论文检索

Liang Du, Henghui Jiang, Xiaodong Li, Yiqing Guo, Yan Chen, Feijiang Li, Peng Zhou, Yuhua Qian

Multi-view clustering (MVC) aims to integrate complementary information from multiple views to enhance clustering performance. Late Fusion Multi-View Clustering (LFMVC) has shown promise by synthesizing diverse clustering results into a unified consensus. However, current LFMVC methods struggle with noisy and redundant partitions and often fail to capture high-order correlations across views. To address these limitations, we present a novel theoretical framework for analyzing the generalization error bounds of multiple kernel k-means, leveraging local Rademacher complexity and principal eigenvalue proportions. Our analysis establishes a convergence rate of O(1/n), significantly improving upon the existing rate in the order of O(sqrt(k/n)). Building on this insight, we propose a low-pass graph filtering strategy within a multiple linear K-means framework to mitigate noise and redundancy, further refining the principal eigenvalue proportion and enhancing clustering accuracy. Experimental results on benchmark datasets confirm that our approach outperforms state-of-the-art methods in clustering performance and robustness.

Kaile Du, Yifan Zhou, Fan Lyu, Yuyang Li, Junzhou Xie, Yixi Shen, Fuyuan Hu, Guangcan Liu

Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only achieve suboptimal performance due to the oversight of the positive-negative imbalance problem, which manifests at both the label and loss levels because of the task-level partial label issue. The imbalance at the label level arises from the substantial absence of negative labels, while the imbalance at the loss level stems from the asymmetric contributions of the positive and negative loss parts to the optimization. To address the issue above, we propose a Rebalance framework for both the Loss and Label levels (RebLL), which integrates two key modules: asymmetric knowledge distillation (AKD) and online relabeling (OR). AKD is proposed to rebalance at the loss level by emphasizing the negative label learning in classification loss and down-weighting the contribution of overconfident predictions in distillation loss. OR is designed for label rebalance, which restores the original class distribution in memory by online relabeling the missing classes. Our comprehensive experiments on the PASCAL VOC and MS-COCO datasets demonstrate that this rebalancing strategy significantly improves performance, achieving new state-of-the-art results even with a vanilla CNN backbone.

Ilan Doron-Arad

We study neural network training (NNT): optimizing a neural network's parameters to minimize the training loss over a given dataset. NNT has been studied extensively under theoretic lenses, mainly on two-layer networks with linear or ReLU activation functions where the parameters can take any real value (here referred to as continuous NNT (C-NNT)). However, less is known about deeper neural networks, which exhibit substantially stronger capabilities in practice. In addition, the complexity of the discrete variant of the problem (D-NNT in short), in which the parameters are taken from a given finite set of options, has remained less explored despite its theoretical and practical significance. In this work, we show that the hardness of NNT is dramatically affected by the network depth. Specifically, we show that, under standard complexity assumptions, D-NNT is not in the complexity class NP even for instances with fixed dimensions and dataset size, having a deep architecture. This separates D-NNT from any NP-complete problem. Furthermore, using a polynomial reduction we show that the above result also holds for C-NNT, albeit with more structured instances. We complement these results with a comprehensive list of NP-hardness lower bounds for D-NNT on two-layer networks, showing that fixing the number of dimensions, the dataset size, or the number of neurons in the hidden layer leaves the problem challenging. Finally, we obtain a pseudo-polynomial algorithm for D-NNT on a two-layer network with a fixed dataset size.

Zhiwei Dong, Mingzhu Shen, Shihao Bai, Xiuying Wei, Jinyang Guo, Ruihao Gong, Song-Lu Chen, Xianglong Liu, Xu-Cheng Yin

Tiny machine learning (TinyML) has attracted heightened attention for its ability to provide low-cost and instantaneous performance on edge devices. Particularly, the commonly used microcontroller unit (MCU) imposes extreme constraints on peak memory (SRAM) and storage (Flash). Existing TinyML methods often rely on a customized and hard-to-obtain inference libraries, as well as necessitate a time-consuming search for a deployable architecture using advanced Neural Architecture Search (NAS) algorithms. To solve these problems, we fully exploit the resources on MCU and deduce hardware-oriented guidelines for designing models under extreme MCU constraints. In detail, we delve into thorough information about the atom operators by collecting the runtime data of Flash, SRAM, and latency to build a dataset named AtomDB. Based on AtomDB, several critical operator guidelines are established to fully utilize limited Flash and SRAM, while minimizing latency. By transferring the guidelines to analyze blocks, we propose a hybrid pattern that organizes appropriate blocks at different network stages to form the AtomNet, a more hardware-oriented architecture, to handle the former SRAM bottleneck and the latter Flash bottleneck. Extensive experiments demonstrate the effectiveness of the exploitation of the hardware characteristics. Remarkably, AtomNet pioneeringly achieve 3.5% accuracy enhancement and more than 15% latency reduction on 320KB MCU using readily available official inference libraries for ImageNet tasks, surpassing the current state-of-the-art method.

Shuyu Dong, Michele Sebag, Kento Uemura, Akito Fujii, Shuang Chang, Yusuke Koyanagi, Koji Maruhashi

Causal learning tackles the computationally demanding task of estimating causal graphs. This paper introduces a new divide-and-conquer approach for causal graph learning, called DCILP. In the divide phase, the Markov blanket MB(Xi) of each variable Xi is identified, and causal learning subproblems associated with each MB(Xi) are independently addressed in parallel. This approach benefits from a more favorable ratio between the number of data samples and the number of variables considered. In counterpart, it can be adversely affected by the presence of hidden confounders, as variables external to MB(Xi) might influence those within it. The reconciliation of the local causal graphs generated during the divide phase is a challenging combinatorial optimization problem, especially in large-scale applications. The main novelty of DCILP is an original formulation of this reconciliation as an integer linear programming (ILP) problem, which can be delegated and efficiently handled by an ILP solver. Through experiments on medium to large scale graphs, and comparisons with state-of-the-art methods, DCILP demonstrates significant improvements in terms of computational complexity, while preserving the learning accuracy on real-world problem and suffering at most a slight loss of accuracy on synthetic problems.

Shaokang Dong, Chao Li, Shangdong Yang, Hongye Cao, Wanqi Yang, Yang Gao

In the field of mixed-motive games, extensive multi-agent learning studies have explored the balance between egoism (individual interest), utilitarianism (collective interest), and egalitarianism (fairness). Traditional approaches often rely on manually designed reward functions, social norms, and alliance/federation mechanisms to transition agents from individualistic behaviors toward cooperative strategies. However, these methods typically require all agents to share private local information or to mandatorily participate in federations, which is impractical in real-world applications. To address these issues, this paper proposes a Flexible-Participation Federation (FPF) framework that allows agents to participate in the federation voluntarily. Furthermore, we extend the federation from a global to a Local Multi-Federation (LMF) framework, enabling agents to form multiple localized federations, thereby promoting more efficient and adaptive cooperation. Theoretical evidence demonstrates that the global FPF model, along with the discrepancy between decentralized egoistic policies and federated utilitarian policies, achieves an O(1/T) convergence rate. Agents in the LMF framework also reach consensus within a sublinear gap. Extensive experiments show that agents opting out of federation participation experience a reduction in egoism, and our approach outperforms multiple baselines in terms of both utilitarianism and egalitarianism.

Peijie Dong, Lujun Li, Zhenheng Tang, Xiang Liu, Zimian Wei, Qiang Wang, Xiaowen Chu

Recent advancements in Zero-shot Neural Architecture Search (NAS) highlight the ability of zero-cost proxies in identifying superior architecture. However, we identify a critical issue with current zero-cost proxies: they aggregate node-wise zero-cost statistics without considering that not all nodes in a neural network equally impact performance estimation. Our observations reveal that node-wise zero-cost statistics significantly vary in their contributions to performance, with each node exhibiting a degree of uncertainty. Based on this insight, we introduce a novel method called Parametric Zero-Cost Proxies (ParZC) framework to enhance the adaptability of zero-cost proxies through parameterization. To address the node indiscrimination, we propose a Mixer Architecture with Bayesian Network (MABN) to explore the node-wise zero-cost statistics and estimate node-specific uncertainty. Moreover, we propose DiffKendall as a loss function to improve ranking consistency. Comprehensive experiments on NAS-Bench-101, 201, and NDS demonstrate the superiority of our proposed ParZC compared to existing zero-shot NAS methods. Additionally, we demonstrate the versatility and adaptability of ParZC on Vision Transformer search space.

Jinzong Dong, Zhaohui Jiang, Dong Pan, Haoyang Yu

Confidence calibration of classification models is a technique to estimate the true posterior probability of the predicted class, which is critical for ensuring reliable decision-making in practical applications. Existing confidence calibration methods mostly use statistical techniques to estimate the calibration curve from data or fit a user-defined calibration function, but often overlook fully mining and utilizing the prior distribution behind the calibration curve. However, a well-informed prior distribution can provide valuable insights beyond the empirical data under the limited data or low-density regions of confidence scores. To fill this gap, this paper proposes a new method that integrates the prior distribution behind the calibration curve with empirical data to estimate a continuous calibration curve, which is realized by modeling the sampling process of calibration data as a binomial process and maximizing the likelihood function of the binomial process. We prove that the calibration curve estimating method is Lipschitz continuous with respect to data distribution and requires smaller sample sizes than histogram binning. Also, a new calibration metric has been designed, leveraging the estimated calibration curve to estimate the true calibration error, and it has been proven to be a consistent calibration measure. Furthermore, realistic calibration datasets can be generated by the binomial process modeling from a preset true calibration curve and confidence score distribution, which can serve as a benchmark to measure and compare the discrepancy between existing calibration metrics and the true calibration error. The effectiveness of our calibration method and metric are verified in real-world and simulated data. We believe our exploration of integrating prior distributions with empirical data will guide the development of better-calibrated models, contributing to trustworthy AI.

Marharyta Domnich, Julius Välja, Rasmus Moorits Veski, Giacomo Magnifico, Kadi Tulver, Eduard Barbu, Raul Vicente

As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to obtain a given output and, hence, are crucial for supporting decision-making. Despite their importance, the evaluation of these explanations often lacks grounding in user studies and remains fragmented, with existing metrics not fully capturing human perspectives. To address this challenge, we developed a diverse set of 30 counterfactual scenarios and collected ratings across 8 evaluation metrics from 206 respondents. Subsequently, we fine-tuned different Large Language Models (LLMs) to predict average or individual human judgment across these metrics. Our methodology allowed LLMs to achieve an accuracy of up to 63% in zero-shot evaluations and 85% (over a 3-classes prediction) with fine-tuning across all metrics. The fine-tuned models predicting human ratings offer better comparability and scalability in evaluating different counterfactual explanation frameworks.

Bao Gia Doan, Afshar Shamsi, Xiao-Yu Guo, Arash Mohammadi, Hamid Alinejad-Rokny, Dino Sejdinovic, Damien Teney, Damith C. Ranasinghe, Ehsan Abbasnejad

Computational complexity of Bayesian learning is impeding its adoption in practical, large-scale tasks, despite demonstrations of significant merits such as improved robustness and resilience to unseen or out-of-distribution inputs over their non-Bayesian counterparts. Although, Deep ensemble methods (Seligmann et al. 2024; Lakshminarayanan, Pritzel, and Blundell 2017) have proven to be highly effective for Bayesian deep learning, their practical application is hindered by substantial computational cost. In this study, we introduce an innovative framework to mitigate the computational burden of ensemble Bayesian deep learning. We explore a more feasible alternative, inspired by the recent success of low-rank adapters, we introduce Bayesian Low-Rank LeArning (Bella). We show, i) Bella achieves a dramatic reduction in the number of trainable parameters required to approximate a Bayesian posterior; and ii) it not only maintains, but in some instances, surpasses the performance–in accuracy and out-of-distribution generalisation–of conventional Bayesian learning methods and non-Bayesian baselines. Our extensive empirical evaluation in large-scale tasks such as ImageNet, CAMELYON17, DomainNet, VQA with CLIP, LLaVA demonstrate the effectiveness and versatility of Bella in building highly scalable and practical Bayesian deep models for real-world applications.

Yanna Ding, Zijie Huang, Xiao Shou, Yihang Guo, Yizhou Sun, Jianxi Gao

Learning curve extrapolation predicts neural network performance from early training epochs and has been applied to accelerate AutoML, facilitating hyperparameter tuning and neural architecture search. However, existing methods typically model the evolution of learning curves in isolation, neglecting the impact of neural network (NN) architectures, which influence the loss landscape and learning trajectories. In this work, we explore whether incorporating neural network architecture improves learning curve modeling and how to effectively integrate this architectural information. Motivated by the dynamical system view of optimization, we propose a novel architecture-aware neural differential equation model to forecast learning curves continuously. We empirically demonstrate its ability to capture the general trend of fluctuating learning curves while quantifying uncertainty through variational parameters. Our model outperforms current state-of-the-art learning curve extrapolation methods and pure time-series modeling approaches for both MLP and CNN-based learning curves. Additionally, we explore the applicability of our method in Neural Architecture Search scenarios, such as training configuration ranking.

Wenjun Ding, Ying An, Lixing Chen, Shichao Kan, Fan Wu, Zhe Qu

Federated Adversarial Learning (FAL) is a robust framework for resisting adversarial attacks on federated learning. Although some FAL studies have developed efficient algorithms, they primarily focus on convergence performance and overlook generalization. Generalization is crucial for evaluating algorithm performance on unseen data. However, generalization analysis is more challenging due to non-smooth adversarial loss functions. A common approach to addressing this issue is to leverage smoothness approximation. In this paper, we develop algorithm stability measures to evaluate the generalization performance of two popular FAL algorithms: Vanilla FAL (VFAL) and Slack FAL (SFAL), using three different smooth approximation methods: 1) Surrogate Smoothness Approximation (SSA), (2) Randomized Smoothness Approximation (RSA), and (3) Over-Parameterized Smoothness Approximation (OPSA). Based on our in-depth analysis, we answer how to properly set the smoothness approximation method to mitigate generalization error in FAL. Moreover, we identify RSA as the most effective generalization error reduction method. In highly data-heterogeneous scenarios, we also recommend employing SFAL to mitigate the deterioration of generalization performance caused by heterogeneity. Based on our theoretical results, we provide insights to help develop more efficient FAL algorithms, such as designing new metrics and dynamic aggregation rules to mitigate heterogeneity.

Francesco Diana, Othmane Marfoq, Chuan Xu, Giovanni Neglia, Frédéric Giroire, Eoin Thomas

Federated Learning (FL) enables multiple clients, such as mobile phones and IoT devices, to collaboratively train a global machine learning model while keeping their data localized. However, recent studies have revealed that the training phase of FL is vulnerable to reconstruction attacks, such as attribute inference attacks (AIA), where adversaries exploit exchanged messages and auxiliary public information to uncover sensitive attributes of targeted clients. While these attacks have been extensively studied in the context of classification tasks, their impact on regression tasks remains largely unexplored. In this paper, we address this gap by proposing novel model-based AIAs specifically designed for regression tasks in FL environments. Our approach considers scenarios where adversaries can either eavesdrop on exchanged messages or directly interfere with the training process. We benchmark our proposed attacks against state-of-the-art methods using real-world datasets. The results demonstrate a significant increase in reconstruction accuracy, particularly in heterogeneous client datasets, a common scenario in FL. The efficacy of our model-based AIAs makes them better candidates for empirically quantifying privacy leakage for federated regression tasks.

Joshua DeOliveira, Walter Gerych, Elke Rundensteiner

Developments in deep neural nets have trended towards increasingly larger overparameterized architectures, resulting in lengthy training sessions with ever more elusive training dynamics. Thus, ensuring these models learn accurate generalizable representations of data efficiently is challenging. Previous works have developed specialized techniques from data-pruning, architecture selection, pseudo-label generation, bias identification, or label refurbishment to improve downstream training. Problematically, most methods require prohibitively expensive iterative model training. In this paper, we demonstrate that we can exploit the recent neural tangent kernel (NTK) theory for understanding and improving model training behavior before ever training a model. First, we show a powerful signal derived from the NTK theory can be computed remarkably fast. We then leverage this signal for the design of a unified suite of surprisingly effective tools for the four important tasks of architecture selection, pseudo-label verification, bias identification, and label refurbishment, all requiring zero model training.

Zhaoyuan Deng, Amith Ananthram, Kathleen McKeown

Live comments, also known as Danmaku, are user-generated messages that are synchronized with video content. These comments overlay directly onto streaming videos, capturing viewer emotions and reactions in real-time. While prior work has leveraged live comments in affective analysis, its use has been limited due to the relative rarity of live comments across different video platforms. To address this, we first construct the Live Comment for Affective Analysis (LCAffect) dataset, which contains live comments for English and Chinese videos spanning diverse genres that elicit a wide spectrum of emotions. Then, using this dataset, we use contrastive learning to train a video encoder to produce synthetic live comment features for enhanced multimodal affective content analysis. Through comprehensive experimentation on a wide range of affective analysis tasks (sentiment, emotion recognition, and sarcasm detection) in both English and Chinese, we demonstrate that these synthetic live comment features significantly improve performance over state-of-the-art methods.

Shilong Deng, Zetao Zheng, Hongcai He, Paul Weng, Jie Shao

A major challenge in Reinforcement Learning (RL) is the difficulty of learning an optimal policy from sparse rewards. Prior works enhance online RL with conventional Imitation Learning (IL) via a handcrafted auxiliary objective, at the cost of restricting the RL policy to be sub-optimal when the offline data is generated by a non-expert policy. Instead, to better leverage valuable information in offline data, we develop Generalized Imitation Learning from Demonstration (GILD), which meta-learns an objective that distills knowledge from offline data and instills intrinsic motivation towards the optimal policy. Distinct from prior works that are exclusive to a specific RL algorithm, GILD is a flexible module intended for diverse vanilla off-policy RL algorithms. In addition, GILD introduces no domain-specific hyperparameter and minimal increase in computational cost. In four challenging MuJoCo tasks with sparse rewards, we show that three RL algorithms enhanced with GILD significantly outperform state-of-the-art methods.

Qi Deng, Shuaicheng Niu, Ronghao Zhang, Yaofo Chen, Runhao Zeng, Jian Chen, Xiping Hu

Test-time adaptation (TTA) aims to fine-tune a trained model online using unlabeled testing data to adapt to new environments or out-of-distribution data, demonstrating broad application potential in real-world scenarios. However, in this optimization process, unsupervised learning objectives like entropy minimization frequently encounter noisy learning signals. These signals produce unreliable gradients, which hinder the model’s ability to converge to an optimal solution quickly and introduce significant instability into the optimization process. In this paper, we seek to resolve these issues from the perspective of optimizer design. Unlike prior TTA using manually designed optimizers like SGD, we employ a learning-to-optimize approach to automatically learn an optimizer, called Meta Gradient Generator (MGG). Specifically, we aim for MGG to effectively utilize historical gradient information during the online optimization process to optimize the current model. To this end, in MGG, we design a lightweight and efficient sequence modeling layer -- gradient memory layer. It exploits a self-supervised reconstruction loss to compress historical gradient information into network parameters, thereby enabling better memorization ability over a long-term adaptation process. We only need a small number of unlabeled samples to pre-train MGG, and then the trained MGG can be deployed to process unseen samples. Promising results on ImageNet-C/R/Sketch/A indicate that our method surpasses current state-of-the-art methods with fewer updates, less data, and significantly shorter adaptation times. Compared with a previous SOTA SAR, we achieve 7.4% accuracy improvement and 4.2x faster adaptation speed on ImageNet-C.

Juncan Deng, Shuaiting Li, Zeyu Wang, Hong Gu, Kedong Xu, Kejie Huang

The Diffusion Transformers Models (DiTs) have transitioned the network architecture from traditional UNets to transformers, demonstrating exceptional capabilities in image generation. Although DiTs have been widely applied to high-definition video generation tasks, their large parameter size hinders inference on edge devices. Vector quantization (VQ) can decompose model weight into a codebook and assignments, allowing extreme weight quantization and significantly reducing memory usage. In this paper, we propose VQ4DiT, a fast post-training vector quantization method for DiTs. We found that traditional VQ methods calibrate only the codebook without calibrating the assignments. This leads to weight sub-vectors being incorrectly assigned to the same assignment, providing inconsistent gradients to the codebook and resulting in a suboptimal result. To address this challenge, VQ4DiT calculates the candidate assignment set for each weight sub-vector based on Euclidean distance and reconstructs the sub-vector based on the weighted average. Then, using the zero-data and block-wise calibration method, the optimal assignment from the set is efficiently selected while calibrating the codebook. VQ4DiT quantizes a DiT XL/2 model on a single NVIDIA A100 GPU within 20 minutes to 5 hours depending on the different quantization settings. Experiments show that VQ4DiT establishes a new state-of-the-art in model size and performance trade-offs, quantizing weights to 2-bit precision while retaining acceptable image generation quality.

Jingda Deng, Jianyong Sun, Qingfu Zhang, Hui Li

Multi-objective Bayesian optimization (MOBO) aims to optimize multiple competing objective functions in the expensive-to-evaluate scenario. The Expected Hypervolume Improvement (EHVI) is a commonly used acquisition function for MOBO and shows a good performance. However, the computation of EHVI becomes challenging as the number of objective functions grows. In this paper, we revisit the formulation of EHVI, as well as its multi-point counterpart qEHVI, and derive much simpler analytic expressions for them. The main contributions of this paper include: (1) first formulating EHVI as a particular hypervolume improvement, and thus immediately obtaining a formal proof of its NP-hardness, faster algorithms in both theory and practice, and more results on its derivatives; (2) first obtaining the analytic expressions of qEHVI for any q > 1 and m ≥ 2 where m is the number of objectives; and (3) demonstrating the advantages of our formulation over existing exact and approximation methods for computing EHVI and qEHVI through a large number of numerical experiments.

Jiaxin Deng, Junbiao Pang, Baochang Zhang, Guodong Guo

Sharpness-Aware Minimization (SAM) has emerged as a promising approach for effectively reducing the generalization error. However, SAM incurs twice the computational cost compared to the base optimizer (e.g., SGD). We propose Asymptotic Unbiased data sampling to accelerate SAM (AUSAM), which maintains the model's generalization capacity while significantly enhancing computational efficiency. Concretely, we probabilistically sample a subset of data points beneficial for SAM optimization based on a theoretically guaranteed criterion, i.e., the Gradient Norm of each Sample (GNS). We further approximate the GNS by evaluating the difference in loss values before and after perturbation in SAM. As a plug-and-play, architecture-agnostic method, our approach consistently accelerates SAM across various tasks and networks, i.e., classification, human pose estimation, and network quantization. On CIFAR-10/100 and Tiny-ImageNet, AUSAM achieves results comparable to SAM while providing a speedup of over 70%. By adjusting hyperparameters, AUSAM can match the speed of the base optimizer while significantly surpassing the base optimizer's performance. Compared to recent dynamic data pruning methods, AUSAM is better suited for SAM and excels in maintaining performance. Additionally, AUSAM accelerates optimization in human pose estimation and model quantization without sacrificing performance, demonstrating its broad practicality.