联邦法:具有个体公平和联盟稳定性的价值意识联邦学习

IF 5.3 3区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Jianfeng Lu;Hangjian Zhang;Pan Zhou;Xiong Wang;Chen Wang;Dapeng Oliver Wu
{"title":"联邦法:具有个体公平和联盟稳定性的价值意识联邦学习","authors":"Jianfeng Lu;Hangjian Zhang;Pan Zhou;Xiong Wang;Chen Wang;Dapeng Oliver Wu","doi":"10.1109/TETCI.2024.3446458","DOIUrl":null,"url":null,"abstract":"A long-standing problem remains with the heterogeneous clients in Federated Learning (FL), who often have diverse gains and requirements for the trained model, while their contributions are hard to evaluate due to the privacy-preserving training. Existing works mainly rely on single-dimension metric to calculate clients' contributions as aggregation weights, which however may damage the social fairness, thus discouraging the cooperation willingness of worse-off clients and causing the revenue instability. To tackle this issue, we propose a novel incentive mechanism named <italic>FedLaw</i> to effectively evaluate clients' contributions and further assign aggregation weights. Specifically, we reuse the local model updates and model the contribution evaluation process as a convex coalition game among multiple players with a non-empty core. By deriving a closed-form expression of the Shapley value, we solve the game core in quadratic time. Moreover, we theoretically prove that <italic>FedLaw</i> guarantees <italic>individual fairness</i>, <italic>coalition stability</i>, <italic>computational efficiency</i>, <italic>collective rationality</i>, <italic>redundancy</i>, <italic>symmetry</i>, <italic>additivity</i>, <italic>strict desirability</i>, and <italic>individual monotonicity</i>, and also show that <italic>FedLaw</i> can achieve a constant convergence bound. Extensive experiments on four real-world datasets validate the superiority of <italic>FedLaw</i> in terms of model aggregation, fairness, and time overhead compared to the state-of-the-art five baselines. Experimental results show that <italic>FedLaw</i> is able to reduce the computation time of contribution evaluation by about 12 times and improve the global model performance by about 2% while ensuring fairness.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"9 1","pages":"1049-1062"},"PeriodicalIF":5.3000,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"FedLaw: Value-Aware Federated Learning With Individual Fairness and Coalition Stability\",\"authors\":\"Jianfeng Lu;Hangjian Zhang;Pan Zhou;Xiong Wang;Chen Wang;Dapeng Oliver Wu\",\"doi\":\"10.1109/TETCI.2024.3446458\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A long-standing problem remains with the heterogeneous clients in Federated Learning (FL), who often have diverse gains and requirements for the trained model, while their contributions are hard to evaluate due to the privacy-preserving training. Existing works mainly rely on single-dimension metric to calculate clients' contributions as aggregation weights, which however may damage the social fairness, thus discouraging the cooperation willingness of worse-off clients and causing the revenue instability. To tackle this issue, we propose a novel incentive mechanism named <italic>FedLaw</i> to effectively evaluate clients' contributions and further assign aggregation weights. Specifically, we reuse the local model updates and model the contribution evaluation process as a convex coalition game among multiple players with a non-empty core. By deriving a closed-form expression of the Shapley value, we solve the game core in quadratic time. Moreover, we theoretically prove that <italic>FedLaw</i> guarantees <italic>individual fairness</i>, <italic>coalition stability</i>, <italic>computational efficiency</i>, <italic>collective rationality</i>, <italic>redundancy</i>, <italic>symmetry</i>, <italic>additivity</i>, <italic>strict desirability</i>, and <italic>individual monotonicity</i>, and also show that <italic>FedLaw</i> can achieve a constant convergence bound. Extensive experiments on four real-world datasets validate the superiority of <italic>FedLaw</i> in terms of model aggregation, fairness, and time overhead compared to the state-of-the-art five baselines. Experimental results show that <italic>FedLaw</i> is able to reduce the computation time of contribution evaluation by about 12 times and improve the global model performance by about 2% while ensuring fairness.\",\"PeriodicalId\":13135,\"journal\":{\"name\":\"IEEE Transactions on Emerging Topics in Computational Intelligence\",\"volume\":\"9 1\",\"pages\":\"1049-1062\"},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2024-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Emerging Topics in Computational Intelligence\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10683883/\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Emerging Topics in Computational Intelligence","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10683883/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

联邦学习(FL)中的异构客户端存在一个长期存在的问题,他们通常对训练模型有不同的收益和需求,而由于隐私保护训练,他们的贡献难以评估。现有的工作主要依靠单一维度的度量来计算客户的贡献作为聚合权重,但这可能会损害社会公平,从而抑制贫困客户的合作意愿,造成收益不稳定。为了解决这一问题,我们提出了一种新的激励机制,称为FedLaw,以有效地评估客户的贡献,并进一步分配聚合权重。具体而言,我们重用了局部模型更新,并将贡献评估过程建模为具有非空核心的多个参与者之间的凸联盟博弈。通过推导Shapley值的封闭表达式,在二次时间内求解了博弈核。此外,我们从理论上证明了FedLaw保证了个体公平性、联盟稳定性、计算效率、集体合理性、冗余性、对称性、可加性、严格可取性和个体单调性,并证明了FedLaw可以实现一个恒定的收敛界。在四个真实数据集上进行的大量实验验证了与最先进的五个基线相比,FedLaw在模型聚合、公平性和时间开销方面的优势。实验结果表明,在保证公平性的前提下,FedLaw能够将贡献评估的计算时间缩短约12倍,将全局模型性能提高约2%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
FedLaw: Value-Aware Federated Learning With Individual Fairness and Coalition Stability
A long-standing problem remains with the heterogeneous clients in Federated Learning (FL), who often have diverse gains and requirements for the trained model, while their contributions are hard to evaluate due to the privacy-preserving training. Existing works mainly rely on single-dimension metric to calculate clients' contributions as aggregation weights, which however may damage the social fairness, thus discouraging the cooperation willingness of worse-off clients and causing the revenue instability. To tackle this issue, we propose a novel incentive mechanism named FedLaw to effectively evaluate clients' contributions and further assign aggregation weights. Specifically, we reuse the local model updates and model the contribution evaluation process as a convex coalition game among multiple players with a non-empty core. By deriving a closed-form expression of the Shapley value, we solve the game core in quadratic time. Moreover, we theoretically prove that FedLaw guarantees individual fairness, coalition stability, computational efficiency, collective rationality, redundancy, symmetry, additivity, strict desirability, and individual monotonicity, and also show that FedLaw can achieve a constant convergence bound. Extensive experiments on four real-world datasets validate the superiority of FedLaw in terms of model aggregation, fairness, and time overhead compared to the state-of-the-art five baselines. Experimental results show that FedLaw is able to reduce the computation time of contribution evaluation by about 12 times and improve the global model performance by about 2% while ensuring fairness.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
10.30
自引率
7.50%
发文量
147
期刊介绍: The IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI) publishes original articles on emerging aspects of computational intelligence, including theory, applications, and surveys. TETCI is an electronics only publication. TETCI publishes six issues per year. Authors are encouraged to submit manuscripts in any emerging topic in computational intelligence, especially nature-inspired computing topics not covered by other IEEE Computational Intelligence Society journals. A few such illustrative examples are glial cell networks, computational neuroscience, Brain Computer Interface, ambient intelligence, non-fuzzy computing with words, artificial life, cultural learning, artificial endocrine networks, social reasoning, artificial hormone networks, computational intelligence for the IoT and Smart-X technologies.
×
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