检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Chuan Liao, Tianchi Deng, Xiaojun Wu, Zihou Huang, Sheng Zheng, Zibin School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing China School of Software Engineering Sun Yat-sen University Zhuhai519000 China Zhuhai Key Laboratory of Trusted Large Language Models China School of Systems Science and Engineering Sun Yat-sen University Guangzhou510006 China

In the field of heterogeneous federated learning (FL), the key challenge is to efficiently and collaboratively train models across multiple clients with different data distributions, model structures, task objectives, computational capabilities, and communication resources. This diversity leads to significant heterogeneity, which increases the complexity of model training. In this paper, we first outline the basic concepts of heterogeneous FL and summarize the research challenges in FL in terms of five aspects: data, model, task, device and communication. In addition, we explore how existing state-of-the-art approaches cope with the heterogeneity of FL, and categorize and review these approaches at three different levels: data-level, model-level, and architecture-level. Subsequently, the paper extensively discusses privacy-preserving strategies in heterogeneous FL environments. Finally, the paper discusses current open issues and directions for future research, aiming to promote the further development of heterogeneous FL. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Graph Attention Network Hashing for Cross-Modal Retrieval 38

An End-to-End Graph Attention Network Hashing for Cross-Moda...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jin, Huilong Zhang, Yingxue Shi, Lei Zhang, Shuang Kou, Feifei Yang, Jiapeng Zhu, Chuangying Luo, Jia College of Engineering Hebei Normal University China College of Computer and Cyber Security Hebei Normal University China State Key Laboratory of Media Convergence and Communication Communication University of China China Key Laboratory of Education Informatization for Nationalities Yunnan Normal University Ministry of Education China School of Computer Science Beijing University of Posts and Telecommunications China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology China Chongqing Research Institute Beijing University of Technology China

Due to its low storage cost and fast search speed, cross-modal retrieval based on hashing has attracted widespread attention and is widely used in real-world applications of social media search. However, most existing hashing methods are often limited by uncomprehensive feature representations and semantic associations, which greatly restricts their performance and applicability in practical applications. To deal with this challenge, in this paper, we propose an end-to-end graph attention network hashing (EGATH) for cross-modal retrieval, which can not only capture direct semantic associations between images and texts but also match semantic content between different modalities. We adopt the contrastive language image pretraining (CLIP) combined with the Transformer to improve understanding and generalization ability in semantic consistency across different data modalities. The classifier based on graph attention network is applied to obtain predicted labels to enhance cross-modal feature representation. We construct hash codes using an optimization strategy and loss function to preserve the semantic information and compactness of the hash code. Comprehensive experiments on the NUS-WIDE, MIRFlickr25K, and MS-COCO benchmark datasets show that our EGATH significantly outperforms against several state-of-the-art methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey on Anti-Money Laundering Techniques in Blockchain Systems

引用

Strategic Study of CAE 2025年第2期27卷 287-303页

作者： Leyuan, Liu Xiangye, Li Tian, Lan Yakun, Cheng Wei, Chen Zhixin, Li Sheng, Cao Weili, Han Xiaosong, Zhang Hongfeng, Chai School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science Fudan University Shanghai200433 China Institute of Financial Technology Fudan University Shanghai200433 China

As the global financial landscape undergoes profound transformation, the blockchain technology has emerged as a cornerstone of Web 3.0 finance and a pivotal frontier in financial technology innovation. However, its decentralized and pseudonymous nature has also been exploited by malicious actors to circumvent regulatory oversight, facilitate money laundering, and conduct other illicit financial activities, posing substantial risks to both national and global financial security. Consequently, there is an urgent need to systematically assess the current progress in anti-money laundering (AML) research, anticipate future directions in blockchain-based AML technologies, and develop effective countermeasures to mitigate the evolving financial security challenges associated with blockchain applications. This study provides a comprehensive review of AML research in blockchain systems, examining the foundational AML frameworks, including traditional AML models and blockchain-based money laundering methodologies. It categorizes existing AML techniques into three primary approaches: rule-based methods, such as transaction parameter threshold setting, address-entity association analysis, and cross-chain association analysis;machine learning-based approaches, including support vector machines, logistic regression, decision trees, random forests, k-means clustering, and combining off-chain information;and deep learning-based methodologies, encompassing convolutional neural networks, recurrent neural networks, graph neural networks, and transformer-based models. Furthermore, this study discusses the practical applications of these techniques and reviews commonly used datasets that support AML research. Looking ahead, the advancement of AML technologies in blockchain systems necessitates progress in several critical areas: the construction of AML datasets capable of addressing data imbalance and annotation uncertainty, development of trusted AML algorithms, design of detection mec

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Bi-CLKT: Bi-Graph Contrastive Learning based Knowledge Tracing

arXiv

引用

arXiv 2022年

作者： Song, Xiangyu Li, Jianxin Lei, Qi Zhao, Wei Chen, Yunliang Mian, Ajmal School of IT Faculty of Science Engineering and Built Environment Deakin University GeelongVIC3220 Australia School of Information Engineering Chang'an University Xi'An China School of Computer Science and Technology Xidian University Xi'An China School of Computer Science China University of Geosciences Wuhan China Department of Computer Science and Software Engineering The University of Western Australia Perth Australia

The goal of Knowledge Tracing (KT) is to estimate how well students have mastered a concept based on their historical learning of related exercises. The benefit of knowledge tracing is that students' learning plans can be better organised and adjusted, and interventions can be made when necessary. With the recent rise of deep learning, Deep Knowledge Tracing (DKT) has utilised Recurrent Neural Networks (RNNs) to accomplish this task with some success. Other works have attempted to introduce Graph Neural Networks (GNNs) and redefine the task accordingly to achieve significant improvements. However, these efforts suffer from at least one of the following drawbacks: 1) they pay too much attention to details of the nodes rather than to high-level semantic information;2) they struggle to effectively establish spatial associations and complex structures of the nodes;and 3) they represent either concepts or exercises only, without integrating them. Inspired by recent advances in self-supervised learning, we propose a Bi-Graph Contrastive Learning based Knowledge Tracing (Bi-CLKT) to address these limitations. Specifically, we design a two-layer comparative learning scheme based on an "exercise-to-exercise" (E2E) relational subgraph. It involves node-level contrastive learning of subgraphs to obtain discriminative representations of exercises, and graph-level contrastive learning to obtain discriminative representations of concepts. Moreover, we designed a joint contrastive loss to obtain better representations and hence better prediction performance. Also, we explored two different variants, using RNN and memory-augmented neural networks as the prediction layer for comparison to obtain better representations of exercises and concepts respectively. Extensive experiments on four real-world datasets show that the proposed Bi-CLKT and its variants outperform other baseline models. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Gradient Compression and Correlation Driven Federated Learning for Wireless Traffic Prediction

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Zhang, Chuanting Zhang, Haixia Dang, Shuping Shihada, Basem Alouini, Mohamed-Slim Shandong University School of Software Jinan250101 China Shandong University School of Control Science and Engineering Jinan250061 China Shandong University Shandong Key Laboratory of Wireless Communication Technologies Jinan250061 China University of Bristol Department of Electrical and Electronic Engineering BristolBS8 1UB United Kingdom Computer Electrical and Mathematical Science and Engineering Division Thuwal23955-6900 Saudi Arabia

Wireless traffic prediction plays an indispensable role in cellular networks to achieve proactive adaptation for communication systems. Along this line, Federated Learning (FL)-based wireless traffic prediction at the edge attracts enormous attention because of the exemption from raw data transmission and enhanced privacy protection. However FL-based wireless traffic prediction methods still rely on heavy data transmissions between local clients and the server for local model updates. Besides, how to model the spatial dependencies of local clients under the framework of FL remains uncertain. To tackle this, we propose an innovative FL algorithm that employs gradient compression and correlation-driven techniques, effectively minimizing data transmission load while preserving prediction accuracy. Our approach begins with the introduction of gradient sparsification in wireless traffic prediction, allowing for significant data compression during model training. We then implement error feedback and gradient tracking methods to mitigate any performance degradation resulting from this compression. Moreover, we develop three tailored model aggregation strategies anchored in gradient correlation, enabling the capture of spatial dependencies across diverse clients. Experiments have been done with two real-world datasets and the results demonstrate that by capturing the spatio-temporal characteristics and correlation among local clients, the proposed algorithm outperforms the state-of-the-art algorithms and can increase the communication efficiency by up to two orders of magnitude without losing prediction accuracy. © 2015 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing

arXiv

引用

arXiv 2024年

作者： Xian, Xiaole He, Xilin Niu, Zenghao Zhang, Junliang Xie, Weicheng Song, Siyang Yu, Zitong Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Great Bay University China

For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional finetuning for different editing effects or tend to affect beyond the editing regions. Alternatively, inpainting methods can edit the target image region while preserving external areas. However, current inpainting methods still suffer from the generation misalignment with facial attributes description and the loss of facial skin details. To address these challenges, (i) a novel data utilization strategy is introduced to construct datasets consisting of attribute-text-image triples from a data-driven perspective, (ii) a Causality-Aware Condition Adapter is proposed to enhance the contextual causality modeling of specific details, which encodes the skin details from the original image while preventing conflicts between these cues and textual conditions. In addition, a Skin Transition Frequency Guidance technique is introduced for the local modeling of contextual causality via sampling guidance driven by low-frequency alignment. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in boosting both fidelity and editability for localized attribute editing. The code is available at https://***/connorxian/CA-Edit. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2M3DF: Advancing 3D Industrial Defect Detection with Multi Perspective Multimodal Fusion Network

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Asad, Mujtaba Azeem, Waqar Jiang, He Mustafa, Hafiz Tayyab Yang, Jie Liu, Wei Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Department of Automation Shanghai200240 China Lahore Garrison University Department of Software Engineering Lahore54000 Pakistan China University of Mining and Technology School of Information and Control Engineering Jiangsu Xuzhou221116 China Zhejiang Normal University School of Computer Science and Technology Jinhua321004 China

In the context of Industrial Anomaly Detection (IAD), ensuring the quality of manufactured products is critical. Traditional 2D based methods often fail to capture anomalies present in complex 3D shapes. For effective anomaly detection in 3D shapes, it is essential to incorporate global semantic context, local geometric structure, and color information of the object. To fully leverage these features, we propose a network named 2M3DF, that leverages knowledge from multi-view RGB images and corresponding point cloud information for enhanced anomaly detection performance. Our model initially employs pre-trained feature extractors that generate local features from multi-view RGB images and corresponding point clouds. The novel inter-modality feature representation and fusion module first adapts these inter-modality features and then effectively aligns and aggregates these multimodality features on a pixel-to-point basis. To learn the normality from point-wise fused multimodal features, we fit a multivariate Gaussian distribution to model the normal feature distribution. Comprehensive experimental evaluations using the MVTec3D-AD and Eyecandies dataset validate the effectiveness of our propose model and demonstrate significant improvements in comparison to existing state-of-the-art methods. Our model achieves a 96.6% mean I-AUROC while delivering real-time results. © 1991-2012 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Load-Balanced Multipath Routing Through software-Defined Networking

Load-Balanced Multipath Routing Through Software-Defined Net...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Tanmay Badageri Bechir Hamdaoui Rami Langar School of Electrical Engineering and Computer Science Oregon State University Corvallis Oregon USA Software and IT Engineering Department Ecole de Technologie Superieure (ETS) Montreal Canada CNRS LIGM Univ. Gustave Eiffel Marne-la-Vallee France

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

software-Defined Networking (SDN) provides the flexibility to dynamically manage network paths, facilitating efficient traffic flow and mutipath routing, thereby improving network resiliency to congestion. This study investigates three distinct SDN-enabled routing strategies: shortest path routing, Equal-Cost Multi-Path (ECMP) routing, and bandwidth-based multipath routing. The comparative result analysis across these three routing strategies revealed that bandwidth-based routing consistently outperforms Shortest Path and ECMP routing across key performance metrics. The study found that Bandwidth-based routing maintains lower delay and jitter, indicating its superior ability to manage network traffic efficiently even as data flow increases. Furthermore, it demonstrates a more modest increase in packet loss, underscoring its effective congestion management. These findings suggest that Bandwidth-based routing provides a more reliable and efficient network performance, particularly in high-traffic conditions, making it a preferable solution for SDN implementations seeking to optimize data flow and network stability.

关键词： Wireless communication Packet loss Telecommunication traffic Routing Reliability engineering Stability analysis software defined networking

来源：评论

学校读者我要写书评

暂无评论

LCM: locally constrained compact point cloud model for masked point modeling 24

LCM: locally constrained compact point cloud model for maske...

引用

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

作者： Yaohua Zha Naiqi Li Yanzi Wang Tao Dai Hang Guo Bin Chen Zhi Wang Zhihao Ouyang Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University and Institute of Visual Intelligence Pengcheng Laboratory Tsinghua Shenzhen International Graduate School Tsinghua University College of Computer Science and Software Engineering Shenzhen University Harbin Institute of Technology Shenzhen Bytedance Inc.

ISBN: (纸本)9798331314385

The pre-trained point cloud model based on Masked Point Modeling (MPM) has exhibited substantial improvements across various tasks. However, these models heavily rely on the Transformer, leading to quadratic complexity and limited decoder, hindering their practice application. To address this limitation, we first conduct a comprehensive analysis of existing Transformer-based MPM, emphasizing the idea that redundancy reduction is crucial for point cloud analysis. To this end, we propose a Locally constrained Compact point cloud Model (LCM) consisting of a locally constrained compact encoder and a locally constrained Mamba-based decoder. Our encoder replaces self-attention with our local aggregation layers to achieve an elegant balance between performance and efficiency. Considering the varying information density between masked and unmasked patches in the decoder inputs of MPM, we introduce a locally constrained Mamba-based decoder. This decoder ensures linear complexity while maximizing the perception of point cloud geometry information from unmasked patches with higher information density. Extensive experimental results show that our compact model significantly surpasses existing Transformer-based models in both performance and efficiency, especially our LCM-based Point-MAE model, compared to the Transformer-based model, achieved an improvement of 1.84%, 0.67%, and 0.60% in average accuracy on the three variants of ScanObjectNN while reducing parameters by 88% and computation by 73%. Code is available at https://***/zyh16143998882/LCM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Predicate and Triplet Learning for Scene Graph Generation

Leveraging Predicate and Triplet Learning for Scene Graph Ge...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jiankai Li Yunhong Wang Xiefan Guo Ruijie Yang Weixin Li IRIP Lab School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Complex & Critical Software Environment Beihang University Beijing China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Scene Graph Generation (SGG) aims to identify entities and predict the relationship triplets in visual scenes. Given the prevalence of large visual variations of subject-object pairs even in the same predicate, it can be quite challenging to model and refine predicate representations directly across such pairs, which is however a common strategy adopted by most existing SGG methods. We observe that visual variations within the identical triplet are relatively small and certain relation cues are shared in the same type of triplet, which can potentially facilitate the relation learning in SGG. Moreover, for the long-tail problem widely studied in SGG task, it is also crucial to deal with the limited types and quantity of triplets in tail predicates. Accordingly, in this paper, we propose a Dual-granularity Relation Modeling (DRM) network to leverage fine-grained triplet cues besides the coarse-grained predicate ones. DRM utilizes contexts and semantics of predicate and triplet with Dual-granularity Constraints, generating compact and balanced representations from two perspectives to facilitate relation recognition. Furthermore, a Dual-granularity Knowledge Transfer (DKT) strategy is introduced to transfer variation from head predicates/triplets to tail ones, aiming to enrich the pattern diversity of tail classes to alleviate the long-tail problem. Extensive experiments demonstrate the effectiveness of our method, which establishes new state-of-the-art performance on Visual Genome, Open Image, and GQA datasets. Our code is available at https://***/jkli1998/DRM

关键词： Visualization Head Triples (Data structure) Semantics Genomics Tail Pattern recognition

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：