检索结果-内蒙古大学图书馆

Symbiosis Rather Than Aggregation: Towards Generalized Federated Learning via Model Symbiosis

IEEE Internet of Things Journal 2025年

作者： Liu, Yuange Liu, Yuru Zhang, Weishan Zheng, Chaoqun Jiang, Wei Luo, Daobin Qiao, Qiao Meng, Lingzhao Zhao, Hongwei Yang, Su College of Computer Science and Technology Qingdao266580 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China Information Science Academy of China Electronics Technology Group Corporation Beijing100036 China Fudan University School of Computer Science Shanghai200433 China

Federated Learning (FL) faces significant challenges in scenarios with non-IID (non-independent and identically distributed) data distributions across participating clients. Traditional aggregation-based approaches often struggle with the inherent misalignment between local and global optimization objectives, leadingwhich leads to gradient divergence and suboptimal generalization performance. This paper proposes a novel FL framework that replaces conventional aggregation with a biologically inspired model symbiosis approach called FedSym, which employs a dual-level symbiotic mechanism. Ectosymbiosis performs coarse-grained hierarchical parameter recombinations through random layer-wise model combination, while endosymbiosis enables fine-grained intra-layer parameter fusion through weighted averaging, collectively steering model updates towards flatter loss landscapes. Our theoretical analysis demonstrates that FedSym's convergence rate is O(1T) under non-IID conditions, which matches the convergence properties of FedAvg. Extensive experimentsevaluations across multiple datasets and model architectures show that FedSym achieves substantial improvements over state-of-the-art FL methods, particularly in challenging scenarios with high data heterogeneity, and demonstrates robust performance across varying numbers of participating clients and federation scales. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Joint Entity and Relation Extraction Based on Prompt Learning and Multi-channel Heterogeneous Graph Enhancement

Joint Entity and Relation Extraction Based on Prompt Learnin...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Haiqing Lv Xiaohui Han Peipei Wang Wenbo Zuo Jing Guo Lijuan Xu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China Information Research Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Joint extraction of entity and relation is crucial in information extraction, aiming to extract all relation triples from unstructured text. However, current joint extraction methods face two main issues. Firstly, they rarely consider the semantic information of entity and relation labels, leading to models that fail to fully understand and utilize the rich semantics in these labels, thereby limiting their performance. Secondly, although table-filling methods are widely used, they focus only on the start or end positions and ignore deep interactions between tables, relying solely on word-level information. To address these issues, we propose the P-MHE framework based on prompt learning and multi-channel heterogeneous graph enhancement. First, we use prompt templates to construct semantic nodes for entity and relation type labels, initializing them along with words as nodes in a heterogeneous graph. We iteratively fuse these semantic nodes through a message-passing mechanism to obtain node representations suitable for entity and relation extraction tasks. Secondly, we design a multi-channel heterogeneous graph to model node relationships from different perspectives, enhancing feature interactions among different types of nodes. Finally, we aggregate the semantic node information of entity and relation type labels after iteration, constructing separate decoding tables for each entity and relation type to better adapt to their respective characteristics. We evaluated our model on four public datasets. Experimental results show that P-MHE outperforms existing models on multiple public datasets. Extensive additional experiments further validate the effectiveness of our model.

关键词： Training Adaptation models Limiting Fuses Semantics Natural languages Information retrieval Feature extraction Data mining Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Intelligent Contract Vulnerability Detection Method Based on Bic-RL

Intelligent Contract Vulnerability Detection Method Based on...

引用

Data Security and Privacy Protection (DSPP), International Conference on

作者： Shuhui Zhang Changdong Hu Tian Lan LianHai Wang Shujiang Xu Wei Shao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

Blockchain technology is praised for its decentralization, anonymity, and tamper-proof nature, but its complex architecture has led to numerous attacks, particularly against smart contracts. These attacks have caused significant economic losses and hindered the development of blockchain technology. Therefore, research on smart contract vulnerability detection methods has significant practical and application value. Existing detection technologies (such as symbolic execution, formal verification, and so on) have limitations, including heavy reliance on contract source code and incomplete feature extraction. This paper proposes a fully automated smart contract vulnerability detection method based on Bic-RL(Smart contracts Detection Based on Bicubic interpolation and Deep Residual Neural networks - Long short-term memory) to address these issues. This method not only simplifies the data processing process but also realizes the complete feature extraction and ensures the high efficiency of detection performance. Performance evaluation shows this method has higher detection accuracy and generalization ability, with an accuracy rate of 84.5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Optimization for RF Energy Harvesting Relay System 11th

Energy Efficiency Optimization for RF Energy Harvesting Rela...

引用

11th EAI International Conference on Broadband Communications, networks, and Systems, BROADNETS 2020

作者： Liang, Guangjun Xin, Jianfang Wang, Qun Xia, Lingling Li, Meng Department of Computer Information and Network Security Jiangsu Police Institute Nanjing China Jiangsu Provincial Public Security Department Key Laboratory of Digital Forensics Nanjing China Electrical Engineering School Anhui Polytechnic University Wuhu China

ISBN: (纸本)9783030687366

This paper conducts research on the RF energy harvesting relay network, and proposes an improved energy harvesting relay protocol, which allows the energy harvesting source node to retransmit data to improve the system diversity gain, and constructs energy harvesting slot allocation, subcarrier pairing, and power Optimized model of distributed system energy efficiency. A resource allocation algorithm based on optimal energy efficiency is further proposed. The Dinkelbach method is used to transform the nonlinear programming problem into a linear programming problem. Then, the Hungarian algorithm and the sub-gradient method are used to obtain the iterative algorithm based on energy efficiency optimization. Simulation shows that the algorithm reduces the complexity of the algorithm and has good global convergence. © 2021, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Cross Modal Sentiment Classification of Social Media Based on Meta Heuristic Algorithm

Cross Modal Sentiment Classification of Social Media Based o...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Wantong Du Wanli Min Yushui Geng Hu Liang Hehu Zhou Ministry of Education Shandong Computer Science Center Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Synthesis Electronic Technology Co. Ltd

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The evolution of online social media has reshaped public behaviors, and social data infused with emotions provides crucial decision support for sentiment analysis tasks. Conventional multimodal approaches, influenced by redundant information in feature extraction during sentiment analysis, often focus solely on modality interactions without considering the unique content of each modality. This paper introduces the HGB-HFN model, addressing feature redundancy by optimizing extracted features using metaheuristic algorithm techniques, achieving a higher accuracy optimal feature dataset at lower computational costs. To counteract the neglect of modal-independent information, a hybrid fusion approach is adopted. It prioritizes visual features to extract precise semantic and emotional information from textual content, training multiple base classifiers to learn independent and diverse discriminative information. Comparative experiments on streaming datasets MOSI and MOSEI demonstrate the computational approach’s superiority in both accuracy and efficiency over existing methods.

关键词： Training Sentiment analysis Visualization Accuracy Social networking (online) Metaheuristics Semantics

来源：评论

学校读者我要写书评

暂无评论

Spatial Formation-Guided network for Group Activity Recognition

Spatial Formation-Guided Network for Group Activity Recognit...

引用

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

作者： Dunbo Ning Wenjing Chen Wei Xie Hao Sun Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning National Language Resources Monitoring and Research Center for Network Media School of Computer Science Central China Normal University Wuhan China School of Computer Science Hubei University of Technology Wuhan China

Effectively modeling the interactions among actors is critical and challenging for Group Activity Recognition (GAR). Previous methods usually divide actors into subgroups based on the similarity of appearance features for modeling multilevel interactions among actors. However, the appearance feature-based grouping scheme does not fully consider the spatial relations of actors, which can provide a discriminative clue for GAR. In this paper, we propose a Spatial Formation-Guided network (SFGN) to capture effective interactions under the guidance of spatial formations. We first design a spatial formation extractor to excavate latent spatial relations among actors for extracting spatial formation features. Then, a formation-guided interaction module is built to utilize the spatial formation features to guide the interactions among actors. Finally, a cross-formation interaction module is further designed to explore the complementarity among diverse spatial formations. Extensive experiments on the volleyball dataset and the collective activity dataset demonstrate that SFGN outperforms the state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Feature Processing Based on Attention Mechanism for Co-Salient Object Detection

Comprehensive Feature Processing Based on Attention Mechanis...

引用

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

作者： Guohua Lv Mao Yuan Zengbin Zhang Zhengyang Zhang Zhenhui Ding Guangxiao Ma Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Shandong Key Laboratory of Ubiquitous Intelligent Computing Jinan China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Co-salient object detection (CoSOD) aims to detect common salient objects across multiple related images. However, existing methods often struggle with limited attention coverage, missing some co-salient objects. To address this, we propose a two-stage feature processing module (FPM) comprising comprehensive feature extraction module (CFE) and feature enhancement module (FEM). CFE extracts comprehensive cosalient features while reducing background noise, and FEM enhances feature representation and adjusts attention weights for full object coverage. Additionally, we introduce an adversarial learning module (ALM) to improve prediction quality by reducing noise in the co-salient regions. Extensive experiments on three benchmark datasets—CoCA, CoSOD3k, and CoSal2015—demonstrate that our model significantly outperforms state-of-the-art methods. The source code is available at https://***/yaobaimiao/CFPAM.

关键词： Attention mechanisms Source coding Noise Object detection Benchmark testing Feature extraction Adversarial machine learning Finite element analysis Background noise Speech processing

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Multiscale Difference-Aware network for Joint Moment Retrieval and Highlight Detection

Cross-Modal Multiscale Difference-Aware Network for Joint Mo...

引用

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

作者： Mingyao Zhou Wenjing Chen Hao Sun Wei Xie Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning National Language Resources Monitoring and Research Center for Network Media School of Computer Science Central China Normal University Wuhan China School of Computer Science Hubei University of Technology Wuhan China

Since the goals of both Moment Retrieval (MR) and Highlight Detection (HD) are to quickly obtain the required content from the video according to user needs, several works have attempted to take advantage of the commonality between both tasks to design transformer-based networks for joint MR and HD. Although these methods achieve impressive performance, they still face some problems: a) Semantic gaps across different modalities. b) Various durations of different query-relevant moments and highlights. c) Smooth transitions among diverse events. To this end, we propose a Cross-modal Multiscale Difference-aware network, named CMDNet. First, a clip-text alignment module is constructed to narrow semantic gaps between different modalities. Second, a multiscale difference perception module is utilized to mine the differential information between adjacent clips and perform multiscale modeling to obtain discriminative representations. Finally, these representations are fed into the MR and HD task heads to retrieve relevant moments and estimate highlight scores precisely. Extensive experiments on three popular datasets demonstrate that CMDNet achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Hyperspectral Image Classification Based on Cross-Domain Spectral Semantic Relation Transformer

Few-Shot Hyperspectral Image Classification Based on Cross-D...

引用

IEEE International Conference on Image Processing

作者： Mengxin Cao Guixin Zhao Aimei Dong Guohua Lv Ying Guo Xiangjun Dong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

In practical hyperspectral image (HSI) classification tasks, we often encounter the problems of few-shot classification and domain misalignment between source domains and target domains. To solve this classification paradigm, a meta-learning method of few-shot learning (FSL) is usually used. However, most existing FSL methods address the problem for domain alignment and neglect the exploration of semantic relationships of objects across domains. In this paper, we propose the cross-domain spectral semantic transformer FSL (SSTFSL), which can fully extract semantic features and spectral detail features for the cross-domain few-shot HSI classification task. Specifically, the multi-head self-attention (MSA) mechanism with enhancement process (EP) of the transformer is used to map out semantically relevant local regions and can enhance the ability of the model to distinguish subtle feature differences in the spectrum. In addition, the matching degree of different branches is computed by relational network learning, which ultimately enables cross-domain few-shot HSI classification. Through extensive experiments, we evaluate the classification performance of SSTFSL on HSI datasets. The results demonstrate that SSTFSL outperforms existing FSL methods and deep learning methods on HSI classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedSimRep: A Federated Learning Method Based on Data Representation Selection 25

FedSimRep: A Federated Learning Method Based on Data Represe...

引用

Proceedings of the 2025 3rd International Conference on Communication networks and Machine Learning

作者： Falu Zhai Lu Wu Chunxiao Wang Tongyang Hao Shucang Zang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan Shandong China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan Shandong China

ISBN: (纸本)9798400713231

As an emerging distributed technology, Federated learning enables model training while protecting privacy without sharing local data. However, the heterogeneity of geographic locations and devices leads to response delays from stragglers. Client grouping in federated learning can tolerate stragglers from a global perspective, but differences in data distribution within groups may result in local performance bias. To address this issue, we propose a federated learning method called FedSimRep, which selects representative clients based on data distribution similarity. FedSimRep performs group training by collecting readiness signals from topological communications and maintains synchronization tables and graphs to track training progress. Additionally, it selects representative clients by leveraging the relationship between local optimization similarity and data distribution similarity to optimize the global model. Experiments and theoretical analyses on public datasets such as MNIST, CIFAR-10, and UEU-Fed demonstrate that FedSimRep achieves significant advantages in terms of accuracy and efficiency.

关键词： Client Grouping

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：