检索结果-内蒙古大学图书馆

Advanced Maximal Biclique Enumeration on GPUs Using Bitmaps

IEEE Transactions on Computers 2025年

作者： Pan, Zhe He, Shuibing Li, Xu Zhang, Xuechen Wang, Rui Yin, Yanlong Chen, Gang Zhejiang University State Key Laboratory of Blockchain and Data Security Hangzhou310027 China Zhejiang University College of Computer Science and Technology Hangzhou310027 China Hangzhou310051 China Washington State University Vancouver School of Engineering and Computer Science VancouverWA98686 United States

Maximal biclique enumeration (MBE) in bipartite graphs is an important problem in data mining with many real-world applications. Parallel MBE algorithms for GPUs are needed for MBE acceleration leveraging its many computing cores. However, enumerating maximal bicliques using GPUs has three main challenges including large memory requirement, thread divergence, and load imbalance. In this paper, we propose GMBE+, an advanced GPU solution for the MBE problem. To overcome the challenges, we design (1) a node-reuse approach to reduce GPU memory usage with advanced node pruning, (2) a bitmap-based set intersection approach to minimize thread divergence, and (3) a load-aware task scheduling framework to achieve load balance among threads within GPU warps, facilitated by a novel set union approach. Our experiments reveal that GMBE+ is 1.2× faster than the latest GPU-based MBE algorithm GMBE on average when running on the same NVIDIA A100 GPU. © 1968-2012 IEEE.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Animal Pose Estimation with Skeleton Anomaly-Aware Learning

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Han, Le Chen, Kaixuan Zhao, Lei Jiang, Yangbo Wang, Pengfei Zheng, Nenggan Zhejiang Hangzhou310007 China Zhejiang University College of Computer Science and Technology Zhejiang Hangzhou310007 China Zhejiang University State Key Laboratory of Blockchain and Data Security Zhejiang Hangzhou310007 China Institute of Blockchain and Data Security. China Zhejiang University School of Software Technology Ningbo China Zhejiang University State Key Lab of Brain-Machine Intelligence Hangzhou310007 China Zhejiang Provincial Government ZJU Collaborative Innovation Center for Artificial Intelligence by MOE Hangzhou310007 China Bengbu University School of Computer and Information Engineering Bengbu233030 China

Animal pose estimation is often constrained by the scarcity of annotations and the diversity of scenarios and species. The pseudo-label generation based unsupervised domain adaptation paradigm, which discriminates the predicted keypoints of unlabeled data based on the skeleton position consistency, has demonstrated effectiveness for such problems. However, existing methods generate pseudo-labels with massive false positives, because they cannot effectively distinguish sample pairs with the same errors. In this study, we propose a cross-domain animal pose estimation model from a novel perspective of skeleton anomaly learning. We construct a graph contrastive learning mechanism to acquire the skeleton anomaly-aware knowledge, which enables the generation of accurate pseudo-labels for target domain and imposes graph constraint on unlabeled data. And a skeleton anomaly-feedback based domain adaptation framework is designed to facilitate implicit alignment of object-specific features and joint training of cross-domain. Besides, we propose a novel rat pose dataset named UDARP-9.4K to address the gap of small-sized animal pose datasets encompassing diverse experimental scenarios. The related datasets are reviewed and evaluated in detail. Extensive experiments are conducted on UDARP-9.4K and two public datasets to demonstrate the superiority of the proposed model in cross-scenarios and cross-species animal pose estimation tasks. Further analysis reveals the effectiveness of the proposed model for skeleton structure feature learning. The UDARP-9.4K dataset is available here. © 1991-2012 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

On Optimizing Inter-and Intra-Chiplet Interconnection Topologies for Robust Multi-Chiplet Systems

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Wang, Xiaohang Xu, Miao Singh, Amit Kumar Jiang, Yingtao Yang, Mei Zhejiang University State Key Laboratory of Blockchain and Data Security China Hangzhou China South China University of Technology School of Software Engineering China University of Essex School of Computer Science and Electronic Engineering United Kingdom University of Nevada Department of Electrical and Computer Engineering Las Vegas United States

Inter-and intra-chiplet interconnection networks play a vital role in the operation of many core systems made of multiple chiplets. However, these networks are susceptible to faults caused by manufacturing defects and attacks resulting from the malicious insertion of hardware Trojans and backdoors. Unlike conventional fault-tolerant or countermeasure methods, this paper focuses on optimizing network robustness to withstand both faults and attacks, while considering the constraints of chiplet area and power budget. To achieve this, this paper first defines network robustness as a quantifiable measure based on various network parameters, after which an optimization problem is formulated to optimize the robustness of the network topology. To efficiently solve this problem, a reinforcement learning algorithm is proposed. Experimental results demonstrate that the proposed method is capable of generating inter-and intra-chiplet interconnection networks that are significantly more robust than existing topology generation methods. Specifically, the proposed method improves robustness over ButterDonut and Kite, respectively by an average of 10.88% and 14.06% under random faults and by 9.37% and 7.81% under targeted attacks. These experimental results confirm that the proposed method is capable of generating robust inter-and intra-chiplet interconnection networks that can withstand both faults and attacks. By optimizing the network topology’s robustness, it provides a valuable contribution to the design and security of chiplet-based core systems. © 2025 IEEE. All rights reserved

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Target-Directed Progressive Gradient Adjusting for transfer learning

引用

Pattern Recognition 2025年 167卷

作者： Bei, Yijun Gao, Kewei Zhao, Zhuoyang Lin, Sen Liu, Erteng Feng, Zunlei School of Software Technology Zhejiang University No. 1689 Jiangnan Road Ningbo315048 China Eastern Institute of Technology No. 568 Tongxin Road Zhuangshi Street Zhenhai District Ningbo315201 China State Key Laboratory of Blockchain and Data Security Zhejiang University No. 38 Zheda Road Xihu District Hangzhou310027 China

Deep learning has revolutionized various tasks and achieved impressive performance, relying on abundant data. Transfer learning has emerged as a promising approach to address the challenges posed by limited data in target domains. Existing techniques typically involve transferring knowledge from pre-trained models in the source domain to the target domain through regularization strategies. These strategies constrain the fine-tuning process within a restricted optimization space, often with limited supervision from target domain samples. While these regularization techniques contribute to good performance, they can also result in the retention of significant source domain knowledge, hindering the optimization toward an ideal solution for the target domain. This paper presents a novel technique, Target-directed Progressive Gradient Adjusting (TPGA), for transfer learning. Unlike the traditional pre-training and fine-tuning paradigm, TPGA progressively adjusts the gradient direction of source domain samples during each iteration, guided by a small number of target domain samples. A theoretical proof of the convergence of TPGA is provided from a gradient optimization perspective. A new transfer learning framework based on TPGA is then proposed. Extensive experiments on image classification and segmentation tasks demonstrate that TPGA outperforms state-of-the-art methods, achieving superior transfer learning performance, especially in scenarios with limited target domain data. © 2025

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptive Label Refinement for label noise learning

引用

Neurocomputing 2025年 639卷

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China School of Computer Science and Technology Hainan University Hainan Haikou570228 China Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing complex manually designed strategies, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in models that are overly sensitive to hyperparameters and challenging to train. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples, proposing a simple yet highly applicable method called Adaptive Label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model's predictions to reduce the risk of fitting incorrect labels. Then, by introducing entropy loss, the model adaptively ’harden’ the high-confidence soft labels based on the confidence differences, guiding the model to focus more on learning from clean samples. This approach is simple and efficient, requiring no auxiliary datasets and minimal hyperparameter tuning, making it more adaptable than existing methods that require careful adjustments for different datasets. We validate ALR's effectiveness through experiments on benchmark datasets with artificial label noise (CIFAR-10/100) and real-world datasets with inherent noise (ANIMAL-10N, Clothing1M, WebVision). The results show that ALR outperforms state-of-the-art methods. © 2025

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

NegCPARBP: Enhancing Privacy Protection for Cross-Project Aging-Related Bug Prediction Based on Negative database

引用

IEEE Transactions on Emerging Topics in Computing 2025年

作者： Zhao, Dongdong Liu, Zhihui Zhang, Fengji Liu, Lei Keung, Jacky Wai Yu, Xiao Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan China Wuhan University of Technology Chongqing Research Institute Chongqing China City University of Hong Kong Department of Computer Science Hong Kong Xi'an Jiaotong University School of Electronic Science and Engineering Xi'an China Zhejiang University State Key Laboratory of Blockchain and Data Security Hangzhou China

The emergence of Aging-Related Bugs (ARBs) poses a significant challenge to software systems, resulting in performance degradation and increased error rates in resourceintensive systems. Consequently, numerous ARB prediction methods have been developed to mitigate these issues. However, in scenarios where training data is limited, the effectiveness of ARB prediction is often suboptimal. To address this problem, CrossProject Aging-Related Bug Prediction (CPARBP) is proposed, which utilizes data from other projects (i.e., source projects) to train a model aimed at predicting potential ARBs in a target project. However, the use of source-project data raises privacy concerns and discourages companies from sharing their data. Therefore, we propose a method called Cross-Project AgingRelated Bug Prediction based on Negative database (NegCPARBP) for privacy protection. NegCPARBP first converts the feature vector of a software file into a binary string. Secondly, the corresponding Negative dataBase (NDB) is generated based on this binary string, containing data that is significantly more expressive from the original feature vector. Furthermore, to ensure more accurate prediction of ARB-prone and ARB-free files based on privacy-protected data (i.e., maintain the data utility), we propose a novel negative database generation algorithm that captures more information about important features, using information gain as a measure. Finally, NegCPARBP extracts a new feature vector from the NDB to represent the original feature vector, facilitating data sharing and ARB prediction objectives. Experimental results on Linux, MySQL, and NetBSD datasets demonstrate that NegCPARBP achieves a high defense against attacks (privacy protection performance reaching 0.97) and better data utility compared to existing privacy protection methods. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

DHFM: Diversity-Enhanced Hypergraph Factorization Machines for Feature Interaction Modeling

引用

ACM Transactions on Knowledge Discovery from data 2025年第4期19卷

作者： Shi, Hongyu Chen, Ling Tang, Xing Lyu, Dandan The State Key Laboratory of Blockchain and Data Security The College of Computer Science and Technology Zhejiang University Hangzhou China

Feature interaction modeling, which exploits interactive information between features, has been widely explored in various applications. Recently, many graph neural network (GNN)-based models are proposed to model feature interactions by predicting the existence of edges between pairwise nodes that represent features. However, these models can only directly model 2-order feature interactions. Although stacking multiple GNN layers can implicitly capture the arbitrary high-order feature interactions, it may lead to the over-smoothing problem. To this end, we propose Diversity-Enhanced Hypergraph Factorization Machines (DHFMs) that incorporate hypergraphs into feature interaction modeling, which can model the diverse feature interactions of different orders explicitly. Specifically, the order-wise hyperedge predictors are proposed to discover beneficial feature interactions and explicitly model the feature interactions of different orders. In addition, diversity measures are introduced in hyperedge predictors and in the results of feature interactions to make discovered feature interactions as diverse as possible and avoid generating correlated errors. Extensive experiments on four real-world datasets demonstrate the superiority of the proposed model. In addition, the case study is conducted to further justify the effectiveness of the proposed model. Copyright © 2025 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Ensemble diversity Factorization machines Feature interaction Hypergraph neural networks

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptive Label Refinement for Label Noise Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China UniSA STEM University of South Australia AdelaideSA5095 Australia Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in overly complex and difficult-to-train models. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples and propose a simple yet highly applicable method called Adaptive Label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model’s predictions to reduce the risk of fitting incorrect labels. Then, by introducing the entropy loss, we gradually ‘harden’ the high-confidence soft labels, guiding the model to better learn from clean samples. This approach is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets, making it more accessible compared to Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

DAAP: privacy-preserving model accuracy estimation on unlabeled datasets through distribution-aware adversarial perturbation 24

DAAP: privacy-preserving model accuracy estimation on unlabe...

引用

Proceedings of the 33rd USENIX Conference on security Symposium

作者： Guodong Cao Zhibo Wang Yunhe Feng Xiaowei Dong School of Cyber Science and Engineering Wuhan University P. R. China The State Key Laboratory of Blockchain and Data Security Zhejiang University P. R. China and School of Cyber Science and Technology Zhejiang University P. R. China Department of Computer Science and Engineering University of North Texas

ISBN: (纸本)9781939133441

In the dynamic field of deep learning, accurately estimating model performance while ensuring data privacy against diverse and unlabeled test datasets presents a critical challenge. This is primarily due to the significant distributional shifts between training and test datasets, which complicates model evaluation. Traditional methods for assessing model accuracy often require direct access to the entire test dataset, posing significant risks of data leakage and model theft. To address these issues, we propose a novel approach: Distribution-Aware Adversarial Perturbation (DAAP). This method is designed to estimate the accuracy of deep learning models on unlabeled test datasets without compromising privacy. Specifically, DAAP leverages a publicly available dataset as an intermediary to bridge the gap between the model and the test data, effectively circumventing direct interaction and mitigating privacy concerns. By strategically applying adversarial perturbations, DAAP minimizes the distributional discrepancies between datasets, enabling precise estimation of model performance on unseen test data. We present two specialized strategies for white-box and black-box model contexts: the former focuses on reducing output entropy disparities, while the latter manipulates distribution discriminators. Overall, the DAAP introduces a novel framework for privacy-preserving accuracy estimation in model evaluation. This novel approach not only addresses critical challenges related to data privacy and distributional shifts but also enhances the reliability and integrity of model performance assessments. Our extensive evaluation on the CIFAR-10-C, CIFAR-100-C, and CelebA datasets demonstrates the effectiveness of DAAP in accurately estimating performance while safeguarding both data and model privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：