FedCLCC: A personalized federated learning algorithm for edge cloud collaboration based on contrastive learning and conditional computing

IF 5.1 2区 工程技术 Q1 Engineering
Kangning Yin, Xinhui Ji, Yan Wang, Zhiguo Wang
{"title":"FedCLCC: A personalized federated learning algorithm for edge cloud collaboration based on contrastive learning and conditional computing","authors":"Kangning Yin, Xinhui Ji, Yan Wang, Zhiguo Wang","doi":"10.1016/j.dt.2024.08.015","DOIUrl":null,"url":null,"abstract":"Federated learning (FL) is a distributed machine learning paradigm for edge cloud computing. FL can facilitate data-driven decision-making in tactical scenarios, effectively addressing both data volume and infrastructure challenges in edge environments. However, the diversity of clients in edge cloud computing presents significant challenges for FL. Personalized federated learning (pFL) received considerable attention in recent years. One example of pFL involves exploiting the global and local information in the local model. Current pFL algorithms experience limitations such as slow convergence speed, catastrophic forgetting, and poor performance in complex tasks, which still have significant shortcomings compared to the centralized learning. To achieve high pFL performance, we propose FedCLCC: Federated Contrastive Learning and Conditional Computing. The core of FedCLCC is the use of contrastive learning and conditional computing. Contrastive learning determines the feature representation similarity to adjust the local model. Conditional computing separates the global and local information and feeds it to their corresponding heads for global and local handling. Our comprehensive experiments demonstrate that FedCLCC outperforms other state-of-the-art FL algorithms.","PeriodicalId":10986,"journal":{"name":"Defence Technology","volume":null,"pages":null},"PeriodicalIF":5.1000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Defence Technology","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1016/j.dt.2024.08.015","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 0

Abstract

Federated learning (FL) is a distributed machine learning paradigm for edge cloud computing. FL can facilitate data-driven decision-making in tactical scenarios, effectively addressing both data volume and infrastructure challenges in edge environments. However, the diversity of clients in edge cloud computing presents significant challenges for FL. Personalized federated learning (pFL) received considerable attention in recent years. One example of pFL involves exploiting the global and local information in the local model. Current pFL algorithms experience limitations such as slow convergence speed, catastrophic forgetting, and poor performance in complex tasks, which still have significant shortcomings compared to the centralized learning. To achieve high pFL performance, we propose FedCLCC: Federated Contrastive Learning and Conditional Computing. The core of FedCLCC is the use of contrastive learning and conditional computing. Contrastive learning determines the feature representation similarity to adjust the local model. Conditional computing separates the global and local information and feeds it to their corresponding heads for global and local handling. Our comprehensive experiments demonstrate that FedCLCC outperforms other state-of-the-art FL algorithms.
FedCLCC:基于对比学习和条件计算的边缘云协作个性化联合学习算法
联合学习(FL)是一种适用于边缘云计算的分布式机器学习范例。FL 可以促进战术场景中的数据驱动决策,有效解决边缘环境中的数据量和基础设施挑战。然而,边缘云计算中客户端的多样性给联合学习带来了巨大挑战。近年来,个性化联合学习(pFL)受到了广泛关注。个性化联合学习的一个例子是利用本地模型中的全局和局部信息。目前的 pFL 算法存在收敛速度慢、灾难性遗忘、在复杂任务中表现不佳等局限性,与集中式学习相比仍有明显不足。为了实现较高的 pFL 性能,我们提出了 FedCLCC:Federated Contrastive Learning and Conditional Computing(联邦对比学习和条件计算)。FedCLCC 的核心是使用对比学习和条件计算。对比学习确定特征表示的相似性,从而调整局部模型。条件计算将全局和局部信息分离开来,并将其反馈到相应的头部进行全局和局部处理。我们的综合实验证明,FedCLCC 优于其他最先进的 FL 算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Defence Technology
Defence Technology Engineering-Computational Mechanics
CiteScore
7.50
自引率
7.80%
发文量
1248
审稿时长
22 weeks
期刊介绍: Defence Technology, sponsored by China Ordnance Society, is published quarterly and aims to become one of the well-known comprehensive journals in the world, which reports on the breakthroughs in defence technology by building up an international academic exchange platform for the defence technology related research. It publishes original research papers having direct bearing on defence, with a balanced coverage on analytical, experimental, numerical simulation and applied investigations. It covers various disciplines of science, technology and engineering.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信