Authors: Hari Srikanth
Abstract: Neural Network based approximations of the Value function make up the core of leading Policy Based methods such as Trust Regional Policy Optimization (TRPO) and Proximal Policy Optimization (PPO). While this adds significant value when dealing with very complex environments, we note that in sufficiently low State and action space environments, a computationally expensive Neural Network architecture offers marginal improvement over simpler Value approximation methods. We present an implementation of Natural Actor Critic algorithms with actor updates through Natural Policy Gradient methods. This paper proposes that Natural Policy Gradient (NPG) methods with Linear Function Approximation as a paradigm for value approximation may surpass the performance and speed of Neural Network based models such as TRPO and PPO within these environments. Over Reinforcement Learning benchmarks Cart Pole and Acrobot, we observe that our algorithm trains much faster than complex neural network architectures, and obtains an equivalent or greater result. This allows us to recommend the use of NPG methods with Linear Function Approximation over TRPO and PPO for both traditional and sparse reward low dimensional problems.
Authors: Ziqi Zhang, Zifeng Zhuang, Donglin Wang, Jingzehua Xu, Miao Liu, Shuai Zhang
Abstract: Typically, traditional Imitation Learning (IL) methods first shape a reward or Q function and then use this shaped function within a reinforcement learning (RL) framework to optimize the empirical policy. However, if the shaped reward/Q function does not adequately represent the ground truth reward/Q function, updating the policy within a multi-step RL framework may result in cumulative bias, further impacting policy learning. Although utilizing behavior cloning (BC) to learn a policy by directly mimicking a few demonstrations in a single-step updating manner can avoid cumulative bias, BC tends to greedily imitate demonstrated actions, limiting its capacity to generalize to unseen state action pairs. To address these challenges, we propose ADR-BC, which aims to enhance behavior cloning through augmented density-based action support, optimizing the policy with this augmented support. Specifically, the objective of ADR-BC shares the similar physical meanings that matching expert distribution while diverging the sub-optimal distribution. Therefore, ADR-BC can achieve more robust expert distribution matching. Meanwhile, as a one-step behavior cloning framework, ADR-BC avoids the cumulative bias associated with multi-step RL frameworks. To validate the performance of ADR-BC, we conduct extensive experiments. Specifically, ADR-BC showcases a 10.5% improvement over the previous state-of-the-art (SOTA) generalized IL baseline, CEIL, across all tasks in the Gym-Mujoco domain. Additionally, it achieves an 89.5% improvement over Implicit Q Learning (IQL) using real rewards across all tasks in the Adroit and Kitchen domains. On the other hand, we conduct extensive ablations to further demonstrate the effectiveness of ADR-BC.
Authors: Shi Mu, Shunpan Liang, Xiang Li
Abstract: Medication recommendation combines patient medical history with biomedical knowledge to assist doctors in determining medication combinations more accurately and safely. Existing approaches based on molecular knowledge overlook the atomic geometric structure of molecules, failing to capture the high-dimensional characteristics and intrinsic physical properties of medications, leading to structural confusion and the inability to extract useful substructures from individual patient visits. To address these limitations, we propose BiMoRec, which overcomes the inherent lack of molecular essential information in 2D molecular structures by incorporating 3D molecular structures and atomic properties. To retain the fast response required of recommendation systems, BiMoRec maximizes the mutual information between the two molecular modalities through bimodal graph contrastive learning, achieving the integration of 2D and 3D molecular graphs, and finally distills substructures through interaction with single patient visits. Specifically, we use deep learning networks to construct a pre-training method to obtain representations of 2D and 3D molecular structures and substructures, and we use contrastive learning to derive mutual information. Subsequently, we generate fused molecular representations through a trained GNN module, re-determining the relevance of substructure representations in conjunction with the patient's clinical history information. Finally, we generate the final medication combination based on the extracted substructure sequences. Our implementation on the MIMIC-III and MIMIC-IV datasets demonstrates that our method achieves state-of-the-art performance. Compared to the next best baseline, our model improves accuracy by 1.8\% while maintaining the same level of DDI as the baseline.
Authors: Lingkai Kong, Molei Tao
Abstract: Explicit, momentum-based dynamics that optimize functions defined on Lie groups can be constructed via variational optimization and momentum trivialization. Structure preserving time discretizations can then turn this dynamics into optimization algorithms. This article investigates two types of discretization, Lie Heavy-Ball, which is a known splitting scheme, and Lie NAG-SC, which is newly proposed. Their convergence rates are explicitly quantified under $L$-smoothness and local strong convexity assumptions. Lie NAG-SC provides acceleration over the momentumless case, i.e. Riemannian gradient descent, but Lie Heavy-Ball does not. When compared to existing accelerated optimizers for general manifolds, both Lie Heavy-Ball and Lie NAG-SC are computationally cheaper and easier to implement, thanks to their utilization of group structure. Only gradient oracle and exponential map are required, but not logarithm map or parallel transport which are computational costly.
Authors: Tirtha Vinchurkar, Janghoon Ock, Amir Barati Farimani
Abstract: The increasing popularity of machine learning (ML) in catalysis has spurred interest in leveraging these techniques to enhance catalyst design. Our study aims to bridge the gap between physics-based studies and data-driven methodologies by integrating ML techniques with eXplainable AI (XAI). Specifically, we employ two XAI techniques: Post-hoc XAI analysis and Symbolic Regression. These techniques help us unravel the correlation between adsorption energy and the properties of the adsorbate-catalyst system. Leveraging a large dataset such as the Open Catalyst Dataset (OC20), we employ a combination of shallow ML techniques and XAI methodologies. Our investigation involves utilizing multiple shallow machine learning techniques to predict adsorption energy, followed by post-hoc analysis for feature importance, inter-feature correlations, and the influence of various feature values on the prediction of adsorption energy. The post-hoc analysis reveals that adsorbate properties exert a greater influence than catalyst properties in our dataset. The top five features based on higher Shapley values are adsorbate electronegativity, the number of adsorbate atoms, catalyst electronegativity, effective coordination number, and the sum of atomic numbers of the adsorbate molecule. There is a positive correlation between catalyst and adsorbate electronegativity with the prediction of adsorption energy. Additionally, symbolic regression yields results consistent with SHAP analysis. It deduces a mathematical relationship indicating that the square of the catalyst electronegativity is directly proportional to the adsorption energy. These consistent correlations resemble those derived from physics-based equations in previous research. Our work establishes a robust framework that integrates ML techniques with XAI, leveraging large datasets like OC20 to enhance catalyst design through model explainability.
Authors: Hakim El Massari, Noreddine Gherabi, Sajida Mhammedi, Hamza Ghandi, Mohamed Bahaj, Muhammad Raza Naqvi
Abstract: Cardiovascular disease is one of the chronic diseases that is on the rise. The complications occur when cardiovascular disease is not discovered early and correctly diagnosed at the right time. Various machine learning approaches, including ontology-based Machine Learning techniques, have lately played an essential role in medical science by building an automated system that can identify heart illness. This paper compares and reviews the most prominent machine learning algorithms, as well as ontology-based Machine Learning classification. Random Forest, Logistic regression, Decision Tree, Naive Bayes, k-Nearest Neighbours, Artificial Neural Network, and Support Vector Machine were among the classification methods explored. The dataset used consists of 70000 instances and can be downloaded from the Kaggle website. The findings are assessed using performance measures generated from the confusion matrix, such as F-Measure, Accuracy, Recall, and Precision. The results showed that the ontology outperformed all the machine learning algorithms.
Authors: Simon A. Lee, Trevor Brokowski, Jeffrey N. Chiang
Abstract: The rapid emergence of antibiotic-resistant bacteria is recognized as a global healthcare crisis, undermining the efficacy of life-saving antibiotics. This crisis is driven by the improper and overuse of antibiotics, which escalates bacterial resistance. In response, this study explores the use of clinical decision support systems, enhanced through the integration of electronic health records (EHRs), to improve antibiotic stewardship. However, EHR systems present numerous data-level challenges, complicating the effective synthesis and utilization of data. In this work, we transform EHR data into a serialized textual representation and employ pretrained foundation models to demonstrate how this enhanced feature representation can aid in antibiotic susceptibility predictions. Our results suggest that this text representation, combined with foundation models, provides a valuable tool to increase interpretability and support antibiotic stewardship efforts.
Authors: Levy Chaves, Eduardo Valle, Alceu Bissoto, Sandra Avila
Abstract: In the evolving landscape of deep learning, selecting the best pre-trained models from a growing number of choices is a challenge. Transferability scorers propose alleviating this scenario, but their recent proliferation, ironically, poses the challenge of their own assessment. In this work, we propose both robust benchmark guidelines for transferability scorers, and a well-founded technique to combine multiple scorers, which we show consistently improves their results. We extensively evaluate 13 scorers from literature across 11 datasets, comprising generalist, fine-grained, and medical imaging datasets. We show that few scorers match the predictive performance of the simple raw metric of models on ImageNet, and that all predictors suffer on medical datasets. Our results highlight the potential of combining different information sources for reliably predicting transferability across varied domains.
Authors: Georgios Tsoumplekas, Ilias Siniosoglou, Vasileios Argyriou, Ioannis D. Moscholios, Panagiotis Sarigiannidis
Abstract: The increased availability of medical data has significantly impacted healthcare by enabling the application of machine / deep learning approaches in various instances. However, medical datasets are usually small and scattered across multiple providers, suffer from high class-imbalance, and are subject to stringent data privacy constraints. In this paper, the application of a data regularization algorithm, suitable for learning under high class-imbalance, in a federated learning setting is proposed. Specifically, the goal of the proposed method is to enhance model performance for cardiovascular disease prediction by tackling the class-imbalance that typically characterizes datasets used for this purpose, as well as by leveraging patient data available in different nodes of a federated ecosystem without compromising their privacy and enabling more resource sensitive allocation. The method is evaluated across four datasets for cardiovascular disease prediction, which are scattered across different clients, achieving improved performance. Meanwhile, its robustness under various hyperparameter settings, as well as its ability to adapt to different resource allocation scenarios, is verified.
Authors: Khiem Le, Nhan Luong-Ha, Manh Nguyen-Duc, Danh Le-Phuoc, Cuong Do, Kok-Seng Wong
Abstract: Federated Learning (FL) is a promising paradigm that offers significant advancements in privacy-preserving, decentralized machine learning by enabling collaborative training of models across distributed devices without centralizing data. However, the practical deployment of FL systems faces a significant bottleneck: the communication overhead caused by frequently exchanging large model updates between numerous devices and a central server. This communication inefficiency can hinder training speed, model performance, and the overall feasibility of real-world FL applications. In this survey, we investigate various strategies and advancements made in communication-efficient FL, highlighting their impact and potential to overcome the communication challenges inherent in FL systems. Specifically, we define measures for communication efficiency, analyze sources of communication inefficiency in FL systems, and provide a taxonomy and comprehensive review of state-of-the-art communication-efficient FL methods. Additionally, we discuss promising future research directions for enhancing the communication efficiency of FL systems. By addressing the communication bottleneck, FL can be effectively applied and enable scalable and practical deployment across diverse applications that require privacy-preserving, decentralized machine learning, such as IoT, healthcare, or finance.
Authors: Yanlin Qu, Jose Blanchet, Peter Glynn
Abstract: Convergence rate analysis for general state-space Markov chains is fundamentally important in areas such as Markov chain Monte Carlo and algorithmic analysis (for computing explicit convergence bounds). This problem, however, is notoriously difficult because traditional analytical methods often do not generate practically useful convergence bounds for realistic Markov chains. We propose the Deep Contractive Drift Calculator (DCDC), the first general-purpose sample-based algorithm for bounding the convergence of Markov chains to stationarity in Wasserstein distance. The DCDC has two components. First, inspired by the new convergence analysis framework in (Qu et.al, 2023), we introduce the Contractive Drift Equation (CDE), the solution of which leads to an explicit convergence bound. Second, we develop an efficient neural-network-based CDE solver. Equipped with these two components, DCDC solves the CDE and converts the solution into a convergence bound. We analyze the sample complexity of the algorithm and further demonstrate the effectiveness of the DCDC by generating convergence bounds for realistic Markov chains arising from stochastic processing networks as well as constant step-size stochastic optimization.
Authors: Jacob Mitchell Springer, Vaishnavh Nagarajan, Aditi Raghunathan
Abstract: Sharpness-Aware Minimization (SAM) has emerged as a promising alternative optimizer to stochastic gradient descent (SGD). The originally-proposed motivation behind SAM was to bias neural networks towards flatter minima that are believed to generalize better. However, recent studies have shown conflicting evidence on the relationship between flatness and generalization, suggesting that flatness does fully explain SAM's success. Sidestepping this debate, we identify an orthogonal effect of SAM that is beneficial out-of-distribution: we argue that SAM implicitly balances the quality of diverse features. SAM achieves this effect by adaptively suppressing well-learned features which gives remaining features opportunity to be learned. We show that this mechanism is beneficial in datasets that contain redundant or spurious features where SGD falls for the simplicity bias and would not otherwise learn all available features. Our insights are supported by experiments on real data: we demonstrate that SAM improves the quality of features in datasets containing redundant or spurious features, including CelebA, Waterbirds, CIFAR-MNIST, and DomainBed.
Authors: Jianan Zhao, Hesham Mostafa, Michael Galkin, Michael Bronstein, Zhaocheng Zhu, Jian Tang
Abstract: Foundation models that can perform inference on any new task without requiring specific training have revolutionized machine learning in vision and language applications. However, applications involving graph-structured data remain a tough nut for foundation models, due to challenges in the unique feature- and label spaces associated with each graph. Traditional graph ML models such as graph neural networks (GNNs) trained on graphs cannot perform inference on a new graph with feature and label spaces different from the training ones. Furthermore, existing models learn functions specific to the training graph and cannot generalize to new graphs. In this work, we tackle these two challenges with a new foundational architecture for inductive node classification named GraphAny. GraphAny models inference on a new graph as an analytical solution to a LinearGNN, thereby solving the first challenge. To solve the second challenge, we learn attention scores for each node to fuse the predictions of multiple LinearGNNs. Specifically, the attention module is carefully parameterized as a function of the entropy-normalized distance-features between multiple LinearGNNs predictions to ensure generalization to new graphs. Empirically, GraphAny trained on the Wisconsin dataset with only 120 labeled nodes can effectively generalize to 30 new graphs with an average accuracy of 67.26\% in an inductive manner, surpassing GCN and GAT trained in the supervised regime, as well as other inductive baselines.
Authors: Minh Nguyen, Batuhan K. Karaman, Heejong Kim, Alan Q. Wang, Fengbei Liu, Mert R. Sabuncu
Abstract: Deep learning models can tease out information from complex inputs. The richer inputs the better these models usually perform. However, models that leverage rich inputs (e.g. multi-sensor, multi-modality, multi-view) can be difficult to deployed widely because some inputs may be missing during deployment. Current popular solutions to this problem includes marginalization, imputation, and training multiple models. Marginalization can obtain calibrated predictions but it is computationally costly and therefore is only feasible for low dimensional inputs. Imputation may result in mis-calibrated predictions because it approximates predictions using point estimates and does not work for high dimensional inputs (e.g. images). Training multiple models whereby each models take different subsets of inputs can work well but requires knowing missing input patterns in advance. Furthermore, training multiple models is costly when models are built on top of foundational models. We propose an efficient way to learn both the conditional distribution using full inputs and the marginal distributions using partial inputs simultaneously using a single model and input mask-out. Input mask-out ensures that learning the marginal distributions does not interfere with learning the conditional distribution. Our approach is general and can be applied to both low- and high-dimensional inputs. We evaluate mask-out in several simulations to show that it can help a single model efficiently learns both conditional and marginal distributions. Experiment results multiple real-world datasets in both classification and segmentation demonstrates the utility of mask-out.
Authors: Jorge F. Silva, Victor Faraggi, Camilo Ramirez, Alvaro Egana, Eduardo Pavez
Abstract: We present new results to model and understand the role of encoder-decoder design in machine learning (ML) from an information-theoretic angle. We use two main information concepts, information sufficiency (IS) and mutual information loss (MIL), to represent predictive structures in machine learning. Our first main result provides a functional expression that characterizes the class of probabilistic models consistent with an IS encoder-decoder latent predictive structure. This result formally justifies the encoder-decoder forward stages many modern ML architectures adopt to learn latent (compressed) representations for classification. To illustrate IS as a realistic and relevant model assumption, we revisit some known ML concepts and present some interesting new examples: invariant, robust, sparse, and digital models. Furthermore, our IS characterization allows us to tackle the fundamental question of how much performance (predictive expressiveness) could be lost, using the cross entropy risk, when a given encoder-decoder architecture is adopted in a learning setting. Here, our second main result shows that a mutual information loss quantifies the lack of expressiveness attributed to the choice of a (biased) encoder-decoder ML design. Finally, we address the problem of universal cross-entropy learning with an encoder-decoder design where necessary and sufficiency conditions are established to meet this requirement. In all these results, Shannon's information measures offer new interpretations and explanations for representation learning.
Authors: Ian Covert, Wenlong Ji, Tatsunori Hashimoto, James Zou
Abstract: Recent works have shown that machine learning models improve at a predictable rate with the total amount of training data, leading to scaling laws that describe the relationship between error and dataset size. These scaling laws can help design a model's training dataset, but they typically take an aggregate view of the data by only considering the dataset's size. We introduce a new perspective by investigating scaling behavior for the value of individual data points: we find that a data point's contribution to model's performance shrinks predictably with the size of the dataset in a log-linear manner. Interestingly, there is significant variability in the scaling exponent among different data points, indicating that certain points are more valuable in small datasets while others are relatively more useful as a part of large datasets. We provide learning theory to support our scaling law, and we observe empirically that it holds across diverse model classes. We further propose a maximum likelihood estimator and an amortized estimator to efficiently learn the individualized scaling behaviors from a small number of noisy observations per data point. Using our estimators, we provide insights into factors that influence the scaling behavior of different data points. Finally, we demonstrate applications of the individualized scaling laws to data valuation and data subset selection. Overall, our work represents a first step towards understanding and utilizing scaling properties for the value of individual data points.
Authors: Yashaswini Murthy, Isaac Grosof, Siva Theja Maguluri, R. Srikant
Abstract: We consider policy optimization methods in reinforcement learning settings where the state space is arbitrarily large, or even countably infinite. The motivation arises from control problems in communication networks, matching markets, and other queueing systems. We consider Natural Policy Gradient (NPG), which is a popular algorithm for finite state spaces. Under reasonable assumptions, we derive a performance bound for NPG that is independent of the size of the state space, provided the error in policy evaluation is within a factor of the true value function. We obtain this result by establishing new policy-independent bounds on the solution to Poisson's equation, i.e., the relative value function, and by combining these bounds with previously known connections between MDPs and learning from experts.
Authors: Elliot Layne, Jason Hartford, S\'ebastien Lachapelle, Mathieu Blanchette, Dhanya Sridhar
Abstract: Many causal systems such as biological processes in cells can only be observed indirectly via measurements, such as gene expression. Causal representation learning -- the task of correctly mapping low-level observations to latent causal variables -- could advance scientific understanding by enabling inference of latent variables such as pathway activation. In this paper, we develop methods for inferring latent variables from multiple related datasets (environments) and tasks. As a running example, we consider the task of predicting a phenotype from gene expression, where we often collect data from multiple cell types or organisms that are related in known ways. The key insight is that the mapping from latent variables driven by gene expression to the phenotype of interest changes sparsely across closely related environments. To model sparse changes, we introduce Tree-Based Regularization (TBR), an objective that minimizes both prediction error and regularizes closely related environments to learn similar predictors. We prove that under assumptions about the degree of sparse changes, TBR identifies the true latent variables up to some simple transformations. We evaluate the theory empirically with both simulations and ground-truth gene expression data. We find that TBR recovers the latent causal variables better than related methods across these settings, even under settings that violate some assumptions of the theory.
Authors: Dimitris Bertsimas, Matthew Peroni
Abstract: As a multitude of capable machine learning (ML) models become widely available in forms such as open-source software and public APIs, central questions remain regarding their use in real-world applications, especially in high-stakes decision-making. Is there always one best model that should be used? When are the models likely to be error-prone? Should a black-box or interpretable model be used? In this work, we develop a prescriptive methodology to address these key questions, introducing a tree-based approach, Optimal Predictive-Policy Trees (OP2T), that yields interpretable policies for adaptively selecting a predictive model or ensemble, along with a parameterized option to reject making a prediction. We base our methods on learning globally optimized prescriptive trees. Our approach enables interpretable and adaptive model selection and rejection while only assuming access to model outputs. By learning policies over different feature spaces, including the model outputs, our approach works with both structured and unstructured datasets. We evaluate our approach on real-world datasets, including regression and classification tasks with both structured and unstructured data. We demonstrate that our approach provides both strong performance against baseline methods while yielding insights that help answer critical questions about which models to use, and when.
Authors: Asmaa Benchama, Khalid Zebbara
Abstract: Deep learning is currently extensively employed across a range of research domains. The continuous advancements in deep learning techniques contribute to solving intricate challenges. Activation functions (AF) are fundamental components within neural networks, enabling them to capture complex patterns and relationships in the data. By introducing non-linearities, AF empowers neural networks to model and adapt to the diverse and nuanced nature of real-world data, enhancing their ability to make accurate predictions across various tasks. In the context of intrusion detection, the Mish, a recent AF, was implemented in the CNN-BiGRU model, using three datasets: ASNM-TUN, ASNM-CDX, and HOGZILLA. The comparison with Rectified Linear Unit (ReLU), a widely used AF, revealed that Mish outperforms ReLU, showcasing superior performance across the evaluated datasets. This study illuminates the effectiveness of AF in elevating the performance of intrusion detection systems.
Authors: Tanapol Kosolwattana, Huazheng Wang, Raed Al Kontar, Ying Lin
Abstract: Online learning has demonstrated notable potential to dynamically allocate limited resources to monitor a large population of processes, effectively balancing the exploitation of processes yielding high rewards, and the exploration of uncertain processes. However, most online learning algorithms were designed under 1) a centralized setting that requires data sharing across processes to obtain an accurate prediction or 2) a homogeneity assumption that estimates a single global model from the decentralized data. To facilitate the online learning of heterogeneous processes from the decentralized data, we propose a federated collaborative online monitoring method, which captures the latent representative models inherent in the population through representation learning and designs a novel federated collaborative UCB algorithm to estimate the representative models from sequentially observed decentralized data. The efficiency of our method is illustrated through theoretical analysis, simulation studies, and decentralized cognitive degradation monitoring in Alzheimer's disease.
Authors: Aastha Acharya, Caleb Lee, Marissa D'Alonzo, Jared Shamwell, Nisar R. Ahmed, Rebecca Russell
Abstract: Deep learning offers promising new ways to accurately model aleatoric uncertainty in robotic estimation systems, particularly when the uncertainty distributions do not conform to traditional assumptions of being fixed and Gaussian. In this study, we formulate and evaluate three fundamental deep learning approaches for conditional probability density modeling to quantify non-Gaussian aleatoric uncertainty: parametric, discretized, and generative modeling. We systematically compare the respective strengths and weaknesses of these three methods on simulated non-Gaussian densities as well as on real-world terrain-relative navigation data. Our results show that these deep learning methods can accurately capture complex uncertainty patterns, highlighting their potential for improving the reliability and robustness of estimation systems.
Authors: Dongwei Lyu, Rie Nakata, Pu Ren, Michael W. Mahoney, Arben Pitarka, Nori Nakata, N. Benjamin Erichson
Abstract: Large earthquakes can be destructive and quickly wreak havoc on a landscape. To mitigate immediate threats, early warning systems have been developed to alert residents, emergency responders, and critical infrastructure operators seconds to a minute before seismic waves arrive. These warnings provide time to take precautions and prevent damage. The success of these systems relies on fast, accurate predictions of ground motion intensities, which is challenging due to the complex physics of earthquakes, wave propagation, and their intricate spatial and temporal interactions. To improve early warning, we propose a novel AI-enabled framework, WaveCastNet, for forecasting ground motions from large earthquakes. WaveCastNet integrates a novel convolutional Long Expressive Memory (ConvLEM) model into a sequence to sequence (seq2seq) forecasting framework to model long-term dependencies and multi-scale patterns in both space and time. WaveCastNet, which shares weights across spatial and temporal dimensions, requires fewer parameters compared to more resource-intensive models like transformers and thus, in turn, reduces inference times. Importantly, WaveCastNet also generalizes better than transformer-based models to different seismic scenarios, including to more rare and critical situations with higher magnitude earthquakes. Our results using simulated data from the San Francisco Bay Area demonstrate the capability to rapidly predict the intensity and timing of destructive ground motions. Importantly, our proposed approach does not require estimating earthquake magnitudes and epicenters, which are prone to errors using conventional approaches; nor does it require empirical ground motion models, which fail to capture strongly heterogeneous wave propagation effects.
Authors: Louis L. Chen, Bobbie Chern, Eric Eckstrand, Amogh Mahapatra, Johannes O. Royset
Abstract: Labeling errors in datasets are common, if not systematic, in practice. They naturally arise in a variety of contexts-human labeling, noisy labeling, and weak labeling (i.e., image classification), for example. This presents a persistent and pervasive stress on machine learning practice. In particular, neural network (NN) architectures can withstand minor amounts of dataset imperfection with traditional countermeasures such as regularization, data augmentation, and batch normalization. However, major dataset imperfections often prove insurmountable. We propose and study the implementation of Rockafellian Relaxation (RR), a new loss reweighting, architecture-independent methodology, for neural network training. Experiments indicate RR can enhance standard neural network methods to achieve robust performance across classification tasks in computer vision and natural language processing (sentiment analysis). We find that RR can mitigate the effects of dataset corruption due to both (heavy) labeling error and/or adversarial perturbation, demonstrating effectiveness across a variety of data domains and machine learning tasks.
Authors: Davide Corsi, Davide Camponogara, Alessandro Farinelli
Abstract: An exciting and promising frontier for Deep Reinforcement Learning (DRL) is its application to real-world robotic systems. While modern DRL approaches achieved remarkable successes in many robotic scenarios (including mobile robotics, surgical assistance, and autonomous driving) unpredictable and non-stationary environments can pose critical challenges to such methods. These features can significantly undermine fundamental requirements for a successful training process, such as the Markovian properties of the transition model. To address this challenge, we propose a new benchmarking environment for aquatic navigation using recent advances in the integration between game engines and DRL. In more detail, we show that our benchmarking environment is problematic even for state-of-the-art DRL approaches that may struggle to generate reliable policies in terms of generalization power and safety. Specifically, we focus on PPO, one of the most widely accepted algorithms, and we propose advanced training techniques (such as curriculum learning and learnable hyperparameters). Our extensive empirical evaluation shows that a well-designed combination of these ingredients can achieve promising results. Our simulation environment and training baselines are freely available to facilitate further research on this open problem and encourage collaboration in the field.
Authors: Lingyi Yang
Abstract: Stability issues with reinforcement learning methods persist. To better understand some of these stability and convergence issues involving deep reinforcement learning methods, we examine a simple linear quadratic example. We interpret the convergence criterion of exact Q-learning in the sense of a monotone scheme and discuss consequences of function approximation on monotonicity properties.
Authors: Ethan Rathbun, Christopher Amato, Alina Oprea
Abstract: Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work we explore a particularly stealthy form of training-time attacks against RL -- backdoor poisoning. Here the adversary intercepts the training of an RL agent with the goal of reliably inducing a particular action when the agent observes a pre-determined trigger at inference time. We uncover theoretical limitations of prior work by proving their inability to generalize across domains and MDPs. Motivated by this, we formulate a novel poisoning attack framework which interlinks the adversary's objectives with those of finding an optimal policy -- guaranteeing attack success in the limit. Using insights from our theoretical analysis we develop ``SleeperNets'' as a universal backdoor attack which exploits a newly proposed threat model and leverages dynamic reward poisoning techniques. We evaluate our attack in 6 environments spanning multiple domains and demonstrate significant improvements in attack success over existing methods, while preserving benign episodic return.
Authors: Ashok Cutkosky, Zakaria Mhammedi
Abstract: We provide an online learning algorithm that obtains regret $G\|w_\star\|\sqrt{T\log(\|w_\star\|G\sqrt{T})} + \|w_\star\|^2 + G^2$ on $G$-Lipschitz convex losses for any comparison point $w_\star$ without knowing either $G$ or $\|w_\star\|$. Importantly, this matches the optimal bound $G\|w_\star\|\sqrt{T}$ available with such knowledge (up to logarithmic factors), unless either $\|w_\star\|$ or $G$ is so large that even $G\|w_\star\|\sqrt{T}$ is roughly linear in $T$. Thus, it matches the optimal bound in all cases in which one can achieve sublinear regret, which arguably most "interesting" scenarios.
Authors: Zachary Ankner, Cody Blakeney, Kartik Sreenivasan, Max Marion, Matthew L. Leavitt, Mansheej Paul
Abstract: In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. While existing work has shown that pruning based on the perplexity of a larger model can yield high-quality data, we investigate whether smaller models can be used for perplexity-based pruning and how pruning is affected by the domain composition of the data being pruned. We demonstrate that for multiple dataset compositions, perplexity-based pruning of pretraining data can \emph{significantly} improve downstream task performance: pruning based on perplexities computed with a 125 million parameter model improves the average performance on downstream tasks of a 3 billion parameter model by up to 2.04 and achieves up to a $1.45\times$ reduction in pretraining steps to reach commensurate baseline performance. Furthermore, we demonstrate that such perplexity-based data pruning also yields downstream performance gains in the over-trained and data-constrained regimes.
Authors: Benedikt Geiger, Peter J. Park
Abstract: Non-negative matrix factorization with the generalized Kullback-Leibler divergence (NMF) and latent Dirichlet allocation (LDA) are two popular approaches for dimensionality reduction of non-negative data. Here, we show that NMF with $\ell_1$ normalization constraints on the columns of both matrices of the decomposition and a Dirichlet prior on the columns of one matrix is equivalent to LDA. To show this, we demonstrate that explicitly accounting for the scaling ambiguity of NMF by adding $\ell_1$ normalization constraints to the optimization problem allows a joint update of both matrices in the widely used multiplicative updates (MU) algorithm. When both of the matrices are normalized, the joint MU algorithm leads to probabilistic latent semantic analysis (PLSA), which is LDA without a Dirichlet prior. Our approach of deriving joint updates for NMF also reveals that a Lasso penalty on one matrix together with an $\ell_1$ normalization constraint on the other matrix is insufficient to induce any sparsity.
Authors: Frederik Wenkel, Semih Cant\"urk, Michael Perlmutter, Guy Wolf
Abstract: Graph neural networks (GNNs) have achieved great success for a variety of tasks such as node classification, graph classification, and link prediction. However, the use of GNNs (and machine learning more generally) to solve combinatorial optimization (CO) problems is much less explored. Here, we introduce a novel GNN architecture which leverages a complex filter bank and localized attention mechanisms designed to solve CO problems on graphs. We show how our method differentiates itself from prior GNN-based CO solvers and how it can be effectively applied to the maximum clique, minimum dominating set, and maximum cut problems in a self-supervised learning setting. In addition to demonstrating competitive overall performance across all tasks, we establish state-of-the-art results for the max cut problem.
Authors: Peter Jan van Leeuwen, J. Christine Chiu, C. Kevin Yang
Abstract: A complete and statistically consistent uncertainty quantification for deep learning is provided, including the sources of uncertainty arising from (1) the new input data, (2) the training and testing data (3) the weight vectors of the neural network, and (4) the neural network because it is not a perfect predictor. Using Bayes Theorem and conditional probability densities, we demonstrate how each uncertainty source can be systematically quantified. We also introduce a fast and practical way to incorporate and combine all sources of errors for the first time. For illustration, the new method is applied to quantify errors in cloud autoconversion rates, predicted from an artificial neural network that was trained by aircraft cloud probe measurements in the Azores and the stochastic collection equation formulated as a two-moment bin model. For this specific example, the output uncertainty arising from uncertainty in the training and testing data is dominant, followed by uncertainty in the input data, in the trained neural network, and uncertainty in the weights. We discuss the usefulness of the methodology for machine learning practice, and how, through inclusion of uncertainty in the training data, the new methodology is less sensitive to input data that falls outside of the training data set.
Authors: Linjiajie Fang, Ruoxue Liu, Jing Zhang, Wenjia Wang, Bing-Yi Jing
Abstract: In offline reinforcement learning (RL), it is necessary to manage out-of-distribution actions to prevent overestimation of value functions. Policy-regularized methods address this problem by constraining the target policy to stay close to the behavior policy. Although several approaches suggest representing the behavior policy as an expressive diffusion model to boost performance, it remains unclear how to regularize the target policy given a diffusion-modeled behavior sampler. In this paper, we propose Diffusion Actor-Critic (DAC) that formulates the Kullback-Leibler (KL) constraint policy iteration as a diffusion noise regression problem, enabling direct representation of target policies as diffusion models. Our approach follows the actor-critic learning paradigm that we alternatively train a diffusion-modeled target policy and a critic network. The actor training loss includes a soft Q-guidance term from the Q-gradient. The soft Q-guidance grounds on the theoretical solution of the KL constraint policy iteration, which prevents the learned policy from taking out-of-distribution actions. For critic training, we train a Q-ensemble to stabilize the estimation of Q-gradient. Additionally, DAC employs lower confidence bound (LCB) to address the overestimation and underestimation of value targets due to function approximation error. Our approach is evaluated on the D4RL benchmarks and outperforms the state-of-the-art in almost all environments. Code is available at \href{https://github.com/Fang-Lin93/DAC}{\texttt{github.com/Fang-Lin93/DAC}}.
Authors: You Li, Guannan Zhao, Shuyu Kong, Yunqi He, Hai Zhou
Abstract: A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient method to evaluate and verify global robustness for deep neural networks, leveraging the PAC verification framework for solid guarantees on verification results. We utilize probabilistic programs to characterize meaningful input regions, setting a realistic standard for global robustness. Additionally, we introduce the cumulative robustness curve as a criterion in evaluating global robustness. We design a statistical method that combines multi-level splitting and regression analysis for the estimation, significantly reducing the execution time. Experimental results demonstrate the efficiency and effectiveness of our verification method and its capability to find rare and diversified counterexamples for adversarial training.
Authors: Haroon Miah, Dimitrios Kollias, Giacinto Luca Pedone, Drew Provan, Frederick Chen
Abstract: Primary Immune thrombocytopenia (ITP) is a rare autoimmune disease characterised by immune-mediated destruction of peripheral blood platelets in patients leading to low platelet counts and bleeding. The diagnosis and effective management of ITP is challenging because there is no established test to confirm the disease and no biomarker with which one can predict the response to treatment and outcome. In this work we conduct a feasibility study to check if machine learning can be applied effectively for diagnosis of ITP using routine blood tests and demographic data in a non-acute outpatient setting. Various ML models, including Logistic Regression, Support Vector Machine, k-Nearest Neighbor, Decision Tree and Random Forest, were applied to data from the UK Adult ITP Registry and a general hematology clinic. Two different approaches were investigated: a demographic-unaware and a demographic-aware one. We conduct extensive experiments to evaluate the predictive performance of these models and approaches, as well as their bias. The results revealed that Decision Tree and Random Forest models were both superior and fair, achieving nearly perfect predictive and fairness scores, with platelet count identified as the most significant variable. Models not provided with demographic information performed better in terms of predictive accuracy but showed lower fairness score, illustrating a trade-off between predictive performance and fairness.
Authors: Geng Sun, Wenwen Xie, Dusit Niyato, Fang Mei, Jiawen Kang, Hongyang Du, Shiwen Mao
Abstract: As a form of artificial intelligence (AI) technology based on interactive learning, deep reinforcement learning (DRL) has been widely applied across various fields and has achieved remarkable accomplishments. However, DRL faces certain limitations, including low sample efficiency and poor generalization. Therefore, we present how to leverage generative AI (GAI) to address these issues above and enhance the performance of DRL algorithms in this paper. We first introduce several classic GAI and DRL algorithms and demonstrate the applications of GAI-enhanced DRL algorithms. Then, we discuss how to use GAI to improve DRL algorithms from the data and policy perspectives. Subsequently, we introduce a framework that demonstrates an actual and novel integration of GAI with DRL, i.e., GAI-enhanced DRL. Additionally, we provide a case study of the framework on UAV-assisted integrated near-field/far-field communication to validate the performance of the proposed framework. Moreover, we present several future directions. Finally, the related code is available at: https://xiewenwen22.github.io/GAI-enhanced-DRL.
Authors: A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon
Abstract: In recent years, deep generative models have been successfully adopted for various molecular design tasks, particularly in the life and material sciences. A critical challenge for pre-trained generative molecular design (GMD) models is to fine-tune them to be better suited for downstream design tasks aimed at optimizing specific molecular properties. However, redesigning and training an existing effective generative model from scratch for each new design task is impractical. Furthermore, the black-box nature of typical downstream tasks$\unicode{x2013}$such as property prediction$\unicode{x2013}$makes it nontrivial to optimize the generative model in a task-specific manner. In this work, we propose a novel approach for a model uncertainty-guided fine-tuning of a pre-trained variational autoencoder (VAE)-based GMD model through performance feedback in an active learning setting. The main idea is to quantify model uncertainty in the generative model, which is made efficient by working within a low-dimensional active subspace of the high-dimensional VAE parameters explaining most of the variability in the model's output. The inclusion of model uncertainty expands the space of viable molecules through decoder diversity. We then explore the resulting model uncertainty class via black-box optimization made tractable by low-dimensionality of the active subspace. This enables us to identify and leverage a diverse set of high-performing models to generate enhanced molecules. Empirical results across six target molecular properties, using multiple VAE-based generative models, demonstrate that our uncertainty-guided fine-tuning approach consistently outperforms the original pre-trained models.
Authors: Zheng Wang, Zheng Wang, Zhaopeng Peng, Zihui Wang, Cheng Wang
Abstract: Federated Learning (FL) stands to gain significant advantages from collaboratively training capacity-heterogeneous models, enabling the utilization of private data and computing power from low-capacity devices. However, the focus on personalizing capacity-heterogeneous models based on client-specific data has been limited, resulting in suboptimal local model utility, particularly for low-capacity clients. The heterogeneity in both data and device capacity poses two key challenges for model personalization: 1) accurately retaining necessary knowledge embedded within reduced submodels for each client, and 2) effectively sharing knowledge through aggregating size-varying parameters. To this end, we introduce Pa3dFL, a novel framework designed to enhance local model performance by decoupling and selectively sharing knowledge among capacity-heterogeneous models. First, we decompose each layer of the model into general and personal parameters. Then, we maintain uniform sizes for the general parameters across clients and aggregate them through direct averaging. Subsequently, we employ a hyper-network to generate size-varying personal parameters for clients using learnable embeddings. Finally, we facilitate the implicit aggregation of personal parameters by aggregating client embeddings through a self-attention module. We conducted extensive experiments on three datasets to evaluate the effectiveness of Pa3dFL. Our findings indicate that Pa3dFL consistently outperforms baseline methods across various heterogeneity settings. Moreover, Pa3dFL demonstrates competitive communication and computation efficiency compared to baseline approaches, highlighting its practicality and adaptability in adverse system conditions.
Authors: Junzhi Wen, Rafal A. Angryk
Abstract: Time series data plays a crucial role across various domains, making it valuable for decision-making and predictive modeling. Machine learning (ML) and deep learning (DL) have shown promise in this regard, yet their performance hinges on data quality and quantity, often constrained by data scarcity and class imbalance, particularly for rare events like solar flares. Data augmentation techniques offer a potential solution to address these challenges, yet their effectiveness on multivariate time series datasets remains underexplored. In this study, we propose a novel data augmentation method for time series data named Mean Gaussian Noise (MGN). We investigate the performance of MGN compared to eight existing basic data augmentation methods on a multivariate time series dataset for solar flare prediction, SWAN-SF, using a ML algorithm for time series data, TimeSeriesSVC. The results demonstrate the efficacy of MGN and highlight its potential for improving classification performance in scenarios with extremely imbalanced data. Our time complexity analysis shows that MGN also has a competitive computational cost compared to the investigated alternative methods.
Authors: Amin Heyrani Nobari, Akash Srivastava, Dan Gutfreund, Kai Xu, Faez Ahmed
Abstract: In this paper, we introduce LInK, a novel framework that integrates contrastive learning of performance and design space with optimization techniques for solving complex inverse problems in engineering design with discrete and continuous variables. We focus on the path synthesis problem for planar linkage mechanisms. By leveraging a multi-modal and transformation-invariant contrastive learning framework, LInK learns a joint representation that captures complex physics and design representations of mechanisms, enabling rapid retrieval from a vast dataset of over 10 million mechanisms. This approach improves precision through the warm start of a hierarchical unconstrained nonlinear optimization algorithm, combining the robustness of traditional optimization with the speed and adaptability of modern deep learning methods. Our results on an existing benchmark demonstrate that LInK outperforms existing methods with 28 times less error compared to a state-of-the-art approach while taking 20 times less time on an existing benchmark. Moreover, we introduce a significantly more challenging benchmark, named LINK-ABC, which involves synthesizing linkages that trace the trajectories of English capital alphabets - an inverse design benchmark task that existing methods struggle with due to large non-linearities and tiny feasible space. Our results demonstrate that LInK not only advances the field of mechanism design but also broadens the applicability of contrastive learning and optimization to other areas of engineering.
Authors: Li Ji-An, Marcus K. Benna
Abstract: Backpropagation (BP), a foundational algorithm for training artificial neural networks, predominates in contemporary deep learning. Although highly successful, it is often considered biologically implausible. A significant limitation arises from the need for precise symmetry between connections in the backward and forward pathways to backpropagate gradient signals accurately, which is not observed in biological brains. Researchers have proposed several algorithms to alleviate this symmetry constraint, such as feedback alignment and direct feedback alignment. However, their divergence from backpropagation dynamics presents challenges, particularly in deeper networks and convolutional layers. Here we introduce the Product Feedback Alignment (PFA) algorithm. Our findings demonstrate that PFA closely approximates BP and achieves comparable performance in deep convolutional networks while avoiding explicit weight symmetry. Our results offer a novel solution to the longstanding weight symmetry problem, leading to more biologically plausible learning in deep convolutional networks compared to earlier methods.
Authors: Seunghwan An, Gyeongdong Woo, Jaesung Lim, ChangHyun Kim, Sungchul Hong, Jong-June Jeon
Abstract: In this paper, our goal is to generate synthetic data for heterogeneous (mixed-type) tabular datasets with high machine learning utility (MLu). Given that the MLu performance relies on accurately approximating the conditional distributions, we focus on devising a synthetic data generation method based on conditional distribution estimation. We propose a novel synthetic data generation method, MaCoDE, by redefining the multi-class classification task of Masked Language Modeling (MLM) as histogram-based non-parametric conditional density estimation. Our proposed method enables estimating conditional densities across arbitrary combinations of target and conditional variables. Furthermore, we demonstrate that our proposed method bridges the theoretical gap between distributional learning and MLM. To validate the effectiveness of our proposed model, we conduct synthetic data generation experiments on 10 real-world datasets. Given the analogy between predicting masked input tokens in MLM and missing data imputation, we also evaluate the performance of multiple imputations on incomplete datasets with various missing data mechanisms. Moreover, our proposed model offers the advantage of enabling adjustments to data privacy levels without requiring re-training.
Authors: Ke Xu, Yu Cheng, Shiqing Long, Junjie Guo, Jue Xiao, Mengfang Sun
Abstract: This paper focuses on the application and optimization of LSTM model in financial risk prediction. The study starts with an overview of the architecture and algorithm foundation of LSTM, and then details the model training process and hyperparameter tuning strategy, and adjusts network parameters through experiments to improve performance. Comparative experiments show that the optimized LSTM model shows significant advantages in AUC index compared with random forest, BP neural network and XGBoost, which verifies its efficiency and practicability in the field of financial risk prediction, especially its ability to deal with complex time series data, which lays a solid foundation for the application of the model in the actual production environment.
Authors: Jung H. Lee, Sujith Vijayan
Abstract: Deep learning (DL) enables deep neural networks (DNNs) to automatically learn complex tasks or rules from given examples without instructions or guiding principles. As we do not engineer DNNs' functions, it is extremely difficult to diagnose their decisions, and multiple lines of studies proposed to explain principles of DNNs/DL operations. Notably, one line of studies suggests that DNNs may learn concepts, the high level features recognizable to humans. Thus, we hypothesized that DNNs develop abstract codes, not necessarily recognizable to humans, which can be used to augment DNNs' decision-making. To address this hypothesis, we combined foundation segmentation models and unsupervised learning to extract internal codes and identify potential use of abstract codes to make DL's decision-making more reliable and safer.
Authors: Alyssa Shuang Sha, Bernardo Pereira Nunes, Armin Haller
Abstract: This survey investigates the multifaceted nature of forgetting in machine learning, drawing insights from neuroscientific research that posits forgetting as an adaptive function rather than a defect, enhancing the learning process and preventing overfitting. This survey focuses on the benefits of forgetting and its applications across various machine learning sub-fields that can help improve model performance and enhance data privacy. Moreover, the paper discusses current challenges, future directions, and ethical considerations regarding the integration of forgetting mechanisms into machine learning models.
Authors: Huaduo Wang, Gopal Gupta
Abstract: We present a novel and systematic method, called Superfast Selection, for selecting the "optimal split" for decision tree and feature selection algorithms over tabular data. The method speeds up split selection on a single feature by lowering the time complexity, from O(MN) (using the standard selection methods) to O(M), where M represents the number of input examples and N the number of unique values. Additionally, the need for pre-encoding, such as one-hot or integer encoding, for feature value heterogeneity is eliminated. To demonstrate the efficiency of Superfast Selection, we empower the CART algorithm by integrating Superfast Selection into it, creating what we call Ultrafast Decision Tree (UDT). This enhancement enables UDT to complete the training process with a time complexity O(KMlogM) (K is the number of features). Additionally, the Training Only Once Tuning enables UDT to avoid the repetitive training process required to find the optimal hyper-parameter. Experiments show that the UDT can finish a single training on KDD99-10% dataset (494K examples with 41 features) within 1 second and tuning with 214.8 sets of hyper-parameters within 0.25 second on a laptop.
Authors: Georg Meinhardt, Kai Yi, Laurent Condat, Peter Richt\'arik
Abstract: In the recent paradigm of Federated Learning (FL), multiple clients train a shared model while keeping their local data private. Resource constraints of clients and communication costs pose major problems for training large models in FL. On the one hand, addressing the resource limitations of the clients, sparse training has proven to be a powerful tool in the centralized setting. On the other hand, communication costs in FL can be addressed by local training, where each client takes multiple gradient steps on its local data. Recent work has shown that local training can provably achieve the optimal accelerated communication complexity [Mishchenko et al., 2022]. Hence, one would like an accelerated sparse training algorithm. In this work we show that naive integration of sparse training and acceleration at the server fails, and how to fix it by letting the clients perform these tasks appropriately. We introduce Sparse-ProxSkip, our method developed for the nonconvex setting, inspired by RandProx [Condat and Richt\'arik, 2022], which provably combines sparse training and acceleration in the convex setting. We demonstrate the good performance of Sparse-ProxSkip in extensive experiments.
Authors: Byoungwoo Park, Jungwon Choi, Sungbin Lim, Juho Lee
Abstract: Recent advancements in diffusion models and diffusion bridges primarily focus on finite-dimensional spaces, yet many real-world problems necessitate operations in infinite-dimensional function spaces for more natural and interpretable formulations. In this paper, we present a theory of stochastic optimal control (SOC) tailored to infinite-dimensional spaces, aiming to extend diffusion-based algorithms to function spaces. Specifically, we demonstrate how Doob's $h$-transform, the fundamental tool for constructing diffusion bridges, can be derived from the SOC perspective and expanded to infinite dimensions. This expansion presents a challenge, as infinite-dimensional spaces typically lack closed-form densities. Leveraging our theory, we establish that solving the optimal control problem with a specific objective function choice is equivalent to learning diffusion-based generative models. We propose two applications: (1) learning bridges between two infinite-dimensional distributions and (2) generative models for sampling from an infinite-dimensional distribution. Our approach proves effective for diverse problems involving continuous function space representations, such as resolution-free images, time-series data, and probability density functions.
Authors: Zhuonan Zheng, Sheng Zhou, Hongjia Xu, Ming Gu, Yilun Xu, Ao Li, Yuhong Li, Jingjun Gu, Jiajun Bu
Abstract: Graph Neural Networks (GNNs) have achieved remarkable success in various graph mining tasks by aggregating information from neighborhoods for representation learning. The success relies on the homophily assumption that nearby nodes exhibit similar behaviors, while it may be violated in many real-world graphs. Recently, heterophilous graph neural networks (HeterGNNs) have attracted increasing attention by modifying the neural message passing schema for heterophilous neighborhoods. However, they suffer from insufficient neighborhood partition and heterophily modeling, both of which are critical but challenging to break through. To tackle these challenges, in this paper, we propose heterophilous distribution propagation (HDP) for graph neural networks. Instead of aggregating information from all neighborhoods, HDP adaptively separates the neighbors into homophilous and heterphilous parts based on the pseudo assignments during training. The heterophilous neighborhood distribution is learned with orthogonality-oriented constraint via a trusted prototype contrastive learning paradigm. Both the homophilous and heterophilous patterns are propagated with a novel semantic-aware message passing mechanism. We conduct extensive experiments on 9 benchmark datasets with different levels of homophily. Experimental results show that our method outperforms representative baselines on heterophilous datasets.
Authors: Shiliang Zuo
Abstract: This work studies the multitasking principal-agent problem. I first show a ``uniformity'' result. Specifically, when the tasks are perfect substitutes, and the agent's cost function is homogeneous to a certain degree, then the optimal contract only depends on the marginal utility of each task and the degree of homogeneity. I then study a setting where the marginal utility of each task is unknown so that the optimal contract must be learned or estimated with observational data. I identify this problem as a regression problem with measurement errors and observe that this problem can be cast as an instrumental regression problem. The current works observe that both the contract and the repeated observations (when available) can act as valid instrumental variables, and propose using the generalized method of moments estimator to compute an approximately optimal contract from offline data. I also study an online setting and show how the optimal contract can be efficiently learned in an online fashion using the two estimators. Here the principal faces an exploration-exploitation tradeoff: she must experiment with new contracts and observe their outcome whilst at the same time ensuring her experimentations are not deviating too much from the optimal contract. This work shows when repeated observations are available and agents are sufficiently ``diverse", the principal can achieve a very low $\widetilde{O}(d)$ cumulative utility loss, even with a ``pure exploitation" algorithm.
Authors: Langzhang Liang, Sunwoo Kim, Kijung Shin, Zenglin Xu, Shirui Pan, Yuan Qi
Abstract: Graph Neural Networks (GNNs) have gained significant attention as a powerful modeling and inference method, especially for homophilic graph-structured data. To empower GNNs in heterophilic graphs, where adjacent nodes exhibit dissimilar labels or features, Signed Message Passing (SMP) has been widely adopted. However, there is a lack of theoretical and empirical analysis regarding the limitations of SMP. In this work, we unveil some potential pitfalls of SMP and their remedies. We first identify two limitations of SMP: undesirable representation update for multi-hop neighbors and vulnerability against oversmoothing issues. To overcome these challenges, we propose a novel message passing function called Multiset to Multiset GNN(M2M-GNN). Our theoretical analyses and extensive experiments demonstrate that M2M-GNN effectively alleviates the aforementioned limitations of SMP, yielding superior performance in comparison
Authors: Ao Xu, Tieru Wu
Abstract: Counterfactual explanation generation is a powerful method for Explainable Artificial Intelligence. It can help users understand why machine learning models make specific decisions, and how to change those decisions. Evaluating the robustness of counterfactual explanation algorithms is therefore crucial. Previous literature has widely studied the robustness based on the perturbation of input instances. However, the robustness defined from the perspective of perturbed instances is sometimes biased, because this definition ignores the impact of learning algorithms on robustness. In this paper, we propose a more reasonable definition, Weak Robust Compatibility, based on the perspective of explanation strength. In practice, we propose WRC-Test to help us generate more robust counterfactuals. Meanwhile, we designed experiments to verify the effectiveness of WRC-Test. Theoretically, we introduce the concepts of PAC learning theory and define the concept of PAC WRC-Approximability. Based on reasonable assumptions, we establish oracle inequalities about weak robustness, which gives a sufficient condition for PAC WRC-Approximability.
Authors: Hanseul Cho, Jaeyoung Cha, Pranjal Awasthi, Srinadh Bhojanapalli, Anupam Gupta, Chulhee Yun
Abstract: Even for simple arithmetic tasks like integer addition, it is challenging for Transformers to generalize to longer sequences than those encountered during training. To tackle this problem, we propose position coupling, a simple yet effective method that directly embeds the structure of the tasks into the positional encoding of a (decoder-only) Transformer. Taking a departure from the vanilla absolute position mechanism assigning unique position IDs to each of the tokens, we assign the same position IDs to two or more "relevant" tokens; for integer addition tasks, we regard digits of the same significance as in the same position. On the empirical side, we show that with the proposed position coupling, a small (1-layer) Transformer trained on 1 to 30-digit additions can generalize up to 200-digit additions (6.67x of the trained length). On the theoretical side, we prove that a 1-layer Transformer with coupled positions can solve the addition task involving exponentially many digits, whereas any 1-layer Transformer without positional information cannot entirely solve it. We also demonstrate that position coupling can be applied to other algorithmic tasks such as addition with multiple summands, Nx2 multiplication, copy/reverse, and a two-dimensional task.
Authors: Mengxiao Zhang, Yuheng Zhang, Haipeng Luo, Paul Mineiro
Abstract: Interactive-Grounded Learning (IGL) [Xie et al., 2021] is a powerful framework in which a learner aims at maximizing unobservable rewards through interacting with an environment and observing reward-dependent feedback on the taken actions. To deal with personalized rewards that are ubiquitous in applications such as recommendation systems, Maghakian et al. [2022] study a version of IGL with context-dependent feedback, but their algorithm does not come with theoretical guarantees. In this work, we consider the same problem and provide the first provably efficient algorithms with sublinear regret under realizability. Our analysis reveals that the step-function estimator of prior work can deviate uncontrollably due to finite-sample effects. Our solution is a novel Lipschitz reward estimator which underestimates the true reward and enjoys favorable generalization performances. Building on this estimator, we propose two algorithms, one based on explore-then-exploit and the other based on inverse-gap weighting. We apply IGL to learning from image feedback and learning from text feedback, which are reward-free settings that arise in practice. Experimental results showcase the importance of using our Lipschitz reward estimator and the overall effectiveness of our algorithms.
Authors: Mengxiao Zhang, Ramiro Deo-Campo Vuong, Haipeng Luo
Abstract: We consider the problem of online multi-agent Nash social welfare (NSW) maximization. While previous works of Hossain et al. [2021], Jones et al. [2023] study similar problems in stochastic multi-agent multi-armed bandits and show that $\sqrt{T}$-regret is possible after $T$ rounds, their fairness measure is the product of all agents' rewards, instead of their NSW (that is, their geometric mean). Given the fundamental role of NSW in the fairness literature, it is more than natural to ask whether no-regret fair learning with NSW as the objective is possible. In this work, we provide a complete answer to this question in various settings. Specifically, in stochastic $N$-agent $K$-armed bandits, we develop an algorithm with $\widetilde{\mathcal{O}}\left(K^{\frac{2}{N}}T^{\frac{N-1}{N}}\right)$ regret and prove that the dependence on $T$ is tight, making it a sharp contrast to the $\sqrt{T}$-regret bounds of Hossain et al. [2021], Jones et al. [2023]. We then consider a more challenging version of the problem with adversarial rewards. Somewhat surprisingly, despite NSW being a concave function, we prove that no algorithm can achieve sublinear regret. To circumvent such negative results, we further consider a setting with full-information feedback and design two algorithms with $\sqrt{T}$-regret: the first one has no dependence on $N$ at all and is applicable to not just NSW but a broad class of welfare functions, while the second one has better dependence on $K$ and is preferable when $N$ is small. Finally, we also show that logarithmic regret is possible whenever there exists one agent who is indifferent about different arms.
Authors: Yukai Zhang, Ao Xu, Zihao Li, Tieru Wu
Abstract: In the realm of Artificial Intelligence (AI), the importance of Explainable Artificial Intelligence (XAI) is increasingly recognized, particularly as AI models become more integral to our lives. One notable single-instance XAI approach is counterfactual explanation, which aids users in comprehending a model's decisions and offers guidance on altering these decisions. Specifically in the context of image classification models, effective image counterfactual explanations can significantly enhance user understanding. This paper introduces a novel method for computing feature importance within the feature space of a black-box model. By employing information fusion techniques, our method maximizes the use of data to address feature counterfactual explanations in the feature space. Subsequently, we utilize an image generation model to transform these feature counterfactual explanations into image counterfactual explanations. Our experiments demonstrate that the counterfactual explanations generated by our method closely resemble the original images in both pixel and feature spaces. Additionally, our method outperforms established baselines, achieving impressive experimental results.
Authors: Hengrui Zhang, Liancheng Fang, Philip S. Yu
Abstract: This paper introduces DiffPuter, an iterative method for missing data imputation that leverages the Expectation-Maximization (EM) algorithm and Diffusion Models. By treating missing data as hidden variables that can be updated during model training, we frame the missing data imputation task as an EM problem. During the M-step, DiffPuter employs a diffusion model to learn the joint distribution of both the observed and currently estimated missing data. In the E-step, DiffPuter re-estimates the missing data based on the conditional probability given the observed data, utilizing the diffusion model learned in the M-step. Starting with an initial imputation, DiffPuter alternates between the M-step and E-step until convergence. Through this iterative process, DiffPuter progressively refines the complete data distribution, yielding increasingly accurate estimations of the missing data. Our theoretical analysis demonstrates that the unconditional training and conditional sampling processes of the diffusion model align precisely with the objectives of the M-step and E-step, respectively. Empirical evaluations across 10 diverse datasets and comparisons with 16 different imputation methods highlight DiffPuter's superior performance. Notably, DiffPuter achieves an average improvement of 8.10% in MAE and 5.64% in RMSE compared to the most competitive existing method.
Authors: Sili Huang, Jifeng Hu, Hechang Chen, Lichao Sun, Bo Yang
Abstract: In-context learning is a promising approach for offline reinforcement learning (RL) to handle online tasks, which can be achieved by providing task prompts. Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem. Despite the self-improvement not requiring gradient updates, current works still suffer from high computational costs when the across-episodic sequence increases with task horizons. To this end, we propose an In-context Decision Transformer (IDT) to achieve self-improvement in a high-level trial-and-error manner. Specifically, IDT is inspired by the efficient hierarchical structure of human decision-making and thus reconstructs the sequence to consist of high-level decisions instead of low-level actions that interact with environments. As one high-level decision can guide multi-step low-level actions, IDT naturally avoids excessively long sequences and solves online tasks more efficiently. Experimental results show that IDT achieves state-of-the-art in long-horizon tasks over current in-context RL methods. In particular, the online evaluation time of our IDT is \textbf{36$\times$} times faster than baselines in the D4RL benchmark and \textbf{27$\times$} times faster in the Grid World benchmark.
Authors: Ben Finkelshtein, \.Ismail \.Ilkan Ceylan, Michael Bronstein, Ron Levie
Abstract: Message Passing Neural Networks (MPNNs) are a staple of graph machine learning. MPNNs iteratively update each node's representation in an input graph by aggregating messages from the node's neighbors, which necessitates a memory complexity of the order of the number of graph edges. This complexity might quickly become prohibitive for large graphs provided they are not very sparse. In this paper, we propose a novel approach to alleviate this problem by approximating the input graph as an intersecting community graph (ICG) -- a combination of intersecting cliques. The key insight is that the number of communities required to approximate a graph does not depend on the graph size. We develop a new constructive version of the Weak Graph Regularity Lemma to efficiently construct an approximating ICG for any input graph. We then devise an efficient graph learning algorithm operating directly on ICG in linear memory and time with respect to the number of nodes (rather than edges). This offers a new and fundamentally different pipeline for learning on very large non-sparse graphs, whose applicability is demonstrated empirically on node classification tasks and spatio-temporal data processing.
Authors: Youngjun Park, Cord Eric Schmidt, Benedikt Marcel Batton, Anne-Christin Hauschild
Abstract: In the healthcare sector, a consciousness surrounding data privacy and corresponding data protection regulations, as well as heterogeneous and non-harmonized data, pose huge challenges to large-scale data analysis. Moreover, clinical data often involves partially overlapping features, as some observations may be missing due to various reasons, such as differences in procedures, diagnostic tests, or other recorded patient history information across hospitals or institutes. To address the challenges posed by partially overlapping features and incomplete data in clinical datasets, a comprehensive approach is required. Particularly in the domain of medical data, promising outcomes are achieved by federated random forests whenever features align. However, for most standard algorithms, like random forest, it is essential that all data sets have identical parameters. Therefore, in this work the concept of federated random forest is adapted to a setting with partially overlapping features. Moreover, our research assesses the effectiveness of the newly developed federated random forest models for partially overlapping clinical data. For aggregating the federated, globally optimized model, only features available locally at each site can be used. We tackled two issues in federation: (i) the quantity of involved parties, (ii) the varying overlap of features. This evaluation was conducted across three clinical datasets. The federated random forest model even in cases where only a subset of features overlaps consistently demonstrates superior performance compared to its local counterpart. This holds true across various scenarios, including datasets with imbalanced classes. Consequently, federated random forests for partially overlapped data offer a promising solution to transcend barriers in collaborative research and corporate cooperation.
Authors: Chao Wang, Giulio Franzese, Alessandro Finamore, Massimo Gallo, Pietro Michiardi
Abstract: Diffusion models for Text-to-Image (T2I) conditional generation have seen tremendous success recently. Despite their success, accurately capturing user intentions with these models still requires a laborious trial and error process. This challenge is commonly identified as a model alignment problem, an issue that has attracted considerable attention by the research community. Instead of relying on fine-grained linguistic analyses of prompts, human annotation, or auxiliary vision-language models to steer image generation, in this work we present a novel method that relies on an information-theoretic alignment measure. In a nutshell, our method uses self-supervised fine-tuning and relies on point-wise mutual information between prompts and images to define a synthetic training set to induce model alignment. Our comparative analysis shows that our method is on-par or superior to the state-of-the-art, yet requires nothing but a pre-trained denoising network to estimate MI and a lightweight fine-tuning strategy.
Authors: Aditya Shankar, Lydia Y. Chen, J\'er\'emie Decouchant, Dimitra Gkorou, Rihan Hai
Abstract: Vertical federated learning (VFL) is a promising area for time series forecasting in industrial applications, such as predictive maintenance and machine control. Critical challenges to address in manufacturing include data privacy and over-fitting on small and noisy datasets during both training and inference. Additionally, to increase industry adaptability, such forecasting models must scale well with the number of parties while ensuring strong convergence and low-tuning complexity. We address those challenges and propose 'Secret-shared Time Series Forecasting with VFL' (STV), a novel framework that exhibits the following key features: i) a privacy-preserving algorithm for forecasting with SARIMAX and autoregressive trees on vertically partitioned data; ii) serverless forecasting using secret sharing and multi-party computation; iii) novel N-party algorithms for matrix multiplication and inverse operations for direct parameter optimization, giving strong convergence with minimal hyperparameter tuning complexity. We conduct evaluations on six representative datasets from public and industry-specific contexts. Our results demonstrate that STV's forecasting accuracy is comparable to those of centralized approaches. They also show that our direct optimization can outperform centralized methods, which include state-of-the-art diffusion models and long-short-term memory, by 23.81% on forecasting accuracy. We also conduct a scalability analysis by examining the communication costs of direct and iterative optimization to navigate the choice between the two. Code and appendix are available: https://github.com/adis98/STV
Authors: Mingze Wang, Haotian He, Jinbo Wang, Zilin Wang, Guanhua Huang, Feiyu Xiong, Zhiyu Li, Weinan E, Lei Wu
Abstract: In this work, we propose an Implicit Regularization Enhancement (IRE) framework to accelerate the discovery of flat solutions in deep learning, thereby improving generalization and convergence. Specifically, IRE decouples the dynamics of flat and sharp directions, which boosts the sharpness reduction along flat directions while maintaining the training stability in sharp directions. We show that IRE can be practically incorporated with {\em generic base optimizers} without introducing significant computational overload. Experiments show that IRE consistently improves the generalization performance for image classification tasks across a variety of benchmark datasets (CIFAR-10/100, ImageNet) and models (ResNets and ViTs). Surprisingly, IRE also achieves a $2\times$ {\em speed-up} compared to AdamW in the pre-training of Llama models (of sizes ranging from 60M to 229M) on datasets including Wikitext-103, Minipile, and Openwebtext. Moreover, we provide theoretical guarantees, showing that IRE can substantially accelerate the convergence towards flat minima in Sharpness-aware Minimization (SAM).
Authors: Tirthankar Roy, Shivendra Srivastava, Beichen Zhang
Abstract: In this study, we discuss how reinforcement learning (RL) provides an effective and efficient framework for solving sociohydrology problems. The efficacy of RL for these types of problems is evident because of its ability to update policies in an iterative manner - something that is also foundational to sociohydrology, where we are interested in representing the co-evolution of human-water interactions. We present a simple case study to demonstrate the implementation of RL in a problem of runoff reduction through management decisions related to changes in land-use land-cover (LULC). We then discuss the benefits of RL for these types of problems and share our perspectives on the future research directions in this area.
Authors: Gezheng Xu, Qi Chen, Charles Ling, Boyu Wang, Changjian Shui
Abstract: AI systems have been shown to produce unfair results for certain subgroups of population, highlighting the need to understand bias on certain sensitive attributes. Current research often falls short, primarily focusing on the subgroups characterized by a single sensitive attribute, while neglecting the nature of intersectional fairness of multiple sensitive attributes. This paper focuses on its one fundamental aspect by discovering diverse high-bias subgroups under intersectional sensitive attributes. Specifically, we propose a Bias-Guided Generative Network (BGGN). By treating each bias value as a reward, BGGN efficiently generates high-bias intersectional sensitive attributes. Experiments on real-world text and image datasets demonstrate a diverse and efficient discovery of BGGN. To further evaluate the generated unseen but possible unfair intersectional sensitive attributes, we formulate them as prompts and use modern generative AI to produce new texts and images. The results of frequently generating biased data provides new insights of discovering potential unfairness in popular modern generative AI systems. Warning: This paper contains generative examples that are offensive in nature.
Authors: Donald Kridel, Jacob Dineen, Daniel Dolk, David Castillo
Abstract: Explainable AI (XAI) has a counterpart in analytical modeling which we refer to as model explainability. We tackle the issue of model explainability in the context of prediction models. We analyze a dataset of loans from a credit card company and apply three stages: execute and compare four different prediction methods, apply the best known explainability techniques in the current literature to the model training sets to identify feature importance (FI) (static case), and finally to cross-check whether the FI set holds up under what if prediction scenarios for continuous and categorical variables (dynamic case). We found inconsistency in FI identification between the static and dynamic cases. We summarize the state of the art in model explainability and suggest further research to advance the field.
Authors: Viktor Martinek, Julia Reuter, Ophelia Frotscher, Sanaz Mostaghim, Markus Richter, Roland Herzog
Abstract: We study the addition of shape constraints and their consideration during the parameter estimation step of symbolic regression (SR). Shape constraints serve as a means to introduce prior knowledge about the shape of the otherwise unknown model function into SR. Unlike previous works that have explored shape constraints in SR, we propose minimizing shape constraint violations during parameter estimation using gradient-based numerical optimization. We test three algorithm variants to evaluate their performance in identifying three symbolic expressions from a synthetically generated data set. This paper examines two benchmark scenarios: one with varying noise levels and another with reduced amounts of training data. The results indicate that incorporating shape constraints into the expression search is particularly beneficial when data is scarce. Compared to using shape constraints only in the selection process, our approach of minimizing violations during parameter estimation shows a statistically significant benefit in some of our test cases, without being significantly worse in any instance.
Authors: Seok-Ju Hahn, Gi-Soo Kim, Junghye Lee
Abstract: In traditional federated learning, a single global model cannot perform equally well for all clients. Therefore, the need to achieve the client-level fairness in federated system has been emphasized, which can be realized by modifying the static aggregation scheme for updating the global model to an adaptive one, in response to the local signals of the participating clients. Our work reveals that existing fairness-aware aggregation strategies can be unified into an online convex optimization framework, in other words, a central server's sequential decision making process. To enhance the decision making capability, we propose simple and intuitive improvements for suboptimal designs within existing methods, presenting AAggFF. Considering practical requirements, we further subdivide our method tailored for the cross-device and the cross-silo settings, respectively. Theoretical analyses guarantee sublinear regret upper bounds for both settings: $\mathcal{O}(\sqrt{T \log{K}})$ for the cross-device setting, and $\mathcal{O}(K \log{T})$ for the cross-silo setting, with $K$ clients and $T$ federation rounds. Extensive experiments demonstrate that the federated system equipped with AAggFF achieves better degree of client-level fairness than existing methods in both practical settings. Code is available at https://github.com/vaseline555/AAggFF
Authors: Stephen Pasteris, Chris Hicks, Vasilios Mavroudis, Mark Herbster
Abstract: We consider the classic problem of online convex optimisation. Whereas the notion of static regret is relevant for stationary problems, the notion of switching regret is more appropriate for non-stationary problems. A switching regret is defined relative to any segmentation of the trial sequence, and is equal to the sum of the static regrets of each segment. In this paper we show that, perhaps surprisingly, we can achieve the asymptotically optimal switching regret on every possible segmentation simultaneously. Our algorithm for doing so is very efficient: having a space and per-trial time complexity that is logarithmic in the time-horizon. Our algorithm also obtains novel bounds on its dynamic regret: being adaptive to variations in the rate of change of the comparator sequence.
Authors: Davide Paglieri, Saurabh Dash, Tim Rockt\"aschel, Jack Parker-Holder
Abstract: Post-Training Quantization (PTQ) enhances the efficiency of Large Language Models (LLMs) by enabling faster operation and compatibility with more accessible hardware through reduced memory usage, at the cost of small performance drops. We explore the role of calibration sets in PTQ, specifically their effect on hidden activations in various notable open-source LLMs. Calibration sets are crucial for evaluating activation magnitudes and identifying outliers, which can distort the quantization range and negatively impact performance. Our analysis reveals a marked contrast in quantization effectiveness across models. The older OPT model, which much of the quantization literature is based on, shows significant performance deterioration and high susceptibility to outliers with varying calibration sets. In contrast, newer models like Llama-2 7B, Llama-3 8B, Command-R 35B, and Mistral 7B demonstrate strong robustness, with Mistral 7B showing near-immunity to outliers and stable activations. These findings suggest a shift in PTQ strategies might be needed. As advancements in pre-training methods reduce the relevance of outliers, there is an emerging need to reassess the fundamentals of current quantization literature. The emphasis should pivot towards optimizing inference speed, rather than primarily focusing on outlier preservation, to align with the evolving characteristics of state-of-the-art LLMs.
Authors: Linus Ericsson, Miguel Espinosa, Chenhongyi Yang, Antreas Antoniou, Amos Storkey, Shay B. Cohen, Steven McDonagh, Elliot J. Crowley
Abstract: Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. create a shift from convolutional structures to transformers. This is not least because the search spaces in NAS often aren't diverse enough to include such transformations a priori. Instead, for NAS to provide greater potential for fundamental design shifts, we need a novel expressive search space design which is built from more fundamental operations. To this end, we introduce einspace, a search space based on a parameterised probabilistic context-free grammar. Our space is versatile, supporting architectures of various sizes and complexities, while also containing diverse network operations which allow it to model convolutions, attention components and more. It contains many existing competitive architectures, and provides flexibility for discovering new ones. Using this search space, we perform experiments to find novel architectures as well as improvements on existing ones on the diverse Unseen NAS datasets. We show that competitive architectures can be obtained by searching from scratch, and we consistently find large improvements when initialising the search with strong baselines. We believe that this work is an important advancement towards a transformative NAS paradigm where search space expressivity and strategic search initialisation play key roles.
Authors: Shangding Gu, Laixi Shi, Yuhao Ding, Alois Knoll, Costas Spanos, Adam Wierman, Ming Jin
Abstract: Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints. However, safe RL often suffers from sample inefficiency, requiring extensive interactions with the environment to learn a safe policy. We propose Efficient Safe Policy Optimization (ESPO), a novel approach that enhances the efficiency of safe RL through sample manipulation. ESPO employs an optimization framework with three modes: maximizing rewards, minimizing costs, and balancing the trade-off between the two. By dynamically adjusting the sampling process based on the observed conflict between reward and safety gradients, ESPO theoretically guarantees convergence, optimization stability, and improved sample complexity bounds. Experiments on the Safety-MuJoCo and Omnisafe benchmarks demonstrate that ESPO significantly outperforms existing primal-based and primal-dual-based baselines in terms of reward maximization and constraint satisfaction. Moreover, ESPO achieves substantial gains in sample efficiency, requiring 25--29% fewer samples than baselines, and reduces training time by 21--38%.
Authors: Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama
Abstract: Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs a simpler approach by solving an ordinary differential equation with an initial condition from a normal distribution, thus streamlining the sample generation process. This paper discusses the convergence properties of FM in terms of the $p$-Wasserstein distance, a measure of distributional discrepancy. We establish that FM can achieve the minmax optimal convergence rate for $1 \leq p \leq 2$, presenting the first theoretical evidence that FM can reach convergence rates comparable to those of diffusion models. Our analysis extends existing frameworks by examining a broader class of mean and variance functions for the vector fields and identifies specific conditions necessary to attain these optimal rates.
Authors: Bao Nguyen, Lorenzo Sani, Xinchi Qiu, Pietro Li\`o, Nicholas D. Lane
Abstract: Graph hypernetworks (GHNs), constructed by combining graph neural networks (GNNs) with hypernetworks (HNs), leverage relational data across various domains such as neural architecture search, molecular property prediction and federated learning. Despite GNNs and HNs being individually successful, we show that GHNs present problems compromising their performance, such as over-smoothing and heterophily. Moreover, we cannot apply GHNs directly to personalized federated learning (PFL) scenarios, where a priori client relation graph may be absent, private, or inaccessible. To mitigate these limitations in the context of PFL, we propose a novel class of HNs, sheaf hypernetworks (SHNs), which combine cellular sheaf theory with HNs to improve parameter sharing for PFL. We thoroughly evaluate SHNs across diverse PFL tasks, including multi-class classification, traffic and weather forecasting. Additionally, we provide a methodology for constructing client relation graphs in scenarios where such graphs are unavailable. We show that SHNs consistently outperform existing PFL solutions in complex non-IID scenarios. While the baselines' performance fluctuates depending on the task, SHNs show improvements of up to 2.7% in accuracy and 5.3% in lower mean squared error over the best-performing baseline.
Authors: Paolo Conti, Jonas Kneifl, Andrea Manzoni, Attilio Frangi, J\"org Fehr, Steven L. Brunton, J. Nathan Kutz
Abstract: The simulation of many complex phenomena in engineering and science requires solving expensive, high-dimensional systems of partial differential equations (PDEs). To circumvent this, reduced-order models (ROMs) have been developed to speed up computations. However, when governing equations are unknown or partially known, typically ROMs lack interpretability and reliability of the predicted solutions. In this work we present a data-driven, non-intrusive framework for building ROMs where the latent variables and dynamics are identified in an interpretable manner and uncertainty is quantified. Starting from a limited amount of high-dimensional, noisy data the proposed framework constructs an efficient ROM by leveraging variational autoencoders for dimensionality reduction along with a newly introduced, variational version of sparse identification of nonlinear dynamics (SINDy), which we refer to as Variational Identification of Nonlinear Dynamics (VINDy). In detail, the method consists of Variational Encoding of Noisy Inputs (VENI) to identify the distribution of reduced coordinates. Simultaneously, we learn the distribution of the coefficients of a pre-determined set of candidate functions by VINDy. Once trained offline, the identified model can be queried for new parameter instances and new initial conditions to compute the corresponding full-time solutions. The probabilistic setup enables uncertainty quantification as the online testing consists of Variational Inference naturally providing Certainty Intervals (VICI). In this work we showcase the effectiveness of the newly proposed VINDy method in identifying interpretable and accurate dynamical system for the R\"ossler system with different noise intensities and sources. Then the performance of the overall method - named VENI, VINDy, VICI - is tested on PDE benchmarks including structural mechanics and fluid dynamics.
Authors: Metod Jazbec, Alexander Timans, Tin Had\v{z}i Veljkovi\'c, Kaspar Sakmann, Dan Zhang, Christian A. Naesseth, Eric Nalisnick
Abstract: Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural networks (EENNs) offer a promising solution: they accelerate inference by allowing intermediate layers to exit and produce a prediction early. Yet a fundamental issue with EENNs is how to determine when to exit without severely degrading performance. In other words, when is it 'safe' for an EENN to go 'fast'? To address this issue, we investigate how to adapt frameworks of risk control to EENNs. Risk control offers a distribution-free, post-hoc solution that tunes the EENN's exiting mechanism so that exits only occur when the output is of sufficient quality. We empirically validate our insights on a range of vision and language tasks, demonstrating that risk control can produce substantial computational savings, all the while preserving user-specified performance goals.
Authors: Ayon Ghosh, L. A. Prashanth, Krishna Jagannathan
Abstract: We consider the problem of estimating the Optimized Certainty Equivalent (OCE) risk from independent and identically distributed (i.i.d.) samples. For the classic sample average approximation (SAA) of OCE, we derive mean-squared error as well as concentration bounds (assuming sub-Gaussianity). Further, we analyze an efficient stochastic approximation-based OCE estimator, and derive finite sample bounds for the same. To show the applicability of our bounds, we consider a risk-aware bandit problem, with OCE as the risk. For this problem, we derive bound on the probability of mis-identification. Finally, we conduct numerical experiments to validate the theoretical findings.
Authors: Simla Burcu Harma, Ayan Chakraborty, Elizaveta Kostenok, Danila Mishin, Dongho Ha, Babak Falsafi, Martin Jaggi, Ming Liu, Yunho Oh, Suvinay Subramanian, Amir Yazdanbakhsh
Abstract: The increasing size of deep neural networks necessitates effective model compression to improve computational efficiency and reduce their memory footprint. Sparsity and quantization are two prominent compression methods that have individually demonstrated significant reduction in computational and memory footprints while preserving model accuracy. While effective, the interplay between these two methods remains an open question. In this paper, we investigate the interaction between these two methods and assess whether their combination impacts final model accuracy. We mathematically prove that applying sparsity before quantization is the optimal sequence for these operations, minimizing error in computation. Our empirical studies across a wide range of models, including OPT and Llama model families (125M-8B) and ViT corroborate these theoretical findings. In addition, through rigorous analysis, we demonstrate that sparsity and quantization are not orthogonal; their interaction can significantly harm model accuracy, with quantization error playing a dominant role in this degradation. Our findings extend to the efficient deployment of large models in resource-limited compute platforms and reduce serving cost, offering insights into best practices for applying these compression methods to maximize efficacy without compromising accuracy.
Authors: Nathan Tsoi, Deyuan Li, Taesoo Daniel Lee, Marynel V\'azquez
Abstract: Multiclass neural network classifiers are typically trained using cross-entropy loss. Following training, the performance of this same neural network is evaluated using an application-specific metric based on the multiclass confusion matrix, such as the Macro $F_\beta$-Score. It is questionable whether the use of cross-entropy will yield a classifier that aligns with the intended application-specific performance criteria, particularly in scenarios where there is a need to emphasize one aspect of classifier performance. For example, if greater precision is preferred over recall, the $\beta$ value in the $F_\beta$ evaluation metric can be adjusted accordingly, but the cross-entropy objective remains unaware of this preference during training. We propose a method that addresses this training-evaluation gap for multiclass neural network classifiers such that users can train these models informed by the desired final $F_\beta$-Score. Following prior work in binary classification, we utilize the concepts of the soft-set confusion matrices and a piecewise-linear approximation of the Heaviside step function. Our method extends the $2 \times 2$ binary soft-set confusion matrix to a multiclass $d \times d$ confusion matrix and proposes dynamic adaptation of the threshold value $\tau$, which parameterizes the piecewise-linear Heaviside approximation during run-time. We present a theoretical analysis that shows that our method can be used to optimize for a soft-set based approximation of Macro-$F_\beta$ that is a consistent estimator of Macro-$F_\beta$, and our extensive experiments show the practical effectiveness of our approach.
Authors: Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin
Abstract: Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data, $\mathbf{x}\sim p^{\rm post}(\mathbf{x})\propto p(\mathbf{x})r(\mathbf{x})$, in a model that consists of a diffusion generative model prior $p(\mathbf{x})$ and a black-box constraint or likelihood function $r(\mathbf{x})$. We state and prove the asymptotic correctness of a data-free learning objective, relative trajectory balance, for training a diffusion model that samples from this posterior, a problem that existing methods solve only approximately or in restricted cases. Relative trajectory balance arises from the generative flow network perspective on diffusion models, which allows the use of deep reinforcement learning techniques to improve mode coverage. Experiments illustrate the broad potential of unbiased inference of arbitrary posteriors under diffusion priors: in vision (classifier guidance), language (infilling under a discrete diffusion LLM), and multimodal data (text-to-image generation). Beyond generative modeling, we apply relative trajectory balance to the problem of continuous control with a score-based behavior prior, achieving state-of-the-art results on benchmarks in offline reinforcement learning.
Authors: Wen-Pu Cai, Wu-Jun Li
Abstract: Large language models~(LLMs) have recently demonstrated promising performance in many tasks. However, the high storage and computational cost of LLMs has become a challenge for deploying LLMs. Weight quantization has been widely used for model compression, which can reduce both storage and computational cost. Most existing weight quantization methods for LLMs use a rank-one codebook for quantization, which results in substantial accuracy loss when the compression ratio is high. In this paper, we propose a novel weight quantization method, called low-rank codebook based quantization~(LCQ), for LLMs. LCQ adopts a low-rank codebook, the rank of which can be larger than one, for quantization. Experiments show that LCQ can achieve better accuracy than existing methods with a negligibly extra storage cost.
Authors: Hao Hu, Yiqin Yang, Jianing Ye, Chengjie Wu, Ziqing Mai, Yujing Hu, Tangjie Lv, Changjie Fan, Qianchuan Zhao, Chongjie Zhang
Abstract: Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and further online fine-tuning is required. In this paper, we tackle the fundamental dilemma of offline-to-online fine-tuning: if the agent remains pessimistic, it may fail to learn a better policy, while if it becomes optimistic directly, performance may suffer from a sudden drop. We show that Bayesian design principles are crucial in solving such a dilemma. Instead of adopting optimistic or pessimistic policies, the agent should act in a way that matches its belief in optimal policies. Such a probability-matching agent can avoid a sudden performance drop while still being guaranteed to find the optimal policy. Based on our theoretical findings, we introduce a novel algorithm that outperforms existing methods on various benchmarks, demonstrating the efficacy of our approach. Overall, the proposed approach provides a new perspective on offline-to-online RL that has the potential to enable more effective learning from offline data.
Authors: Linlin Yu, Bowen Yang, Tianhao Wang, Kangshuo Li, Feng Chen
Abstract: The fusion of raw features from multiple sensors on an autonomous vehicle to create a Bird's Eye View (BEV) representation is crucial for planning and control systems. There is growing interest in using deep learning models for BEV semantic segmentation. Anticipating segmentation errors and improving the explainability of DNNs is essential for autonomous driving, yet it is under-studied. This paper introduces a benchmark for predictive uncertainty quantification in BEV segmentation. The benchmark assesses various approaches across three popular datasets using two representative backbones and focuses on the effectiveness of predicted uncertainty in identifying misclassified and out-of-distribution (OOD) pixels, as well as calibration. Empirical findings highlight the challenges in uncertainty quantification. Our results find that evidential deep learning based approaches show the most promise by efficiently quantifying aleatoric and epistemic uncertainty. We propose the Uncertainty-Focal-Cross-Entropy (UFCE) loss, designed for highly imbalanced data, which consistently improves the segmentation quality and calibration. Additionally, we introduce a vacuity-scaled regularization term that enhances the model's focus on high uncertainty pixels, improving epistemic uncertainty quantification.
Authors: Michail Theologitis, Georgios Frangias, Georgios Anestis, Vasilis Samoladas, Antonios Deligiannakis
Abstract: Driven by the ever-growing volume and decentralized nature of data, coupled with the escalating size of modern models, distributed deep learning (DDL) has been entrenched as the preferred paradigm for training. However, frequent synchronization of DL models, encompassing millions to many billions of parameters, creates a communication bottleneck, severely hindering scalability. Worse yet, DDL algorithms typically waste valuable bandwidth, and make themselves less practical in bandwidth-constrained federated settings, by relying on overly simplistic, periodic, and rigid synchronization schedules. To address these shortcomings, we propose Federated Dynamic Averaging (FDA), a communication-efficient DDL strategy that dynamically triggers synchronization based on the value of the model variance. Through extensive experiments across a wide range of learning tasks we demonstrate that FDA reduces communication cost by orders of magnitude, compared to both traditional and cutting-edge communication-efficient algorithms. Remarkably, FDA achieves this without sacrificing convergence speed - in stark contrast to the trade-offs encountered in the field. Additionally, we show that FDA maintains robust performance across diverse data heterogeneity settings.
Authors: Amr Alkhatib, Henrik Bostr\"om, Michalis Vazirgiannis
Abstract: Characteristic rules have been advocated for their ability to improve interpretability over discriminative rules within the area of rule learning. However, the former type of rule has not yet been used by techniques for explaining predictions. A novel explanation technique, called CEGA (Characteristic Explanatory General Association rules), is proposed, which employs association rule mining to aggregate multiple explanations generated by any standard local explanation technique into a set of characteristic rules. An empirical investigation is presented, in which CEGA is compared to two state-of-the-art methods, Anchors and GLocalX, for producing local and aggregated explanations in the form of discriminative rules. The results suggest that the proposed approach provides a better trade-off between fidelity and complexity compared to the two state-of-the-art approaches; CEGA and Anchors significantly outperform GLocalX with respect to fidelity, while CEGA and GLocalX significantly outperform Anchors with respect to the number of generated rules. The effect of changing the format of the explanations of CEGA to discriminative rules and using LIME and SHAP as local explanation techniques instead of Anchors are also investigated. The results show that the characteristic explanatory rules still compete favorably with rules in the standard discriminative format. The results also indicate that using CEGA in combination with either SHAP or Anchors consistently leads to a higher fidelity compared to using LIME as the local explanation technique.
Authors: Konstantin Hess, Dennis Frauen, Valentyn Melnychuk, Stefan Feuerriegel
Abstract: Estimating potential outcomes for treatments over time based on observational data is important for personalized decision-making in medicine. Yet, existing neural methods for this task suffer from either (a) bias or (b) large variance. In order to address both limitations, we introduce the G-transformer (GT). Our GT is a novel, neural end-to-end model designed for unbiased, low-variance estimation of conditional average potential outcomes (CAPOs) over time. Specifically, our GT is the first neural model to perform regression-based iterative G-computation for CAPOs in the time-varying setting. We evaluate the effectiveness of our GT across various experiments. In sum, this work represents a significant step towards personalized decision-making from electronic health records.
Authors: Xiaojun Jia, Tianyu Pang, Chao Du, Yihao Huang, Jindong Gu, Yang Liu, Xiaochun Cao, Min Lin
Abstract: Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. Although GCG is a significant milestone, its attacking efficiency remains unsatisfactory. In this paper, we present several improved (empirical) techniques for optimization-based jailbreaks like GCG. We first observe that the single target template of "Sure" largely limits the attacking performance of GCG; given this, we propose to apply diverse target templates containing harmful self-suggestion and/or guidance to mislead LLMs. Besides, from the optimization aspects, we propose an automatic multi-coordinate updating strategy in GCG (i.e., adaptively deciding how many tokens to replace in each step) to accelerate convergence, as well as tricks like easy-to-hard initialisation. Then, we combine these improved technologies to develop an efficient jailbreak method, dubbed $\mathcal{I}$-GCG. In our experiments, we evaluate on a series of benchmarks (such as NeurIPS 2023 Red Teaming Track). The results demonstrate that our improved techniques can help GCG outperform state-of-the-art jailbreaking attacks and achieve nearly 100% attack success rate. The code is released at https://github.com/jiaxiaojunQAQ/I-GCG.
Authors: Niloufar Zakariaei, Arman Rahmim, Eldad Haber
Abstract: Dynamic Positron Emission Tomography (dPET) imaging and Time-Activity Curve (TAC) analyses are essential for understanding and quantifying the biodistribution of radiopharmaceuticals over time and space. Traditional compartmental modeling, while foundational, commonly struggles to fully capture the complexities of biological systems, including non-linear dynamics and variability. This study introduces an innovative data-driven neural network-based framework, inspired by Reaction Diffusion systems, designed to address these limitations. Our approach, which adaptively fits TACs from dPET, enables the direct calibration of diffusion coefficients and reaction terms from observed data, offering significant improvements in predictive accuracy and robustness over traditional methods, especially in complex biological scenarios. By more accurately modeling the spatio-temporal dynamics of radiopharmaceuticals, our method advances modeling of pharmacokinetic and pharmacodynamic processes, enabling new possibilities in quantitative nuclear medicine.
Authors: Jacek Karolczak, Jerzy Stefanowski
Abstract: The need for interpreting machine learning models is addressed through prototype explanations within the context of tree ensembles. An algorithm named Adaptive Prototype Explanations of Tree Ensembles (A-PETE) is proposed to automatise the selection of prototypes for these classifiers. Its unique characteristics is using a specialised distance measure and a modified k-medoid approach. Experiments demonstrated its competitive predictive accuracy with respect to earlier explanation algorithms. It also provides a a sufficient number of prototypes for the purpose of interpreting the random forest classifier.
Authors: Kieran A. Murphy, Sam Dillavou, Dani S. Bassett
Abstract: Disentanglement is the endeavour to use machine learning to divide information about a dataset into meaningful fragments. In practice these fragments are representation (sub)spaces, often the set of channels in the latent space of a variational autoencoder (VAE). Assessments of disentanglement predominantly employ metrics that are coarse-grained at the model level, but this approach can obscure much about the process of information fragmentation. Here we propose to study the learned channels in aggregate, as the fragments of information learned by an ensemble of repeat training runs. Additionally, we depart from prior work where measures of similarity between individual subspaces neglected the nature of data embeddings as probability distributions. Instead, we view representation subspaces as communication channels that perform a soft clustering of the data; consequently, we generalize two classic information-theoretic measures of similarity between clustering assignments to compare representation spaces. We develop a lightweight method of estimation based on fingerprinting representation subspaces by their ability to distinguish dataset samples, allowing us to identify, analyze, and leverage meaningful structure in ensembles of VAEs trained on synthetic and natural datasets. Using this fully unsupervised pipeline we identify "hotspots" in the space of information fragments: groups of nearly identical representation subspaces that appear repeatedly in an ensemble of VAEs, particularly as regularization is increased. Finally, we leverage the proposed methodology to achieve ensemble learning with VAEs, boosting the information content of a set of weak learners -- a capability not possible with previous methods of assessing channel similarity.
Authors: Fengdi Che, Chenjun Xiao, Jincheng Mei, Bo Dai, Ramki Gummadi, Oscar A Ramirez, Christopher K Harris, A. Rupam Mahmood, Dale Schuurmans
Abstract: We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturally satisfied for expected updates over the entire state-action space or learning with a batch of complete trajectories from episodic Markov decision processes. Notably, using only a target network or an over-parameterized model does not provide such a convergence guarantee. Additionally, we extend our results to learning with truncated trajectories, showing that convergence is achievable for all tasks with minor modifications, akin to value truncation for the final states in trajectories. Our primary result focuses on temporal difference estimation for prediction, providing high-probability value estimation error bounds and empirical analysis on Baird's counterexample and a Four-room task. Furthermore, we explore the control setting, demonstrating that similar convergence conditions apply to Q-learning.
Authors: Qinhua Jiang, Xishun Liao, Yaofa Gong, Jiaqi Ma
Abstract: Work zone is one of the major causes of non-recurrent traffic congestion and road incidents. Despite the significance of its impact, studies on predicting the traffic impact of work zones remain scarce. In this paper, we propose a data integration pipeline that enhances the utilization of work zone and traffic data from diversified platforms, and introduce a novel deep learning model to predict the traffic speed and incident likelihood during planned work zone events. The proposed model transforms traffic patterns into 2D space-time images for both model input and output and employs an attention-based multi-context convolutional encoder-decoder architecture to capture the spatial-temporal dependencies between work zone events and traffic variations. Trained and validated on four years of archived work zone traffic data from Maryland, USA, the model demonstrates superior performance over baseline models in predicting traffic speed, incident likelihood, and inferred traffic attributes such as queue length and congestion timings (i.e., start time and duration). Specifically, the proposed model outperforms the baseline models by reducing the prediction error of traffic speed by 5% to 34%, queue length by 11% to 29%, congestion timing by 6% to 17%, and increasing the accuracy of incident predictions by 5% to 7%. Consequently, this model offers substantial promise for enhancing the planning and traffic management of work zones.
Authors: Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Awadallah, Alexander Rakhlin
Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a central tool for language model alignment. We consider online exploration in RLHF, which exploits interactive access to human or AI feedback by deliberately encouraging the model to produce diverse, maximally informative responses. By allowing RLHF to confidently stray from the pre-trained model, online exploration offers the possibility of novel, potentially super-human capabilities, but its full potential as a paradigm for language model training has yet to be realized, owing to computational and statistical bottlenecks in directly adapting existing reinforcement learning techniques. We propose a new algorithm for online exploration in RLHF, Exploratory Preference Optimization (XPO), which is simple and practical -- a one-line change to (online) Direct Preference Optimization (DPO; Rafailov et al., 2023) -- yet enjoys the strongest known provable guarantees and promising empirical performance. XPO augments the DPO objective with a novel and principled exploration bonus, empowering the algorithm to explore outside the support of the initial model and human feedback data. In theory, we show that XPO is provably sample-efficient and converges to a near-optimal language model policy under natural exploration conditions, irrespective of whether the initial model has good coverage. Our analysis, which builds on the observation that DPO implicitly performs a form of $Q^{\star}$-approximation (or, Bellman error minimization), combines previously disparate techniques from language modeling and theoretical reinforcement learning in a serendipitous fashion through the perspective of KL-regularized Markov decision processes. Empirically, we find that XPO is more sample-efficient than non-exploratory DPO variants in a preliminary evaluation.
Authors: Tri Dao, Albert Gu
Abstract: While Transformers have been the main architecture behind deep learning's success in language modeling, state-space models (SSMs) such as Mamba have recently been shown to match or outperform Transformers at small to medium scale. We show that these families of models are actually quite closely related, and develop a rich framework of theoretical connections between SSMs and variants of attention, connected through various decompositions of a well-studied class of structured semiseparable matrices. Our state space duality (SSD) framework allows us to design a new architecture (Mamba-2) whose core layer is an a refinement of Mamba's selective SSM that is 2-8X faster, while continuing to be competitive with Transformers on language modeling.
Authors: Jianqing Liang, Min Chen, Jiye Liang
Abstract: The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or positional and structural encodings. Despite making some progress, existing works tend to overlook external information of graphs, specifically the correlation between graphs. Intuitively, graphs with similar structures should have similar representations. Therefore, we propose Graph External Attention (GEA) -- a novel attention mechanism that leverages multiple external node/edge key-value units to capture inter-graph correlations implicitly. On this basis, we design an effective architecture called Graph External Attention Enhanced Transformer (GEAET), which integrates local structure and global interaction information for more comprehensive graph representations. Extensive experiments on benchmark datasets demonstrate that GEAET achieves state-of-the-art empirical performance. The source code is available for reproducibility at: https://github.com/icm1018/GEAET.
Authors: Zhouxing Shi, Qirui Jin, Zico Kolter, Suman Jana, Cho-Jui Hsieh, Huan Zhang
Abstract: Branch-and-bound (BaB) is among the most effective methods for neural network (NN) verification. However, existing works on BaB have mostly focused on NNs with piecewise linear activations, especially ReLU networks. In this paper, we develop a general framework, named GenBaB, to conduct BaB for general nonlinearities in general computational graphs based on linear bound propagation. To decide which neuron to branch, we design a new branching heuristic which leverages linear bounds as shortcuts to efficiently estimate the potential improvement after branching. To decide nontrivial branching points for general nonlinear functions, we propose to optimize branching points offline, which can be efficiently leveraged during verification with a lookup table. We demonstrate the effectiveness of our GenBaB on verifying a wide range of NNs, including networks with activation functions such as Sigmoid, Tanh, Sine and GeLU, as well as networks involving multi-dimensional nonlinear operations such as multiplications in LSTMs and Vision Transformers. Our framework also allows the verification of general nonlinear computation graphs and enables verification applications beyond simple neural networks, particularly for AC Optimal Power Flow (ACOPF). GenBaB is part of the latest $\alpha,\!\beta$-CROWN, the winner of the 4th International Verification of Neural Networks Competition (VNN-COMP 2023).
Authors: Nicolas Zucchet, Antonio Orvieto
Abstract: Recurrent neural networks (RNNs) notoriously struggle to learn long-term memories, primarily due to vanishing and exploding gradients. The recent success of state-space models (SSMs), a subclass of RNNs, to overcome such difficulties challenges our theoretical understanding. In this paper, we delve into the optimization challenges of RNNs and discover that, as the memory of a network increases, changes in its parameters result in increasingly large output variations, making gradient-based learning highly sensitive, even without exploding gradients. Our analysis further reveals the importance of the element-wise recurrence design pattern combined with careful parametrizations in mitigating this effect. This feature is present in SSMs, as well as in other architectures, such as LSTMs. Overall, our insights provide a new explanation for some of the difficulties in gradient-based learning of RNNs and why some architectures perform better than others.
Authors: Beibin Li, Yi Zhang, S\'ebastien Bubeck, Jeevan Pathuri, Ishai Menache
Abstract: We study the efficacy of Small Language Models (SLMs) in facilitating application usage through natural language interactions. Our focus here is on a particular internal application used in Microsoft for cloud supply chain fulfilment. Our experiments show that small models can outperform much larger ones in terms of both accuracy and running time, even when fine-tuned on small datasets. Alongside these results, we also highlight SLM-based system design considerations.
Authors: Shengchao Chen, Guodong Long, Jing Jiang, Chengqi Zhang
Abstract: This paper demonstrates that pre-trained language models (PLMs) are strong foundation models for on-device meteorological variables modeling. We present LM-Weather, a generic approach to taming PLMs, that have learned massive sequential knowledge from the universe of natural language databases, to acquire an immediate capability to obtain highly customized models for heterogeneous meteorological data on devices while keeping high efficiency. Concretely, we introduce a lightweight personalized adapter into PLMs and endows it with weather pattern awareness. During communication between clients and the server, low-rank-based transmission is performed to effectively fuse the global knowledge among devices while maintaining high communication efficiency and ensuring privacy. Experiments on real-wold dataset show that LM-Weather outperforms the state-of-the-art results by a large margin across various tasks (e.g., forecasting and imputation at different scales). We provide extensive and in-depth analyses experiments, which verify that LM-Weather can (1) indeed leverage sequential knowledge from natural language to accurately handle meteorological sequence, (2) allows each devices obtain highly customized models under significant heterogeneity, and (3) generalize under data-limited and out-of-distribution (OOD) scenarios.
Authors: John Hawkins, David Tivey
Abstract: Identifying critical research within the growing body of academic work is an essential element of quality research. Systematic review processes, used in evidence-based medicine, formalise this as a procedure that must be followed in a research program. However, it comes with an increasing burden in terms of the time required to identify the important articles of research for a given topic. In this work, we develop a method for building a general-purpose filtering system that matches a research question, posed as a natural language description of the required content, against a candidate set of articles obtained via the application of broad search terms. Our results demonstrate that transformer models, pre-trained on biomedical literature then fine tuned for the specific task, offer a promising solution to this problem. The model can remove large volumes of irrelevant articles for most research questions.
Authors: Yujia Liu, Tong Bu, Jianhao Ding, Zecheng Hao, Tiejun Huang, Zhaofei Yu
Abstract: Spiking Neural Networks (SNNs) have attracted great attention for their energy-efficient operations and biologically inspired structures, offering potential advantages over Artificial Neural Networks (ANNs) in terms of energy efficiency and interpretability. Nonetheless, similar to ANNs, the robustness of SNNs remains a challenge, especially when facing adversarial attacks. Existing techniques, whether adapted from ANNs or specifically designed for SNNs, exhibit limitations in training SNNs or defending against strong attacks. In this paper, we propose a novel approach to enhance the robustness of SNNs through gradient sparsity regularization. We observe that SNNs exhibit greater resilience to random perturbations compared to adversarial perturbations, even at larger scales. Motivated by this, we aim to narrow the gap between SNNs under adversarial and random perturbations, thereby improving their overall robustness. To achieve this, we theoretically prove that this performance gap is upper bounded by the gradient sparsity of the probability associated with the true label concerning the input image, laying the groundwork for a practical strategy to train robust SNNs by regularizing the gradient sparsity. We validate the effectiveness of our approach through extensive experiments on both image-based and event-based datasets. The results demonstrate notable improvements in the robustness of SNNs. Our work highlights the importance of gradient sparsity in SNNs and its role in enhancing robustness.
Authors: Mohamed Hibat-Allah, Ejaaz Merali, Giacomo Torlai, Roger G Melko, Juan Carrasquilla
Abstract: Rydberg atom array experiments have demonstrated the ability to act as powerful quantum simulators, preparing strongly-correlated phases of matter which are challenging to study for conventional computer simulations. A key direction has been the implementation of interactions on frustrated geometries, in an effort to prepare exotic many-body states such as spin liquids and glasses. In this paper, we apply two-dimensional recurrent neural network (RNN) wave functions to study the ground states of Rydberg atom arrays on the kagome lattice. We implement an annealing scheme to find the RNN variational parameters in regions of the phase diagram where exotic phases may occur, corresponding to rough optimization landscapes. For Rydberg atom array Hamiltonians studied previously on the kagome lattice, our RNN ground states show no evidence of exotic spin liquid or emergent glassy behavior. In the latter case, we argue that the presence of a non-zero Edwards-Anderson order parameter is an artifact of the long autocorrelations times experienced with quantum Monte Carlo simulations. This result emphasizes the utility of autoregressive models, such as RNNs, to explore Rydberg atom array physics on frustrated lattices and beyond.
Authors: Jiaxing Qiu, Douglas E. Lake, Teague R. Henry
Abstract: This paper introduced a clustered estimator of the Network Information Criterion (NICc) to approximate leave-one-cluster-out cross-validated deviance, which can be used as an alternative to cluster-based cross-validation when modeling clustered data. Stone proved that Akaike Information Criterion (AIC) is an asymptotic equivalence to leave-one-observation-out cross-validation if the parametric model is true. Ripley pointed out that the Network Information Criterion (NIC) derived in Stone's proof, is a better approximation to leave-one-observation-out cross-validation when the model is not true. For clustered data, we derived a clustered estimator of NIC, referred to as NICc, by substituting the Fisher information matrix in NIC with its estimator that adjusts for clustering. This adjustment imposes a larger penalty in NICc than the unclustered estimator of NIC when modeling clustered data, thereby preventing overfitting more effectively. In a simulation study and an empirical example, we used linear and logistic regression to model clustered data with Gaussian or binomial response, respectively. We showed that NICc is a better approximation to leave-one-cluster-out deviance and prevents overfitting more effectively than AIC and Bayesian Information Criterion (BIC). NICc leads to more accurate model selection, as determined by cluster-based cross-validation, compared to AIC and BIC.
Authors: Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin
Abstract: Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. However, the contribution of the input prompt to the generated content still remains obscure to humans, underscoring the necessity of elucidating and explaining the causality between input and output pairs. Existing works for providing prompt-specific explanation often confine model output to be classification or next-word prediction. Few initial attempts aiming to explain the entire language generation often treat input prompt texts independently, ignoring their combinatorial effects on the follow-up generation. In this study, we introduce a counterfactual explanation framework based on joint prompt attribution, XPrompt, which aims to explain how a few prompt texts collaboratively influences the LLM's complete generation. Particularly, we formulate the task of prompt attribution for generation interpretation as a combinatorial optimization problem, and introduce a probabilistic algorithm to search for the casual input combination in the discrete space. We define and utilize multiple metrics to evaluate the produced explanations, demonstrating both faithfulness and efficiency of our framework.
Authors: Sushant Agarwal, Gautam Kamath, Mahbod Majid, Argyris Mouzakis, Rose Silver, Jonathan Ullman
Abstract: We study differentially private (DP) mean estimation in the case where each person holds multiple samples. Commonly referred to as the "user-level" setting, DP here requires the usual notion of distributional stability when all of a person's datapoints can be modified. Informally, if $n$ people each have $m$ samples from an unknown $d$-dimensional distribution with bounded $k$-th moments, we show that \[n = \tilde \Theta\left(\frac{d}{\alpha^2 m} + \frac{d }{ \alpha m^{1/2} \varepsilon} + \frac{d}{\alpha^{k/(k-1)} m \varepsilon} + \frac{d}{\varepsilon}\right)\] people are necessary and sufficient to estimate the mean up to distance $\alpha$ in $\ell_2$-norm under $\varepsilon$-differential privacy (and its common relaxations). In the multivariate setting, we give computationally efficient algorithms under approximate DP (with slightly degraded sample complexity) and computationally inefficient algorithms under pure DP, and our nearly matching lower bounds hold for the most permissive case of approximate DP. Our computationally efficient estimators are based on the well known noisy-clipped-mean approach, but the analysis for our setting requires new bounds on the tails of sums of independent, vector-valued, bounded-moments random variables, and a new argument for bounding the bias introduced by clipping.
Authors: Thorsten Buss, Frank Gaede, Gregor Kasieczka, Claudius Krause, David Shih
Abstract: In the quest to build generative surrogate models as computationally efficient alternatives to rule-based simulations, the quality of the generated samples remains a crucial frontier. So far, normalizing flows have been among the models with the best fidelity. However, as the latent space in such models is required to have the same dimensionality as the data space, scaling up normalizing flows to high dimensional datasets is not straightforward. The prior L2LFlows approach successfully used a series of separate normalizing flows and sequence of conditioning steps to circumvent this problem. In this work, we extend L2LFlows to simulate showers with a 9-times larger profile in the lateral direction. To achieve this, we introduce convolutional layers and U-Net-type connections, move from masked autoregressive flows to coupling layers, and demonstrate the successful modelling of showers in the ILD Electromagnetic Calorimeter as well as Dataset 3 from the public CaloChallenge dataset.
Authors: Bastien Arcelin, Nicolas Chaverou
Abstract: Creating realistic or stylized facial and lip sync animation is a tedious task. It requires lot of time and skills to sync the lips with audio and convey the right emotion to the character's face. To allow animators to spend more time on the artistic and creative part of the animation, we present Audio2Rig: a new deep learning based tool leveraging previously animated sequences of a show, to generate facial and lip sync rig animation from an audio file. Based in Maya, it learns from any production rig without any adjustment and generates high quality and stylized animations which mimic the style of the show. Audio2Rig fits in the animator workflow: since it generates keys on the rig controllers, the animation can be easily retaken. The method is based on 3 neural network modules which can learn an arbitrary number of controllers. Hence, different configurations can be created for specific parts of the face (such as the tongue, lips or eyes). With Audio2Rig, animators can also pick different emotions and adjust their intensities to experiment or customize the output, and have high level controls on the keyframes setting. Our method shows excellent results, generating fine animation details while respecting the show style. Finally, as the training relies on the studio data and is done internally, it ensures data privacy and prevents from copyright infringement.
Authors: Haibo Jin, Andy Zhou, Joe D. Menke, Haohan Wang
Abstract: Large Language Models (LLMs) are typically harmless but remain vulnerable to carefully crafted prompts known as ``jailbreaks'', which can bypass protective measures and induce harmful behavior. Recent advancements in LLMs have incorporated moderation guardrails that can filter outputs, which trigger processing errors for certain malicious questions. Existing red-teaming benchmarks often neglect to include questions that trigger moderation guardrails, making it difficult to evaluate jailbreak effectiveness. To address this issue, we introduce JAMBench, a harmful behavior benchmark designed to trigger and evaluate moderation guardrails. JAMBench involves 160 manually crafted instructions covering four major risk categories at multiple severity levels. Furthermore, we propose a jailbreak method, JAM (Jailbreak Against Moderation), designed to attack moderation guardrails using jailbreak prefixes to bypass input-level filters and a fine-tuned shadow model functionally equivalent to the guardrail model to generate cipher characters to bypass output-level filters. Our extensive experiments on four LLMs demonstrate that JAM achieves higher jailbreak success ($\sim$ $\times$ 19.88) and lower filtered-out rates ($\sim$ $\times$ 1/6) than baselines.
Authors: Maya Anderson, Guy Amit, Abigail Goldsteen
Abstract: Retrieval Augmented Generation (RAG) systems have shown great promise in natural language processing. However, their reliance on data stored in a retrieval database, which may contain proprietary or sensitive information, introduces new privacy concerns. Specifically, an attacker may be able to infer whether a certain text passage appears in the retrieval database by observing the outputs of the RAG system, an attack known as a Membership Inference Attack (MIA). Despite the significance of this threat, MIAs against RAG systems have yet remained under-explored. This study addresses this gap by introducing an efficient and easy-to-use method for conducting MIA against RAG systems. We demonstrate the effectiveness of our attack using two benchmark datasets and multiple generative models, showing that the membership of a document in the retrieval database can be efficiently determined through the creation of an appropriate prompt in both black-box and gray-box settings. Our findings highlight the importance of implementing security countermeasures in deployed RAG systems to protect the privacy and security of retrieval databases.
Authors: Seamus Somerstep, Ya'acov Ritov, Yuekai Sun
Abstract: In many prediction problems, the predictive model affects the distribution of the prediction target. This phenomenon is known as performativity and is often caused by the behavior of individuals with vested interests in the outcome of the predictive model. Although performativity is generally problematic because it manifests as distribution shifts, we develop algorithmic fairness practices that leverage performativity to achieve stronger group fairness guarantees in social classification problems (compared to what is achievable in non-performative settings). In particular, we leverage the policymaker's ability to steer the population to remedy inequities in the long term. A crucial benefit of this approach is that it is possible to resolve the incompatibilities between conflicting group fairness definitions.
Authors: Zhiyi Li, Yunbei Xu, Ruohan Zhan
Abstract: The Robust Satisficing (RS) model is an emerging approach to robust optimization, offering streamlined procedures and robust generalization across various applications. However, the statistical theory of RS remains unexplored in the literature. This paper fills in the gap by comprehensively analyzing the theoretical properties of the RS model. Notably, the RS structure offers a more straightforward path to deriving statistical guarantees compared to the seminal Distributionally Robust Optimization (DRO), resulting in a richer set of results. In particular, we establish two-sided confidence intervals for the optimal loss without the need to solve a minimax optimization problem explicitly. We further provide finite-sample generalization error bounds for the RS optimizer. Importantly, our results extend to scenarios involving distribution shifts, where discrepancies exist between the sampling and target distributions. Our numerical experiments show that the RS model consistently outperforms the baseline empirical risk minimization in small-sample regimes and under distribution shifts. Furthermore, compared to the DRO model, the RS model exhibits lower sensitivity to hyperparameter tuning, highlighting its practicability for robustness considerations.
Authors: Serdar Yildiz, Ahmet Nezih Kasim
Abstract: The growing importance of person reidentification in computer vision has highlighted the need for more extensive and diverse datasets. In response, we introduce the ENTIRe-ID dataset, an extensive collection comprising over 4.45 million images from 37 different cameras in varied environments. This dataset is uniquely designed to tackle the challenges of domain variability and model generalization, areas where existing datasets for person re-identification have fallen short. The ENTIRe-ID dataset stands out for its coverage of a wide array of real-world scenarios, encompassing various lighting conditions, angles of view, and diverse human activities. This design ensures a realistic and robust training platform for ReID models. The ENTIRe-ID dataset is publicly available at https://serdaryildiz.github.io/ENTIRe-ID
Authors: Mathieu Ciancone, Imene Kerboua, Marion Schaeffer, Wissam Siblini
Abstract: In recent years, numerous embedding models have been made available and widely used for various NLP tasks. Choosing a model that performs well for several tasks in English has been largely simplified by the Massive Text Embedding Benchmark (MTEB), but extensions to other languages remain challenging. This is why we expand MTEB to propose the first massive benchmark of sentence embeddings for French. Not only we gather 22 existing datasets in an easy-to-use interface, but we also create three new French datasets for a global evaluation over 8 different tasks. We perform a large scale comparison with 46 carefully selected embedding models, conduct comprehensive statistical tests, and analyze the correlation between model performance and many of their characteristics. We find out that even if no model is the best on all tasks, large multilingual models pre-trained on sentence similarity perform particularly well. Our work comes with open-source code, new datasets and a public leaderboard.
Authors: Harsh Chaudhari, Giorgio Severi, John Abascal, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea
Abstract: Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs) in chatbot applications, enabling developers to adapt and personalize the LLM output without expensive training or fine-tuning. RAG systems use an external knowledge database to retrieve the most relevant documents for a given query, providing this context to the LLM generator. While RAG achieves impressive utility in many applications, its adoption to enable personalized generative models introduces new security risks. In this work, we propose new attack surfaces for an adversary to compromise a victim's RAG system, by injecting a single malicious document in its knowledge database. We design Phantom, general two-step attack framework against RAG augmented LLMs. The first step involves crafting a poisoned document designed to be retrieved by the RAG system within the top-k results only when an adversarial trigger, a specific sequence of words acting as backdoor, is present in the victim's queries. In the second step, a specially crafted adversarial string within the poisoned document triggers various adversarial attacks in the LLM generator, including denial of service, reputation damage, privacy violations, and harmful behaviors. We demonstrate our attacks on multiple LLM architectures, including Gemma, Vicuna, and Llama.
Authors: Hao Chen, Yujin Han, Diganta Misra, Xiang Li, Kai Hu, Difan Zou, Masashi Sugiyama, Jindong Wang, Bhiksha Raj
Abstract: Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with paired data and conditions, such as image-text and image-class pairs. Despite rigorous filtering, these pre-training datasets often inevitably contain corrupted pairs where conditions do not accurately describe the data. This paper presents the first comprehensive study on the impact of such corruption in pre-training data of DMs. We synthetically corrupt ImageNet-1K and CC3M to pre-train and evaluate over 50 conditional DMs. Our empirical findings reveal that various types of slight corruption in pre-training can significantly enhance the quality, diversity, and fidelity of the generated images across different DMs, both during pre-training and downstream adaptation stages. Theoretically, we consider a Gaussian mixture model and prove that slight corruption in the condition leads to higher entropy and a reduced 2-Wasserstein distance to the ground truth of the data distribution generated by the corruptly trained DMs. Inspired by our analysis, we propose a simple method to improve the training of DMs on practical datasets by adding condition embedding perturbations (CEP). CEP significantly improves the performance of various DMs in both pre-training and downstream tasks. We hope that our study provides new insights into understanding the data and pre-training processes of DMs.
Authors: Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin, Dinesh Manocha, Mengdi Wang, Amrit Singh Bedi, Furong Huang
Abstract: Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billions of model parameters. A promising alternative, alignment via decoding, adjusts the response distribution directly without model updates to maximize a target reward $r$, thus providing a lightweight and adaptable framework for alignment. However, principled decoding methods rely on oracle access to an optimal Q-function ($Q^*$), which is often unavailable in practice. Hence, prior SoTA methods either approximate this $Q^*$ using $Q^{\pi_{\texttt{sft}}}$ (derived from the reference $\texttt{SFT}$ model) or rely on short-term rewards, resulting in sub-optimal decoding performance. In this work, we propose Transfer $Q^*$, which implicitly estimates the optimal value function for a target reward $r$ through a baseline model $\rho_{\texttt{BL}}$ aligned with a baseline reward $\rho_{\texttt{BL}}$ (which can be different from the target reward $r$). Theoretical analyses of Transfer $Q^*$ provide a rigorous characterization of its optimality, deriving an upper bound on the sub-optimality gap and identifying a hyperparameter to control the deviation from the pre-trained reference $\texttt{SFT}$ model based on user needs. Our approach significantly reduces the sub-optimality gap observed in prior SoTA methods and demonstrates superior empirical performance across key metrics such as coherence, diversity, and quality in extensive tests on several synthetic and real datasets.
Authors: Haoyan Zhai, Qianli Hu, Jiangning Chen
Abstract: Optimization problems characterized by both discrete and continuous variables are common across various disciplines, presenting unique challenges due to their complex solution landscapes and the difficulty of navigating mixed-variable spaces effectively. To Address these challenges, we introduce a hybrid Reinforcement Learning (RL) framework that synergizes RL for discrete variable selection with Bayesian Optimization for continuous variable adjustment. This framework stands out by its strategic integration of RL and continuous optimization techniques, enabling it to dynamically adapt to the problem's mixed-variable nature. By employing RL for exploring discrete decision spaces and Bayesian Optimization to refine continuous parameters, our approach not only demonstrates flexibility but also enhances optimization performance. Our experiments on synthetic functions and real-world machine learning hyperparameter tuning tasks reveal that our method consistently outperforms traditional RL, random search, and standalone Bayesian optimization in terms of effectiveness and efficiency.
Authors: Shivendra Agrawal, Suresh Nayak, Ashutosh Naik, Bradley Hayes
Abstract: The ability to shop independently, especially in grocery stores, is important for maintaining a high quality of life. This can be particularly challenging for people with visual impairments (PVI). Stores carry thousands of products, with approximately 30,000 new products introduced each year in the US market alone, presenting a challenge even for modern computer vision solutions. Through this work, we present a proof-of-concept socially assistive robotic system we call ShelfHelp, and propose novel technical solutions for enhancing instrumented canes traditionally meant for navigation tasks with additional capability within the domain of shopping. ShelfHelp includes a novel visual product locator algorithm designed for use in grocery stores and a novel planner that autonomously issues verbal manipulation guidance commands to guide the user during product retrieval. Through a human subjects study, we show the system's success in locating and providing effective manipulation guidance to retrieve desired products with novice users. We compare two autonomous verbal guidance modes achieving comparable performance to a human assistance baseline and present encouraging findings that validate our system's efficiency and effectiveness and through positive subjective metrics including competence, intelligence, and ease of use.
Authors: Edouard Yvinec, Gabriel Kasser
Abstract: The wide acceptance of large language models (LLMs) has unlocked new applications and social risks. Popular countermeasures aim at detecting misinformation, usually involve domain specific models trained to recognize the relevance of any information. Instead of evaluating the validity of the information, we propose to investigate LLM generated text from the perspective of trust. In this study, we define trust as the ability to know if an input text was generated by a LLM or a human. To do so, we design SPOT, an efficient method, that classifies the source of any, standalone, text input based on originality score. This score is derived from the prediction of a given LLM to detect other LLMs. We empirically demonstrate the robustness of the method to the architecture, training data, evaluation data, task and compression of modern LLMs.
Authors: Aquia Richburg, Marine Carpuat
Abstract: A new paradigm for machine translation has recently emerged: fine-tuning large language models (LLM) on parallel text has been shown to outperform dedicated translation systems trained in a supervised fashion on much larger amounts of parallel data (Xu et al., 2024a; Alves et al., 2024). However, it remains unclear whether this paradigm can enable massively multilingual machine translation or whether it requires fine-tuning dedicated models for a small number of language pairs. How does translation fine-tuning impact the MT capabilities of LLMs for zero-shot languages, zero-shot language pairs, and translation tasks that do not involve English? To address these questions, we conduct an extensive empirical evaluation of the translation quality of the TOWER family of language models (Alves et al., 2024) on 132 translation tasks from the multi-parallel FLORES-200 data. We find that translation fine-tuning improves translation quality even for zero-shot languages on average, but that the impact is uneven depending on the language pairs involved. These results call for further research to effectively enable massively multilingual translation with LLMs.
Authors: Dorin Pomian, Abhiram Bellur, Malinda Dilhara, Zarina Kurbatova, Egor Bogomolov, Andrey Sokolov, Timofey Bryksin, Danny Dig
Abstract: Excessively long methods, loaded with multiple responsibilities, are challenging to understand, debug, reuse, and maintain. The solution lies in the widely recognized Extract Method refactoring. While the application of this refactoring is supported in modern IDEs, recommending which code fragments to extract has been the topic of many research tools. However, they often struggle to replicate real-world developer practices, resulting in recommendations that do not align with what a human developer would do in real life. To address this issue, we introduce EM-Assist, an IntelliJ IDEA plugin that uses LLMs to generate refactoring suggestions and subsequently validates, enhances, and ranks them. Finally, EM-Assist uses the IntelliJ IDE to apply the user-selected recommendation. In our extensive evaluation of 1,752 real-world refactorings that actually took place in open-source projects, EM-Assist's recall rate was 53.4% among its top-5 recommendations, compared to 39.4% for the previous best-in-class tool that relies solely on static analysis. Moreover, we conducted a usability survey with 18 industrial developers and 94.4% gave a positive rating.
Authors: Mingyang Jiang, Yueyuan Li, Songan Zhang, Chunxiang Wang, Ming Yang
Abstract: Path planning plays a pivotal role in automated parking, yet current methods struggle to efficiently handle the intricate and diverse parking scenarios. One potential solution is the reinforcement learning-based method, leveraging its exploration in unrecorded situations. However, a key challenge lies in training reinforcement learning methods is the inherent randomness in converging to a feasible policy. This paper introduces a novel solution, the Hybrid POlicy Path plannEr (HOPE), which integrates a reinforcement learning agent with Reeds-Shepp curves, enabling effective planning across diverse scenarios. The paper presents a method to calculate and implement an action mask mechanism in path planning, significantly boosting the efficiency and effectiveness of reinforcement learning training. A transformer is employed as the network structure to fuse environmental information and generate planned paths. To facilitate the training and evaluation of the proposed planner, we propose a criterion for categorizing the difficulty level of parking scenarios based on space and obstacle distribution. Experimental results demonstrate that our approach outperforms typical rule-based algorithms and traditional reinforcement learning methods, showcasing higher planning success rates and generalization across various scenarios. The code for our solution will be openly available on \href{GitHub}{https://github.com/jiamiya/HOPE}. % after the paper's acceptance.
Authors: Alissa A. Valentine, Lauren A. Lepow, Alexander W. Charney, Isotta Landi
Abstract: In psychiatry, negative patient descriptions and stigmatizing language can contribute to healthcare disparities in two ways: (1) read by patients they can harm their trust and engagement with the medical center; (2) read by future providers they may negatively influence the future perspective of a patient. By leveraging large language models, this work aims to identify the sentiment expressed in psychiatric clinical notes based on the reader's point of view. Extracting sentences from the Mount Sinai Health System's large and diverse clinical notes, we used prompts and in-context learning to adapt three large language models (GPT-3.5, Llama 2, Mistral) to classify the sentiment conveyed by the sentences according to the provider or non-provider point of view. Results showed that GPT-3.5 aligns best to provider point of view, whereas Mistral aligns best to non-provider point of view.
Authors: Daniel Messenger, Greg Dwyer, Vanja Dukic
Abstract: Species subject to predation and environmental threats commonly exhibit variable periods of population boom and bust over long timescales. Understanding and predicting such behavior, especially given the inherent heterogeneity and stochasticity of exogenous driving factors over short timescales, is an ongoing challenge. A modeling paradigm gaining popularity in the ecological sciences for such multi-scale effects is to couple short-term continuous dynamics to long-term discrete updates. We develop a data-driven method utilizing weak-form equation learning to extract such hybrid governing equations for population dynamics and to estimate the requisite parameters using sparse intermittent measurements of the discrete and continuous variables. The method produces a set of short-term continuous dynamical system equations parametrized by long-term variables, and long-term discrete equations parametrized by short-term variables, allowing direct assessment of interdependencies between the two time scales. We demonstrate the utility of the method on a variety of ecological scenarios and provide extensive tests using models previously derived for epizootics experienced by the North American spongy moth (Lymantria dispar dispar).
Authors: Jiachen Liang, Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen
Abstract: Traditional semi-supervised learning (SSL) assumes that the feature distributions of labeled and unlabeled data are consistent which rarely holds in realistic scenarios. In this paper, we propose a novel SSL setting, where unlabeled samples are drawn from a mixed distribution that deviates from the feature distribution of labeled samples. Under this setting, previous SSL methods tend to predict wrong pseudo-labels with the model fitted on labeled data, resulting in noise accumulation. To tackle this issue, we propose Self-Supervised Feature Adaptation (SSFA), a generic framework for improving SSL performance when labeled and unlabeled data come from different distributions. SSFA decouples the prediction of pseudo-labels from the current model to improve the quality of pseudo-labels. Particularly, SSFA incorporates a self-supervised task into the SSL framework and uses it to adapt the feature extractor of the model to the unlabeled data. In this way, the extracted features better fit the distribution of unlabeled data, thereby generating high-quality pseudo-labels. Extensive experiments show that our proposed SSFA is applicable to various pseudo-label-based SSL learners and significantly improves performance in labeled, unlabeled, and even unseen distributions.
Authors: Yang Chen, Tian He, Junfeng Fu, Ling Wang, Jingcai Guo, Hong Cheng
Abstract: Supervised and self-supervised learning are two main training paradigms for skeleton-based human action recognition. However, the former one-hot classification requires labor-intensive predefined action categories annotations, while the latter involves skeleton transformations (e.g., cropping) in the pretext tasks that may impair the skeleton structure. To address these challenges, we introduce a novel skeleton-based training framework (C$^2$VL) based on Cross-modal Contrastive learning that uses the progressive distillation to learn task-agnostic human skeleton action representation from the Vision-Language knowledge prompts. Specifically, we establish the vision-language action concept space through vision-language knowledge prompts generated by pre-trained large multimodal models (LMMs), which enrich the fine-grained details that the skeleton action space lacks. Moreover, we propose the intra-modal self-similarity and inter-modal cross-consistency softened targets in the cross-modal contrastive process to progressively control and guide the degree of pulling vision-language knowledge prompts and corresponding skeletons closer. These soft instance discrimination and self-knowledge distillation strategies contribute to the learning of better skeleton-based action representations from the noisy skeleton-vision-language pairs. During the inference phase, our method requires only the skeleton data as the input for action recognition and no longer for vision-language prompts. Extensive experiments show that our method achieves state-of-the-art results on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets. The code will be available in the future.
Authors: Gary A. McCully, John D. Hastings, Shengjie Xu, Adam Fortier
Abstract: Detecting vulnerabilities within compiled binaries is challenging due to lost high-level code structures and other factors such as architectural dependencies, compilers, and optimization options. To address these obstacles, this research explores vulnerability detection by using natural language processing (NLP) embedding techniques with word2vec, BERT, and RoBERTa to learn semantics from intermediate representation (LLVM) code. Long short-term memory (LSTM) neural networks were trained on embeddings from encoders created using approximately 118k LLVM functions from the Juliet dataset. This study is pioneering in its comparison of word2vec models with multiple bidirectional transformer (BERT, RoBERTa) embeddings built using LLVM code to train neural networks to detect vulnerabilities in compiled binaries. word2vec Continuous Bag of Words (CBOW) models achieved 92.3% validation accuracy in detecting vulnerabilities, outperforming word2vec Skip-Gram, BERT, and RoBERTa. This suggests that complex contextual NLP embeddings may not provide advantages over simpler word2vec models for this task when a limited number (e.g. 118K) of data samples are used to train the bidirectional transformer-based models. The comparative results provide novel insights into selecting optimal embeddings for learning compiler-independent semantic code representations to advance machine learning detection of vulnerabilities in compiled binaries.
Authors: Richard Luo, Austin Peng, Adithya Vasudev, Rishabh Jain
Abstract: Video is an increasingly prominent and information-dense medium, yet it poses substantial challenges for language models. A typical video consists of a sequence of shorter segments, or shots, that collectively form a coherent narrative. Each shot is analogous to a word in a sentence where multiple data streams of information (such as visual and auditory data) must be processed simultaneously. Comprehension of the entire video requires not only understanding the visual-audio information of each shot but also requires that the model links the ideas between each shot to generate a larger, all-encompassing story. Despite significant progress in the field, current works often overlook videos' more granular shot-by-shot semantic information. In this project, we propose a family of efficient large language vision models (LLVMs) to boost video summarization and captioning called Shotluck Holmes. By leveraging better pretraining and data collection strategies, we extend the abilities of existing small LLVMs from being able to understand a picture to being able to understand a sequence of frames. Specifically, we show that Shotluck Holmes achieves better performance than state-of-the-art results on the Shot2Story video captioning and summary task with significantly smaller and more computationally efficient models.
Authors: Byeonghu Na, Suhyeon Jo, Yeongmin Kim, Il-Chul Moon
Abstract: Relation extraction (RE) is a fundamental task in natural language processing, aiming to identify relations between target entities in text. While many RE methods are designed for a single sentence or document, cross-document RE has emerged to address relations across multiple long documents. Given the nature of long documents in cross-document RE, extracting document embeddings is challenging due to the length constraints of pre-trained language models. Therefore, we propose REward-based Input Construction (REIC), the first learning-based sentence selector for cross-document RE. REIC extracts sentences based on relational evidence, enabling the RE module to effectively infer relations. Since supervision of evidence sentences is generally unavailable, we train REIC using reinforcement learning with RE prediction scores as rewards. Experimental results demonstrate the superiority of our method over heuristic methods for different RE structures and backbones in cross-document RE. Our code is publicly available at https://github.com/aailabkaist/REIC.
Authors: Zhiwei Wang, Yongkang Wang, Wen Zhang
Abstract: Accurately predicting antibody-antigen binding residues, i.e., paratopes and epitopes, is crucial in antibody design. However, existing methods solely focus on uni-modal data (either sequence or structure), disregarding the complementary information present in multi-modal data, and most methods predict paratopes and epitopes separately, overlooking their specific spatial interactions. In this paper, we propose a novel Multi-modal contrastive learning and Interaction informativeness estimation-based method for Paratope and Epitope prediction, named MIPE, by using both sequence and structure data of antibodies and antigens. MIPE implements a multi-modal contrastive learning strategy, which maximizes representations of binding and non-binding residues within each modality and meanwhile aligns uni-modal representations towards effective modal representations. To exploit the spatial interaction information, MIPE also incorporates an interaction informativeness estimation that computes the estimated interaction matrices between antibodies and antigens, thereby approximating them to the actual ones. Extensive experiments demonstrate the superiority of our method compared to baselines. Additionally, the ablation studies and visualizations demonstrate the superiority of MIPE owing to the better representations acquired through multi-modal contrastive learning and the interaction patterns comprehended by the interaction informativeness estimation.
Authors: Kidist Amde Mekonnen, Nicola Dall'Asen, Paolo Rota
Abstract: Diffusion Probabilistic Models (DPMs) have emerged as a powerful class of deep generative models, achieving remarkable performance in image synthesis tasks. However, these models face challenges in terms of widespread adoption due to their reliance on sequential denoising steps during sample generation. This dependence leads to substantial computational requirements, making them unsuitable for resource-constrained or real-time processing systems. To address these challenges, we propose a novel method that integrates denoising phases directly into the model's architecture, thereby reducing the need for resource-intensive computations. Our approach combines diffusion models with generative adversarial networks (GANs) through knowledge distillation, enabling more efficient training and evaluation. By utilizing a pre-trained diffusion model as a teacher model, we train a student model through adversarial learning, employing layerwise transformations for denoising and submodules for predicting the teacher model's output at various points in time. This integration significantly reduces the number of parameters and denoising steps required, leading to improved sampling speed at test time. We validate our method with extensive experiments, demonstrating comparable performance with reduced computational requirements compared to existing approaches. By enabling the deployment of diffusion models on resource-constrained devices, our research mitigates their computational burden and paves the way for wider accessibility and practical use across the research community and end-users. Our code is publicly available at https://github.com/kidist-amde/Adv-KD
Authors: Kidist Amde Mekonnen
Abstract: Deep learning algorithms have a large number of trainable parameters often with sizes of hundreds of thousands or more. Training this algorithm requires a large amount of training data and generating a sufficiently large dataset for these algorithms is costly\cite{noguchi2019image}. GANs are generative neural networks that use two deep learning networks that are competing with each other. The networks are generator and discriminator networks. The generator tries to generate realistic images which resemble the actual training dataset by approximating the training data distribution and the discriminator is trained to classify images as real or fake(generated)\cite{goodfellow2016nips}. Training these GAN algorithms also requires a large amount of training dataset\cite{noguchi2019image}. In this study, the aim is to address the question, "Given an unconditioned pretrained generator network and a pretrained classifier, is it feasible to develop a conditioned generator without relying on any training dataset?" The paper begins with a general introduction to the problem. The subsequent sections are structured as follows: Section 2 provides background information on the problem. Section 3 reviews relevant literature on the topic. Section 4 outlines the methodology employed in this study. Section 5 presents the experimental results. Section 6 discusses the findings and proposes potential future research directions. Finally, Section 7 offers concluding remarks. The implementation can be accessed \href{https://github.com/kidist-amde/BigGAN-PyTorch}{here}.
Authors: Takaya Tanaka, Yutaka Yamaguti
Abstract: Successive image generation using cyclic transformations is demonstrated by extending the CycleGAN model to transform images among three different categories. Repeated application of the trained generators produces sequences of images that transition among the different categories. The generated image sequences occupy a more limited region of the image space compared with the original training dataset. Quantitative evaluation using precision and recall metrics indicates that the generated images have high quality but reduced diversity relative to the training dataset. Such successive generation processes are characterized as chaotic dynamics in terms of dynamical system theory. Positive Lyapunov exponents estimated from the generated trajectories confirm the presence of chaotic dynamics, with the Lyapunov dimension of the attractor found to be comparable to the intrinsic dimension of the training data manifold. The results suggest that chaotic dynamics in the image space defined by the deep generative model contribute to the diversity of the generated images, constituting a novel approach for multi-class image generation. This model can be interpreted as an extension of classical associative memory to perform hetero-association among image categories.
Authors: Lorenzo Innocenti, Giacomo Blanco, Luca Barco, Claudio Rossi
Abstract: Urban heat islands, defined as specific zones exhibiting substantially higher temperatures than their immediate environs, pose significant threats to environmental sustainability and public health. This study introduces a novel machine-learning model that amalgamates data from the Sentinel-3 satellite, meteorological predictions, and additional remote sensing inputs. The primary aim is to generate detailed spatiotemporal maps that forecast the peak temperatures within a 24-hour period in Turin. Experimental results validate the model's proficiency in predicting temperature patterns, achieving a Mean Absolute Error (MAE) of 2.09 degrees Celsius for the year 2023 at a resolution of 20 meters per pixel, thereby enriching our knowledge of urban climatic behavior. This investigation enhances the understanding of urban microclimates, emphasizing the importance of cross-disciplinary data integration, and laying the groundwork for informed policy-making aimed at alleviating the negative impacts of extreme urban temperatures.
Authors: Riccardo Benaglia, Angelo Porrello, Pietro Buzzega, Simone Calderara, Rita Cucchiara
Abstract: Trajectory forecasting is crucial for video surveillance analytics, as it enables the anticipation of future movements for a set of agents, e.g. basketball players engaged in intricate interactions with long-term intentions. Deep generative models offer a natural learning approach for trajectory forecasting, yet they encounter difficulties in achieving an optimal balance between sampling fidelity and diversity. We address this challenge by leveraging Vector Quantized Variational Autoencoders (VQ-VAEs), which utilize a discrete latent space to tackle the issue of posterior collapse. Specifically, we introduce an instance-based codebook that allows tailored latent representations for each example. In a nutshell, the rows of the codebook are dynamically adjusted to reflect contextual information (i.e., past motion patterns extracted from the observed trajectories). In this way, the discretization process gains flexibility, leading to improved reconstructions. Notably, instance-level dynamics are injected into the codebook through low-rank updates, which restrict the customization of the codebook to a lower dimension space. The resulting discrete space serves as the basis of the subsequent step, which regards the training of a diffusion-based predictive model. We show that such a two-fold framework, augmented with instance-level discretization, leads to accurate and diverse forecasts, yielding state-of-the-art performance on three established benchmarks.
Authors: Yiwen Sun, Wenye Li
Abstract: OpenTensor is a reproduction of AlphaTensor, which discovered a new algorithm that outperforms the state-of-the-art methods for matrix multiplication by Deep Reinforcement Learning (DRL). While AlphaTensor provides a promising framework for solving scientific problems, it is really hard to reproduce due to the massive tricks and lack of source codes. In this paper, we clean up the algorithm pipeline, clarify the technical details, and make some improvements to the training process. Computational results show that OpenTensor can successfully find efficient matrix multiplication algorithms.
Authors: Allen Hao Huang
Abstract: Activation functions are core components of all deep learning architectures. Currently, the most popular activation functions are smooth ReLU variants like GELU and SiLU. These are self-gated activation functions where the range of the gating function is between zero and one. In this paper, we explore the viability of using arctan as a gating mechanism. A self-gated activation function that uses arctan as its gating function has a monotonically increasing first derivative. To make this activation function competitive, it is necessary to introduce a trainable parameter for every MLP block to expand the range of the gating function beyond zero and one. We find that this technique also improves existing self-gated activation functions. We conduct an empirical evaluation of Expanded ArcTan Linear Unit (xATLU), Expanded GELU (xGELU), and Expanded SiLU (xSiLU) and show that they outperform existing activation functions within a transformer architecture. Additionally, expanded gating ranges show promising results in improving first-order Gated Linear Units (GLU).
Authors: Christian Janos Lebeda, Matthew Regehr, Gautam Kamath, Thomas Steinke
Abstract: We consider the problem of computing tight privacy guarantees for the composition of subsampled differentially private mechanisms. Recent algorithms can numerically compute the privacy parameters to arbitrary precision but must be carefully applied. Our main contribution is to address two common points of confusion. First, some privacy accountants assume that the privacy guarantees for the composition of a subsampled mechanism are determined by self-composing the worst-case datasets for the uncomposed mechanism. We show that this is not true in general. Second, Poisson subsampling is sometimes assumed to have similar privacy guarantees compared to sampling without replacement. We show that the privacy guarantees may in fact differ significantly between the two sampling schemes. In particular, we give an example of hyperparameters that result in $\varepsilon \approx 1$ for Poisson subsampling and $\varepsilon > 10$ for sampling without replacement. This occurs for some parameters that could realistically be chosen for DP-SGD.
Authors: Jingwei Li, Jing Dong, Tianxing He, Jingzhao Zhang
Abstract: Identifying whether an artwork was used to train a diffusion model is an important research topic, given the rising popularity of AI-generated art and the associated copyright concerns. The work approaches this problem from the membership inference attack (MIA) perspective. We first identify the limitations of applying existing MIA methods for copyright protection: the required access of internal U-nets and the choice of non-member datasets for evaluation. To address the above problems, we introduce a novel black-box membership inference attack method that operates without needing access to the model's internal U-net. We then construct a DALL-E generated dataset for a more comprehensive evaluation. We validate our method across various setups, and our experimental results outperform previous works.
Authors: Xuhan Zuo, Minghao Wang, Tianqing Zhu, Lefeng Zhang, Shui Yu, Wanlei Zhou
Abstract: With the growing need to comply with privacy regulations and respond to user data deletion requests, integrating machine unlearning into IoT-based federated learning has become imperative. Traditional unlearning methods, however, often lack verifiable mechanisms, leading to challenges in establishing trust. This paper delves into the innovative integration of blockchain technology with federated learning to surmount these obstacles. Blockchain fortifies the unlearning process through its inherent qualities of immutability, transparency, and robust security. It facilitates verifiable certification, harmonizes security with privacy, and sustains system efficiency. We introduce a framework that melds blockchain with federated learning, thereby ensuring an immutable record of unlearning requests and actions. This strategy not only bolsters the trustworthiness and integrity of the federated learning model but also adeptly addresses efficiency and security challenges typical in IoT environments. Our key contributions encompass a certification mechanism for the unlearning process, the enhancement of data security and privacy, and the optimization of data management to ensure system responsiveness in IoT scenarios.
Authors: Gloaguen Thibaud, Jovanovi\'c Nikola, Staab Robin, Vechev Martin
Abstract: Watermarking has emerged as a promising way to detect LLM-generated text. To apply a watermark an LLM provider, given a secret key, augments generations with a signal that is later detectable by any party with the same key. Recent work has proposed three main families of watermarking schemes, two of which focus on the property of preserving the LLM distribution. This is motivated by it being a tractable proxy for maintaining LLM capabilities, but also by the idea that concealing a watermark deployment makes it harder for malicious actors to hide misuse by avoiding a certain LLM or attacking its watermark. Yet, despite much discourse around detectability, no prior work has investigated if any of these scheme families are detectable in a realistic black-box setting. We tackle this for the first time, developing rigorous statistical tests to detect the presence of all three most popular watermarking scheme families using only a limited number of black-box queries. We experimentally confirm the effectiveness of our methods on a range of schemes and a diverse set of open-source models. Our findings indicate that current watermarking schemes are more detectable than previously believed, and that obscuring the fact that a watermark was deployed may not be a viable way for providers to protect against adversaries. We further apply our methods to test for watermark presence behind the most popular public APIs: GPT4, Claude 3, Gemini 1.0 Pro, finding no strong evidence of a watermark at this point in time.
Authors: Qizhang Li, Yiwen Guo, Wangmeng Zuo, Hao Chen
Abstract: Despite numerous efforts to ensure large language models (LLMs) adhere to safety standards and produce harmless content, some successes have been achieved in bypassing these restrictions, known as jailbreak attacks against LLMs. Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing jailbreak attacks automatically. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs struggles to precisely reflect the magnitude of loss change that results from token replacements in the prompt, leading to limited attack success rates against safety-aligned LLMs, even in the white-box setting. In this paper, we explore a new perspective on this problem, suggesting that it can be alleviated by leveraging innovations inspired in transfer-based attacks that were originally proposed for attacking black-box image classification models. For the first time, we appropriate the ideologies of effective methods among these transfer-based attacks, i.e., Skip Gradient Method and Intermediate Level Attack, for improving the effectiveness of automatically generated adversarial examples against white-box LLMs. With appropriate adaptations, we inject these ideologies into gradient-based adversarial prompt generation processes and achieve significant performance gains without introducing obvious computational cost. Meanwhile, by discussing mechanisms behind the gains, new insights are drawn, and proper combinations of these methods are also developed. Our empirical results show that the developed combination achieves >30% absolute increase in attack success rates compared with GCG for attacking the Llama-2-7B-Chat model on AdvBench.
Authors: Yumeng He, Yunbo Wang, Xiaokang Yang
Abstract: Decoupling the illumination in 3D scenes is crucial for novel view synthesis and relighting. In this paper, we propose a novel method for representing a scene illuminated by a point light using a set of relightable 3D Gaussian points. Inspired by the Blinn-Phong model, our approach decomposes the scene into ambient, diffuse, and specular components, enabling the synthesis of realistic lighting effects. To facilitate the decomposition of geometric information independent of lighting conditions, we introduce a novel bilevel optimization-based meta-learning framework. The fundamental idea is to view the rendering tasks under various lighting positions as a multi-task learning problem, which our meta-learning approach effectively addresses by generalizing the learned Gaussian geometries not only across different viewpoints but also across diverse light positions. Experimental results demonstrate the effectiveness of our approach in terms of training efficiency and rendering quality compared to existing methods for free-viewpoint relighting.
Authors: Shiyin Lu, Yang Li, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Han-Jia Ye
Abstract: Current Multimodal Large Language Models (MLLMs) typically integrate a pre-trained LLM with another pre-trained vision transformer through a connector, such as an MLP, endowing the LLM with visual capabilities. However, the misalignment between two embedding strategies in MLLMs -- the structural textual embeddings based on an embedding look-up table and the continuous embeddings generated directly by the vision encoder -- makes challenges for a more seamless fusion of visual and textual information. We propose Ovis, a novel MLLM architecture designed to structurally align visual and textual embeddings. Ovis integrates an additional learnable visual embedding table into the visual encoder's process. To capture rich visual semantics, each image patch indexes the visual embedding table multiple times, resulting in a final visual embedding that is a probabilistic combination of the indexed embeddings. This structural approach mirrors the method used for generating textual embeddings. Empirical evaluations on various multimodal benchmarks demonstrate that Ovis outperforms open-source MLLMs of similar parameter scales and even surpasses the proprietary model Qwen-VL-Plus overall. These results highlight the potential of Ovis' structured visual representation for advancing MLLM architectural design and promoting more effective multimodal learning. Both the source code and the training dataset of Ovis will be made publicly available.
Authors: Fernando Moreno-Pino, \'Alvaro Arroyo, Harrison Waldon, Xiaowen Dong, \'Alvaro Cartea
Abstract: Time-series data in real-world settings typically exhibit long-range dependencies and are observed at non-uniform intervals. In these settings, traditional sequence-based recurrent models struggle. To overcome this, researchers often replace recurrent architectures with Neural ODE-based models to account for irregularly sampled data and use Transformer-based architectures to account for long-range dependencies. Despite the success of these two approaches, both incur very high computational costs for input sequences of even moderate length. To address this challenge, we introduce the Rough Transformer, a variation of the Transformer model that operates on continuous-time representations of input sequences and incurs significantly lower computational costs. In particular, we propose \textit{multi-view signature attention}, which uses path signatures to augment vanilla attention and to capture both local and global (multi-scale) dependencies in the input data, while remaining robust to changes in the sequence length and sampling frequency and yielding improved spatial processing. We find that, on a variety of time-series-related tasks, Rough Transformers consistently outperform their vanilla attention counterparts while obtaining the representational benefits of Neural ODE-based models, all at a fraction of the computational time and memory resources.
Authors: Shahrzad Haddadan, Cheng Xin, Jie Gao
Abstract: We consider a cooperative learning scenario where a collection of networked agents with individually owned classifiers dynamically update their predictions, for the same classification task, through communication or observations of each other's predictions. Clearly if highly influential vertices use erroneous classifiers, there will be a negative effect on the accuracy of all the agents in the network. We ask the following question: how can we optimally fix the prediction of a few classifiers so as maximize the overall accuracy in the entire network. To this end we consider an aggregate and an egalitarian objective function. We show a polynomial time algorithm for optimizing the aggregate objective function, and show that optimizing the egalitarian objective function is NP-hard. Furthermore, we develop approximation algorithms for the egalitarian improvement. The performance of all of our algorithms are guaranteed by mathematical analysis and backed by experiments on synthetic and real data.
Authors: Nanna E. Hartong, Ilias Sachpazidis, Oliver Blanck, Lucas Etzel, Jan C. Peeken, Stephanie E. Combs, Horst Urbach, Maxim Zaitsev, Dimos Baltas, Ilinca Popp, Anca-Ligia Grosu, Tobias Fechter
Abstract: Background: The aim of this study was to investigate the role of clinical, dosimetric and pretherapeutic magnetic resonance imaging (MRI) features for lesion-specific outcome prediction of stereotactic radiotherapy (SRT) in patients with brain metastases from malignant melanoma (MBM). Methods: In this multicenter, retrospective analysis, we reviewed 517 MBM from 130 patients treated with SRT (single fraction or hypofractionated). For each gross tumor volume (GTV) 1576 radiomic features (RF) were calculated (788 each for the GTV and for a 3 mm margin around the GTV). Clinical parameters, radiation dose and RF from pretherapeutic contrast-enhanced T1-weighted MRI from different institutions were evaluated with a feature processing and elimination pipeline in a nested cross-validation scheme. Results: Seventy-two (72) of 517 lesions (13.9%) showed a local failure (LF) after SRT. The processing pipeline showed clinical, dosimetric and radiomic features providing information for LF prediction. The most prominent ones were the correlation of the gray level co-occurrence matrix of the margin (hazard ratio (HR): 0.37, confidence interval (CI): 0.23-0.58) and systemic therapy before SRT (HR: 0.55, CI: 0.42-0.70). The majority of RF associated with LF was calculated in the margin around the GTV. Conclusions: Pretherapeutic MRI based RF connected with lesion-specific outcome after SRT could be identified, despite multicentric data and minor differences in imaging protocols. Image data analysis of the surrounding metastatic environment may provide therapy-relevant information with the potential to further individualize radiotherapy strategies.
Authors: Seongheon Park, Hyuk Kwon, Kwanghoon Sohn, Kibok Lee
Abstract: Open-world semi-supervised learning (OWSSL) extends conventional semi-supervised learning to open-world scenarios by taking account of novel categories in unlabeled datasets. Despite the recent advancements in OWSSL, the success often relies on the assumptions that 1) labeled and unlabeled datasets share the same balanced class prior distribution, which does not generally hold in real-world applications, and 2) unlabeled training datasets are utilized for evaluation, where such transductive inference might not adequately address challenges in the wild. In this paper, we aim to generalize OWSSL by addressing them. Our work suggests that practical OWSSL may require different training settings, evaluation methods, and learning strategies compared to those prevalent in the existing literature.
Authors: Yueqin Yin, Zhendong Wang, Yujia Xie, Weizhu Chen, Mingyuan Zhou
Abstract: Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability. To overcome this limitation, we introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation. Specifically, we employ an Exponential Moving Average (EMA) model in conjunction with a replay buffer to enable dynamic updates of response segments, effectively integrating real-time feedback with insights from historical data. Our comprehensive evaluations of the LLaMA3-8B and Mistral-7B models across benchmarks, including the Open LLM Leaderboard, IFEval, AlpacaEval 2.0, and MT-Bench, demonstrate that SAPO matches or surpasses established offline contrastive baselines, such as DPO and Odds Ratio Preference Optimization, and outperforms offline self-play methods like SPIN. Our code is available at https://github.com/yinyueqin/SAPO
Authors: Chinmay Datar, Taniya Kapoor, Abhishek Chandra, Qing Sun, Iryna Burak, Erik Lien Bolager, Anna Veselovska, Massimo Fornasier, Felix Dietrich
Abstract: Approximation of solutions to partial differential equations (PDE) is an important problem in computational science and engineering. Using neural networks as an ansatz for the solution has proven a challenge in terms of training time and approximation accuracy. In this contribution, we discuss how sampling the hidden weights and biases of the ansatz network from data-agnostic and data-dependent probability distributions allows us to progress on both challenges. In most examples, the random sampling schemes outperform iterative, gradient-based optimization of physics-informed neural networks regarding training time and accuracy by several orders of magnitude. For time-dependent PDE, we construct neural basis functions only in the spatial domain and then solve the associated ordinary differential equation with classical methods from scientific computing over a long time horizon. This alleviates one of the greatest challenges for neural PDE solvers because it does not require us to parameterize the solution in time. For second-order elliptic PDE in Barron spaces, we prove the existence of sampled networks with $L^2$ convergence to the solution. We demonstrate our approach on several time-dependent and static PDEs. We also illustrate how sampled networks can effectively solve inverse problems in this setting. Benefits compared to common numerical schemes include spectral convergence and mesh-free construction of basis functions.
Authors: Rui Ren, Jingbang Yang, Linxiao Yang, Xinyue Gu, Liang Sun
Abstract: The newly deployed service -- one kind of change service, could lead to a new type of minority fault. Existing state-of-the-art methods for fault localization rarely consider the imbalanced fault classification in change service. This paper proposes a novel method that utilizes decision rule sets to deal with highly imbalanced data by optimizing the F1 score subject to cardinality constraints. The proposed method greedily generates the rule with maximal marginal gain and uses an efficient minorize-maximization (MM) approach to select rules iteratively, maximizing a non-monotone submodular lower bound. Compared with existing fault localization algorithms, our algorithm can adapt to the imbalanced fault scenario of change service, and provide interpretable fault causes which are easy to understand and verify. Our method can also be deployed in the online training setting, with only about 15% training overhead compared to the current SOTA methods. Empirical studies showcase that our algorithm outperforms existing fault localization algorithms in both accuracy and model interpretability.
Authors: Nikos G. Evgenidis, Nikos A. Mitsiou, Sotiris A. Tegos, Panagiotis D. Diamantoulakis, Panagiotis Sarigiannidis, Ioannis T. Rekanos, George K. Karagiannidis
Abstract: In response to the increasing number of devices anticipated in next-generation networks, a shift toward over-the-air (OTA) computing has been proposed. Leveraging the superposition of multiple access channels, OTA computing enables efficient resource management by supporting simultaneous uncoded transmission in the time and the frequency domain. Thus, to advance the integration of OTA computing, our study presents a theoretical analysis addressing practical issues encountered in current digital communication transceivers, such as time sampling error and intersymbol interference (ISI). To this end, we examine the theoretical mean squared error (MSE) for OTA transmission under time sampling error and ISI, while also exploring methods for minimizing the MSE in the OTA transmission. Utilizing alternating optimization, we also derive optimal power policies for both the devices and the base station. Additionally, we propose a novel deep neural network (DNN)-based approach to design waveforms enhancing OTA transmission performance under time sampling error and ISI. To ensure fair comparison with existing waveforms like the raised cosine (RC) and the better-than-raised-cosine (BRTC), we incorporate a custom loss function integrating energy and bandwidth constraints, along with practical design considerations such as waveform symmetry. Simulation results validate our theoretical analysis and demonstrate performance gains of the designed pulse over RC and BTRC waveforms. To facilitate testing of our results without necessitating the DNN structure recreation, we provide curve fitting parameters for select DNN-based waveforms as well.
Authors: Emmanuel Ramasso, Rafael de O. Teloli, Romain Marcel
Abstract: This paper investigates the use of deep transfer learning based on convolutional neural networks (CNNs) to monitor the condition of bolted joints using acoustic emissions. Bolted structures are critical components in many mechanical systems, and the ability to monitor their condition status is crucial for effective structural health monitoring. We evaluated the performance of our methodology using the ORION-AE benchmark, a structure composed of two thin beams connected by three bolts, where highly noisy acoustic emission measurements were taken to detect changes in the applied tightening torque of the bolts. The data used from this structure is derived from the transformation of acoustic emission data streams into images using continuous wavelet transform, and leveraging pretrained CNNs for feature extraction and denoising. Our experiments compared single-sensor versus multiple-sensor fusion for estimating the tightening level (loosening) of bolts and evaluated the use of raw versus prefiltered data on the performance. We particularly focused on the generalization capabilities of CNN-based transfer learning across different measurement campaigns and we studied ordinal loss functions to penalize incorrect predictions less severely when close to the ground truth, thereby encouraging misclassification errors to be in adjacent classes. Network configurations as well as learning rate schedulers are also investigated, and super-convergence is obtained, i.e., high classification accuracy is achieved in a few number of iterations with different networks. Furthermore, results demonstrate the generalization capabilities of CNN-based transfer learning for monitoring bolted structures by acoustic emission with varying amounts of prior information required during training.
Authors: \.Ilker I\c{s}{\i}k, Ebru Aydin Gol, Ramazan Gokberk Cinbis
Abstract: Temporal logic is a framework for representing and reasoning about propositions that evolve over time. It is commonly used for specifying requirements in various domains, including hardware and software systems, as well as robotics. Specification mining or formula generation involves extracting temporal logic formulae from system traces and has numerous applications, such as detecting bugs and improving interpretability. Although there has been a surge of deep learning-based methods for temporal logic satisfiability checking in recent years, the specification mining literature has been lagging behind in adopting deep learning methods despite their many advantages, such as scalability. In this paper, we introduce autoregressive models that can generate linear temporal logic formulae from traces, towards addressing the specification mining problem. We propose multiple architectures for this task: transformer encoder-decoder, decoder-only transformer, and Mamba, which is an emerging alternative to transformer models. Additionally, we devise a metric for quantifying the distinctiveness of the generated formulae and a straightforward algorithm to enforce the syntax constraints. Our experiments show that the proposed architectures yield promising results, generating correct and distinct formulae at a fraction of the compute cost needed for the combinatorial baseline.
Authors: Xiaoke Wang, Xiaochen Yang, Rui Zhu, Jing-Hao Xue
Abstract: Positive-unlabeled (PU) learning aims to train a classifier using the data containing only labeled-positive instances and unlabeled instances. However, existing PU learning methods are generally hard to achieve satisfactory performance on trifurcate data, where the positive instances distribute on both sides of the negative instances. To address this issue, firstly we propose a PU classifier with asymmetric loss (PUAL), by introducing a structure of asymmetric loss on positive instances into the objective function of the global and local learning classifier. Then we develop a kernel-based algorithm to enable PUAL to obtain non-linear decision boundary. We show that, through experiments on both simulated and real-world datasets, PUAL can achieve satisfactory classification on trifurcate data.
Authors: Tianyang Xu, Shujin Wu, Shizhe Diao, Xiaoze Liu, Xingyao Wang, Yangyi Chen, Jing Gao
Abstract: Large language models (LLMs) often generate inaccurate or fabricated information and generally fail to indicate their confidence, which limits their broader applications. Previous work elicits confidence from LLMs by direct or self-consistency prompting, or constructing specific datasets for supervised finetuning. The prompting-based approaches have inferior performance, and the training-based approaches are limited to binary or inaccurate group-level confidence estimates. In this work, we present the advanced SaySelf, a training framework that teaches LLMs to express more accurate fine-grained confidence estimates. In addition, beyond the confidence scores, SaySelf initiates the process of directing LLMs to produce self-reflective rationales that clearly identify gaps in their parametric knowledge and explain their uncertainty. This is achieved by using an LLM to automatically summarize the uncertainties in specific knowledge via natural language. The summarization is based on the analysis of the inconsistency in multiple sampled reasoning chains, and the resulting data is utilized for supervised fine-tuning. Moreover, we utilize reinforcement learning with a meticulously crafted reward function to calibrate the confidence estimates, motivating LLMs to deliver accurate, high-confidence predictions and to penalize overconfidence in erroneous outputs. Experimental results in both in-distribution and out-of-distribution datasets demonstrate the effectiveness of SaySelf in reducing the confidence calibration error and maintaining the task performance. We show that the generated self-reflective rationales are reasonable and can further contribute to the calibration. The code is made public at \url{https://github.com/xu1868/SaySelf}.
Authors: Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bo Li, Radha Poovendran
Abstract: In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data of clients is typically non-i.i.d. and heterogeneous, resulting in varying contributions from individual clients to the final performance of the global model. In response, many contribution evaluation methods were proposed, where the server could evaluate the contribution made by each client and incentivize the high-contributing clients to sustain their long-term participation in FL. Existing studies mainly focus on developing new metrics or algorithms to better measure the contribution of each client. However, the security of contribution evaluation methods of FL operating in adversarial environments is largely unexplored. In this paper, we propose the first model poisoning attack on contribution evaluation methods in FL, termed ACE. Specifically, we show that any malicious client utilizing ACE could manipulate the parameters of its local model such that it is evaluated to have a high contribution by the server, even when its local training data is indeed of low quality. We perform both theoretical analysis and empirical evaluations of ACE. Theoretically, we show our design of ACE can effectively boost the malicious client's perceived contribution when the server employs the widely-used cosine distance metric to measure contribution. Empirically, our results show ACE effectively and efficiently deceive five state-of-the-art contribution evaluation methods. In addition, ACE preserves the accuracy of the final global models on testing inputs. We also explore six countermeasures to defend ACE. Our results show they are inadequate to thwart ACE, highlighting the urgent need for new defenses to safeguard the contribution evaluation methods in FL.
Authors: Felix Mujkanovic, Ntumba Elie Nsampi, Christian Theobalt, Hans-Peter Seidel, Thomas Leimk\"uhler
Abstract: Gaussian scale spaces are a cornerstone of signal representation and processing, with applications in filtering, multiscale analysis, anti-aliasing, and many more. However, obtaining such a scale space is costly and cumbersome, in particular for continuous representations such as neural fields. We present an efficient and lightweight method to learn the fully continuous, anisotropic Gaussian scale space of an arbitrary signal. Based on Fourier feature modulation and Lipschitz bounding, our approach is trained self-supervised, i.e., training does not require any manual filtering. Our neural Gaussian scale-space fields faithfully capture multiscale representations across a broad range of modalities, and support a diverse set of applications. These include images, geometry, light-stage data, texture anti-aliasing, and multiscale optimization.
Authors: Muhammad Muneeb Saad, Mubashir Husain Rehmani, Ruairi O'Reilly
Abstract: Generative Adversarial Networks (GANs) have high computational costs to train their complex architectures. Throughout the training process, GANs' output is analyzed qualitatively based on the loss and synthetic images' diversity and quality. Based on this qualitative analysis, training is manually halted once the desired synthetic images are generated. By utilizing an early stopping criterion, the computational cost and dependence on manual oversight can be reduced yet impacted by training problems such as mode collapse, non-convergence, and instability. This is particularly prevalent in biomedical imagery, where training problems degrade the diversity and quality of synthetic images, and the high computational cost associated with training makes complex architectures increasingly inaccessible. This work proposes a novel early stopping criteria to quantitatively detect training problems, halt training, and reduce the computational costs associated with synthesizing biomedical images. Firstly, the range of generator and discriminator loss values is investigated to assess whether mode collapse, non-convergence, and instability occur sequentially, concurrently, or interchangeably throughout the training of GANs. Secondly, utilizing these occurrences in conjunction with the Mean Structural Similarity Index (MS-SSIM) and Fr\'echet Inception Distance (FID) scores of synthetic images forms the basis of the proposed early stopping criteria. This work helps identify the occurrence of training problems in GANs using low-resource computational cost and reduces training time to generate diversified and high-quality synthetic images.
Authors: Eleanor Clifford, Adhithya Saravanan, Harry Langford, Cheng Zhang, Yiren Zhao, Robert Mullins, Ilia Shumailov, Jamie Hayes
Abstract: Modern Machine Learning models are expensive IP and business competitiveness often depends on keeping this IP confidential. This in turn restricts how these models are deployed -- for example it is unclear how to deploy a model on-device without inevitably leaking the underlying model. At the same time, confidential computing technologies such as Multi-Party Computation or Homomorphic encryption remain impractical for wide adoption. In this paper we take a different approach and investigate feasibility of ML-specific mechanisms that deter unauthorized model use by restricting the model to only be usable on specific hardware, making adoption on unauthorized hardware inconvenient. That way, even if IP is compromised, it cannot be trivially used without specialised hardware or major model adjustment. In a sense, we seek to enable cheap locking of machine learning models into specific hardware. We demonstrate that locking mechanisms are feasible by either targeting efficiency of model representations, such making models incompatible with quantisation, or tie the model's operation on specific characteristics of hardware, such as number of cycles for arithmetic operations. We demonstrate that locking comes with negligible work and latency overheads, while significantly restricting usability of the resultant model on unauthorized hardware.
Authors: Yi Yang, Qingwen Zhang, Kei Ikemura, Nazre Batool, John Folkesson
Abstract: Addressing hard cases in autonomous driving, such as anomalous road users, extreme weather conditions, and complex traffic interactions, presents significant challenges. To ensure safety, it is crucial to detect and manage these scenarios effectively for autonomous driving systems. However, the rarity and high-risk nature of these cases demand extensive, diverse datasets for training robust models. Vision-Language Foundation Models (VLMs) have shown remarkable zero-shot capabilities as being trained on extensive datasets. This work explores the potential of VLMs in detecting hard cases in autonomous driving. We demonstrate the capability of VLMs such as GPT-4v in detecting hard cases in traffic participant motion prediction on both agent and scenario levels. We introduce a feasible pipeline where VLMs, fed with sequential image frames with designed prompts, effectively identify challenging agents or scenarios, which are verified by existing prediction models. Moreover, by taking advantage of this detection of hard cases by VLMs, we further improve the training efficiency of the existing motion prediction pipeline by performing data selection for the training samples suggested by GPT. We show the effectiveness and feasibility of our pipeline incorporating VLMs with state-of-the-art methods on NuScenes datasets. The code is accessible at https://github.com/KTH-RPL/Detect_VLM.
Authors: Jean Barbier, Francesco Camilli, Marco Mondelli, Yizhou Xu
Abstract: We consider a prototypical problem of Bayesian inference for a structured spiked model: a low-rank signal is corrupted by additive noise. While both information-theoretic and algorithmic limits are well understood when the noise is i.i.d. Gaussian, the more realistic case of structured noise still proves to be challenging. To capture the structure while maintaining mathematical tractability, a line of work has focused on rotationally invariant noise. However, existing studies either provide sub-optimal algorithms or they are limited to a special class of noise ensembles. In this paper, we establish the first characterization of the information-theoretic limits for a noise matrix drawn from a general trace ensemble. These limits are then achieved by an efficient algorithm inspired by the theory of adaptive Thouless-Anderson-Palmer (TAP) equations. Our approach leverages tools from statistical physics (replica method) and random matrix theory (generalized spherical integrals), and it unveils the equivalence between the rotationally invariant model and a surrogate Gaussian model.
Authors: Jiesong Lian, Yucong Huang, Mingzhi Wang, Chengdong Ma, Yixue Hao, Ying Wen, Yaodong Yang
Abstract: For solving zero-sum games involving non-transitivity, a common approach is to maintain population policies to approximate the Nash Equilibrium (NE). Previous research has shown that the Policy Space Response Oracle (PSRO) is an effective multi-agent reinforcement learning framework for these games. However, repeatedly training new policies from scratch to approximate the Best Response (BR) to opponents' mixed policies at each iteration is inefficient and costly. While some PSRO methods initialize a new BR policy by inheriting from past BR policies, this approach limits the exploration of new policies, especially against challenging opponents.To address this issue, we propose Fusion-PSRO, which uses model fusion to initialize the policy for better approximation to BR. With Top-k probabilities from NE, we select high-quality base policies and fuse them into a new BR policy through model averaging. This approach allows the initialized policy to incorporate multiple expert policies, making it easier to handle difficult opponents compared to inheriting or initializing from scratch. Additionally, our method only modifies the policy initialization, enabling its application to nearly all PSRO variants without additional training overhead.Our experiments with non-transitive matrix games, Leduc poker, and the more complex Liars Dice demonstrate that Fusion-PSRO enhances the performance of nearly all PSRO variants, achieving lower exploitability.
Authors: Kanghee Park, Jiayu Wang, Taylor Berg-Kirkpatrick, Nadia Polikarpova, Loris D'Antoni
Abstract: Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-formed markup. Constrained decoding approaches mitigate this problem by greedily restricting what tokens an LLM can output at each step to guarantee that the output matches a given constraint. Specifically, in grammar-constrained decoding (GCD), the LLM's output must follow a given grammar. In this paper we demonstrate that GCD techniques (and in general constrained decoding techniques) can distort the LLM's distribution, leading to outputs that are grammatical but appear with likelihoods that are not proportional to the ones given by the LLM, and so ultimately are low-quality. We call the problem of aligning sampling with a grammar constraint, grammar-aligned decoding (GAD), and propose adaptive sampling with approximate expected futures (ASAp), a decoding algorithm that guarantees the output to be grammatical while provably producing outputs that match the conditional probability of the LLM's distribution conditioned on the given grammar constraint. Our algorithm uses prior sample outputs to soundly overapproximate the future grammaticality of different output prefixes. Our evaluation on code generation and structured NLP tasks shows how ASAp often produces outputs with higher likelihood (according to the LLM's distribution) than existing GCD techniques, while still enforcing the desired grammatical constraints.
Authors: Xinxi Zhang, Song Wen, Ligong Han, Felix Juefei-Xu, Akash Srivastava, Junzhou Huang, Hao Wang, Molei Tao, Dimitris N. Metaxas
Abstract: Adapting large-scale pre-trained generative models in a parameter-efficient manner is gaining traction. Traditional methods like low rank adaptation achieve parameter efficiency by imposing constraints but may not be optimal for tasks requiring high representation capacity. We propose a novel spectrum-aware adaptation framework for generative models. Our method adjusts both singular values and their basis vectors of pretrained weights. Using the Kronecker product and efficient Stiefel optimizers, we achieve parameter-efficient adaptation of orthogonal matrices. We introduce Spectral Orthogonal Decomposition Adaptation (SODA), which balances computational efficiency and representation capacity. Extensive evaluations on text-to-image diffusion models demonstrate SODA's effectiveness, offering a spectrum-aware alternative to existing fine-tuning methods.
Authors: Xin Wen, Bingchen Zhao, Yilun Chen, Jiangmiao Pang, Xiaojuan Qi
Abstract: Severe data imbalance naturally exists among web-scale vision-language datasets. Despite this, we find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning, and demonstrates significant effectiveness in learning generalizable representations. With an aim to investigate the reasons behind this finding, we conduct controlled experiments to study various underlying factors, and reveal that CLIP's pretext task forms a dynamic classification problem wherein only a subset of classes is present in training. This isolates the bias from dominant classes and implicitly balances the learning signal. Furthermore, the robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts, which are inaccessible to supervised learning. Our study not only uncovers the mechanisms behind CLIP's generalizability beyond data imbalance but also provides transferable insights for the research community. The findings are validated in both supervised and self-supervised learning, enabling models trained on imbalanced data to achieve CLIP-level performance on diverse recognition tasks. Code will be available at: https://github.com/CVMI-Lab/clip-beyond-tail.
Authors: Peng Zhao, Jia-Wei Shan, Yu-Jie Zhang, Zhi-Hua Zhou
Abstract: In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to known labels. This paper studies a new problem setting in which there are unknown classes in the training data misperceived as other labels, and thus their existence appears unknown from the given supervision. We attribute the unknown unknowns to the fact that the training dataset is badly advised by the incompletely perceived label space due to the insufficient feature information. To this end, we propose the exploratory machine learning, which examines and investigates training data by actively augmenting the feature space to discover potentially hidden classes. Our method consists of three ingredients including rejection model, feature exploration, and model cascade. We provide theoretical analysis to justify its superiority, and validate the effectiveness on both synthetic and real datasets.
Authors: Yehuda Dar, Daniel LeJeune, Richard G. Baraniuk
Abstract: We study a fundamental transfer learning process from source to target linear regression tasks, including overparameterized settings where there are more learned parameters than data samples. The target task learning is addressed by using its training data together with the parameters previously computed for the source task. We define a transfer learning approach to the target task as a linear regression optimization with a regularization on the distance between the to-be-learned target parameters and the already-learned source parameters. We analytically characterize the generalization performance of our transfer learning approach and demonstrate its ability to resolve the peak in generalization errors in double descent phenomena of the minimum L2-norm solution to linear regression. Moreover, we show that for sufficiently related tasks, the optimally tuned transfer learning approach can outperform the optimally tuned ridge regression method, even when the true parameter vector conforms to an isotropic Gaussian prior distribution. Namely, we demonstrate that transfer learning can beat the minimum mean square error (MMSE) solution of the independent target task. Our results emphasize the ability of transfer learning to extend the solution space to the target task and, by that, to have an improved MMSE solution. We formulate the linear MMSE solution to our transfer learning setting and point out its key differences from the common design philosophy to transfer learning.
Authors: Weijing Chen, Guoqiang Ma, Tao Fan, Yan Kang, Qian Xu, Qiang Yang
Abstract: Gradient boosting decision tree (GBDT) is a widely used ensemble algorithm in the industry. Its vertical federated learning version, SecureBoost, is one of the most popular algorithms used in cross-silo privacy-preserving modeling. As the area of privacy computation thrives in recent years, demands for large-scale and high-performance federated learning have grown dramatically in real-world applications. In this paper, to fulfill these requirements, we propose SecureBoost+ that is both novel and improved from the prior work SecureBoost. SecureBoost+ integrates several ciphertext calculation optimizations and engineering optimizations. The experimental results demonstrate that Secureboost+ has significant performance improvements on large and high dimensional data sets compared to SecureBoost. It makes effective and efficient large-scale vertical federated learning possible.
Authors: Ahmad Khajenezhad, Seyed Ali Osia, Mahmood Karimian, Hamid Beigy
Abstract: Transformers have become widely used in various tasks, such as natural language processing and machine vision. This paper proposes Gransformer, an algorithm based on Transformer for generating graphs. We modify the Transformer encoder to exploit the structural information of the given graph. The attention mechanism is adapted to consider the presence or absence of edges between each pair of nodes. We also introduce a graph-based familiarity measure between node pairs that applies to both the attention and the positional encoding. This measure of familiarity is based on message-passing algorithms and contains structural information about the graph. Also, this measure is autoregressive, which allows our model to acquire the necessary conditional probabilities in a single forward pass. In the output layer, we also use a masked autoencoder for density estimation to efficiently model the sequential generation of dependent edges connected to each node. In addition, we propose a technique to prevent the model from generating isolated nodes without connection to preceding nodes by using BFS node orderings. We evaluate this method using synthetic and real-world datasets and compare it with related ones, including recurrent models and graph convolutional networks. Experimental results show that the proposed method performs comparatively to these methods.
Authors: Meiby Ortiz-Bouza, Selin Aviyente
Abstract: Many real-world systems can be represented as graphs where the different entities in the system are presented by nodes and their interactions by edges. An important task in studying large datasets with graphical structure is graph clustering. While there has been a lot of work on graph clustering using the connectivity between the nodes, many real-world networks also have node attributes. Clustering attributed graphs requires joint modeling of graph structure and node attributes. Recent work has focused on combining these two complementary sources of information through graph convolutional networks and graph filtering. However, these methods are mostly limited to lowpass filtering and do not explicitly learn the filter parameters for the clustering task. In this paper, we introduce a graph signal processing based approach, where we learn the parameters of Finite Impulse Response (FIR) and Autoregressive Moving Average (ARMA) graph filters optimized for clustering. The proposed approach is formulated as a two-step iterative optimization problem, focusing on learning interpretable graph filters that are optimal for the given data and that maximize the separation between different clusters. The proposed approach is evaluated on attributed networks and compared to the state-of-the-art methods.
Authors: Simla Burcu Harma, Ayan Chakraborty, Nicholas Sperry, Babak Falsafi, Martin Jaggi, Yunho Oh
Abstract: The unprecedented demand for computing resources to train DNN models has led to a search for minimal numerical encoding. Recent state-of-the-art (SOTA) proposals advocate for multi-level scaled narrow bitwidth numerical formats. In this paper, we show that single-level scaling is sufficient to maintain training accuracy while maximizing arithmetic density. We identify a previously proposed single-level scaled format for 8-bit training, Hybrid Block Floating Point (HBFP), as the optimal candidate to minimize. We perform a full-scale exploration of the HBFP design space using mathematical tools to study the interplay among various parameters and identify opportunities for even smaller encodings across layers and epochs. Based on our findings, we propose Accuracy Booster, a mixed-mantissa HBFP technique that uses 4-bit mantissas for over 99% of all arithmetic operations in training and 6-bit mantissas only in the last epoch and first/last layers. We show Accuracy Booster enables increasing arithmetic density over all other SOTA formats by at least 2.3x while achieving state-of-the-art accuracies in 4-bit training.
Authors: Parvin Malekzadeh, Konstantinos N. Plataniotis
Abstract: Reinforcement learning (RL) has garnered significant attention for developing decision-making agents that aim to maximize rewards, specified by an external supervisor, within fully observable environments. However, many real-world problems involve partial observations, formulated as partially observable Markov decision processes (POMDPs). Previous studies have tackled RL in POMDPs by either incorporating the memory of past actions and observations or by inferring the true state of the environment from observed data. However, aggregating observed data over time becomes impractical in continuous spaces. Moreover, inference-based RL approaches often require many samples to perform well, as they focus solely on reward maximization and neglect uncertainty in the inferred state. Active inference (AIF) is a framework formulated in POMDPs and directs agents to select actions by minimizing a function called expected free energy (EFE). This supplies reward-maximizing (exploitative) behaviour, as in RL, with information-seeking (exploratory) behaviour. Despite this exploratory behaviour of AIF, its usage is limited to discrete spaces due to the computational challenges associated with EFE. In this paper, we propose a unified principle that establishes a theoretical connection between AIF and RL, enabling seamless integration of these two approaches and overcoming their aforementioned limitations in continuous space POMDP settings. We substantiate our findings with theoretical analysis, providing novel perspectives for utilizing AIF in the design of artificial agents. Experimental results demonstrate the superior learning capabilities of our method in solving continuous space partially observable tasks. Notably, our approach harnesses information-seeking exploration, enabling it to effectively solve reward-free problems and rendering explicit task reward design by an external supervisor optional.
Authors: Vincent Zhihao Zheng, Seongjin Choi, Lijun Sun
Abstract: Deep learning models for traffic forecasting often assume the residual is independent and isotropic across time and space. This assumption simplifies loss functions such as mean absolute error, but real-world residual processes often exhibit significant autocorrelation and structured spatiotemporal correlation. This paper introduces a dynamic regression (DR) framework to enhance existing spatiotemporal traffic forecasting models by incorporating structured learning for the residual process. We assume the residual of the base model (i.e., a well-developed traffic forecasting model) follows a matrix-variate seasonal autoregressive (AR) model, which is seamlessly integrated into the training process through the redesign of the loss function. Importantly, the parameters of the DR framework are jointly optimized alongside the base model. We evaluate the effectiveness of the proposed framework on state-of-the-art (SOTA) deep traffic forecasting models using both speed and flow datasets, demonstrating improved performance and providing interpretable AR coefficients and spatiotemporal covariance matrices.
Authors: Shuze Liu, Shangtong Zhang
Abstract: Most reinforcement learning practitioners evaluate their policies with online Monte Carlo estimators for either hyperparameter tuning or testing different algorithmic design choices, where the policy is repeatedly executed in the environment to get the average outcome. Such massive interactions with the environment are prohibitive in many scenarios. In this paper, we propose novel methods that improve the data efficiency of online Monte Carlo estimators while maintaining their unbiasedness. We first propose a tailored closed-form behavior policy that provably reduces the variance of an online Monte Carlo estimator. We then design efficient algorithms to learn this closed-form behavior policy from previously collected offline data. Theoretical analysis is provided to characterize how the behavior policy learning error affects the amount of reduced variance. Compared with previous works, our method achieves better empirical performance in a broader set of environments, with fewer requirements for offline data.
Authors: Xinwen Zhang, Yihan Zhang, Tianbao Yang, Richard Souvenir, Hongchang Gao
Abstract: Federated learning has attracted increasing attention due to the promise of balancing privacy and large-scale learning; numerous approaches have been proposed. However, most existing approaches focus on problems with balanced data, and prediction performance is far from satisfactory for many real-world applications where the number of samples in different classes is highly imbalanced. To address this challenging problem, we developed a novel federated learning method for imbalanced data by directly optimizing the area under curve (AUC) score. In particular, we formulate the AUC maximization problem as a federated compositional minimax optimization problem, develop a local stochastic compositional gradient descent ascent with momentum algorithm, and provide bounds on the computational and communication complexities of our algorithm. To the best of our knowledge, this is the first work to achieve such favorable theoretical results. Finally, extensive experimental results confirm the efficacy of our method.
Authors: Haohui Wang, Yuzhen Mao, Yujun Yan, Yaoqing Yang, Jianhui Sun, Kevin Choi, Balaji Veeramani, Alison Hu, Edward Bowen, Tyler Cody, Dawei Zhou
Abstract: Non-IID transfer learning on graphs is crucial in many high-stakes domains. The majority of existing works assume stationary distribution for both source and target domains. However, real-world graphs are intrinsically dynamic, presenting challenges in terms of domain evolution and dynamic discrepancy between source and target domains. To bridge the gap, we shift the problem to the dynamic setting and pose the question: given the label-rich source graphs and the label-scarce target graphs both observed in previous T timestamps, how can we effectively characterize the evolving domain discrepancy and optimize the generalization performance of the target domain at the incoming T+1 timestamp? To answer it, we propose a generalization bound for dynamic non-IID transfer learning on graphs, which implies the generalization performance is dominated by domain evolution and domain discrepancy between source and target graphs. Inspired by the theoretical results, we introduce a novel generic framework named EvoluNet. It leverages a transformer-based temporal encoding module to model temporal information of the evolving domains and then uses a dynamic domain unification module to efficiently learn domain-invariant representations across the source and target domains. Finally, EvoluNet outperforms the state-of-the-art models by up to 12.1%, demonstrating its effectiveness in transferring knowledge from dynamic source graphs to dynamic target graphs.
Authors: Tailin Zhou, Zehong Lin, Jun Zhang, Danny H. K. Tsang
Abstract: Model averaging is a widely adopted technique in federated learning (FL) that aggregates multiple client models to obtain a global model. Remarkably, model averaging in FL yields a superior global model, even when client models are trained with non-convex objective functions and on heterogeneous local datasets. However, the rationale behind its success remains poorly understood. To shed light on this issue, we first visualize the loss landscape of FL over client and global models to illustrate their geometric properties. The visualization shows that the client models encompass the global model within a common basin, and interestingly, the global model may deviate from the basin's center while still outperforming the client models. To gain further insights into model averaging in FL, we decompose the expected loss of the global model into five factors related to the client models. Specifically, our analysis reveals that the global model loss after early training mainly arises from \textit{i)} the client model's loss on non-overlapping data between client datasets and the global dataset and \textit{ii)} the maximum distance between the global and client models. Based on the findings from our loss landscape visualization and loss decomposition, we propose utilizing iterative moving averaging (IMA) on the global model at the late training phase to reduce its deviation from the expected minimum, while constraining client exploration to limit the maximum distance between the global and client models. Our experiments demonstrate that incorporating IMA into existing FL methods significantly improves their accuracy and training speed on various heterogeneous data setups of benchmark datasets. Code is available at \url{https://github.com/TailinZhou/FedIMA}.
Authors: Haohui Wang, Baoyu Jing, Kaize Ding, Yada Zhu, Wei Cheng, Si Zhang, Yonghui Fan, Liqing Zhang, Dawei Zhou
Abstract: In the context of long-tail classification on graphs, the vast majority of existing work primarily revolves around the development of model debiasing strategies, intending to mitigate class imbalances and enhance the overall performance. Despite the notable success, there is very limited literature that provides a theoretical tool for characterizing the behaviors of long-tail classes in graphs and gaining insight into generalization performance in real-world scenarios. To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i.e., each task corresponds to the prediction of one particular class. Our theoretical results show that the generalization performance of long-tail classification is dominated by the overall loss range and the task complexity. Building upon the theoretical findings, we propose a novel generic framework HierTail for long-tail classification on graphs. In particular, we start with a hierarchical task grouping module that allows us to assign related tasks into hypertasks and thus control the complexity of the task space; then, we further design a balanced contrastive learning module to adaptively balance the gradients of both head and tail classes to control the loss range across all tasks in a unified fashion. Extensive experiments demonstrate the effectiveness of HierTail in characterizing long-tail classes on real graphs, which achieves up to 12.9% improvement over the leading baseline method in accuracy.
Authors: Harikrishnan N B, Arham Jain, Nithin Nagaraj
Abstract: Decision Tree is a well understood Machine Learning model that is based on minimizing impurities in the internal nodes. The most common impurity measures are Shannon entropy and Gini impurity. These impurity measures are insensitive to the order of training data and hence the final tree obtained is invariant to any permutation of the data. This is a limitation in terms of modeling when there are temporal order dependencies between data instances. In this research, we propose the adoption of Effort-To-Compress (ETC) - a complexity measure, for the first time, as an alternative impurity measure. Unlike Shannon entropy and Gini impurity, structural impurity based on ETC is able to capture order dependencies in the data, thus obtaining potentially different decision trees for different permutations of the same data instances, a concept we term as Permutation Decision Trees (PDT). We then introduce the notion of Permutation Bagging achieved using permutation decision trees without the need for random feature selection and sub-sampling. We conduct a performance comparison between Permutation Decision Trees and classical decision trees across various real-world datasets, including Appendicitis, Breast Cancer Wisconsin, Diabetes Pima Indian, Ionosphere, Iris, Sonar, and Wine. Our findings reveal that PDT demonstrates comparable performance to classical decision trees across most datasets. Remarkably, in certain instances, PDT even slightly surpasses the performance of classical decision trees. In comparing Permutation Bagging with Random Forest, we attain comparable performance to Random Forest models consisting of 50 to 1000 trees, using merely 21 trees. This highlights the efficiency and effectiveness of Permutation Bagging in achieving comparable performance outcomes with significantly fewer trees.
Authors: Hongchang Gao
Abstract: Stochastic multi-level compositional optimization problems cover many new machine learning paradigms, e.g., multi-step model-agnostic meta-learning, which require efficient optimization algorithms for large-scale data. This paper studies the decentralized stochastic multi-level optimization algorithm, which is challenging because the multi-level structure and decentralized communication scheme may make the number of levels significantly affect the order of the convergence rate. To this end, we develop two novel decentralized optimization algorithms to optimize the multi-level compositional optimization problem. Our theoretical results show that both algorithms can achieve the level-independent convergence rate for nonconvex problems under much milder conditions compared with existing single-machine algorithms. To the best of our knowledge, this is the first work that achieves the level-independent convergence rate under the decentralized setting. Moreover, extensive experiments confirm the efficacy of our proposed algorithms.
Authors: Thu Trang Nguyen, Thach Le Nguyen, Georgiana Ifrim
Abstract: Time series classification is a task which deals with temporal sequences, a prevalent data type common in domains such as human activity recognition, sports analytics and general sensing. In this area, interest in explainability has been growing as explanation is key to understand the data and the model better. Recently, a great variety of techniques have been proposed and adapted for time series to provide explanation in the form of saliency maps, where the importance of each data point in the time series is quantified with a numerical value. However, the saliency maps can and often disagree, so it is unclear which one to use. This paper provides a novel framework to quantitatively evaluate and rank explanation methods for time series classification. We show how to robustly evaluate the informativeness of a given explanation method (i.e., relevance for the classification task), and how to compare explanations side-by-side. The goal is to recommend the best explainer for a given time series classification dataset. We propose AMEE, a Model-Agnostic Explanation Evaluation framework, for recommending saliency-based explanations for time series classification. In this approach, data perturbation is added to the input time series guided by each explanation. Our results show that perturbing discriminative parts of the time series leads to significant changes in classification accuracy, which can be used to evaluate each explanation. To be robust to different types of perturbations and different types of classifiers, we aggregate the accuracy loss across perturbations and classifiers. This novel approach allows us to recommend the best explainer among a set of different explainers, including random and oracle explainers. We provide a quantitative and qualitative analysis for synthetic datasets, a variety of timeseries datasets, as well as a real-world case study with known expert ground truth.
Authors: Jos\'e Ram\'on Pareja Monturiol, David P\'erez-Garc\'ia, Alejandro Pozas-Kerstjens
Abstract: Tensor networks are factorizations of high-dimensional tensors into networks of smaller tensors. They have applications in physics and mathematics, and recently have been proposed as promising machine learning architectures. To ease the integration of tensor networks in machine learning pipelines, we introduce TensorKrowch, an open source Python library built on top of PyTorch. Providing a user-friendly interface, TensorKrowch allows users to construct any tensor network, train it, and integrate it as a layer in more intricate deep learning models. In this paper, we describe the main functionality and basic usage of TensorKrowch, and provide technical details on its building blocks and the optimizations performed to achieve efficient operation.
Authors: Hiroki Naganuma, Ryuichiro Hataya, Ioannis Mitliagkas
Abstract: In out-of-distribution (OOD) generalization tasks, fine-tuning pre-trained models has become a prevalent strategy. Different from most prior work that has focused on advancing learning algorithms, we systematically examined how pre-trained model size, pre-training dataset size, and training strategies impact generalization and uncertainty calibration on downstream tasks. We evaluated 100 models across diverse pre-trained model sizes, \update{five} pre-training datasets, and five data augmentations through extensive experiments on four distribution shift datasets totaling over 120,000 GPU hours. Our results demonstrate the significant impact of pre-trained model selection, with optimal choices substantially improving OOD accuracy over algorithm improvement alone. We find larger models and bigger pre-training data improve OOD performance and calibration, in contrast to some prior studies that found modern deep networks to calibrate worse than classical shallow models. Our work underscores the overlooked importance of pre-trained model selection for out-of-distribution generalization and calibration.
Authors: Shikai Fang, Qingsong Wen, Yingtao Luo, Shandian Zhe, Liang Sun
Abstract: In real-world scenarios like traffic and energy, massive time-series data with missing values and noises are widely observed, even sampled irregularly. While many imputation methods have been proposed, most of them work with a local horizon, which means models are trained by splitting the long sequence into batches of fit-sized patches. This local horizon can make models ignore global trends or periodic patterns. More importantly, almost all methods assume the observations are sampled at regular time stamps, and fail to handle complex irregular sampled time series arising from different applications. Thirdly, most existing methods are learned in an offline manner. Thus, it is not suitable for many applications with fast-arriving streaming data. To overcome these limitations, we propose BayOTIDE: Bayesian Online Multivariate Time series Imputation with functional decomposition. We treat the multivariate time series as the weighted combination of groups of low-rank temporal factors with different patterns. We apply a group of Gaussian Processes (GPs) with different kernels as functional priors to fit the factors. For computational efficiency, we further convert the GPs into a state-space prior by constructing an equivalent stochastic differential equation (SDE), and developing a scalable algorithm for online inference. The proposed method can not only handle imputation over arbitrary time stamps, but also offer uncertainty quantification and interpretability for the downstream application. We evaluate our method on both synthetic and real-world datasets.We release the code at {https://github.com/xuangu-fang/BayOTIDE}
Authors: Ruocheng Wang, Eric Zelikman, Gabriel Poesia, Yewen Pu, Nick Haber, Noah D. Goodman
Abstract: Inductive reasoning is a core problem-solving capacity: humans can identify underlying principles from a few examples, which robustly generalize to novel scenarios. Recent work evaluates large language models (LLMs) on inductive reasoning tasks by directly prompting them yielding "in context learning." This works well for straightforward inductive tasks but performs poorly on complex tasks such as the Abstraction and Reasoning Corpus (ARC). In this work, we propose to improve the inductive reasoning ability of LLMs by generating explicit hypotheses at multiple levels of abstraction: we prompt the LLM to propose multiple abstract hypotheses about the problem, in natural language, then implement the natural language hypotheses as concrete Python programs. These programs can be verified by running on observed examples and generalized to novel inputs. To reduce the hypothesis search space, we explore steps to filter the set of hypotheses to implement: we either ask the LLM to summarize them into a smaller set of hypotheses or ask human annotators to select a subset. We verify our pipeline's effectiveness on the ARC visual inductive reasoning benchmark, its variant 1D-ARC, string transformation dataset SyGuS, and list transformation dataset List Functions. On a random 100-problem subset of ARC, our automated pipeline using LLM summaries achieves 30% accuracy, outperforming the direct prompting baseline (accuracy of 17%). With the minimal human input of selecting from LLM-generated candidates, performance is boosted to 33%. Our ablations show that both abstract hypothesis generation and concrete program representations benefit LLMs on inductive reasoning tasks.
Authors: Juan Elenter, Navid NaderiAlizadeh, Tara Javidi, Alejandro Ribeiro
Abstract: Continual learning is inherently a constrained learning problem. The goal is to learn a predictor under a no-forgetting requirement. Although several prior studies formulate it as such, they do not solve the constrained problem explicitly. In this work, we show that it is both possible and beneficial to undertake the constrained optimization problem directly. To do this, we leverage recent results in constrained learning through Lagrangian duality. We focus on memory-based methods, where a small subset of samples from previous tasks can be stored in a replay buffer. In this setting, we analyze two versions of the continual learning problem: a coarse approach with constraints at the task level and a fine approach with constraints at the sample level. We show that dual variables indicate the sensitivity of the optimal value of the continual learning problem with respect to constraint perturbations. We then leverage this result to partition the buffer in the coarse approach, allocating more resources to harder tasks, and to populate the buffer in the fine approach, including only impactful samples. We derive a deviation bound on dual variables as sensitivity indicators, and empirically corroborate this result in diverse continual learning benchmarks. We also discuss the limitations of these methods with respect to the amount of memory available and the expressiveness of the parametrization.
Authors: Pierre-Olivier C\^ot\'e, Amin Nikanjam, Nafisa Ahmed, Dmytro Humeniuk, Foutse Khomh
Abstract: Context: Machine Learning (ML) is integrated into a growing number of systems for various applications. Because the performance of an ML model is highly dependent on the quality of the data it has been trained on, there is a growing interest in approaches to detect and repair data errors (i.e., data cleaning). Researchers are also exploring how ML can be used for data cleaning; hence creating a dual relationship between ML and data cleaning. To the best of our knowledge, there is no study that comprehensively reviews this relationship. Objective: This paper's objectives are twofold. First, it aims to summarize the latest approaches for data cleaning for ML and ML for data cleaning. Second, it provides future work recommendations. Method: We conduct a systematic literature review of the papers published between 2016 and 2022 inclusively. We identify different types of data cleaning activities with and for ML: feature cleaning, label cleaning, entity matching, outlier detection, imputation, and holistic data cleaning. Results: We summarize the content of 101 papers covering various data cleaning activities and provide 24 future work recommendations. Our review highlights many promising data cleaning techniques that can be further extended. Conclusion: We believe that our review of the literature will help the community develop better approaches to clean data.
Authors: Xiaoqiang Lin, Zhaoxuan Wu, Zhongxiang Dai, Wenyang Hu, Yao Shu, See-Kiong Ng, Patrick Jaillet, Bryan Kian Hsiang Low
Abstract: Large language models (LLMs) have shown remarkable instruction-following capabilities and achieved impressive performances in various applications. However, the performances of LLMs depend heavily on the instructions given to them, which are typically manually tuned with substantial human efforts. Recent work has used the query-efficient Bayesian optimization (BO) algorithm to automatically optimize the instructions given to black-box LLMs. However, BO usually falls short when optimizing highly sophisticated (e.g., high-dimensional) objective functions, such as the functions mapping an instruction to the performance of an LLM. This is mainly due to the limited expressive power of the Gaussian process (GP) which is used by BO as a surrogate to model the objective function. Meanwhile, it has been repeatedly shown that neural networks (NNs), especially pre-trained transformers, possess strong expressive power and can model highly complex functions. So, we adopt a neural bandit algorithm which replaces the GP in BO by an NN surrogate to optimize instructions for black-box LLMs. More importantly, the neural bandit algorithm allows us to naturally couple the NN surrogate with the hidden representation learned by a pre-trained transformer (i.e., an open-source LLM), which significantly boosts its performance. These motivate us to propose our INSTruction optimization usIng Neural bandits Coupled with Transformers (INSTINCT) algorithm. We perform instruction optimization for ChatGPT and use extensive experiments to show that INSTINCT consistently outperforms baselines in different tasks, e.g., various instruction induction tasks and the task of improving zero-shot chain-of-thought instructions. Our code is available at https://github.com/xqlin98/INSTINCT.
Authors: Hannes St\"ark, Bowen Jing, Regina Barzilay, Tommi Jaakkola
Abstract: A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket's discrete residue types and the molecule's binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches.
Authors: Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik, Nadav Dym, Haggai Maron
Abstract: Permutation symmetries of deep networks make basic operations like model merging and similarity estimation challenging. In many cases, aligning the weights of the networks, i.e., finding optimal permutations between their weights, is necessary. Unfortunately, weight alignment is an NP-hard problem. Prior research has mainly focused on solving relaxed versions of the alignment problem, leading to either time-consuming methods or sub-optimal solutions. To accelerate the alignment process and improve its quality, we propose a novel framework aimed at learning to solve the weight alignment problem, which we name Deep-Align. To that end, we first prove that weight alignment adheres to two fundamental symmetries and then, propose a deep architecture that respects these symmetries. Notably, our framework does not require any labeled data. We provide a theoretical analysis of our approach and evaluate Deep-Align on several types of network architectures and learning setups. Our experimental results indicate that a feed-forward pass with Deep-Align produces better or equivalent alignments compared to those produced by current optimization algorithms. Additionally, our alignments can be used as an effective initialization for other methods, leading to improved solutions with a significant speedup in convergence.
Authors: Megh Shukla, Mathieu Salzmann, Alexandre Alahi
Abstract: Deep heteroscedastic regression involves jointly optimizing the mean and covariance of the predicted distribution using the negative log-likelihood. However, recent works show that this may result in sub-optimal convergence due to the challenges associated with covariance estimation. While the literature addresses this by proposing alternate formulations to mitigate the impact of the predicted covariance, we focus on improving the predicted covariance itself. We study two questions: (1) Does the predicted covariance truly capture the randomness of the predicted mean? (2) In the absence of supervision, how can we quantify the accuracy of covariance estimation? We address (1) with a Taylor Induced Covariance (TIC), which captures the randomness of the predicted mean by incorporating its gradient and curvature through the second order Taylor polynomial. Furthermore, we tackle (2) by introducing a Task Agnostic Correlations (TAC) metric, which combines the notion of correlations and absolute error to evaluate the covariance. We evaluate TIC-TAC across multiple experiments spanning synthetic and real-world datasets. Our results show that not only does TIC accurately learn the covariance, it additionally facilitates an improved convergence of the negative log-likelihood. Our code is available at https://github.com/vita-epfl/TIC-TAC
Authors: Litian Liu, Yao Qin
Abstract: Efficient and versatile Out-of-Distribution (OOD) detection is essential for the safe deployment of AI yet remains challenging for existing algorithms. Inspired by Neural Collapse, we discover that features of in-distribution (ID) samples cluster closer to the weight vectors compared to features of OOD samples. In addition, we reveal that ID features tend to expand in space to structure a simplex Equiangular Tight Framework, which nicely explains the prevalent observation that ID features reside further from the origin than OOD features. Taking both insights from Neural Collapse into consideration, we propose to leverage feature proximity to weight vectors for OOD detection and further complement this perspective by using feature norms to filter OOD samples. Extensive experiments on off-the-shelf models demonstrate the efficiency and effectiveness of our method across diverse classification tasks and model architectures, enhancing the generalization capability of OOD detection.
Authors: Bobby He, Thomas Hofmann
Abstract: A simple design recipe for deep Transformers is to compose identical building blocks. But standard transformer blocks are far from simple, interweaving attention and MLP sub-blocks with skip connections & normalisation layers in precise arrangements. This complexity leads to brittle architectures, where seemingly minor changes can significantly reduce training speed, or render models untrainable. In this work, we ask to what extent the standard transformer block can be simplified? Combining signal propagation theory and empirical observations, we motivate modifications that allow many block components to be removed with no loss of training speed, including skip connections, projection or value parameters, sequential sub-blocks and normalisation layers. In experiments on both autoregressive decoder-only and BERT encoder-only models, our simplified transformers emulate the per-update training speed and performance of standard transformers, while enjoying 15% faster training throughput, and using 15% fewer parameters.
Authors: Stella Ho, Ming Liu, Shang Gao, Longxiang Gao
Abstract: Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP domain. In this work, we consider a few-shot continual active learning setting where labeled data are inadequate, and unlabeled data are abundant but with a limited annotation budget. We exploit meta-learning and propose a method, called Meta-Continual Active Learning. This method sequentially queries the most informative examples from a pool of unlabeled data for annotation to enhance task-specific performance and tackle continual learning problems through meta-objective. Specifically, we employ meta-learning and experience replay to address inter-task confusion and catastrophic forgetting. We further incorporate textual augmentations to avoid memory over-fitting caused by experience replay and sample queries, thereby ensuring generalization. We conduct extensive experiments on benchmark text classification datasets from diverse domains to validate the feasibility and effectiveness of meta-continual active learning. We also analyze the impact of different active learning strategies on various meta continual learning models. The experimental results demonstrate that introducing randomness into sample selection is the best default strategy for maintaining generalization in meta-continual learning framework.
Authors: Christina Winkler, David Rolnick
Abstract: This study investigates how conditional normalizing flows can be applied to remote sensing data products in climate science for spatio-temporal prediction. The method is chosen due to its desired properties such as exact likelihood computation, predictive uncertainty estimation and efficient inference and sampling which facilitates faster exploration of climate scenarios. Experimental findings reveal that the conditioned spatio-temporal flow surpasses both deterministic and stochastic baselines in prolonged rollout scenarios. It exhibits stable extrapolation beyond the training time horizon for extended rollout durations. These findings contribute valuable insights to the field of spatio-temporal modeling, with potential applications spanning diverse scientific disciplines.
Authors: Shyam Venkatasubramanian, Ahmed Aloui, Vahid Tarokh
Abstract: Advancing loss function design is pivotal for optimizing neural network training and performance. This work introduces Random Linear Projections (RLP) loss, a novel approach that enhances training efficiency by leveraging geometric relationships within the data. Distinct from traditional loss functions that target minimizing pointwise errors, RLP loss operates by minimizing the distance between sets of hyperplanes connecting fixed-size subsets of feature-prediction pairs and feature-label pairs. Our empirical evaluations, conducted across benchmark datasets and synthetic examples, demonstrate that neural networks trained with RLP loss outperform those trained with traditional loss functions, achieving improved performance with fewer data samples, and exhibiting greater robustness to additive noise. We provide theoretical analysis supporting our empirical findings.
Authors: Albert Gu, Tri Dao
Abstract: Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention, gated convolution and recurrent models, and structured state space models (SSMs) have been developed to address Transformers' computational inefficiency on long sequences, but they have not performed as well as attention on important modalities such as language. We identify that a key weakness of such models is their inability to perform content-based reasoning, and make several improvements. First, simply letting the SSM parameters be functions of the input addresses their weakness with discrete modalities, allowing the model to selectively propagate or forget information along the sequence length dimension depending on the current token. Second, even though this change prevents the use of efficient convolutions, we design a hardware-aware parallel algorithm in recurrent mode. We integrate these selective SSMs into a simplified end-to-end neural network architecture without attention or even MLP blocks (Mamba). Mamba enjoys fast inference (5$\times$ higher throughput than Transformers) and linear scaling in sequence length, and its performance improves on real data up to million-length sequences. As a general sequence model backbone, Mamba achieves state-of-the-art performance across several modalities such as language, audio, and genomics. On language modeling, our Mamba-3B model outperforms Transformers of the same size and matches Transformers twice its size, both in pretraining and downstream evaluation.
Authors: Jeongwhan Choi, Hyowon Wi, Jayoung Kim, Yehjin Shin, Kookjin Lee, Nathaniel Trask, Noseong Park
Abstract: Transformers, renowned for their self-attention mechanism, have achieved state-of-the-art performance across various tasks in natural language processing, computer vision, time-series modeling, etc. However, one of the challenges with deep Transformer models is the oversmoothing problem, where representations across layers converge to indistinguishable values, leading to significant performance degradation. We interpret the original self-attention as a simple graph filter and redesign it from a graph signal processing (GSP) perspective. We propose a graph-filter-based self-attention (GFSA) to learn a general yet effective one, whose complexity, however, is slightly larger than that of the original self-attention mechanism. We demonstrate that GFSA improves the performance of Transformers in various fields, including computer vision, natural language processing, graph regression, speech recognition, and code classification.
Authors: Seonguk Seo, Jinkyu Kim, Geeho Kim, Bohyung Han
Abstract: We propose a novel contrastive learning framework to effectively address the challenges of data heterogeneity in federated learning. We first analyze the inconsistency of gradient updates across clients during local training and establish its dependence on the distribution of feature representations, leading to the derivation of the supervised contrastive learning (SCL) objective to mitigate local deviations. In addition, we show that a na\"ive adoption of SCL in federated learning leads to representation collapse, resulting in slow convergence and limited performance gains. To address this issue, we introduce a relaxed contrastive learning loss that imposes a divergence penalty on excessively similar sample pairs within each class. This strategy prevents collapsed representations and enhances feature transferability, facilitating collaborative training and leading to significant performance improvements. Our framework outperforms all existing federated learning approaches by huge margins on the standard benchmarks through extensive experimental results.
Authors: Yuta Kawakami, Manabu Kuroki, Jin Tian
Abstract: There has been considerable recent interest in estimating heterogeneous causal effects. In this paper, we study conditional average partial causal effects (CAPCE) to reveal the heterogeneity of causal effects with continuous treatment. We provide conditions for identifying CAPCE in an instrumental variable setting. Notably, CAPCE is identifiable under a weaker assumption than required by a commonly used measure for estimating heterogeneous causal effects of continuous treatment. We develop three families of CAPCE estimators: sieve, parametric, and reproducing kernel Hilbert space (RKHS)-based, and analyze their statistical properties. We illustrate the proposed CAPCE estimators on synthetic and real-world data.
Authors: Logan Hallee, Rohan Kapur, Arjun Patel, Jason P. Gleghorn, Bohdan Khomtchouk
Abstract: The advancement of transformer neural networks has significantly elevated the capabilities of sentence similarity models, but they struggle with highly discriminative tasks and produce sub-optimal representations of important documents like scientific literature. With the increased reliance on retrieval augmentation and search, representing diverse documents as concise and descriptive vectors is crucial. This paper improves upon the vectors embeddings of scientific literature by assembling niche datasets using co-citations as a similarity metric, focusing on biomedical domains. We apply a novel Mixture of Experts (MoE) extension pipeline to pretrained BERT models, where every multi-layer perceptron section is enlarged and copied into multiple distinct experts. Our MoE variants perform well over $N$ scientific domains with $N$ dedicated experts, whereas standard BERT models excel in only one domain. Notably, extending just a single transformer block to MoE captures 85% of the benefit seen from full MoE extension at every layer. This holds promise for versatile and efficient One-Size-Fits-All transformer networks for numerically representing diverse inputs. Our methodology marks significant advancements in representing scientific text and holds promise for enhancing vector database search and compilation.
Authors: Haitao Mao, Zhikai Chen, Wenzhuo Tang, Jianan Zhao, Yao Ma, Tong Zhao, Neil Shah, Mikhail Galkin, Jiliang Tang
Abstract: Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a ``graph vocabulary'', in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, expressiveness, and stability. Such a vocabulary perspective can potentially advance the future GFM design in line with the neural scaling laws. All relevant resources with GFM design can be found here.
Authors: Haibo Jin, Ruoxi Chen, Andy Zhou, Yang Zhang, Haohan Wang
Abstract: The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with jailbreaks prior to the release. Therefore, such testing will require a method that can generate jailbreaks massively and efficiently. In this paper, we follow a novel yet intuitive strategy to generate jailbreaks in the style of the human generation. We propose a role-playing system that assigns four different roles to the user LLMs to collaborate on new jailbreaks. Furthermore, we collect existing jailbreaks and split them into different independent characteristics using clustering frequency and semantic patterns sentence by sentence. We organize these characteristics into a knowledge graph, making them more accessible and easier to retrieve. Our system of different roles will leverage this knowledge graph to generate new jailbreaks, which have proved effective in inducing LLMs to generate unethical or guideline-violating responses. In addition, we also pioneer a setting in our system that will automatically follow the government-issued guidelines to generate jailbreaks to test whether LLMs follow the guidelines accordingly. We refer to our system as GUARD (Guideline Upholding through Adaptive Role-play Diagnostics). We have empirically validated the effectiveness of GUARD on three cutting-edge open-sourced LLMs (Vicuna-13B, LongChat-7B, and Llama-2-7B), as well as a widely-utilized commercial LLM (ChatGPT). Moreover, our work extends to the realm of vision language models (MiniGPT-v2 and Gemini Vision Pro), showcasing GUARD's versatility and contributing valuable insights for the development of safer, more reliable LLM-based applications across diverse modalities.
Authors: Lunyiu Nie, Zhimin Ding, Erdong Hu, Christopher Jermaine, Swarat Chaudhuri
Abstract: Large Language Models (LLMs) have a natural role in answering complex queries about data streams, but the high computational cost of LLM inference makes them infeasible in many such tasks. We propose online cascade learning, the first approach to address this challenge. The objective here is to learn a "cascade" of models, starting with lower-capacity models (such as logistic regression) and ending with a powerful LLM, along with a deferral policy that determines the model to be used on a given input. We formulate the task of learning cascades online as an imitation-learning problem, where smaller models are updated over time imitating the collected LLM demonstrations, and give a no-regret algorithm for the problem. Experimental results across four benchmarks show that our method parallels LLMs in accuracy while cutting down inference costs by as much as 90% with strong robustness against input distribution shifts, underscoring its efficacy and adaptability in stream processing.
Authors: Elvis Dohmatob, Yunzhen Feng, Pu Yang, Francois Charton, Julia Kempe
Abstract: As AI model size grows, neural scaling laws have become a crucial tool to predict the improvements of large models when increasing capacity and the size of original (human or natural) training data. Yet, the widespread use of popular models means that the ecosystem of online data and text will co-evolve to progressively contain increased amounts of synthesized data. In this paper we ask: How will the scaling laws change in the inevitable regime where synthetic data makes its way into the training corpus? Will future models, still improve, or be doomed to degenerate up to total (model) collapse? We develop a theoretical framework of model collapse through the lens of scaling laws. We discover a wide range of decay phenomena, analyzing loss of scaling, shifted scaling with number of generations, the ''un-learning" of skills, and grokking when mixing human and synthesized data. Our theory is validated by large-scale experiments with a transformer on an arithmetic task and text generation using the large language model Llama2.
Authors: Keitaro Sakamoto, Issei Sato
Abstract: End-to-end (E2E) training, optimizing the entire model through error backpropagation, fundamentally supports the advancements of deep learning. Despite its high performance, E2E training faces the problems of memory consumption, parallel computing, and discrepancy with the functionalities of the actual brain. Various alternative methods have been proposed to overcome these difficulties; however, no one can yet match the performance of E2E training, thereby falling short in practicality. Furthermore, there is no deep understanding regarding differences in the trained model properties beyond the performance gap. In this paper, we reconsider why E2E training demonstrates a superior performance through a comparison with layer-wise training, a non-E2E method that locally sets errors. On the basis of the observation that E2E training has an advantage in propagating input information, we analyze the information plane dynamics of intermediate representations based on the Hilbert-Schmidt independence criterion (HSIC). The results of our normalized HSIC value analysis reveal the E2E training ability to exhibit different information dynamics across layers, in addition to efficient information propagation. Furthermore, we show that this layer-role differentiation leads to the final representation following the information bottleneck principle. It suggests the need to consider the cooperative interactions between layers, not just the final layer when analyzing the information bottleneck of deep learning.
Authors: Ben Rank, Stelios Triantafyllou, Debmalya Mandal, Goran Radanovic
Abstract: When Reinforcement Learning (RL) agents are deployed in practice, they might impact their environment and change its dynamics. We propose a new framework to model this phenomenon, where the current environment depends on the deployed policy as well as its previous dynamics. This is a generalization of Performative RL (PRL) [Mandal et al., 2023]. Unlike PRL, our framework allows to model scenarios where the environment gradually adjusts to a deployed policy. We adapt two algorithms from the performative prediction literature to our setting and propose a novel algorithm called Mixed Delayed Repeated Retraining (MDRR). We provide conditions under which these algorithms converge and compare them using three metrics: number of retrainings, approximation guarantee, and number of samples per deployment. MDRR is the first algorithm in this setting which combines samples from multiple deployments in its training. This makes MDRR particularly suitable for scenarios where the environment's response strongly depends on its previous dynamics, which are common in practice. We experimentally compare the algorithms using a simulation-based testbed and our results show that MDRR converges significantly faster than previous approaches.
Authors: Yuchen Liang, Peizhong Ju, Yingbin Liang, Ness Shroff
Abstract: The denoising diffusion model has recently emerged as a powerful generative technique that converts noise into data. While there are many studies providing theoretical guarantees for diffusion processes based on discretized stochastic differential equation (D-SDE), many generative samplers in real applications directly employ a discrete-time (DT) diffusion process. However, there are very few studies analyzing these DT processes, e.g., convergence for DT diffusion processes has been obtained only for distributions with bounded support. In this paper, we establish the convergence guarantee for substantially larger classes of distributions under DT diffusion processes and further improve the convergence rate for distributions with bounded support. In particular, we first establish the convergence rates for both smooth and general (possibly non-smooth) distributions having a finite second moment. We then specialize our results to a number of interesting classes of distributions with explicit parameter dependencies, including distributions with Lipschitz scores, Gaussian mixture distributions, and any distributions with early-stopping. We further propose a novel accelerated sampler and show that it improves the convergence rates of the corresponding regular sampler by orders of magnitude with respect to all system parameters. Our study features a novel analytical technique that constructs a tilting factor representation of the convergence error and exploits Tweedie's formula for handling Taylor expansion power terms.
Authors: Nicola Mariella, Albert Akhriev, Francesco Tacchino, Christa Zoufal, Juan Carlos Gonzalez-Espitia, Benedek Harsanyi, Eugene Koskin, Ivano Tavernelli, Stefan Woerner, Marianna Rapsomaniki, Sergiy Zhuk, Jannis Born
Abstract: Optimal Transport (OT) has fueled machine learning (ML) across many domains. When paired data measurements $(\boldsymbol{\mu}, \boldsymbol{\nu})$ are coupled to covariates, a challenging conditional distribution learning setting arises. Existing approaches for learning a $\textit{global}$ transport map parameterized through a potentially unseen context utilize Neural OT and largely rely on Brenier's theorem. Here, we propose a first-of-its-kind quantum computing formulation for amortized optimization of contextualized transportation plans. We exploit a direct link between doubly stochastic matrices and unitary operators thus unravelling a natural connection between OT and quantum computation. We verify our method (QontOT) on synthetic and real data by predicting variations in cell type distributions conditioned on drug dosage. Importantly we conduct a 24-qubit hardware experiment on a task challenging for classical computers and report a performance that cannot be matched with our classical neural OT approach. In sum, this is a first step toward learning to predict contextualized transportation plans through quantum computing.
Authors: Myung Jun Kim, L\'eo Grinsztajn, Ga\"el Varoquaux
Abstract: Pretrained deep-learning models are the go-to solution for images or text. However, for tabular data the standard is still to train tree-based models. Indeed, transfer learning on tables hits the challenge of data integration: finding correspondences, correspondences in the entries (entity matching) where different words may denote the same entity, correspondences across columns (schema matching), which may come in different orders, names... We propose a neural architecture that does not need such correspondences. As a result, we can pretrain it on background data that has not been matched. The architecture -- CARTE for Context Aware Representation of Table Entries -- uses a graph representation of tabular (or relational) data to process tables with different columns, string embedding of entries and columns names to model an open vocabulary, and a graph-attentional network to contextualize entries with column names and neighboring entries. An extensive benchmark shows that CARTE facilitates learning, outperforming a solid set of baselines including the best tree-based models. CARTE also enables joint learning across tables with unmatched columns, enhancing a small table with bigger ones. CARTE opens the door to large pretrained models for tabular data.
Authors: Dohyeong Kim, Mineui Hong, Jeongho Park, Songhwai Oh
Abstract: In many real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. To address these considerations, we propose a constrained multi-objective RL algorithm named Constrained Multi-Objective Gradient Aggregator (CoMOGA). In the field of multi-objective optimization, managing conflicts between the gradients of the multiple objectives is crucial to prevent policies from converging to local optima. It is also essential to efficiently handle safety constraints for stable training and constraint satisfaction. We address these challenges straightforwardly by treating the maximization of multiple objectives as a constrained optimization problem (COP), where the constraints are defined to improve the original objectives. Existing safety constraints are then integrated into the COP, and the policy is updated using a linear approximation, which ensures the avoidance of gradient conflicts. Despite its simplicity, CoMOGA guarantees optimal convergence in tabular settings. Through various experiments, we have confirmed that preventing gradient conflicts is critical, and the proposed method achieves constraint satisfaction across all tasks.
Authors: Bartosz Cywi\'nski, Kamil Deja, Tomasz Trzci\'nski, Bart{\l}omiej Twardowski, {\L}ukasz Kuci\'nski
Abstract: We introduce GUIDE, a novel continual learning approach that directs diffusion models to rehearse samples at risk of being forgotten. Existing generative strategies combat catastrophic forgetting by randomly sampling rehearsal examples from a generative model. Such an approach contradicts buffer-based approaches where sampling strategy plays an important role. We propose to bridge this gap by incorporating classifier guidance into the diffusion process to produce rehearsal examples specifically targeting information forgotten by a continuously trained model. This approach enables the generation of samples from preceding task distributions, which are more likely to be misclassified in the context of recently encountered classes. Our experimental results show that GUIDE significantly reduces catastrophic forgetting, outperforming conventional random sampling approaches and surpassing recent state-of-the-art methods in continual learning with generative replay.
Authors: Thomas M. Sutter, Yang Meng, Andrea Agostini, Daphn\'e Chopard, Norbert Fortin, Julia E. Vogt, Bahbak Shahbaba, Stephan Mandt
Abstract: Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or both across modalities to learn a shared representation. Such architectures impose hard constraints on the model. In this work, we show that a better latent representation can be obtained by replacing these hard constraints with a soft constraint. We propose a new mixture-of-experts prior, softly guiding each modality's latent representation towards a shared aggregate posterior. This approach results in a superior latent representation and allows each encoding to preserve information better from its uncompressed original features. In extensive experiments on multiple benchmark datasets and two challenging real-world datasets, we show improved learned latent representations and imputation of missing data modalities compared to existing methods.
Authors: Luca Grillotti, Maxence Faldor, Borja G. Le\'on, Antoine Cully
Abstract: A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to solve complex continuous control tasks. However, most approaches return only one solution specialized for a specific problem. We introduce Quality-Diversity Actor-Critic (QDAC), an off-policy actor-critic deep reinforcement learning algorithm that leverages a value function critic and a successor features critic to learn high-performing and diverse behaviors. In this framework, the actor optimizes an objective that seamlessly unifies both critics using constrained optimization to (1) maximize return, while (2) executing diverse skills. Compared with other Quality-Diversity methods, QDAC achieves significantly higher performance and more diverse behaviors on six challenging continuous control locomotion tasks. We also demonstrate that we can harness the learned skills to adapt better than other baselines to five perturbed environments. Finally, qualitative analyses showcase a range of remarkable behaviors: adaptive-intelligent-robotics.github.io/QDAC.
Authors: Yunrui Li, Hao Xu, Pengyu Hong
Abstract: In the dynamic field of nuclear magnetic resonance (NMR) spectroscopy, artificial intelligence (AI) has ushered in a transformative era for molecular studies. AI-driven NMR prediction, powered by advanced machine learning and predictive algorithms, has fundamentally reshaped the interpretation of NMR spectra. This innovation empowers us to forecast spectral patterns swiftly and accurately across a broad spectrum of molecular structures. Furthermore, the advent of generative modeling offers a groundbreaking approach, making it feasible to make informed prediction of 2D NMR from chemical language (such as SMILES, IUPAC Name). Our method mirrors the multifaceted nature of NMR imaging experiments, producing 2D NMRs for the same molecule based on different conditions, such as solvents and temperatures. Our methodology is versatile, catering to both monosaccharide-derived small molecules, oligosaccharides and large polysaccharides. A deeper exploration of the discrepancies in these predictions can provide insights into the influence of elements such as functional groups, repeating units, and the modification of the monomers on the outcomes. Given the complex nature involved in the generation of 2D NMRs, our objective is to fully leverage the potential of AI to enhance the precision, efficiency, and comprehensibility of NMR spectral analysis, ultimately advancing both the field of NMR spectroscopy and the broader realm of molecular research.
Authors: Mohammad Jafari, Yimeng Zhang, Yihua Zhang, Sijia Liu
Abstract: As machine learning tasks continue to evolve, the trend has been to gather larger datasets and train increasingly larger models. While this has led to advancements in accuracy, it has also escalated computational costs to unsustainable levels. Addressing this, our work aims to strike a delicate balance between computational efficiency and model accuracy, a persisting challenge in the field. We introduce a novel method that employs core subset selection for reweighting, effectively optimizing both computational time and model performance. By focusing on a strategically selected coreset, our approach offers a robust representation, as it efficiently minimizes the influence of outliers. The re-calibrated weights are then mapped back to and propagated across the entire dataset. Our experimental results substantiate the effectiveness of this approach, underscoring its potential as a scalable and precise solution for model training.
Authors: Gavin Kerrigan, Giosue Migliorini, Padhraic Smyth
Abstract: We study the geometry of conditional optimal transport (COT) and prove a dynamical formulation which generalizes the Benamou-Brenier Theorem. Equipped with these tools, we propose a simulation-free flow-based method for conditional generative modeling. Our method couples an arbitrary source distribution to a specified target distribution through a triangular COT plan, and a conditional generative model is obtained by approximating the geodesic path of measures induced by this COT plan. Our theory and methods are applicable in infinite-dimensional settings, making them well suited for a wide class of Bayesian inverse problems. Empirically, we demonstrate that our method is competitive on several challenging conditional generation tasks, including an infinite-dimensional inverse problem.
Authors: Subhojyoti Mukherjee, Anusha Lalitha, Aniket Deshmukh, Ge Liu, Yifei Ma, Branislav Kveton
Abstract: One emergent ability of large language models (LLMs) is that query-specific examples can be included in the prompt at inference time. In this work, we use active learning for adaptive prompt design and call it Active In-context Prompt Design (AIPD). We design the LLM prompt by adaptively choosing few-shot examples from a training set to optimize performance on a test set. The training examples are initially unlabeled and we obtain the label of the most informative ones, which maximally reduces uncertainty in the LLM prediction. We propose two algorithms, GO and SAL, which differ in how the few-shot examples are chosen. We analyze these algorithms in linear models: first GO and then use its equivalence with SAL. We experiment with many different tasks in small, medium-sized, and large language models; and show that GO and SAL outperform other methods for choosing few-shot examples in the LLM prompt at inference time.
Authors: Manuel Gloeckler, Michael Deistler, Christian Weilbach, Frank Wood, Jakob H. Macke
Abstract: Amortized Bayesian inference trains neural networks to solve stochastic inference problems using model simulations, thereby making it possible to rapidly perform Bayesian inference for any newly observed data. However, current simulation-based amortized inference methods are simulation-hungry and inflexible: They require the specification of a fixed parametric prior, simulator, and inference tasks ahead of time. Here, we present a new amortized inference method -- the Simformer -- which overcomes these limitations. By training a probabilistic diffusion model with transformer architectures, the Simformer outperforms current state-of-the-art amortized inference approaches on benchmark tasks and is substantially more flexible: It can be applied to models with function-valued parameters, it can handle inference scenarios with missing or unstructured data, and it can sample arbitrary conditionals of the joint distribution of parameters and data, including both posterior and likelihood. We showcase the performance and flexibility of the Simformer on simulators from ecology, epidemiology, and neuroscience, and demonstrate that it opens up new possibilities and application domains for amortized Bayesian inference on simulation-based models.
Authors: Kafeng Wang, Jianfei Chen, He Li, Zhenpeng Mi, Jun Zhu
Abstract: Diffusion models have been extensively used in data generation tasks and are recognized as one of the best generative models. However, their time-consuming deployment, long inference time, and requirements on large memory limit their application on mobile devices. In this paper, we propose a method based on the improved Straight-Through Estimator to improve the deployment efficiency of diffusion models. Specifically, we add sparse masks to the Convolution and Linear layers in a pre-trained diffusion model, then use design progressive sparsity for model training in the fine-tuning stage, and switch the inference mask on and off, which supports a flexible choice of sparsity during inference according to the FID and MACs requirements. Experiments on four datasets conducted on a state-of-the-art Transformer-based diffusion model demonstrate that our method reduces MACs by $50\%$ while increasing FID by only 1.5 on average. Under other MACs conditions, the FID is also lower than 1$\sim$137 compared to other methods.
Authors: Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari, Aniket Deshmukh, Ge Liu, Yifei Ma, Branislav Kveton
Abstract: Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations, we study the problem of data collection for learning preference models. The key idea in our work is to generalize the optimal design, a method for computing information gathering policies, to ranked lists. To show the generality of our ideas, we study both absolute and relative feedback on the lists. We design efficient algorithms for both settings and analyze them. We prove that our preference model estimators improve with more data and so does the ranking error under the estimators. Finally, we experiment with several synthetic and real-world datasets to show the statistical efficiency of our algorithms.
Authors: Jinghan Jia, Yihua Zhang, Yimeng Zhang, Jiancheng Liu, Bharat Runwal, James Diffenderfer, Bhavya Kailkhura, Sijia Liu
Abstract: Large Language Models (LLMs) have highlighted the necessity of effective unlearning mechanisms to comply with data regulations and ethical AI practices. LLM unlearning aims at removing undesired data influences and associated model capabilities without compromising utility out of the scope of unlearning. While interest in studying LLM unlearning is growing,the impact of the optimizer choice for LLM unlearning remains under-explored. In this work, we shed light on the significance of optimizer selection in LLM unlearning for the first time, establishing a clear connection between {second-order optimization} and influence unlearning (a classical approach using influence functions to update the model for data influence removal). This insight propels us to develop a second-order unlearning framework, termed SOUL, built upon the second-order clipped stochastic optimization (Sophia)-based LLM training method. SOUL extends the static, one-shot model update using influence unlearning to a dynamic, iterative unlearning process. Our extensive experiments show that SOUL consistently outperforms conventional first-order methods across various unlearning tasks, models, and metrics, suggesting the promise of second-order optimization in providing a scalable and easily implementable solution for LLM unlearning.
Authors: Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Jiang Bian, Shirui Pan, Qingsong Wen
Abstract: The study of time series data is crucial for understanding trends and anomalies over time, enabling predictive insights across various sectors. Spatio-temporal data, on the other hand, is vital for analyzing phenomena in both space and time, providing a dynamic perspective on complex system interactions. Recently, diffusion models have seen widespread application in time series and spatio-temporal data mining. Not only do they enhance the generative and inferential capabilities for sequential and temporal data, but they also extend to other downstream tasks. In this survey, we comprehensively and thoroughly review the use of diffusion models in time series and spatio-temporal data, categorizing them by model category, task type, data modality, and practical application domain. In detail, we categorize diffusion models into unconditioned and conditioned types and discuss time series data and spatio-temporal data separately. Unconditioned models, which operate unsupervised, are subdivided into probability-based and score-based models, serving predictive and generative tasks such as forecasting, anomaly detection, classification, and imputation. Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks. Our survey extensively covers their application in various fields, including healthcare, recommendation, climate, energy, audio, and transportation, providing a foundational understanding of how these models analyze and generate data. Through this structured overview, we aim to provide researchers and practitioners with a comprehensive understanding of diffusion models for time series and spatio-temporal data analysis, aiming to direct future innovations and applications by addressing traditional challenges and exploring innovative solutions within the diffusion model framework.
Authors: Xiyuan Wang, Pan Li, Muhan Zhang
Abstract: Graph is a fundamental data structure to model interconnections between entities. Set, on the contrary, stores independent elements. To learn graph representations, current Graph Neural Networks (GNNs) primarily use message passing to encode the interconnections. In contrast, this paper introduces a novel graph-to-set conversion method that bijectively transforms interconnected nodes into a set of independent points and then uses a set encoder to learn the graph representation. This conversion method holds dual significance. Firstly, it enables using set encoders to learn from graphs, thereby significantly expanding the design space of GNNs. Secondly, for Transformer, a specific set encoder, we provide a novel and principled approach to inject graph information losslessly, different from all the heuristic structural/positional encoding methods adopted in previous graph transformers. To demonstrate the effectiveness of our approach, we introduce Point Set Transformer (PST), a transformer architecture that accepts a point set converted from a graph as input. Theoretically, PST exhibits superior expressivity for both short-range substructure counting and long-range shortest path distance tasks compared to existing GNNs. Extensive experiments further validate PST's outstanding real-world performance. Besides Transformer, we also devise a Deepset-based set encoder, which achieves performance comparable to representative GNNs, affirming the versatility of our graph-to-set method.
Authors: Shuaipeng Li, Penghao Zhao, Hailin Zhang, Xingwu Sun, Hao Wu, Dian Jiao, Weiyan Wang, Chengjun Liu, Zheng Fang, Jinbao Xue, Yangyu Tao, Bin Cui, Di Wang
Abstract: In current deep learning tasks, Adam style optimizers such as Adam, Adagrad, RMSProp, Adafactor, and Lion have been widely used as alternatives to SGD style optimizers. These optimizers typically update model parameters using the sign of gradients, resulting in more stable convergence curves. The learning rate and the batch size are the most critical hyperparameters for optimizers, which require careful tuning to enable effective convergence. Previous research has shown that the optimal learning rate increases linearly or follows similar rules with batch size for SGD style optimizers. However, this conclusion is not applicable to Adam style optimizers. In this paper, we elucidate the connection between optimal learning rates and batch sizes for Adam style optimizers through both theoretical analysis and extensive experiments. First, we raise the scaling law between batch sizes and optimal learning rates in the sign of gradient case, in which we prove that the optimal learning rate first rises and then falls as the batch size increases. Moreover, the peak value of the surge will gradually move toward the larger batch size as training progresses. Second, we conducted experiments on various CV and NLP tasks and verified the correctness of the scaling law.
Authors: Yiyang Zhou, Zhiyuan Fan, Dongjie Cheng, Sihan Yang, Zhaorun Chen, Chenhang Cui, Xiyao Wang, Yun Li, Linjun Zhang, Huaxiu Yao
Abstract: Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image, indicating a misalignment between image and text pairs. This misalignment arises because the model tends to prioritize textual information over visual input, even when both the language model and visual representations are of high quality. Existing methods leverage additional models or human annotations to curate preference data and enhance modality alignment through preference optimization. These approaches may not effectively reflect the target LVLM's preferences, making the curated preferences easily distinguishable. Our work addresses these challenges by proposing the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning. In the reward modeling, we employ a step-wise strategy and incorporate visual constraints into the self-rewarding process to place greater emphasis on visual input. Empirical results demonstrate that CSR enhances performance and reduces hallucinations across ten benchmarks and tasks, achieving substantial improvements over existing methods by 7.62%. Our empirical results are further supported by rigorous theoretical analysis, under mild assumptions, verifying the effectiveness of introducing visual constraints into the self-rewarding paradigm. Additionally, CSR shows compatibility with different vision-language models and the ability to incrementally improve performance through iterative fine-tuning. Our data and code are available at https://github.com/YiyangZhou/CSR.
Authors: Aaron Defazio (Alice), Xingyu (Alice), Yang, Harsh Mehta, Konstantin Mishchenko, Ahmed Khaled, Ashok Cutkosky
Abstract: Existing learning rate schedules that do not require specification of the optimization stopping step T are greatly out-performed by learning rate schedules that depend on T. We propose an approach that avoids the need for this stopping time by eschewing the use of schedules entirely, while exhibiting state-of-the-art performance compared to schedules across a wide family of problems ranging from convex problems to large-scale deep learning problems. Our Schedule-Free approach introduces no additional hyper-parameters over standard optimizers with momentum. Our method is a direct consequence of a new theory we develop that unifies scheduling and iterate averaging. An open source implementation of our method is available (https://github.com/facebookresearch/schedule_free).
Authors: Wenfei Liang, Yanan Zhao, Rui She, Yiming Li, Wee Peng Tay
Abstract: Personalized subgraph Federated Learning (FL) is a task that customizes Graph Neural Networks (GNNs) to individual client needs, accommodating diverse data distributions. However, applying hypernetworks in FL, while aiming to facilitate model personalization, often encounters challenges due to inadequate representation of client-specific characteristics. To overcome these limitations, we propose a model called FedSheafHN, using enhanced collaboration graph embedding and efficient personalized model parameter generation. Specifically, our model embeds each client's local subgraph into a server-constructed collaboration graph. We utilize sheaf diffusion in the collaboration graph to learn client representations. Our model improves the integration and interpretation of complex client characteristics. Furthermore, our model ensures the generation of personalized models through advanced hypernetworks optimized for parallel operations across clients. Empirical evaluations demonstrate that FedSheafHN outperforms existing methods in most scenarios, in terms of client model performance on various graph-structured datasets. It also has fast model convergence and effective new clients generalization.
Authors: Fredrik D. Johansson
Abstract: Evaluating observational estimators of causal effects demands information that is rarely available: unconfounded interventions and outcomes from the population of interest, created either by randomization or adjustment. As a result, it is customary to fall back on simulators when creating benchmark tasks. Simulators offer great control but are often too simplistic to make challenging tasks, either because they are hand-designed and lack the nuances of real-world data, or because they are fit to observational data without structural constraints. In this work, we propose a general, repeatable strategy for turning observational data into sequential structural causal models and challenging estimation tasks by following two simple principles: 1) fitting real-world data where possible, and 2) creating complexity by composing simple, hand-designed mechanisms. We implement these ideas in a highly configurable software package and apply it to the well-known Adult income data set to construct the \tt IncomeSCM simulator. From this, we devise multiple estimation tasks and sample data sets to compare established estimators of causal effects. The tasks present a suitable challenge, with effect estimates varying greatly in quality between methods, despite similar performance in the modeling of factual outcomes, highlighting the need for dedicated causal estimators and model selection criteria.
Authors: Mohammad Mahdi Maheri, Sandra Siby, Sina Abdollahi, Anastasia Borovykh, Hamed Haddadi
Abstract: Personalized learning is a proposed approach to address the problem of data heterogeneity in collaborative machine learning. In a decentralized setting, the two main challenges of personalization are client clustering and data privacy. In this paper, we address these challenges by developing P4 (Personalized Private Peer-to-Peer) a method that ensures that each client receives a personalized model while maintaining differential privacy guarantee of each client's local dataset during and after the training. Our approach includes the design of a lightweight algorithm to identify similar clients and group them in a private, peer-to-peer (P2P) manner. Once grouped, we develop differentially-private knowledge distillation for clients to co-train with minimal impact on accuracy. We evaluate our proposed method on three benchmark datasets (FEMNIST or Federated EMNIST, CIFAR-10 and CIFAR-100) and two different neural network architectures (Linear and CNN-based networks) across a range of privacy parameters. The results demonstrate the potential of P4, as it outperforms the state-of-the-art of differential private P2P by up to 40 percent in terms of accuracy. We also show the practicality of P4 by implementing it on resource constrained devices, and validating that it has minimal overhead, e.g., about 7 seconds to run collaborative training between two clients.
Authors: Nicklas Hansen, Jyothir S V, Vlad Sobal, Yann LeCun, Xiaolong Wang, Hao Su
Abstract: Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual whole-body humanoid control based on reinforcement learning, without any simplifying assumptions, reward design, or skill primitives. Specifically, we propose a hierarchical world model in which a high-level agent generates commands based on visual observations for a low-level agent to execute, both of which are trained with rewards. Our approach produces highly performant control policies in 8 tasks with a simulated 56-DoF humanoid, while synthesizing motions that are broadly preferred by humans. Code and videos: https://nicklashansen.com/rlpuppeteer
Authors: Tiansheng Huang, Sihao Hu, Fatih Ilhan, Selim Furkan Tekin, Ling Liu
Abstract: Recent studies show that Large Language Models (LLMs) with safety alignment can be jail-broken by fine-tuning on a dataset mixed with harmful data. First time in the literature, we show that the jail-broken effect can be mitigated by separating states in the finetuning stage to optimize the alignment and user datasets. Unfortunately, our subsequent study shows that this simple Bi-State Optimization (BSO) solution experiences convergence instability when steps invested in its alignment state is too small, leading to downgraded alignment performance. By statistical analysis, we show that the \textit{excess drift} towards consensus could be a probable reason for the instability. To remedy this issue, we propose \textbf{L}azy(\textbf{i}) \textbf{s}afety \textbf{a}lignment (\textbf{Lisa}), which introduces a proximal term to constraint the drift of each state. Theoretically, the benefit of the proximal term is supported by the convergence analysis, wherein we show that a sufficient large proximal factor is necessary to guarantee Lisa's convergence. Empirically, our results on four downstream finetuning tasks show that Lisa with a proximal term can significantly increase alignment performance while maintaining the LLM's accuracy on the user tasks. Code is available at \url{https://github.com/git-disl/Lisa}.
Authors: Vicky Zayats, Peter Chen, Melissa Ferrari, Dirk Padfield
Abstract: Integrating multiple generative foundation models, especially those trained on different modalities, into something greater than the sum of its parts poses significant challenges. Two key hurdles are the availability of aligned data (concepts that contain similar meaning but is expressed differently in different modalities), and effectively leveraging unimodal representations in cross-domain generative tasks, without compromising their original unimodal capabilities. We propose Zipper, a multi-tower decoder architecture that addresses these concerns by using cross-attention to flexibly compose multimodal generative models from independently pre-trained unimodal decoders. In our experiments fusing speech and text modalities, we show the proposed architecture performs very competitively in scenarios with limited aligned text-speech data. We also showcase the flexibility of our model to selectively maintain unimodal (e.g., text-to-text generation) generation performance by freezing the corresponding modal tower (e.g. text). In cross-modal tasks such as automatic speech recognition (ASR) where the output modality is text, we show that freezing the text backbone results in negligible performance degradation. In cross-modal tasks such as text-to-speech generation (TTS) where the output modality is speech, we show that using a pre-trained speech backbone results in superior performance to the baseline.
Authors: Yufei Zhao, Shiduo Wang, Hua Duan
Abstract: Existing heterogeneous graph neural network algorithms (HGNNs) mostly rely on meta-paths to capture the rich semantic information contained in heterogeneous graphs (also known as heterogeneous information networks (HINs)), but most of these HGNNs focus on different ways of feature aggre gation and ignore the properties of the meta-paths themselves. This paper studies meta-paths in three commonly used data sets and finds that there are huge differences in the number of neighbors connected by different meta paths. At the same time, the noise information contained in large neigh bor paths will have an adverse impact on model performance. Therefore, this paper proposes a Heterogeneous Graph Neural Network Classification and Aggregation Algorithm Based on Large and Small Neighbor Path Iden tification(LSPI). LSPI firstly divides the meta-paths into large and small neighbor paths through the path discriminator , and in order to reduce the noise interference problem in large neighbor paths, LSPI selects neighbor nodes with higher similarity from both topology and feature perspectives, and passes small neighbor paths and filtered large neighbor paths through different graph convolution components. Aggregation is performed to obtain feature information under different subgraphs, and then LSPI uses subgraph level attention to fuse the feature information under different subgraphs to generate the final node embedding. Finally this paper verifies the superiority of the method through extensive experiments and also gives suggestions on the number of nodes to be retained in large neighbor paths through exper iments. The complete reproducible code adn data has been published at: https://github.com/liuhua811/LSPIA.
Authors: Dorina Weichert, Alexander Kister, Sebastian Houben, Patrick Link, Gunar Ernis
Abstract: The practical use of Bayesian Optimization (BO) in engineering applications imposes special requirements: high sampling efficiency on the one hand and finding a robust solution on the other hand. We address the case of adversarial robustness, where all parameters are controllable during the optimization process, but a subset of them is uncontrollable or even adversely perturbed at the time of application. To this end, we develop an efficient information-based acquisition function that we call Robust Entropy Search (RES). We empirically demonstrate its benefits in experiments on synthetic and real-life data. The results showthat RES reliably finds robust optima, outperforming state-of-the-art algorithms.
Authors: Kiyoung Seong, Seonghyun Park, Seonghwan Kim, Woo Youn Kim, Sungsoo Ahn
Abstract: Understanding transition paths between meta-stable states in molecular systems is fundamental for material design and drug discovery. However, sampling these paths via molecular dynamics simulations is computationally prohibitive due to the high-energy barriers between the meta-stable states. Recent machine learning approaches are often restricted to simple systems or rely on collective variables (CVs) extracted from expensive domain knowledge. In this work, we propose to leverage generative flow networks (GFlowNets) to sample transition paths without relying on CVs. We reformulate the problem as amortized energy-based sampling over molecular trajectories and train a bias potential by minimizing the squared log-ratio between the target distribution and the generator, derived from the flow matching objective of GFlowNets. Our evaluation on three proteins (Alanine Dipeptide, Polyproline, and Chignolin) demonstrates that our approach, called TPS-GFN, generates more realistic and diverse transition paths than the previous CV-free machine learning approach.
Authors: Jieun Yook, Junpyo Seo, Joon Huh, Han Joon Byun, Byung-ro Mooon
Abstract: We propose a new transformer model for the Traveling Salesman Problem (TSP) called CycleFormer. We identified distinctive characteristics that need to be considered when applying a conventional transformer model to TSP and aimed to fully incorporate these elements into the TSP-specific transformer. Unlike the token sets in typical language models, which are limited and static, the token (node) set in TSP is unlimited and dynamic. To exploit this fact to the fullest, we equated the encoder output with the decoder linear layer and directly connected the context vector of the encoder to the decoder encoding. Additionally, we added a positional encoding to the encoder tokens that reflects the two-dimensional nature of TSP, and devised a circular positional encoding for the decoder tokens that considers the cyclic properties of a tour. By incorporating these ideas, CycleFormer outperforms state-of-the-art (SOTA) transformer models for TSP from TSP-50 to TSP-500. Notably, on TSP-500, the optimality gap was reduced by approximately 2.8 times, from 3.09% to 1.10%, compared to the existing SOTA. The code will be made available at https://github.com/Giventicket/CycleFormer.
Authors: Jiangwei Zhao, Zejia Liu, Xiaohan Guo, Lili Pan
Abstract: Disentanglement, a critical concern in interpretable machine learning, has also garnered significant attention from the computer vision community. Many existing GAN-based class disentanglement (unsupervised) approaches, such as InfoGAN and its variants, primarily aim to maximize the mutual information (MI) between the generated image and its latent codes. However, this focus may lead to a tendency for the network to generate highly similar images when presented with the same latent class factor, potentially resulting in mode collapse or mode dropping. To alleviate this problem, we propose \texttt{CoDeGAN} (Contrastive Disentanglement for Generative Adversarial Networks), where we relax similarity constraints for disentanglement from the image domain to the feature domain. This modification not only enhances the stability of GAN training but also improves their disentangling capabilities. Moreover, we integrate self-supervised pre-training into CoDeGAN to learn semantic representations, significantly facilitating unsupervised disentanglement. Extensive experimental results demonstrate the superiority of our method over state-of-the-art approaches across multiple benchmarks. The code is available at https://github.com/learninginvision/CoDeGAN.
Authors: Devansh Jalota, Yinyu Ye
Abstract: Fisher markets are one of the most fundamental models for resource allocation. However, the problem of computing equilibrium prices in Fisher markets typically relies on complete knowledge of users' budgets and utility functions and requires transactions to happen in a static market where all users are present simultaneously. Motivated by these practical considerations, we study an online variant of Fisher markets, wherein users with privately known utility and budget parameters, drawn i.i.d. from a distribution, arrive sequentially. In this setting, we first study the limitations of static pricing algorithms, which set uniform prices for all users, along two performance metrics: (i) regret, i.e., the optimality gap in the objective of the Eisenberg-Gale program between an online algorithm and an oracle with complete information, and (ii) capacity violations, i.e., the over-consumption of goods relative to their capacities. Given the limitations of static pricing, we design adaptive posted-pricing algorithms, one with knowledge of the distribution of users' budget and utility parameters and another that adjusts prices solely based on past observations of user consumption, i.e., revealed preference feedback, with improved performance guarantees. Finally, we present numerical experiments to compare our revealed preference algorithm's performance to several benchmarks.
Authors: Ljubomir Rokvic, Panayiotis Danassis, Sai Praneeth Karimireddy, Boi Faltings
Abstract: In Federated Learning, it is crucial to handle low-quality, corrupted, or malicious data. However, traditional data valuation methods are not suitable due to privacy concerns. To address this, we propose a simple yet effective approach that utilizes a new influence approximation called "lazy influence" to filter and score data while preserving privacy. To do this, each participant uses their own data to estimate the influence of another participant's batch and sends a differentially private obfuscated score to the central coordinator. Our method has been shown to successfully filter out biased and corrupted data in various simulated and real-world settings, achieving a recall rate of over $>90\%$ (sometimes up to $100\%$) while maintaining strong differential privacy guarantees with $\varepsilon \leq 1$.
Authors: Sunil Hwang, Jaehong Yoon, Youngwan Lee, Sung Ju Hwang
Abstract: Masked Video Autoencoder (MVA) approaches have demonstrated their potential by significantly outperforming previous video representation learning methods. However, they waste an excessive amount of computations and memory in predicting uninformative tokens/frames due to random masking strategies. (e.g., over 16 nodes with 128 NVIDIA A100 GPUs). To resolve this issue, we exploit the unequal information density among the patches in videos and propose EVEREST, a surprisingly efficient MVA approach for video representation learning that finds tokens containing rich motion features and discards uninformative ones during both pre-training and fine-tuning. We further present an information-intensive frame selection strategy that allows the model to focus on informative and causal frames with minimal redundancy. Our method significantly reduces the computation and memory requirements of MVA, enabling the pre-training and fine-tuning on a single machine with 8 GPUs while achieving comparable performance to computation- and memory-heavy baselines on multiple benchmarks and the uncurated Ego4D dataset. We hope that our work contributes to reducing the barrier to further research on video understanding.
Authors: Cheng Tan, Zhangyang Gao, Hanqun Cao, Xingran Chen, Ge Wang, Lirong Wu, Jun Xia, Jiangbin Zheng, Stan Z. Li
Abstract: The secondary structure of ribonucleic acid (RNA) is more stable and accessible in the cell than its tertiary structure, making it essential for functional prediction. Although deep learning has shown promising results in this field, current methods suffer from poor generalization and high complexity. In this work, we reformulate the RNA secondary structure prediction as a K-Rook problem, thereby simplifying the prediction process into probabilistic matching within a finite solution space. Building on this innovative perspective, we introduce RFold, a simple yet effective method that learns to predict the most matching K-Rook solution from the given sequence. RFold employs a bi-dimensional optimization strategy that decomposes the probabilistic matching problem into row-wise and column-wise components to reduce the matching complexity, simplifying the solving process while guaranteeing the validity of the output. Extensive experiments demonstrate that RFold achieves competitive performance and about eight times faster inference efficiency than the state-of-the-art approaches. The code and Colab demo are available in \href{http://github.com/A4Bio/RFold}{http://github.com/A4Bio/RFold}.
URLs: http://github.com/A4Bio/RFold, http://github.com/A4Bio/RFold
Authors: Sujay Kazi, Martin Larocca, M. Cerezo
Abstract: The importance of symmetries has recently been recognized in quantum machine learning from the simple motto: if a task exhibits a symmetry (given by a group $\mathfrak{G}$), the learning model should respect said symmetry. This can be instantiated via $\mathfrak{G}$-equivariant Quantum Neural Networks (QNNs), i.e., parametrized quantum circuits whose gates are generated by operators commuting with a given representation of $\mathfrak{G}$. In practice, however, there might be additional restrictions to the types of gates one can use, such as being able to act on at most $k$ qubits. In this work we study how the interplay between symmetry and $k$-bodyness in the QNN generators affect its expressiveness for the special case of $\mathfrak{G}=S_n$, the symmetric group. Our results show that if the QNN is generated by one- and two-body $S_n$-equivariant gates, the QNN is semi-universal but not universal. That is, the QNN can generate any arbitrary special unitary matrix in the invariant subspaces, but has no control over the relative phases between them. Then, we show that in order to reach universality one needs to include $n$-body generators (if $n$ is even) or $(n-1)$-body generators (if $n$ is odd). As such, our results brings us a step closer to better understanding the capabilities and limitations of equivariant QNNs.
Authors: Eliya Nachmani, Alon Levkovitch, Roy Hirsch, Julian Salazar, Chulayuth Asawaroengchai, Soroosh Mariooryad, Ehud Rivlin, RJ Skerry-Ryan, Michelle Tadmor Ramanovich
Abstract: We present Spectron, a novel approach to adapting pre-trained large language models (LLMs) to perform spoken question answering (QA) and speech continuation. By endowing the LLM with a pre-trained speech encoder, our model becomes able to take speech inputs and generate speech outputs. The entire system is trained end-to-end and operates directly on spectrograms, simplifying our architecture. Key to our approach is a training objective that jointly supervises speech recognition, text continuation, and speech synthesis using only paired speech-text pairs, enabling a `cross-modal' chain-of-thought within a single decoding pass. Our method surpasses existing spoken language models in speaker preservation and semantic coherence. Furthermore, the proposed model improves upon direct initialization in retaining the knowledge of the original LLM as demonstrated through spoken QA datasets. We release our audio samples (https://michelleramanovich.github.io/spectron/spectron) and spoken QA dataset (https://github.com/google-research-datasets/LLAMA1-Test-Set).
URLs: https://michelleramanovich.github.io/spectron/spectron), https://github.com/google-research-datasets/LLAMA1-Test-Set).
Authors: Sotiris Anagnostidis, Dario Pavllo, Luca Biggio, Lorenzo Noci, Aurelien Lucchi, Thomas Hofmann
Abstract: Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens in the sequence, thus incurring a quadratic cost. In this study, we present a novel approach that dynamically prunes contextual information while preserving the model's expressiveness, resulting in reduced memory and computational requirements during inference. Our method employs a learnable mechanism that determines which uninformative tokens can be dropped from the context at any point across the generation process. By doing so, our approach not only addresses performance concerns but also enhances interpretability, providing valuable insight into the model's decision-making process. Our technique can be applied to existing pre-trained models through a straightforward fine-tuning process, and the pruning strength can be specified by a sparsity parameter. Notably, our empirical findings demonstrate that we can effectively prune up to 80\% of the context without significant performance degradation on downstream tasks, offering a valuable tool for mitigating inference costs. Our reference implementation achieves up to $2\times$ increase in inference throughput and even greater memory savings.
Authors: Alessandro B. Palmarini, Christopher G. Lucas, N. Siddharth
Abstract: DreamCoder is an inductive program synthesis system that, whilst solving problems, learns to simplify search in an iterative wake-sleep procedure. The cost of search is amortized by training a neural search policy, reducing search breadth and effectively "compiling" useful information to compose program solutions across tasks. Additionally, a library of program components is learnt to compress and express discovered solutions in fewer components, reducing search depth. We present a novel approach for library learning that directly leverages the neural search policy, effectively "decompiling" its amortized knowledge to extract relevant program components. This provides stronger amortized inference: the amortized knowledge learnt to reduce search breadth is now also used to reduce search depth. We integrate our approach with DreamCoder and demonstrate faster domain proficiency with improved generalization on a range of domains, particularly when fewer example solutions are available.
Authors: Xue Yang, Zifeng Liu, Xiaohu Tang, Rongxing Lu, Bo Liu
Abstract: With the emergence of privacy leaks in federated learning, secure aggregation protocols that mainly adopt either homomorphic encryption or threshold secret sharing have been widely developed for federated learning to protect the privacy of the local training data of each client. However, these existing protocols suffer from many shortcomings, such as the dependence on a trusted third party, the vulnerability to clients being corrupted, low efficiency, the trade-off between security and fault tolerance, etc. To solve these disadvantages, we propose an efficient and multi-private key secure aggregation scheme for federated learning. Specifically, we skillfully modify the variant ElGamal encryption technique to achieve homomorphic addition operation, which has two important advantages: 1) The server and each client can freely select public and private keys without introducing a trust third party and 2) Compared to the variant ElGamal encryption, the plaintext space is relatively large, which is more suitable for the deep model. Besides, for the high dimensional deep model parameter, we introduce a super-increasing sequence to compress multi-dimensional data into 1-D, which can greatly reduce encryption and decryption times as well as communication for ciphertext transmission. Detailed security analyses show that our proposed scheme achieves the semantic security of both individual local gradients and the aggregated result while achieving optimal robustness in tolerating both client collusion and dropped clients. Extensive simulations demonstrate that the accuracy of our scheme is almost the same as the non-private approach, while the efficiency of our scheme is much better than the state-of-the-art homomorphic encryption-based secure aggregation schemes. More importantly, the efficiency advantages of our scheme will become increasingly prominent as the number of model parameters increases.
Authors: Javier Naranjo-Alcazar, Jordi Grau-Haro, David Almenar, Pedro Zuccarello
Abstract: The Sterile Insect Technique (SIT) is a biological pest control technique based on the release into the environment of sterile males of the insect species whose population is to be controlled. The entire SIT process involves mass-rearing within a biofactory, sorting of the specimens by sex, sterilization, and subsequent release of the sterile males into the environment. The reason for avoiding the release of female specimens is because, unlike males, females bite, with the subsequent risk of disease transmission. In the case of Aedes mosquito biofactories for SIT, the key point of the whole process is sex separation. This process is nowadays performed by a combination of mechanical devices and AI-based vision systems. However, there is still a possibility of false negatives, so a last stage of verification is necessary before releasing them into the environment. It is known that the sound produced by the flapping of adult male mosquitoes is different from that produced by females, so this feature can be used to detect the presence of females in containers prior to environmental release. This paper presents a study for the detection of females in Aedes mosquito release vessels for SIT programs. The containers used consist of PVC a tubular design of 8.8cm diameter and 12.5cm height. The containers were placed in an experimental setup that allowed the recording of the sound of mosquito flight inside of them. Each container was filled with 250 specimens considering the cases of (i) only male mosquitoes, (ii) only female mosquitoes, and (iii) 75% males and 25% females. Case (i) was used for training and testing, whereas cases (ii) and (iii) were used only for testing. Two algorithms were implemented for the detection of female mosquitoes: an unsupervised outlier detection algorithm (iForest) and a one-class SVM trained with male-only recordings.
Authors: Jessy Lin, Yuqing Du, Olivia Watkins, Danijar Hafner, Pieter Abbeel, Dan Klein, Anca Dragan
Abstract: To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents that leverage diverse language -- language like "this button turns on the TV" or "I put the bowls away" -- that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future: what they will observe, how the world will behave, and which situations will be rewarded. This perspective unifies language understanding with future prediction as a powerful self-supervised learning objective. We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations, and learns to act from imagined model rollouts. While current methods that learn language-conditioned policies degrade in performance with more diverse types of language, we show that Dynalang learns to leverage environment descriptions, game rules, and instructions to excel on tasks ranging from game-playing to navigating photorealistic home scans. Finally, we show that our method enables additional capabilities due to learning a generative model: Dynalang can be pretrained on text-only data, enabling learning from offline datasets, and generate language grounded in an environment.
Authors: Cheik Traor\'e, Vassilis Apidopoulos, Saverio Salzo, Silvia Villa
Abstract: In the context of finite sums minimization, variance reduction techniques are widely used to improve the performance of state-of-the-art stochastic gradient methods. Their practical impact is clear, as well as their theoretical properties. Stochastic proximal point algorithms have been studied as an alternative to stochastic gradient algorithms since they are more stable with respect to the choice of the stepsize but their variance reduced versions are not as studied as the gradient ones. In this work, we propose the first unified study of variance reduction techniques for stochastic proximal point algorithms. We introduce a generic stochastic proximal algorithm that can be specified to give the proximal version of SVRG, SAGA, and some of their variants for smooth and convex functions. We provide several convergence results for the iterates and the objective function values. In addition, under the Polyak-{\L}ojasiewicz (PL) condition, we obtain linear convergence rates for the iterates and the function values. Our numerical experiments demonstrate the advantages of the proximal variance reduction methods over their gradient counterparts, especially about the stability with respect to the choice of the stepsize for difficult problems.
Authors: Urte Adomaityte, Leonardo Defilippis, Bruno Loureiro, Gabriele Sicuro
Abstract: We investigate the high-dimensional properties of robust regression estimators in the presence of heavy-tailed contamination of both the covariates and response functions. In particular, we provide a sharp asymptotic characterisation of M-estimators trained on a family of elliptical covariate and noise data distributions including cases where second and higher moments do not exist. We show that, despite being consistent, the Huber loss with optimally tuned location parameter $\delta$ is suboptimal in the high-dimensional regime in the presence of heavy-tailed noise, highlighting the necessity of further regularisation to achieve optimal performance. This result also uncovers the existence of a transition in $\delta$ as a function of the sample complexity and contamination. Moreover, we derive the decay rates for the excess risk of ridge regression. We show that, while it is both optimal and universal for covariate distributions with finite second moment, its decay rate can be considerably faster when the covariates' second moment does not exist. Finally, we show that our formulas readily generalise to a richer family of models and data distributions, such as generalised linear estimation with arbitrary convex regularisation trained on mixture models.
Authors: Richard Osuala, Smriti Joshi, Apostolia Tsirikoglou, Lidia Garrucho, Walter H. L. Pinaya, Oliver Diaz, Karim Lekadir
Abstract: Despite its benefits for tumour detection and treatment, the administration of contrast agents in dynamic contrast-enhanced MRI (DCE-MRI) is associated with a range of issues, including their invasiveness, bioaccumulation, and a risk of nephrogenic systemic fibrosis. This study explores the feasibility of producing synthetic contrast enhancements by translating pre-contrast T1-weighted fat-saturated breast MRI to their corresponding first DCE-MRI sequence leveraging the capabilities of a generative adversarial network (GAN). Additionally, we introduce a Scaled Aggregate Measure (SAMe) designed for quantitatively evaluating the quality of synthetic data in a principled manner and serving as a basis for selecting the optimal generative model. We assess the generated DCE-MRI data using quantitative image quality metrics and apply them to the downstream task of 3D breast tumour segmentation. Our results highlight the potential of post-contrast DCE-MRI synthesis in enhancing the robustness of breast tumour segmentation models via data augmentation. Our code is available at https://github.com/RichardObi/pre_post_synthesis.
Authors: Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik, D. A. Forsyth, Anand Bhattad
Abstract: Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a set of collections of generated images, prequalified to fool simple, signal-based classifiers into believing they are real. We then show that prequalified generated images can be identified reliably by classifiers that only look at geometric properties. We use three such classifiers. All three classifiers are denied access to image pixels, and look only at derived geometric features. The first classifier looks at the perspective field of the image, the second looks at lines detected in the image, and the third looks at relations between detected objects and shadows. Our procedure detects generated images more reliably than SOTA local signal based detectors, for images from a number of distinct generators. Saliency maps suggest that the classifiers can identify geometric problems reliably. We conclude that current generators cannot reliably reproduce geometric properties of real images.
Authors: Jiajun Cui, Minghe Yu, Bo Jiang, Aimin Zhou, Jianyong Wang, Wei Zhang
Abstract: Knowledge tracing (KT) plays a crucial role in computer-aided education and intelligent tutoring systems, aiming to assess students' knowledge proficiency by predicting their future performance on new questions based on their past response records. While existing deep learning knowledge tracing (DLKT) methods have significantly improved prediction accuracy and achieved state-of-the-art results, they often suffer from a lack of interpretability. To address this limitation, current approaches have explored incorporating psychological influences to achieve more explainable predictions, but they tend to overlook the potential influences of historical responses. In fact, understanding how models make predictions based on response influences can enhance the transparency and trustworthiness of the knowledge tracing process, presenting an opportunity for a new paradigm of interpretable KT. However, measuring unobservable response influences is challenging. In this paper, we resort to counterfactual reasoning that intervenes in each response to answer \textit{what if a student had answered a question incorrectly that he/she actually answered correctly, and vice versa}. Based on this, we propose RCKT, a novel response influence-based counterfactual knowledge tracing framework. RCKT generates response influences by comparing prediction outcomes from factual sequences and constructed counterfactual sequences after interventions. Additionally, we introduce maximization and inference techniques to leverage accumulated influences from different past responses, further improving the model's performance and credibility. Extensive experimental results demonstrate that our RCKT method outperforms state-of-the-art knowledge tracing methods on four datasets against six baselines, and provides credible interpretations of response influences.
Authors: Simisola Odimayo, Chollette C. Olisah, Khadija Mohammed
Abstract: Alzheimer's disease (AD), the predominant form of dementia, is a growing global challenge, emphasizing the urgent need for accurate and early diagnosis. Current clinical diagnoses rely on radiologist expert interpretation, which is prone to human error. Deep learning has thus far shown promise for early AD diagnosis. However, existing methods often overlook focal structural atrophy critical for enhanced understanding of the cerebral cortex neurodegeneration. This paper proposes a deep learning framework that includes a novel structure-focused neurodegeneration CNN architecture named SNeurodCNN and an image brightness enhancement preprocessor using gamma correction. The SNeurodCNN architecture takes as input the focal structural atrophy features resulting from segmentation of brain structures captured through magnetic resonance imaging (MRI). As a result, the architecture considers only necessary CNN components, which comprises of two downsampling convolutional blocks and two fully connected layers, for achieving the desired classification task, and utilises regularisation techniques to regularise learnable parameters. Leveraging mid-sagittal and para-sagittal brain image viewpoints from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, our framework demonstrated exceptional performance. The para-sagittal viewpoint achieved 97.8% accuracy, 97.0% specificity, and 98.5% sensitivity, while the mid-sagittal viewpoint offered deeper insights with 98.1% accuracy, 97.2% specificity, and 99.0% sensitivity. Model analysis revealed the ability of SNeurodCNN to capture the structural dynamics of mild cognitive impairment (MCI) and AD in the frontal lobe, occipital lobe, cerebellum, temporal, and parietal lobe, suggesting its potential as a brain structural change digi-biomarker for early AD diagnosis. This work can be reproduced using code we made available on GitHub.
Authors: Vincent Zhihao Zheng, Lijun Sun
Abstract: Accurately modeling the correlation structure of errors is essential for reliable uncertainty quantification in probabilistic time series forecasting. Recent deep learning models for multivariate time series have developed efficient parameterizations for time-varying contemporaneous covariance, but they often assume temporal independence of errors for simplicity. However, real-world data frequently exhibit significant error autocorrelation and cross-lag correlation due to factors such as missing covariates. In this paper, we present a plug-and-play method that learns the covariance structure of errors over multiple steps for autoregressive models with Gaussian-distributed errors. To achieve scalable inference and computational efficiency, we model the contemporaneous covariance using a low-rank-plus-diagonal parameterization and characterize cross-covariance through a group of independent latent temporal processes. The learned covariance matrix can be used to calibrate predictions based on observed residuals. We evaluate our method on probabilistic models built on RNN and Transformer architectures, and the results confirm the effectiveness of our approach in enhancing predictive accuracy and uncertainty quantification without significantly increasing the parameter size.
Authors: Hannes Stark, Bowen Jing, Chenyu Wang, Gabriele Corso, Bonnie Berger, Regina Barzilay, Tommi Jaakkola
Abstract: Discrete diffusion or flow models could enable faster and more controllable sequence generation than autoregressive models. We show that na\"ive linear flow matching on the simplex is insufficient toward this goal since it suffers from discontinuities in the training target and further pathologies. To overcome this, we develop Dirichlet flow matching on the simplex based on mixtures of Dirichlet distributions as probability paths. In this framework, we derive a connection between the mixtures' scores and the flow's vector field that allows for classifier and classifier-free guidance. Further, we provide distilled Dirichlet flow matching, which enables one-step sequence generation with minimal performance hits, resulting in $O(L)$ speedups compared to autoregressive models. On complex DNA sequence generation tasks, we demonstrate superior performance compared to all baselines in distributional metrics and in achieving desired design targets for generated sequences. Finally, we show that our classifier-free guidance approach improves unconditional generation and is effective for generating DNA that satisfies design targets. Code is available at https://github.com/HannesStark/dirichlet-flow-matching.
URLs: https://github.com/HannesStark/dirichlet-flow-matching.
Authors: Karan Chadha, John Duchi, Rohith Kuditipudi
Abstract: We consider the task of constructing confidence intervals with differential privacy. We propose two private variants of the non-parametric bootstrap, which privately compute the median of the results of multiple "little" bootstraps run on partitions of the data and give asymptotic bounds on the coverage error of the resulting confidence intervals. For a fixed differential privacy parameter $\epsilon$, our methods enjoy the same error rates as that of the non-private bootstrap to within logarithmic factors in the sample size $n$. We empirically validate the performance of our methods for mean estimation, median estimation, and logistic regression with both real and synthetic data. Our methods achieve similar coverage accuracy to existing methods (and non-private baselines) while providing notably shorter ($\gtrsim 10$ times) confidence intervals than previous approaches.
Authors: Jincheng Cao, Ruichen Jiang, Erfan Yazdandoost Hamedani, Aryan Mokhtari
Abstract: In this paper, we focus on simple bilevel optimization problems, where we minimize a convex smooth objective function over the optimal solution set of another convex smooth constrained optimization problem. We present a novel bilevel optimization method that locally approximates the solution set of the lower-level problem using a cutting plane approach and employs an accelerated gradient-based update to reduce the upper-level objective function over the approximated solution set. We measure the performance of our method in terms of suboptimality and infeasibility errors and provide non-asymptotic convergence guarantees for both error criteria. Specifically, when the feasible set is compact, we show that our method requires at most $\mathcal{O}(\max\{1/\sqrt{\epsilon_{f}}, 1/\epsilon_g\})$ iterations to find a solution that is $\epsilon_f$-suboptimal and $\epsilon_g$-infeasible. Moreover, under the additional assumption that the lower-level objective satisfies the $r$-th H\"olderian error bound, we show that our method achieves an iteration complexity of $\mathcal{O}(\max\{\epsilon_{f}^{-\frac{2r-1}{2r}},\epsilon_{g}^{-\frac{2r-1}{2r}}\})$, which matches the optimal complexity of single-level convex constrained optimization when $r=1$.
Authors: Zhen Guo, Adriana Meza Soria, Wei Sun, Yikang Shen, Rameswar Panda
Abstract: We introduce API Pack, a massive multi-programming language dataset containing more than 1 million instruction-API call pairs to improve the API call generation capabilities of large language models. By fine-tuning CodeLlama-13B on 20,000 Python instances from API Pack, we achieved around 10% and 5% higher accuracy compared to GPT-3.5 and GPT-4, respectively, in generating unseen API calls. Fine-tuning on API Pack enables cross-programming language generalization by leveraging a large amount of data in one language and small amounts of data from other languages. Scaling the training data to 1 million instances further improves the model's generalization to new APIs not encountered during training. We open-source the API Pack dataset, trained models, and associated source code at https://github.com/zguo0525/API-Pack to facilitate further research.
Authors: Chengshuai Shi, Kun Yang, Zihan Chen, Jundong Li, Jing Yang, Cong Shen
Abstract: The remarkable instruction-following capability of large language models (LLMs) has sparked a growing interest in automatically finding good prompts, i.e., prompt optimization. Most existing works follow the scheme of selecting from a pre-generated pool of candidate prompts. However, these designs mainly focus on the generation strategy, while limited attention has been paid to the selection method. Especially, the cost incurred during the selection (e.g., accessing LLM and evaluating the responses) is rarely explicitly considered. To overcome this limitation, this work provides a principled framework, TRIPLE, to efficiently perform prompt selection under an explicit budget constraint. TRIPLE is built on a novel connection established between prompt optimization and fixed-budget best arm identification (BAI-FB) in multi-armed bandits (MAB); thus, it is capable of leveraging the rich toolbox from BAI-FB systematically and also incorporating unique characteristics of prompt optimization. Extensive experiments on multiple well-adopted tasks using various LLMs demonstrate the remarkable performance improvement of TRIPLE over baselines while satisfying the limited budget constraints. As an extension, variants of TRIPLE are proposed to efficiently select examples for few-shot prompts, also achieving superior empirical performance.
Authors: Zijun Liu, Boqun Kou, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu
Abstract: Despite the strong performance of large language models (LLMs) across a wide range of tasks, they still have reliability issues. Previous studies indicate that strong LLMs like GPT-4-turbo excel in evaluating the reliability of responses from LLMs, but face efficiency and local deployment issues. Thus, to enable weak LLMs to effectively assess the reliability of LLM responses, we propose a novel cross-query-comparison-based method called $\textit{Meta Ranking}$ (MR). Unlike previous few-shot methods that solely based on in-context learning capabilities in LLMs, MR assesses reliability by pairwisely ranking the target query-response pair with multiple reference query-response pairs. We found that MR is highly effective in error detection for LLM responses, where weak LLMs, such as Phi-2, could surpass strong baselines like GPT-3.5-turbo, requiring only five reference samples and significantly improving efficiency. We further demonstrate that MR can enhance strong LLMs' performance in two practical applications: model cascading and instruction tuning. In model cascading, we combine open- and closed-source LLMs to achieve performance comparable to GPT-4-turbo with lower costs. In instruction tuning, we use MR for iterative training data filtering, significantly reducing data processing time and enabling LLaMA-7B and Phi-2 to surpass Alpaca-13B with fewer training tokens. These results underscore the high potential of MR in both efficiency and effectiveness.
Authors: James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Jiankang Deng, Ioannis Patras
Abstract: The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the computational cost of scaling the number of experts high enough to achieve fine-grained specialization. In this paper, we propose the Multilinear Mixture of Experts ($\mu$MoE) layer to address this, focusing on vision models. $\mu$MoE layers enable scalable expert specialization by performing an implicit computation on prohibitively large weight tensors entirely in factorized form. Consequently, $\mu$MoEs (1) avoid the restrictively high inference-time costs of 'soft' MoEs, yet (2) do not inherit the training issues of the popular 'sparse' MoEs' discrete (non-differentiable) expert routing. We present both qualitative and quantitative evidence that scaling $\mu$MoE layers when fine-tuning foundation models for vision tasks leads to more specialized experts at the class-level, further enabling manual bias correction in CelebA attribute classification. Finally, we show qualitative results demonstrating the expert specialism achieved when pre-training large GPT2 and MLP-Mixer models with parameter-matched $\mu$MoE blocks at every layer, maintaining comparable accuracy. Our code is available at: https://github.com/james-oldfield/muMoE.
Authors: Jianhong Wang, Yang Li, Yuan Zhang, Wei Pan, Samuel Kaski
Abstract: Ad hoc teamwork poses a challenging problem, requiring the design of an agent to collaborate with teammates without prior coordination or joint training. Open ad hoc teamwork (OAHT) further complicates this challenge by considering environments with a changing number of teammates, referred to as open teams. One promising solution in practice to this problem is leveraging the generalizability of graph neural networks to handle an unrestricted number of agents, named graph-based policy learning (GPL). However, its joint Q-value representation over a coordination graph lacks convincing explanations. In this paper, we establish a new theory to understand the joint Q-value representation for OAHT, from the perspective of cooperative game theory, and validate its learning paradigm. Building on our theory, we propose a novel algorithm named CIAO, compatible with GPL framework, with additional provable implementation tricks that can facilitate learning. The demos of experimental results are available on https://sites.google.com/view/ciao2024, and the code of experiments is published on https://github.com/hsvgbkhgbv/CIAO.
URLs: https://sites.google.com/view/ciao2024,, https://github.com/hsvgbkhgbv/CIAO.
Authors: Yihong Dong, Xue Jiang, Huanyu Liu, Zhi Jin, Bin Gu, Mengfei Yang, Ge Li
Abstract: Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could explicitly or implicitly include test data, leading to LLMs being more susceptible to data contamination. However, due to the opacity of training data, the black-box access of models, and the rapid growth of synthetic training data, detecting and mitigating data contamination for LLMs faces significant challenges. In this paper, we propose CDD, which stands for Contamination Detection via output Distribution for LLMs. CDD necessitates only the sampled texts to detect data contamination, by identifying the peakedness of LLM's output distribution. To mitigate the impact of data contamination in evaluation, we also present TED: Trustworthy Evaluation via output Distribution, based on the correction of LLM's output distribution. To facilitate this study, we introduce two benchmarks, i.e., DetCon and ComiEval, for data contamination detection and contamination mitigation evaluation tasks. Extensive experimental results show that CDD achieves the average relative improvements of 21.8\%-30.2\% over other contamination detection approaches in terms of Accuracy, F1 Score, and AUC metrics, and can effectively detect implicit contamination. TED substantially mitigates performance improvements up to 66.9\% attributed to data contamination across various contamination setups. In real-world applications, we reveal that ChatGPT exhibits a high potential to suffer from data contamination on HumanEval benchmark.
Authors: Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, Rui Yan
Abstract: Recent research trends in computational biology have increasingly focused on integrating text and bio-entity modeling, especially in the context of molecules and proteins. However, previous efforts like BioT5 faced challenges in generalizing across diverse tasks and lacked a nuanced understanding of molecular structures, particularly in their textual representations (e.g., IUPAC). This paper introduces BioT5+, an extension of the BioT5 framework, tailored to enhance biological research and drug discovery. BioT5+ incorporates several novel features: integration of IUPAC names for molecular understanding, inclusion of extensive bio-text and molecule data from sources like bioRxiv and PubChem, the multi-task instruction tuning for generality across tasks, and a numerical tokenization technique for improved processing of numerical data. These enhancements allow BioT5+ to bridge the gap between molecular representations and their textual descriptions, providing a more holistic understanding of biological entities, and largely improving the grounded reasoning of bio-text and bio-sequences. The model is pre-trained and fine-tuned with a large number of experiments, including \emph{3 types of problems (classification, regression, generation), 15 kinds of tasks, and 21 total benchmark datasets}, demonstrating the remarkable performance and state-of-the-art results in most cases. BioT5+ stands out for its ability to capture intricate relationships in biological data, thereby contributing significantly to bioinformatics and computational biology. Our code is available at \url{https://github.com/QizhiPei/BioT5}.
Authors: Matthew Dowling, Yuan Zhao, Il Memming Park
Abstract: State-space graphical models and the variational autoencoder framework provide a principled apparatus for learning dynamical systems from data. State-of-the-art probabilistic approaches are often able to scale to large problems at the cost of flexibility of the variational posterior or expressivity of the dynamics model. However, those consolidations can be detrimental if the ultimate goal is to learn a generative model capable of explaining the spatiotemporal structure of the data and making accurate forecasts. We introduce a low-rank structured variational autoencoding framework for nonlinear Gaussian state-space graphical models capable of capturing dense covariance structures that are important for learning dynamical systems with predictive capabilities. Our inference algorithm exploits the covariance structures that arise naturally from sample based approximate Gaussian message passing and low-rank amortized posterior updates -- effectively performing approximate variational smoothing with time complexity scaling linearly in the state dimensionality. In comparisons with other deep state-space model architectures our approach consistently demonstrates the ability to learn a more predictive generative model. Furthermore, when applied to neural physiological recordings, our approach is able to learn a dynamical system capable of forecasting population spiking and behavioral correlates from a small portion of single trials.
Authors: Lei Li, Tianfang Zhang, Xinglin Zhang, Jiaqi Liu, Bingqi Ma, Yan Luo, Tao Chen
Abstract: Within the domain of medical analysis, extensive research has explored the potential of mutual learning between Masked Autoencoders(MAEs) and multimodal data. However, the impact of MAEs on intermodality remains a key challenge. We introduce MedFLIP, a Fast Language-Image Pre-training method for Medical analysis. We explore MAEs for zero-shot learning with crossed domains, which enhances the model's ability to learn from limited data, a common scenario in medical diagnostics. We verify that masking an image does not affect inter-modal learning. Furthermore, we propose the SVD loss to enhance the representation learning for characteristics of medical images, aiming to improve classification accuracy by leveraging the structural intricacies of such data. Our theory posits that masking encourages semantic preservation, robust feature extraction, regularization, domain adaptation, and invariance learning. Lastly, we validate using language will improve the zero-shot performance for the medical image analysis. MedFLIP's scaling of the masking process marks an advancement in the field, offering a pathway to rapid and precise medical image analysis without the traditional computational bottlenecks. Through experiments and validation, MedFLIP demonstrates efficient performance improvements, helps for future research and application in medical diagnostics.
Authors: Marco Casadio, Tanvi Dinkar, Ekaterina Komendantskaya, Luca Arnaboldi, Matthew L. Daggitt, Omri Isac, Guy Katz, Verena Rieser, Oliver Lemon
Abstract: Deep neural networks have exhibited substantial success in the field of Natural Language Processing and ensuring their safety and reliability is crucial: there are safety critical contexts where such models must be robust to variability or attack, and give guarantees over their output. Unlike Computer Vision, NLP lacks a unified verification methodology and, despite recent advancements in literature, they are often light on the pragmatical issues of NLP verification. In this paper, we attempt to distil and evaluate general components of an NLP verification pipeline, that emerges from the progress in the field to date. Our contributions are two-fold. Firstly, we give a general (i.e. algorithm-independent) characterisation of verifiable subspaces that result from embedding sentences into continuous spaces. We identify, and give an effective method to deal with, the technical challenge of semantic generalisability of verified subspaces; and propose it as a standard metric in the NLP verification pipelines (alongside with the standard metrics of model accuracy and model verifiability). Secondly, we propose a general methodology to analyse the effect of the embedding gap -- a problem that refers to the discrepancy between verification of geometric subspaces, and the semantic meaning of sentences which the geometric subspaces are supposed to represent. In extreme cases, poor choices in embedding of sentences may invalidate verification results. We propose a number of practical NLP methods that can help to quantify the effects of the embedding gap; and in particular we propose the metric of falsifiability of semantic subspaces as another fundamental metric to be reported as part of the NLP verification pipeline. We believe that together these general principles pave the way towards a more consolidated and effective development of this new domain.
Authors: Kangjie Zheng, Siyu Long, Tianyu Lu, Junwei Yang, Xinyu Dai, Ming Zhang, Zaiqing Nie, Wei-Ying Ma, Hao Zhou
Abstract: Protein language models have demonstrated significant potential in the field of protein engineering. However, current protein language models primarily operate at the residue scale, which limits their ability to provide information at the atom level. This limitation prevents us from fully exploiting the capabilities of protein language models for applications involving both proteins and small molecules. In this paper, we propose ESM-AA (ESM All-Atom), a novel approach that enables atom-scale and residue-scale unified molecular modeling. ESM-AA achieves this by pre-training on multi-scale code-switch protein sequences and utilizing a multi-scale position encoding to capture relationships among residues and atoms. Experimental results indicate that ESM-AA surpasses previous methods in protein-molecule tasks, demonstrating the full utilization of protein language models. Further investigations reveal that through unified molecular modeling, ESM-AA not only gains molecular knowledge but also retains its understanding of proteins. The source codes of ESM-AA are publicly released at https://github.com/zhengkangjie/ESM-AA.
Authors: Jiwoong Im, Nayoung Kwon, Taewoo Park, Jiheon Woo, Jaeho Lee, Yongjune Kim
Abstract: We propose a communication-efficient collaborative inference framework in the domain of edge inference, focusing on the efficient use of vision transformer (ViT) models. The partitioning strategy of conventional collaborative inference fails to reduce communication cost because of the inherent architecture of ViTs maintaining consistent layer dimensions across the entire transformer encoder. Therefore, instead of employing the partitioning strategy, our framework utilizes a lightweight ViT model on the edge device, with the server deploying a complicated ViT model. To enhance communication efficiency and achieve the classification accuracy of the server model, we propose two strategies: 1) attention-aware patch selection and 2) entropy-aware image transmission. Attention-aware patch selection leverages the attention scores generated by the edge device's transformer encoder to identify and select the image patches critical for classification. This strategy enables the edge device to transmit only the essential patches to the server, significantly improving communication efficiency. Entropy-aware image transmission uses min-entropy as a metric to accurately determine whether to depend on the lightweight model on the edge device or to request the inference from the server model. In our framework, the lightweight ViT model on the edge device acts as a semantic encoder, efficiently identifying and selecting the crucial image information required for the classification task. Our experiments demonstrate that the proposed collaborative inference framework can reduce communication overhead by 68% with only a minimal loss in accuracy compared to the server model on the ImageNet dataset.
Authors: Yiwen Tang, Ray Zhang, Jiaming Liu, Zoey Guo, Dong Wang, Zhigang Wang, Bin Zhao, Shanghang Zhang, Peng Gao, Hongsheng Li, Xuelong Li
Abstract: Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D domains. However, such 2D-to-3D approaches are still limited, due to the potential loss of spatial geometries and high computation cost. More importantly, their frameworks are mainly designed for 2D models, lacking a general any-to-3D paradigm. In this paper, we introduce Any2Point, a parameter-efficient method to empower any-modality large models (vision, language, audio) for 3D understanding. Given a frozen transformer from any source modality, we propose a 3D-to-any (1D or 2D) virtual projection strategy that correlates the input 3D points to the original 1D or 2D positions within the source modality. This mechanism enables us to assign each 3D token with a positional encoding paired with the pre-trained model, which avoids 3D geometry loss caused by the true projection and better motivates the transformer for 3D learning with 1D/2D positional priors. Then, within each transformer block, we insert an any-to-3D guided adapter module for parameter-efficient fine-tuning. The adapter incorporates prior spatial knowledge from the source modality to guide the local feature aggregation of 3D tokens, compelling the semantic adaption of any-modality transformers. We conduct extensive experiments to showcase the effectiveness and efficiency of our method. Code and models are released at https://github.com/Ivan-Tang-3D/Any2Point.
Authors: Duy P. Nguyen, Kai-Chieh Hsu, Wenhao Yu, Jie Tan, Jaime F. Fisac
Abstract: Ensuring the safe operation of legged robots in uncertain, novel environments is crucial to their widespread adoption. Despite recent advances in safety filters that can keep arbitrary task-driven policies from incurring safety failures, existing solutions for legged robot locomotion still rely on simplified dynamics and may fail when the robot is perturbed away from predefined stable gaits. This paper presents a general approach that leverages offline game-theoretic reinforcement learning to synthesize a highly robust safety filter for high-order nonlinear dynamics. This gameplay filter then maintains runtime safety by continually simulating adversarial futures and precluding task-driven actions that would cause it to lose future games (and thereby violate safety). Validated on a 36-dimensional quadruped robot locomotion task, the gameplay safety filter exhibits inherent robustness to the sim-to-real gap without manual tuning or heuristic designs. Physical experiments demonstrate the effectiveness of the gameplay safety filter under perturbations, such as tugging and unmodeled irregular terrains, while simulation studies shed light on how to trade off computation and conservativeness without compromising safety.
Authors: Mahsa Shoaran, Uisub Shin, MohammadAli Shaeri
Abstract: Integrating smart algorithms on neural devices presents significant opportunities for various brain disorders. In this paper, we review the latest advancements in the development of three categories of intelligent neural prostheses featuring embedded signal processing on the implantable or wearable device. These include: 1) Neural interfaces for closed-loop symptom tracking and responsive stimulation; 2) Neural interfaces for emerging network-related conditions, such as psychiatric disorders; and 3) Intelligent BMI SoCs for movement recovery following paralysis.
Authors: Fan Shi, Chong Zhang, Takahiro Miki, Joonho Lee, Marco Hutter, Stelian Coros
Abstract: Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques, especially deep reinforcement learning (RL). Controllers employing neural networks have demonstrated empirical and qualitative robustness against real-world uncertainties, including sensor noise and external perturbations. However, formally investigating the vulnerabilities of these locomotion controllers remains a challenge. This difficulty arises from the requirement to pinpoint vulnerabilities across a long-tailed distribution within a high-dimensional, temporally sequential space. As a first step towards quantitative verification, we propose a computational method that leverages sequential adversarial attacks to identify weaknesses in learned locomotion controllers. Our research demonstrates that, even state-of-the-art robust controllers can fail significantly under well-designed, low-magnitude adversarial sequence. Through experiments in simulation and on the real robot, we validate our approach's effectiveness, and we illustrate how the results it generates can be used to robustify the original policy and offer valuable insights into the safety of these black-box policies. Project page: https://fanshi14.github.io/me/rss24.html
Authors: Corinne Aars, Lauren Adams, Xiaokan Tian, Zhaoyu Wang, Colton Wismer, Jason Wu, Pablo Rivas, Korn Sooksatra, Matthew Fendt
Abstract: This study presents the development and evaluation of a ByT5-based multilingual translation model tailored for translating the Bible into underrepresented languages. Utilizing the comprehensive Johns Hopkins University Bible Corpus, we trained the model to capture the intricate nuances of character-based and morphologically rich languages. Our results, measured by the BLEU score and supplemented with sample translations, suggest the model can improve accessibility to sacred texts. It effectively handles the distinctive biblical lexicon and structure, thus bridging the linguistic divide. The study also discusses the model's limitations and suggests pathways for future enhancements, focusing on expanding access to sacred literature across linguistic boundaries.
Authors: Meiling Li, Hongrun Ren, Haixu Xiong, Zhenxing Qian, Xinpeng Zhang
Abstract: Generation models have shown promising performance in various tasks, making trading around machine learning models possible. In this paper, we aim at a novel prompt trading scenario, prompt bundle trading (PBT) system, and propose an online pricing mechanism. Based on the combinatorial multi-armed bandit (CMAB) and three-stage hierarchical Stackelburg (HS) game, our pricing mechanism considers the profits of the consumer, platform, and seller, simultaneously achieving the profit satisfaction of these three participants. We break down the pricing issue into two steps, namely unknown category selection and incentive strategy optimization. The former step is to select a set of categories with the highest qualities, and the latter is to derive the optimal strategy for each participant based on the chosen categories. Unlike the existing fixed pricing mode, the PBT pricing mechanism we propose is more flexible and diverse, which is more in accord with the transaction needs of real-world scenarios. We test our method on a simulated text-to-image dataset. The experimental results demonstrate the effectiveness of our algorithm, which provides a feasible price-setting standard for the prompt marketplaces.
Authors: John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, Ofir Press
Abstract: Language model (LM) agents are increasingly being used to automate complicated tasks in digital environments. Just as humans benefit from powerful software applications, such as integrated development environments, for complex tasks like software engineering, we posit that LM agents represent a new category of end users with their own needs and abilities, and would benefit from specially-built interfaces to the software they use. We investigate how interface design affects the performance of language model agents. As a result of this exploration, we introduce SWE-agent: a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively, far exceeding the previous state-of-the-art achieved with non-interactive LMs. Finally, we provide insight on how the design of the ACI can impact agents' behavior and performance.
Authors: Bruno Deprez, Toon Vanderschueren, Bart Baesens, Tim Verdonck, Wouter Verbeke
Abstract: Money laundering presents a pervasive challenge, burdening society by financing illegal activities. To more effectively combat and detect money laundering, the use of network information is increasingly being explored, exploiting that money laundering necessarily involves interconnected parties. This has lead to a surge in literature on network analytics (NA) for anti-money laundering (AML). The literature, however, is fragmented and a comprehensive overview of existing work is missing. This results in limited understanding of the methods that may be applied and their comparative detection power. Therefore, this paper presents an extensive and systematic review of the literature. We identify and analyse 97 papers in the Web of Science and Scopus databases, resulting in a taxonomy of approaches following the fraud analytics framework of Bockel-Rickermann et al.. Moreover, this paper presents a comprehensive experimental framework to evaluate and compare the performance of prominent NA methods in a uniform setup. The framework is applied on the publicly available Elliptic data set and implements manual feature engineering, random walk-based methods, and deep learning GNNs. We conclude from the results that network analytics increases the predictive power of the AML model with graph neural networks giving the best results. An open source implementation of the experimental framework is provided to facilitate researchers and practitioners to extend upon these results and experiment on proprietary data. As such, we aim to promote a standardised approach towards the analysis and evaluation of network analytics for AML.
Authors: Bangyu Lan, Stefano Stramigioli, Kenan Niu
Abstract: Accurate bone tracking is crucial for kinematic analysis in orthopedic surgery and prosthetic robotics. Traditional methods (e.g., skin markers) are subject to soft tissue artifacts, and the bone pins used in surgery introduce the risk of additional trauma and infection. For electromyography (EMG), its inability to directly measure joint angles requires complex algorithms for kinematic estimation. To address these issues, A-mode ultrasound-based tracking has been proposed as a non-invasive and safe alternative. However, this approach suffers from limited accuracy in peak detection when processing received ultrasound signals. To build a precise and real-time bone tracking approach, this paper introduces a deep learning-based method for anatomical region recognition and bone tracking using A-mode ultrasound signals, specifically focused on the knee joint. The algorithm is capable of simultaneously performing bone tracking and identifying the anatomical region where the A-mode ultrasound transducer is placed. It contains the fully connection between all encoding and decoding layers of the cascaded U-Nets to focus only on the signal region that is most likely to have the bone peak, thus pinpointing the exact location of the peak and classifying the anatomical region of the signal. The experiment showed a 97% accuracy in the classification of the anatomical regions and a precision of around 0.5$\pm$1mm under dynamic tracking conditions for various anatomical areas surrounding the knee joint. In general, this approach shows great potential beyond the traditional method, in terms of the accuracy achieved and the recognition of the anatomical region where the ultrasound has been attached as an additional functionality.
Authors: Zixian Guo, Ming Liu, Zhilong Ji, Jinfeng Bai, Yiwen Guo, Wangmeng Zuo
Abstract: Learning a skill generally relies on both practical experience by doer and insightful high-level guidance by instructor. Will this strategy also work well for solving complex non-convex optimization problems? Here, a common gradient-based optimizer acts like a disciplined doer, making locally optimal update at each step. Recent methods utilize large language models (LLMs) to optimize solutions for concrete problems by inferring from natural language instructions, akin to a high-level instructor. In this paper, we show that these two optimizers are complementary to each other, suggesting a collaborative optimization approach. The gradient-based optimizer and LLM-based optimizer are combined in an interleaved manner. We instruct LLMs using task descriptions and timely optimization trajectories recorded during gradient-based optimization. Inferred results from LLMs are used as restarting points for the next stage of gradient optimization. By leveraging both the locally rigorous gradient-based optimizer and the high-level deductive LLM-based optimizer, our combined optimization method consistently yields improvements over competitive baseline prompt tuning methods. Our results demonstrate the synergistic effect of conventional gradient-based optimization and the inference ability of LLMs. The code is released at https://github.com/guozix/LLM-catalyst.
Authors: Dylan Zhang, Justin Wang, Francois Charton
Abstract: Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow instructions not seen during training remain under-explored. Our investigation begins with a series of synthetic experiments within the theoretical framework of a Turing-complete algorithm called Markov algorithm, which allows fine-grained control over the instruction-tuning data. Generalization and robustness with respect to the training distribution emerge once a diverse enough set of tasks is provided, even though very few examples are provided for each task. We extend these initial results to a real-world application scenario of code generation and find that a more diverse instruction set, extending beyond code-related tasks, improves the performance of code generation. Our observations suggest that a more diverse semantic space for instruction-tuning sets greatly improves the model's ability to follow instructions and perform tasks.
Authors: Hossam M. Zawbaa, Wael Rashwan, Sourav Dutta, Haytham Assem
Abstract: Detecting out-of-scope user utterances is essential for task-oriented dialogues and intent classification. Current methodologies face difficulties with the unpredictable distribution of outliers and often rely on assumptions about data distributions. We present the Dual Encoder for Threshold-Based Re-Classification (DETER) to address these challenges. This end-to-end framework efficiently detects out-of-scope intents without requiring assumptions on data distributions or additional post-processing steps. The core of DETER utilizes dual text encoders, the Universal Sentence Encoder (USE) and the Transformer-based Denoising AutoEncoder (TSDAE), to generate user utterance embeddings, which are classified through a branched neural architecture. Further, DETER generates synthetic outliers using self-supervision and incorporates out-of-scope phrases from open-domain datasets. This approach ensures a comprehensive training set for out-of-scope detection. Additionally, a threshold-based re-classification mechanism refines the model's initial predictions. Evaluations on the CLINC-150, Stackoverflow, and Banking77 datasets demonstrate DETER's efficacy. Our model outperforms previous benchmarks, increasing up to 13% and 5% in F1 score for known and unknown intents on CLINC-150 and Stackoverflow, and 16% for known and 24% % for unknown intents on Banking77. The source code has been released at https://github.com/Hossam-Mohammed-tech/Intent_Classification_OOS.
URLs: https://github.com/Hossam-Mohammed-tech/Intent_Classification_OOS.
Authors: Mohammad Kalbasi, MohammadAli Shaeri, Vincent Alexandre Mendez, Solaiman Shokur, Silvestro Micera, Mahsa Shoaran
Abstract: Advancements in neural engineering have enabled the development of Robotic Prosthetic Hands (RPHs) aimed at restoring hand functionality. Current commercial RPHs offer limited control through basic on/off commands. Recent progresses in machine learning enable finger movement decoding with higher degrees of freedom, yet the high computational complexity of such models limits their application in portable devices. Future RPH designs must balance portability, low power consumption, and high decoding accuracy to be practical for individuals with disabilities. To this end, we introduce a novel attractor-based neural network to realize on-chip movement decoding for next-generation portable RPHs. The proposed architecture comprises an encoder, an attention layer, an attractor network, and a refinement regressor. We tested our model on four healthy subjects and achieved a decoding accuracy of 80.3%. Our proposed model is over 120 and 50 times more compact compared to state-of-the-art LSTM and CNN models, respectively, with comparable (or superior) decoding accuracy. Therefore, it exhibits minimal hardware complexity and can be effectively integrated as a System-on-Chip.
Authors: Miriam Navarro, \'Alvaro Becerra, Roberto Daza, Ruth Cobos, Aythami Morales, Julian Fierrez
Abstract: In this paper, we present an approach in the Multimodal Learning Analytics field. Within this approach, we have developed a tool to visualize and analyze eye movement data collected during learning sessions in online courses. The tool is named VAAD (an acronym for Visual Attention Analysis Dashboard). These eye movement data have been gathered using an eye-tracker and subsequently processed and visualized for interpretation. The purpose of the tool is to conduct a descriptive analysis of the data by facilitating its visualization, enabling the identification of differences and learning patterns among various learner populations. Additionally, it integrates a predictive module capable of anticipating learner activities during a learning session. Consequently, VAAD holds the potential to offer valuable insights into online learning behaviors from both descriptive and predictive perspectives.
Authors: Alaa Nfissi, Wassim Bouachir, Nizar Bouguila, Brian Mishara
Abstract: In speech emotion recognition (SER), using predefined features without considering their practical importance may lead to high dimensional datasets, including redundant and irrelevant information. Consequently, high-dimensional learning often results in decreasing model accuracy while increasing computational complexity. Our work underlines the importance of carefully considering and analyzing features in order to build efficient SER systems. We present a new supervised SER method based on an efficient feature engineering approach. We pay particular attention to the explainability of results to evaluate feature relevance and refine feature sets. This is performed iteratively through feature evaluation loop, using Shapley values to boost feature selection and improve overall framework performance. Our approach allows thus to balance the benefits between model performance and transparency. The proposed method outperforms human-level performance (HLP) and state-of-the-art machine learning methods in emotion recognition on the TESS dataset.
Authors: Matthew Watson, Divyashree Shivakumar Sreepathihalli, Francois Chollet, Martin Gorner, Kiranbir Sodhia, Ramesh Sampath, Tirth Patel, Haifeng Jin, Neel Kovelamudi, Gabriel Rasskin, Samaneh Saadat, Luke Wood, Chen Qian, Jonathan Bischof, Ian Stenbit, Abheesht Sharma, Anshuman Mishra
Abstract: We present the Keras domain packages KerasCV and KerasNLP, extensions of the Keras API for Computer Vision and Natural Language Processing workflows, capable of running on either JAX, TensorFlow, or PyTorch. These domain packages are designed to enable fast experimentation, with a focus on ease-of-use and performance. We adopt a modular, layered design: at the library's lowest level of abstraction, we provide building blocks for creating models and data preprocessing pipelines, and at the library's highest level of abstraction, we provide pretrained ``task" models for popular architectures such as Stable Diffusion, YOLOv8, GPT2, BERT, Mistral, CLIP, Gemma, T5, etc. Task models have built-in preprocessing, pretrained weights, and can be fine-tuned on raw inputs. To enable efficient training, we support XLA compilation for all models, and run all preprocessing via a compiled graph of TensorFlow operations using the tf.data API. The libraries are fully open-source (Apache 2.0 license) and available on GitHub.