible through local installation or Hugging Face, for animal detection and classification in images and videos. As two real-world applications, Pytorch-Wildlife has been utilized to train animal classification models for species recognition in the Amazon Rainforest and for invasive opossum recognition in the Galapagos Islands. The Opossum model achieves 98% accuracy, and the Amazon model has 92% recognition accuracy for 36 animals in 90% of the data. As Pytorch-Wildlife evolves, we aim to integrate more conservation tasks, addressing various environmental challenges. Pytorch-Wildlife is available at https://github.com/microsoft/CameraTraps.
Authors: Tommy Rochussen
Abstract: Bayesian neural network posterior distributions have a great number of modes that correspond to the same network function. The abundance of such modes can make it difficult for approximate inference methods to do their job. Recent work has demonstrated the benefits of partial stochasticity for approximate inference in Bayesian neural networks; inference can be less costly and performance can sometimes be improved. I propose a structured way to select the deterministic subset of weights that removes neuron permutation symmetries, and therefore the corresponding redundant posterior modes. With a drastically simplified posterior distribution, the performance of existing approximate inference schemes is found to be greatly improved.
Authors: Suraj Anand, Michael A. Lepori, Jack Merullo, Ellie Pavlick
Abstract: Language models have the ability to perform in-context learning (ICL), allowing them to flexibly adapt their behavior based on context. This contrasts with in-weights learning, where information is statically encoded in model parameters from iterated observations of the data. Despite this apparent ability to learn in-context, language models are known to struggle when faced with unseen or rarely seen tokens. Hence, we study $\textbf{structural in-context learning}$, which we define as the ability of a model to execute in-context learning on arbitrary tokens -- so called because the model must generalize on the basis of e.g. sentence structure or task structure, rather than semantic content encoded in token embeddings. An ideal model would be able to do both: flexibly deploy in-weights operations (in order to robustly accommodate ambiguous or unknown contexts using encoded semantic information) and structural in-context operations (in order to accommodate novel tokens). We study structural in-context algorithms in a simple part-of-speech setting using both practical and toy models. We find that active forgetting, a technique that was recently introduced to help models generalize to new languages, forces models to adopt structural in-context learning solutions. Finally, we introduce $\textbf{temporary forgetting}$, a straightforward extension of active forgetting that enables one to control how much a model relies on in-weights vs. in-context solutions. Importantly, temporary forgetting allows us to induce a $\textit{dual process strategy}$ where in-context and in-weights solutions coexist within a single model.
Authors: Benedikt Alkin, Maximilian Beck, Korbinian P\"oppel, Sepp Hochreiter, Johannes Brandstetter
Abstract: Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing. Recently, the Long Short-Term Memory (LSTM) has been extended to a scalable and performant architecture - the xLSTM - which overcomes long-standing LSTM limitations via exponential gating and parallelizable matrix memory structure. In this report, we introduce Vision-LSTM (ViL), an adaption of the xLSTM building blocks to computer vision. ViL comprises a stack of xLSTM blocks where odd blocks process the sequence of patch tokens from top to bottom while even blocks go from bottom to top. Experiments show that ViL holds promise to be further deployed as new generic backbone for computer vision architectures.
Authors: Jincheng Zhou
Abstract: Question-Options Generation (QOG) is a task that involves generating a set of question-options pairs given context. This task has various applications, including fine-tuning large models, information retrieval, and automated multiple-choice question generation for education. In this paper, we develop QOG models using three different methods based on fine-tuning sequence-to-sequence language models (LMs). Experiments demonstrate that the end-to-end QOG model is computationally efficient and stable during both training and inference, outperforming other methods. Furthermore, our analysis indicates that our QOG models are competitive on the QOG task compared to the large language model Llama 3-8B.
Authors: Harald Semmelrock, Tony Ross-Hellauer, Simone Kopeinik, Dieter Theiler, Armin Haberl, Stefan Thalmann, Dominik Kowald
Abstract: Research in various fields is currently experiencing challenges regarding the reproducibility of results. This problem is also prevalent in machine learning (ML) research. The issue arises, for example, due to unpublished data and/or source code and the sensitivity of ML training conditions. Although different solutions have been proposed to address this issue, such as using ML platforms, the level of reproducibility in ML-driven research remains unsatisfactory. Therefore, in this article, we discuss the reproducibility of ML-driven research with three main aims: (i) identifying the barriers to reproducibility when applying ML in research as well as categorize the barriers to different types of reproducibility (description, code, data, and experiment reproducibility), (ii) discussing potential drivers such as tools, practices, and interventions that support ML reproducibility, as well as distinguish between technology-driven drivers, procedural drivers, and drivers related to awareness and education, and (iii) mapping the drivers to the barriers. With this work, we hope to provide insights and to contribute to the decision-making process regarding the adoption of different solutions to support ML reproducibility.
Authors: Erik Jones, Anca Dragan, Jacob Steinhardt
Abstract: Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that individually testing models for misuse is inadequate; adversaries can misuse combinations of models even when each individual model is safe. The adversary accomplishes this by first decomposing tasks into subtasks, then solving each subtask with the best-suited model. For example, an adversary might solve challenging-but-benign subtasks with an aligned frontier model, and easy-but-malicious subtasks with a weaker misaligned model. We study two decomposition methods: manual decomposition where a human identifies a natural decomposition of a task, and automated decomposition where a weak model generates benign tasks for a frontier model to solve, then uses the solutions in-context to solve the original task. Using these decompositions, we empirically show that adversaries can create vulnerable code, explicit images, python scripts for hacking, and manipulative tweets at much higher rates with combinations of models than either individual model. Our work suggests that even perfectly-aligned frontier systems can enable misuse without ever producing malicious outputs, and that red-teaming efforts should extend beyond single models in isolation.
Authors: Chen Liu, Ke Xu, Liangbo L. Shen, Guillaume Huguet, Zilong Wang, Alexander Tong, Danilo Bzdok, Jay Stewart, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy
Abstract: The forecasting of disease progression from images is a holy grail for clinical decision making. However, this task is complicated by the inherent high dimensionality, temporal sparsity and sampling irregularity in longitudinal image acquisitions. Existing methods often rely on extracting hand-crafted features and performing time-series analysis in this vector space, leading to a loss of rich spatial information within the images. To overcome these challenges, we introduce ImageFlowNet, a novel framework that learns latent-space flow fields that evolve multiscale representations in joint embedding spaces using neural ODEs and SDEs to model disease progression in the image domain. Notably, ImageFlowNet learns multiscale joint representation spaces by combining cohorts of patients together so that information can be transferred between the patient samples. The dynamics then provide plausible trajectories of progression, with the SDE providing alternative trajectories from the same starting point. We provide theoretical insights that support our formulation of ODEs, and motivate our regularizations involving high-level visual features, latent space organization, and trajectory smoothness. We then demonstrate ImageFlowNet's effectiveness through empirical evaluations on three longitudinal medical image datasets depicting progression in retinal geographic atrophy, multiple sclerosis, and glioblastoma.
Authors: Guangkun Nie, Qinghao Zhao, Gongzheng Tang, Jun Li, Shenda Hong
Abstract: Photoplethysmography (PPG) is emerging as a crucial tool for monitoring human hemodynamics, with recent studies highlighting its potential in assessing vascular aging through deep learning. However, real-world age distributions are often imbalanced, posing significant challenges for deep learning models. In this paper, we introduce a novel, simple, and effective loss function named the Dist Loss to address deep imbalanced regression tasks. We trained a one-dimensional convolutional neural network (Net1D) incorporating the Dist Loss on the extensive UK Biobank dataset (n=502,389) to estimate vascular age from PPG signals and validate its efficacy in characterizing cardiovascular health. The model's performance was validated on a 40% held-out test set, achieving state-of-the-art results, especially in regions with small sample sizes. Furthermore, we divided the population into three subgroups based on the difference between predicted vascular age and chronological age: less than -10 years, between -10 and 10 years, and greater than 10 years. We analyzed the relationship between predicted vascular age and several cardiovascular events over a follow-up period of up to 10 years, including death, coronary heart disease, and heart failure. Our results indicate that the predicted vascular age has significant potential to reflect an individual's cardiovascular health status. Our code will be available at https://github.com/Ngk03/AI-vascular-age.
Authors: Paul Primus, Gerhard Widmer
Abstract: Matching raw audio signals with textual descriptions requires understanding the audio's content and the description's semantics and then drawing connections between the two modalities. This paper investigates a hybrid retrieval system that utilizes audio metadata as an additional clue to understand the content of audio signals before matching them with textual queries. We experimented with metadata often attached to audio recordings, such as keywords and natural-language descriptions, and we investigated late and mid-level fusion strategies to merge audio and metadata. Our hybrid approach with keyword metadata and late fusion improved the retrieval performance over a content-based baseline by 2.36 and 3.69 pp. mAP@10 on the ClothoV2 and AudioCaps benchmarks, respectively.
Authors: Haorui Wang, Marta Skreta, Cher-Tian Ser, Wenhao Gao, Lingkai Kong, Felix Strieth-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: Pai Peng, Yunqing 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: Fredrik Nestaas, Edoardo Debenedetti, Florian Tram\`er
Abstract: Large Language Models (LLMs) are increasingly used in applications where the model selects from competing third-party content, such as in LLM-powered search engines or chatbot plugins. In this paper, we introduce Preference Manipulation Attacks, a new class of attacks that manipulate an LLM's selections to favor the attacker. We demonstrate that carefully crafted website content or plugin documentations can trick an LLM to promote the attacker products and discredit competitors, thereby increasing user traffic and monetization. We show this leads to a prisoner's dilemma, where all parties are incentivized to launch attacks, but the collective effect degrades the LLM's outputs for everyone. We demonstrate our attacks on production LLM search engines (Bing and Perplexity) and plugin APIs (for GPT-4 and Claude). As LLMs are increasingly used to rank third-party content, we expect Preference Manipulation Attacks to emerge as a significant threat.
Authors: Ali Kazemi Arani, Triet Huynh Minh Le, Mansooreh Zahedi, M. Ali Babar
Abstract: Context: Machine learning (ML) and deep learning (DL) analyze raw data to extract valuable insights in specific phases. The rise of continuous practices in software projects emphasizes automating Continuous Integration (CI) with these learning-based methods, while the growing adoption of such approaches underscores the need for systematizing knowledge. Objective: Our objective is to comprehensively review and analyze existing literature concerning learning-based methods within the CI domain. We endeavour to identify and analyse various techniques documented in the literature, emphasizing the fundamental attributes of training phases within learning-based solutions in the context of CI. Method: We conducted a Systematic Literature Review (SLR) involving 52 primary studies. Through statistical and thematic analyses, we explored the correlations between CI tasks and the training phases of learning-based methodologies across the selected studies, encompassing a spectrum from data engineering techniques to evaluation metrics. Results: This paper presents an analysis of the automation of CI tasks utilizing learning-based methods. We identify and analyze nine types of data sources, four steps in data preparation, four feature types, nine subsets of data features, five approaches for hyperparameter selection and tuning, and fifteen evaluation metrics. Furthermore, we discuss the latest techniques employed, existing gaps in CI task automation, and the characteristics of the utilized learning-based techniques. Conclusion: This study provides a comprehensive overview of learning-based methods in CI, offering valuable insights for researchers and practitioners developing CI task automation. It also highlights the need for further research to advance these methods in CI.
Authors: Giuseppe Serra, Peter Tino, Zhao Xu, Xin Yao
Abstract: Nowadays, neural network (NN) and deep learning (DL) techniques are widely adopted in many applications, including recommender systems. Given the sparse and stochastic nature of collaborative filtering (CF) data, recent works have critically analyzed the effective improvement of neural-based approaches compared to simpler and often transparent algorithms for recommendation. Previous results showed that NN and DL models can be outperformed by traditional algorithms in many tasks. Moreover, given the largely black-box nature of neural-based methods, interpretable results are not naturally obtained. Following on this debate, we first present a transparent probabilistic model that topologically organizes user and product latent classes based on the review information. In contrast to popular neural techniques for representation learning, we readily obtain a statistical, visualization-friendly tool that can be easily inspected to understand user and product characteristics from a textual-based perspective. Then, given the limitations of common embedding techniques, we investigate the possibility of using the estimated interpretable quantities as model input for a rating prediction task. To contribute to the recent debates, we evaluate our results in terms of both capacity for interpretability and predictive performances in comparison with popular text-based neural approaches. The results demonstrate that the proposed latent class representations can yield competitive predictive performances, compared to popular, but difficult-to-interpret approaches.
Authors: Rongzhe Wei, Eli Chien, Pan Li
Abstract: Graph diffusion, which iteratively propagates real-valued substances among the graph, is used in numerous graph/network-involved applications. However, releasing diffusion vectors may reveal sensitive linking information in the data such as transaction information in financial network data. However, protecting the privacy of graph data is challenging due to its interconnected nature. This work proposes a novel graph diffusion framework with edge-level differential privacy guarantees by using noisy diffusion iterates. The algorithm injects Laplace noise per diffusion iteration and adopts a degree-based thresholding function to mitigate the high sensitivity induced by low-degree nodes. Our privacy loss analysis is based on Privacy Amplification by Iteration (PABI), which to our best knowledge, is the first effort that analyzes PABI with Laplace noise and provides relevant applications. We also introduce a novel Infinity-Wasserstein distance tracking method, which tightens the analysis of privacy leakage and makes PABI more applicable in practice. We evaluate this framework by applying it to Personalized Pagerank computation for ranking tasks. Experiments on real-world network data demonstrate the superiority of our method under stringent privacy conditions.
Authors: Mingrui Zhang, Chunyang Wang, Stephan Kramer, Joseph G. Wallwork, Siyi Li, Jiancheng Liu, Xiang Chen, Matthew D. Piggott
Abstract: Solving complex Partial Differential Equations (PDEs) accurately and efficiently is an essential and challenging problem in all scientific and engineering disciplines. Mesh movement methods provide the capability to improve the accuracy of the numerical solution without increasing the overall mesh degree of freedom count. Conventional sophisticated mesh movement methods are extremely expensive and struggle to handle scenarios with complex boundary geometries. However, existing learning-based methods require re-training from scratch given a different PDE type or boundary geometry, which limits their applicability, and also often suffer from robustness issues in the form of inverted elements. In this paper, we introduce the Universal Mesh Movement Network (UM2N), which -- once trained -- can be applied in a non-intrusive, zero-shot manner to move meshes with different size distributions and structures, for solvers applicable to different PDE types and boundary geometries. UM2N consists of a Graph Transformer (GT) encoder for extracting features and a Graph Attention Network (GAT) based decoder for moving the mesh. We evaluate our method on advection and Navier-Stokes based examples, as well as a real-world tsunami simulation case. Our method outperforms existing learning-based mesh movement methods in terms of the benchmarks described above. In comparison to the conventional sophisticated Monge-Amp\`ere PDE-solver based method, our approach not only significantly accelerates mesh movement, but also proves effective in scenarios where the conventional method fails. Our project page is at https://erizmr.github.io/UM2N/.