检索结果-内蒙古大学图书馆

Discovering Personalized Characteristic Communities in Attributed Graphs

学校读者我要写书评

暂无评论

Discovering Personalized Characteristic Communities in Attri...

International Conference on data engineering

作者： Yudong Niu Yuchen Li Panagiotis Karras Yanhao Wang Zhao Li School of Computing and Information Systems Singapore Management University Singapore Department of Computer Science University of Copenhagen Copenhagen Denmark School of Data Science and Engineering East China Normal University Shanghai China Zhejiang Lab Hangzhou China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

What is the widest community in which a person exercises a strong impact? Although extensive attention has been devoted to searching communities containing given individuals, the problem of finding their unique communities of influence has barely been examined. In this paper, we study the novel problem of Characteristic cOmmunity Discovery (COD) in attributed graphs. Our goal is to identify the largest community, taking into account the query attribute, in which the query node has a significant impact. The key challenge of the COD problem is that it requires evaluating the influence of the query node over a large number of hierarchically structured communities. We first propose a novel compressed COD evaluation approach to accelerate the influence estimation by eliminating redundant computations for overlapping communities. Then, we further devise a local hierarchical reclustering method to alleviate the skewness of hierarchical communities generated by global clustering for a specific query attribute. Extensive experiments confirm the effectiveness and efficiency of our solutions to COD: they find characteristic communities better than existing community search methods by several quality measures and achieve up to 25 x speedups against well-crafted baselines.

关键词： Estimation Search problems data engineering

S2AC: ENERGY-BASED REINFORCEMENT LEARNING WITH STEIN SOFT ACTOR CRITIC

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Messaoud, Safa Mokeddem, Billel Xue, Zhenghai Pang, Linsey An, Bo Chen, Haipeng Chawla, Sanjay Qatar Computing Research Institute Hamad Bin Khalifa University Qatar School of Computer Science and Engineering Nanyang Technological University Singapore SalesForce Skywork AI Singapore Data Science William & Mary

Learning expressive stochastic policies instead of deterministic ones has been proposed to achieve better stability, sample complexity, and robustness. Notably, in Maximum Entropy Reinforcement Learning (MaxEnt RL), the policy is modeled as an expressive Energy-Based Model (EBM) over the Q-values. However, this formulation requires the estimation of the entropy of such EBMs, which is an open problem. To address this, previous MaxEnt RL methods either implicitly estimate the entropy, resulting in high computational complexity and variance (SQL), or follow a variational inference procedure that fits simplified actor distributions (e.g., Gaussian) for tractability (SAC). We propose Stein Soft Actor-Critic (S2AC), a MaxEnt RL algorithm that learns expressive policies without compromising efficiency. Specifically, S2AC uses parameterized Stein Variational Gradient Descent (SVGD) as the underlying policy. We derive a closed-form expression of the entropy of such policies. Our formula is computationally efficient and only depends on first-order derivatives and vector products. Empirical results show that S2AC yields more optimal solutions to the MaxEnt objective than SQL and SAC in the multi-goal environment, and outperforms SAC and SQL on the MuJoCo benchmark. © 2024, CC BY.

关键词： Reinforcement learning

A Client-Server Based Recognition System: Non-Contact Single/Multiple Emotional and Behavioral State Assessment Methods

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Zhu, Xianxun Liu, Zhaozhao Cambria, Erik Yu, Xiaohan Fan, Xuhui Chen, Hui Wang, Rui School of Communication and Information Engineering Shanghai University No. 99 Shangda Road Shanghai Shanghai200444 China College of Computing and Data Science Nanyang Technological University 50 Nanyang Ave Singapore639798 Singapore School of Computing Macquarie University Balaclava Road North RydeNSW2109 Australia

In the current global health context, the demand for precise assessments of mental states is rapidly increasing. Traditional methods typically rely on face-to-face interactions, which are not only time-consuming but also highly subjective. To address this, contactless assessment methods based on audio and video can be employed. However, existing solutions often lack a comprehensive end-to-end system that integrates voice, text, imagery, and physical gestures—key aspects of concern for medical professionals. In response, this study introduces a client-server based multimodal emotion and behavior recognition system. This system merges multiple modalities including voice, text, facial expressions, and body movements to achieve a contactless, end-to-end assessment of mental states. It not only tailors analysis to the specific needs of different conditions but also generates customized diagnostic reports, significantly enhancing the efficiency and accuracy of assessments. Furthermore, to optimize diagnostic efficiency and decision-making accuracy, we have developed an intuitive visual interface. We have validated and tested this system in actual hospital settings, meeting the fundamental requirements of physicians for mental state analysis. The open-source code for this system is available at: \url{https://***/SHULiuZZ/RCHBAS}. © 2024, The Authors. All rights reserved.

关键词： Open systems

ARE YOU SURE? ENHANCING MULTIMODAL PRE-TRAINING WITH MISSING MODALITIES THROUGH UNCERTAINTY ESTIMATION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Nguyen, Duy A. Do, Quan Huu Doan, Khoa D. Do, Minh N. Siebel School of Computing and Data Science University of Illinois Urbana-ChampaignIL United States College of Engineering and Computer Science VinUniversity Hanoi Viet Nam Department of Electrical and Computer Engineering University of Illinois Urbana-ChampaignIL United States

Multimodal learning has demonstrated incredible successes by integrating diverse data sources, yet it often relies on the availability of all modalities - an assumption that rarely holds in real-world applications. Pretrained multimodal models, while effective, struggle when confronted with small-scale and incomplete datasets (i.e., missing modalities), limiting their practical applicability. Previous studies on reconstructing missing modalities have overlooked the reconstruction’s potential unreliability, which could compromise the quality of the final outputs. We present SURE (Scalable Uncertainty and Reconstruction Estimation), a novel framework that extends the capabilities of pretrained multimodal models by introducing latent space reconstruction and uncertainty estimation for both reconstructed modalities and downstream tasks. Our method is architecture-agnostic, reconstructs missing modalities, and delivers reliable uncertainty estimates, improving both interpretability and performance. SURE introduces a unique Pearson Correlation-based loss and applies statistical error propagation in deep networks for the first time, allowing precise quantification of uncertainties from missing data and model predictions. Extensive experiments across tasks such as sentiment analysis, genre classification, and action recognition show that SURE consistently achieves state-of-the-art performance, ensuring robust predictions even in the presence of incomplete data. © 2025, CC BY.

关键词：

Beyond the Limit of Weight-Sharing: Pioneering Space-Evolving NAS with Large Language Models

学校读者我要写书评

暂无评论

Beyond the Limit of Weight-Sharing: Pioneering Space-Evolvin...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiu Su Shan You Hongyan Xu Xiuxing Li Jun Long Yi Chen Chang Xu Big Data Institute Central South University School of Computer Science Faculty of Engineering The University of Sydney SenseTime Research School of Computer Science and Engineering University of New South Wales Institute of Computing Technology Chinese Academy of Sciences School of Computer Science Hong Kong University of Science and Technology

Large language models (LLMs) offer impressive performance across diverse fields, but their increasing complexity raises both design costs and the need for specialized expertise. These challenges are intensified for Neural Architecture Search (NAS) methods reliant on weight-sharing techniques. This paper introduces GNAS, a new NAS method that boosts the search process with the aid of LLMs for efficient model discovery. With insights from existing architectures, GNAS swiftly identifies superior models that can adapt to changing resource constraints. We provide a mathematical framework to facilitate the transfer of knowledge across different model sizes, thereby improving search efficiency. Our experiments conducted on ImageNet, NAS-Bench-Macro, and ChannelBench-Macro confirm the effectiveness of GNAS across both CNN and Transformer architectures.

关键词：

The Analysis for the Traffic Risks in Barcelona before and after the COVID-19 Based on Deep Learning 2

学校读者我要写书评

暂无评论

The Analysis for the Traffic Risks in Barcelona before and a...

2nd International Seminar on Artificial Intelligence, Networking and Information Technology, AINIT 2021

作者： Shao, Yinghui Zhang, Enkai Han, Ziheng School of Computing Wuhun China Guizhou University College of Large Data and Information Engineering Guizhou China Harbin Engineering University College of Computer Science and Technology Harbin China

ISBN: (纸本)9781665412964

Big Traffic data [1] is cross-border multi-source data for multiple industries, but traffic roads have brought significant economic and social benefits, the number of traffic accidents and casualties is on the rise. Among them, traffic accidents are related to many factors, such as weather and population density. The data set used in this article is open source in Barcelona. The Random Forest algorithm is used to screen essential risk factors, establish a traffic risk prediction model, and compare traffic risks before and after COVID-19. It is concluded that the outbreak of the new crown virus -19-19 has a great impact on people's travel and transportation. Finally, the R square of the model established by Random Forest is 0.9. The K-means clustering algorithm is used to determine the location of the accident handling centre. Moreover, the scope of each accident risk management centre can cover more than 85 percent of traffic accident sites from 2016 to 2020. © 2021 IEEE.

关键词： Decision trees

Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yu, Yi Xia, Song Lin, Xun Kong, Chenqi Yang, Wenhan Lu, Shijian Tan, Yap-Peng Kot, Alex C. Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Computer Science and Engineering Beihang University Beijing China College of Computing and Data Science Nanyang Technological University Singapore

Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive unseen models in black-box scenarios. Despite the widespread exploration of defense methods, including those on transferability, they show limitations: inefficient deployment, ineffective defense, and degraded performance on clean images. In this work, we introduce a novel training paradigm aimed at enhancing robustness against transferable adversarial examples (TAEs) in a more efficient and effective way. We propose a model that exhibits random guessing behavior when presented with clean data x as input, and generates accurate predictions when with triggered data x + τ. Importantly, the trigger τ remains constant for all data instances. We refer to these models as models with trigger activation. We are surprised to find that these models exhibit certain robustness against TAEs. Through the consideration of first-order gradients, we provide a theoretical analysis of this robustness. Moreover, through the joint optimization of the learnable trigger and the model, we achieve improved robustness to transferable attacks. Extensive experiments conducted across diverse datasets, evaluating a variety of attacking methods, underscore the effectiveness and superiority of our approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep neural networks

Free-rider and conflict aware collaboration formation for cross-silo federated learning 24

学校读者我要写书评

暂无评论

Free-rider and conflict aware collaboration formation for cr...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Mengmeng Chen Xiaohu Wu Xiaoli Tang Tiantian He Yew-Soon Ong Qiqi Liu Qicheng Lao Han Yu Beijing University of Posts and Telecommunications China College of Computing and Data Science Nanyang Technological University Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore and Centre for Frontier AI Research Agency for Science Technology and Research Singapore College of Computing and Data Science Nanyang Technological University Singapore and Institute of High Performance Computing Agency for Science Technology and Research Singapore and Centre for Frontier AI Research Agency for Science Technology and Research Singapore School of Engineering Westlake University China

ISBN: (纸本)9798331314385

Federated learning (FL) is a machine learning paradigm that allows multiple FL participants (FL-PTs) to collaborate on training models without sharing private data. Due to data heterogeneity, negative transfer may occur in the FL training process. This necessitates FL-PT selection based on their data complementarity. In cross-silo FL, organizations that engage in business activities are key sources of FL-PTs. The resulting FL ecosystem has two features: (i) self-interest, and (ii) competition among FL-PTs. This requires the desirable FL-PT selection strategy to simultaneously mitigate the problems of free riders and conflicts of interest among competitors. To this end, we propose an optimal FL collaboration formation strategy-FedEgoists-which ensures that: (1) a FL-PT can benefit from FL if and only if it benefits the FL ecosystem, and (2) a FL-PT will not contribute to its competitors or their supporters. It provides an efficient clustering solution to group FL-PTs into coalitions, ensuring that within each coalition, FL-PTs share the same interest. We theoretically prove that the FL-PT coalitions formed are optimal since no coalitions can collaborate together to improve the utility of any of their members. Extensive experiments on widely adopted benchmark datasets demonstrate the effectiveness of FedEgoists compared to nine state-of-the-art baseline methods, and its ability to establish efficient collaborative networks in cross-silos FL with FL-PTs that engage in business activities.

关键词：

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab China School of Information and Communication Technology Griffith University Australia University of Technology Sydney Australia RMIT University Australia

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: SPONGE for triggering widespread misidentifications and BLINDING for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement (∼10%-60% absolute and ∼2-7× relative) in attack efficacy over state-of-the-art attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Denial-of-service attack