检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Li, Yang Xia, Chunhe Li, Chang Li, Xiaojian Wang, Tianbo School of Computer Science and Engineering Beihang University Beijing100191 China Key Laboratory of Beijing Network Technology Beihang University Beijing100191 China Guangxi Collaborative Innovation Center Multi-Source Information Integration and Intelligent Processing Guangxi Normal University Guilin541004 China School of Computer Science and Technology Zhengzhou University of Light Industry Zhengzhou450000 China College of Computer Science and Information Technology Guangxi Normal University Guilin541004 China School of Cyber Science and Technology Beihang University Beijing100191 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China

Federated learning based on homomorphic encryption has received widespread attention due to its high security and enhanced protection of user data privacy. However, the characteristics of encrypted computation lead to three challenging problems: "computation-efficiency", "attack-tracing" and "contribution-assessment". The first refers to the efficiency of encrypted computation during model aggregation, the second refers to tracing malicious attacks in an encrypted state, and the third refers to the fairness of contribution assessment for local models after encryption. This paper proposes a federated learning storage security model with homomorphic encryption (FLSSM) to protect federated learning model privacy and address the three issues mentioned above. First, we utilize different nodes to aggregate local models in parallel, thereby improving encrypted models’ aggregation efficiency. Second, we introduce trusted supervise nodes to examine local models when the global model is attacked, enabling the tracing of malicious attacks under homomorphic encryption. Finally, we fairly reward local training nodes with encrypted local models based on trusted training time. Experiments on multiple real-world datasets show that our model significantly outperforms baseline models in terms of both efficiency and security metrics. Copyright © 2025, 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

Joint Optimization of Offloading and Caching in Full-Duplex-Enabled Edge Computing Networks

引用

IEEE Transactions on Mobile Computing 2025年

作者： Dai, Xingxia Tian, Shujuan Liu, Haolin Li, Zhetao Jiang, Hongbo Deng, Qingyong Xiangtan University School of Computer Science School of Cyberspace Security Xiangtan411105 China Jinan University College of Information Science and Technology Guangzhou510632 China Hunan University College of Computer Science and Electronic Engineering Changsha Hunan410082 China Guangxi Normal University Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guilin541004 China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin541004 China

Edge computing (EC) reduces task processing and content download delay by providing computation and caching resources directly to task offloading (TO) users and content request (CR) users. However, existing studies often focus exclusively on either TO users or CR users within EC networks, neglecting the interaction between these two groups. To address this gap, we investigate the offloading and caching decision-making in scenarios where TO and CR users coexist. Furthermore, we employ full-duplex (FD) technology to enhance spectral utilization for edge-end transmissions. Specifically, we jointly optimize offloading and caching in FD-enabled EC networks. To accomplish this, we decompose the formulated optimization problem into three sub-problems using the alternating optimization (AO) method. We then propose a three-subproblem alternating iterative delay minimization algorithm to effectively tackle the challenges of offloading and caching. Additionally, we analyze the convergence and complexity of our proposed algorithm. Finally, we conduct extensive simulations to evaluate the effectiveness of our approach. The simulation results demonstrate that the delay reduction achieved by our algorithm is between 24.78% and 89.23% greater than that of comparative algorithms. © 2002-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Phrase-based hashtag recommendation for microblog posts

引用

science China(information sciences) 2017年第1期60卷 132-144页

作者： Yeyun GONG Qi ZHANG Xiaoying HAN Xuanjing HUANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University

In microblogs, authors use hashtags to mark keywords or topics. These manually labeled tags can be used to benefit various live social media applications(e.g., microblog retrieval, classification). However,because only a small portion of microblogs contain hashtags, recommending hashtags for use in microblogs are a worthwhile exercise. In addition, human inference often relies on the intrinsic grouping of words into ***, existing work uses only unigrams to model corpora. In this work, we propose a novel phrase-based topical translation model to address this problem. We use the bag-of-phrases model to better capture the underlying topics of posted microblogs. We regard the phrases and hashtags in a microblog as two different languages that are talking about the same thing. Thus, the hashtag recommendation task can be viewed as a translation process from phrases to hashtags. To handle the topical information of microblogs, the proposed model regards translation probability as being topic specific. We test the methods on data collected from realworld microblogging services. The results demonstrate that the proposed method outperforms state-of-the-art methods that use the unigram model.

关键词： recommendation topic model translation phrase extraction hashtag

来源：评论

学校读者我要写书评

暂无评论

Complex networks and computing

引用

中国高等学校学术文摘·计算机科学 2009年第3期3卷 322-323页

作者： Shuigeng ZHOU Zhongzhi ZHANG Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai 200433 China

Nowadays complex networks are pervasive in various areas of science and technology. Popular examples of complex networks include the Internet, social networks of collaboration, citations and co-authoring, as well as biological networks such as gene and protein interactions and others. Complex networks research spans across mathematics, computer science, engineering, biology and the social sciences. Even in computer science area, increasing problems are either found to be related to complex networks or studied from the perspective of complex networks, such as searching on Web and P2P networks, routing in sensor networks, language processing, software engineering etc. The interaction and mergence of complex networks and computing is inspiring new chances and challenges in computer science.

关键词： complex networks computer science protein interactions collaboration social perspective software research problems language Internet related found area Web P2P new

来源：评论

学校读者我要写书评

暂无评论

Sequence-Aware Online Container Scheduling with Reinforcement Learning in Parked Vehicle Edge Computing

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wu, Jianqiu Guo, Jianxiong Tang, Zhiqing Luo, Chuanwen Wang, Tian Jia, Weijia Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Department of Computer Science Zhuhai519087 China Beijing Normal University Advanced Institute of Natural Sciences Zhuhai519087 China Beijing Normal-Hong Kong Baptist University Guangdong Key Lab of AI and Multi-Modal Data Processing Zhuhai519087 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing100083 China

intelligent vehicles, often parked for long periods, are ideally suited to serve as computational nodes to expand the Mobile Edge Computing (MEC) infrastructure, with containerization significantly enhancing the system's load balancing, self-healing, resource isolation, and security. However, fluctuations in task demand and frequent container image downloads during peak hours create high loads on containerized nodes, as multiple mobile devices offload tasks simultaneously, leading to significant processing delays. Many existing studies make the simplified assumption of predefined patterns of task arrivals, which overlooks this issue and makes suboptimal decisions. In this paper, we consider a Parked Vehicles (PVs)-extended MEC scenario, where multiple devices request services on PVs functioning as edge servers, all controlled by a central base station. Task arrivals follow observed patterns based on long-term trends, such as peak and off-peak periods, resembling realistic arrival patterns rather than predefined ones. To optimize task offloading by identifying these patterns, we propose the Sequence-Aware Task Scheduling (SATS) algorithm, which is a policy gradient-based deep reinforcement learning approach that integrates Transformer and LSTM architectures to capture patterns in time-series task arrivals and relationships between nodes in a collaborative and containerized environment, thereby enhancing the efficiency of online task scheduling. The primary objective of SATS is to optimize the task offloading policy and minimize delay and energy consumption for all devices and PVs. Extensive numerical comparisons against baselines demonstrate the effectiveness and advantages of our algorithm. © 1967-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Fusion Analysis of Resting-State Networks and Its Application to Alzheimer's Disease

引用

Tsinghua science and Technology 2019年第4期24卷 456-467页

作者： Shengbing Pei Jihong Guan Shuigeng Zhou the Department of Computer Science and Technology Tongji University Shanghai Key Lab of Intelligent Information Processing School of Computer ScienceFudan University

Functional networks are extracted from resting-state functional magnetic resonance imaging data to explore the biomarkers for distinguishing brain disorders in disease diagnosis. Previous works have primarily focused on using a single Resting-State Network(RSN) with various techniques. Here, we apply fusion analysis of RSNs to capturing biomarkers that can combine the complementary information among the RSNs. Experiments are carried out on three groups of subjects, i.e., Cognition Normal(CN), Early Mild Cognitive Impairment(EMCI), and Alzheimer's Disease(AD) groups, which correspond to the three progressing stages of AD; each group contains18 subjects. First, we apply group Independent Component Analysis(ICA) to extracting the Default Mode Network(DMN) and Dorsal Attention Network(DAN) for each subject group. Then, by obtaining the common DMN and DAN as templates for each group, we employ the individual ICA to extract the DMN and DAN for each ***, we fuse the DMNs and DANs to explore the biomarkers. The results show that(1) the templates generated by group ICA can extract the RSN for each subject by individual ICA effectively;(2) the RSNs combined with the fusion analysis can obtain more informative biomarkers than without fusion analysis;(3) the most different regions of DMN and DAN are found between CN and EMCI and between EMCI and AD, which show differences. For the DMN, the difference in the medial prefrontal cortex between the EMCI and AD is smaller than that between CN and EMCI, whereas that in the posterior cingulate between EMCI and AD is larger. As for the DAN, the difference in the intraparietal sulcus is smaller than that between CN and EMCI;(4) extracting DMN and DAN for each subject via the back reconstruction of group ICA is invalid.

关键词： Independent Component Analysis(ICA) group analysis fusion analysis Alzheimer’s Disease(AD)

来源：评论

学校读者我要写书评

暂无评论

DualGOFiller: A Dual-Channel Graph Neural Network with Contrastive Learning for Enhancing Function Prediction in Partially Annotated Proteins 29th

DualGOFiller: A Dual-Channel Graph Neural Network with Cont...

引用

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Wang, Shaojun Liu, Hancheng Zhai, Weiqi Zhu, Shanfeng Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China Ministry of Education Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing and Shanghai Institute of Artificial Intelligence Algorithm Fudan University Shanghai200433 China Zhangjiang Fudan International Innovation Center Shanghai200433 China

ISBN: (纸本)9783031902512

Protein function prediction remains a critical and challenging task in the field of bioinformatics. Despite various existing computational methods, most focus on predicting functions for novel proteins, often overlooking those with incomplete annotations. Predicting missing Gene Ontology (GO) terms for these partially annotated proteins is also important for gaining a comprehensive understanding of their biological roles. To address this gap, we introduce DualGOFiller, a dual-channel graph neural network (GNN) model, which is a novel method specifically focused on predicting missing GO terms for partially annotated proteins. DualGOFiller integrates heterogeneous (protein-GO bipartite graph) and homogeneous (protein-protein interaction network and GO directed acyclic graph) network information, enriched with attribute data from protein sequences and GO term descriptions. It further employs graph contrastive learning (GCL) to strengthen the alignment across different views. Experiments demonstrate the superiority of DualGOFiller over state-of-the-art methods, including traditional recommendation system approaches and several protein function prediction methods. The ablation study further confirms the significant contributions of key component in DualGOFiller for boosting predictive performance. The source code is available at https://***/Zhulab-Fudan/DualGOFiller. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction

arXiv

引用

arXiv 2025年

作者： Ma, Chenglong Li, Zilong Li, Yuanlin Han, Jing Zhang, Junping Zhang, Yi Liu, Jiannan Shan, Hongming Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Department of Oral Maxillofacial Head and Neck Oncology Shanghai Ninth People’ s Hospital Shanghai Jiao Tong University School of Medicine College of Stomatology Shanghai Jiao Tong University National Center for Stomatology National Clinical Research Center for Oral Diseases Shanghai Key Laboratory of Stomatology Shanghai Research Institute of Stomatology Shanghai200011 China School of Cyber Science and Engineering Sichuan University Sichuan Chengdu610065 China

Metal artifacts in computed tomography (CT) images can significantly degrade image quality and impede accurate diagnosis. Supervised metal artifact reduction (MAR) methods, trained using simulated datasets, often struggle to perform well on real clinical CT images due to a substantial domain gap. Although state-of-the-art semi-supervised methods use pseudo ground-truths generated by a prior network to mitigate this issue, their reliance on a fixed prior limits both the quality and quantity of these pseudo ground-truths, introducing confirmation bias and reducing clinical applicability. To address these limitations, we propose a novel radiologist-in-the-loop selftraining framework for MAR, termed RISE-MAR, which can integrate radiologists’ feedback into the semi-supervised learning process, progressively improving the quality and quantity of pseudo ground-truths for enhanced generalization on real clinical CT images. For quality assurance, we introduce a clinical quality assessor model that emulates radiologist evaluations, effectively selecting high-quality pseudo ground-truths for semi-supervised training. For quantity assurance, our self-training framework iteratively generates additional high-quality pseudo ground-truths, expanding the clinical dataset and further improving model generalization. Extensive experimental results on multiple clinical datasets demonstrate the superior generalization performance of our RISE-MAR over state-of-the-art methods, advancing the development of MAR models for practical application. Code is available at https:// ***/Masaaki-75/rise-mar . © 2025, CC BY-NC-SA.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A survey on high coherence visual media retargeting： recent advances and applications

引用

Frontiers of computer science 2016年第5期10卷 778-796页

作者： Weimin TAN Bo YAN School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai 201203 China

The numerous works on media retargeting call for a thorough and comprehensive survey for reviewing and categorizing existing works and providing insights that can help future design of retargeting approaches and its applica- tions. First, we present the basic problem of media retarget- ing and detail state-of-the-art retargeting methods devised to solve it. Second, we review recent works on objective quality assessment of media retargeting, where we find that although these works are designed to make the objective assessment result in accordance with the subjective evaluation, they are only suitable for certain situations. Considering the subjective nature of aesthetics, designing objective assessment metric for media retargeting could be a promising area for investiga- tion. Third, we elaborate on other applications extended from retargeting techniques. We show how to apply the retarget- ing techniques in other fields to solve their challenging prob- lems, and reveal that retargeting technique is not just a simple scaling algorithm, but a thought or concept, which has great flexibility and is quite useful. We believe this review can help researchers and practitioners to solve the existing problems of media retargeting and bring new ideas in their works.

关键词： media retargeting quality assessment aesthet-ics enhancement image retrieval video synopsis

来源：评论

学校读者我要写书评

暂无评论

Rate-Splitting Multiple Access Enabled Green Probabilistic Semantic Communication over Wireless Networks

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Xu, Ruopeng Yang, Zhaohui Mao, Yijie Huang, Chongwen Yang, Qianqian Xu, Lexi Xu, Wei Zhang, Zhaoyang Zhejiang University College of Information Science and Electronic Engineering China Hangzhou310027 China ShanghaiTech University School of Information Science and Technology Shanghai201210 China Zhejiang Prov. Key Lab. of Multi-Modal Communication Networks and Intelligent Information Processing Hangzhou310027 China China United Network Communications Corporation Research Institute Beijing100048 China Southeast University National Mobile Communications Research Laboratory Nanjing211189 China

In this paper, we propose a multi-user green probabilistic semantic communication (PSC) system for semantic communication (SemCom) facilitated by probabilistic knowledge graphs (PKGs), which are knowledge graphs (KGs) integrated with probability to represent semantic information. In the considered model, semantic information of different users is represented by PKGs. On this basis, we design a semantic compression model for multi-user downlink task-oriented SemCom, utilizing the semantic compression ratio (SCR) as a parameter to connect the computation and communication processes of information transmission. Utilizing rate-splitting multiple access (RSMA) technology, the transmitted messages are splitted into shared and private ones. Considering the limited wireless resources and constraint in semantic communication, an optimization problem with the goal of minimizing system energy consumption comprehensively considering the computation and communication process is formulated. In order to address the optimization problem, we propose an alternating optimization algorithm that tackles sub-problems of power allocation and beamforming design with successive convex approximation (SCA) method, semantic compression ratio optimization with variable substitution method, and computation capacity allocation with obtaining closed-form optimal solution. Simulation results verify the effectiveness of the proposed algorithm. © 2017 IEEE.

关键词： Knowledge graph

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：