计算机科学

计算机科学 ›› 2022, Vol. 49 ›› Issue (12): 46-52.doi: 10.11896/jsjkx.220500272

• 联邦学习* • 上一篇    下一篇

联邦学习激励机制研究综述

梁文雅1, 刘波1, 林伟伟2,3, 严远超1   

  1. 1 华南师范大学计算机学院 广州510631
    2 华南理工大学计算机科学与工程学院 广州510640
    3 鹏程实验室 广东 深圳518066
  • 收稿日期:2022-05-29 修回日期:2022-08-05 出版日期:2022-12-15 发布日期:2022-12-14
  • 通讯作者: 刘波(liugubin530@126.com);林伟伟(linww@scut.edu.cn)
  • 作者简介:(1799871545@qq.com)
  • 基金资助:
    广东省重点领域研发计划项目(2021B0101420002);国家自然科学基金面上项目(62002078,61872084);广州市开发区国际合作项目(2020GH10);鹏城实验室重大任务项目(PCL2021A09)

Survey of Incentive Mechanism for Federated Learning

LIANG Wen-ya1, LIU Bo1, LIN Wei-wei2,3, YAN Yuan-chao1   

  1. 1 School of Computer Science,South China Normal University,Guangzhou 510631,China
    2 School of Computer Science and Engineering,South China University of Technology,Guangzhou 510640,China
    3 Pengcheng Laboratory,Shenzhen,Guangdong 518066,China
  • Received:2022-05-29 Revised:2022-08-05 Online:2022-12-15 Published:2022-12-14
  • About author:LIANG Wen-ya,born in 1997,postgra-duate.Her main research interests include federated learning and incentive mechanism.LIU Bo,born in 1968,Ph.D,professor,is a member of China Computer Federation.His main research interests include cloud computing,big data technology and distributed security technology.LIN Wei-wei,born in 1980,Ph.D,professor,is a member of China Computer Federation.His main research interests include cloud computing,big data technology and AI application technology.
  • Supported by:
    Key Research and Development Program of Guangdong Province(2021B0101420002),General Project of National Natural Science Foundation of China(62002078,61872084),Guangzhou Development Zone International Cooperation Project(2020GH10) and Major Key Project of PCL(PCL2021A09).

PDF (PC)

872

摘要： 联邦学习(Federated Learning,FL)以多方数据参与为驱动,参与方与中央服务器通过不断交换模型参数,而不是直接上传原始数据的方式来实现数据共享和隐私保护。在实际的应用中,FL全局模型的精确性依赖于多个稳定且高质量的客户端参与,但客户端之间数据质量不平衡的问题会导致在训练过程中客户端处于不公平地位甚至直接不参与训练。因此,如何激励客户端积极可靠地参与到FL中,是保证FL被广泛推广和应用的关键。文中主要介绍了在FL中激励机制的必要性,并根据激励机制在FL训练过程中存在的子问题将现有研究分为面向贡献测量、面向客户选择、面向支付分配以及面向多子问题优化的激励机制。对现有的激励方案进行分析和对比,并在此基础上总结激励机制在发展中存在的挑战,探索FL激励机制未来的研究方向。

关键词: 联邦学习, 激励机制, 贡献测量, 客户选择, 支付分配

Abstract: Federated Learning(FL) is driven by multi-party data participation,where participants and central servers continuously exchange model parameters rather than directly upload raw data to achieve data sharing and privacy protection.In practical applications,the accuracy of the FL global model relies on multiple stable and high-quality clients participating,but there is an imba-lance in the data quality of participating clients,which can lead to the client being in an unfair position in the training process or not participating in training.Therefore,how to motivate clients to participate in federated learning actively and reliably is the key,which ensuring that FL is widely promoted and applied.This paper mainly introduces the necessity of incentive mechanisms in FL and divides the existing research into incentive mechanisms based on contribution measurement,client selection,payment allocation and multiple sub-problems optimization according to the sub-problems of incentive mechanisms in the FL training process,analyzes and compares existing incentive schemes,and summarizes the challenges in the development of incentive mechanisms on this basis,and explores the future research direction of FL incentive mechanisms.

Key words: Federated learning, Incentive mechanism, Contribution measurement, Client selection, Payment allocation

中图分类号: 

  • TP181
[1]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[2]LIM W Y B,LUONG N C,HOANG D T,et al.Federated lear-ning in mobile edge networks:A comprehensive survey[J].IEEE Communications Surveys & Tutorials,2020,22(3):2031-2063.
[3]MCMAHAN B,MOORE E,RAMAGE D,et al.Communica-tion-efficient learning of deep networks from decentralized data[C]//Artificial Intelligence and Statistics.PMLR,2017:1273-1282.
[4]LIM W Y B,NG J S,XIONG Z,et al.Decentralized edge intelligence:A dynamic resource allocation framework for hierarchical federated learning[J].IEEE Transactions on Parallel and Distributed Systems,2021,33(3):536-550.
[5]MEHMOOD A,NATGUNANATHAN I,XIANG Y,et al.Protection of big data privacy[J].IEEE Access,2016,4:1821-1834.
[6]LUNDERVOLD A S,LUNDERVOLD A.An overview of deep learning in medical imaging focusing on MRI[J].Zeitschrift fur Medizinische Physik,2019,29(2):102-127.
[7]ZHAO Y,ZHAO J,JIANG L,et al.Privacy-preserving blockchain-based federated learning for IoT devices[J].IEEE Internet of Things Journal,2020,8(3):1817-1829.
[8]AHMED L,AHMAD K,SAID N,et al.Active Learning Based Federated Learning for Waste and Natural Disaster Image Classification[J].IEEE Access,2020,8:208518-208531.
[9]LI T,SAHU A K,ZAHEER M,et al.Federated optimization in heterogeneous networks[J].Proceedings of Machine Learning and Systems,2020,2:429-450.
[10]LIU J,WANG J H,RONG C,et al.FedPA:An adaptively partial model aggregation strategy in Federated Learning[J].Computer Networks,2021,199:108468.
[11]BONAWITZ K,IVANOV V,KREUTER B,et al.Practical secure aggregation for privacy-preserving machine learning[C]//Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security.2017:1175-1191.
[12]LI S B,YANG L,LI C J,et al.Overview of Federated Learning:Technology,Applications and Future[J].Computer Integrated Manufacturing System,2022,28(7):2119-2138.
[13]ZHAN Y,ZHANG J,HONG Z,et al.A survey of incentive mechanism design for federated learning[J].IEEE Transactions on Emerging Topics in Computing,2022,10(2):1035-1044.
[14]ZENG R,ZENG C,WANG X,et al.A Comprehensive Survey of Incentive Mechanism for Federated Learning[J].arXiv:2106.15406,2021.
[15]BLUM A,HAGHTALAB N,PHILLIPS R L,et al.One for one,or all for all:Equilibria and optimality of collaboration in federated learning[C]//International Conference on Machine Learning.PMLR,2021:1005-1014.
[16]ZHANG X N,ZHU J M,GAO S,et al.Federal learning incentive mechanism based on blockchain and Bayesian game[J].Chinese Science:Information Science,2022,52(6):971-991.
[17]NG K L,CHEN Z,LIU Z,et al.A multi-player game for stu-dying federated learning incentive schemes[C]//Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence.2021:5279-5281.
[18]KANG J,XIONG Z,NIYATO D,et al.Incentive design for efficient federated learning in mobile networks:A contract theoryapproach[C]//2019 IEEE VTS Asia Pacific Wireless Communications Symposium(APWCS).IEEE,2019:1-5.
[19]ZHAN Y,LI P,QU Z,et al.A learning-based incentive mechanism for federated learning[J].IEEE Internet of Things Journal,2020,7(7):6360-6368.
[20]SONG T,TONG Y,WEI S.Profit allocation for federated lear-ning[C]//2019 IEEE International Conference on Big Data(Big Data).IEEE,2019:2577-2586.
[21]ZHANG J,LI C,ROBLES-KELLY A,et al.Hierarchically fair federated learning[J].arXiv:2004.10386,2020.
[22]NISHIO T,SHINKUMAR,MANDAYAM N B.Estimation of individual device contributions for incentivizing federated lear-ning[C]//2020 IEEE Globecom Workshops.IEEE,2020:1-6.
[23]YAN B,LIU B,WANG L,et al.Fedcm:A real-time contribution measurement method for participants in federated learning[C]//2021 International Joint Conference on Neural Networks(IJCNN).IEEE,2021:1-8.
[24]ZHANG J,WU Y,PAN R.Incentive mechanism for horizontal federated learning based on reputation and reverse auction[C]//Proceedings of the Web Conference 2021.2021:947-956.
[25]TANG M,WONG V W S.An incentive mechanism for cross-silo federated learning:A public goods perspective[C]//IEEE INFOCOM 2021-IEEE Conference on Computer Communications.IEEE,2021:1-10.
[26]KANG J,XIONG Z,NIYATO D,et al.Incentive mechanism for reliable federated learning:A joint optimization approach to combining reputation and contract theory[J].IEEE Internet of Things Journal,2019,6(6):10700-10714.
[27]HU R,GONG Y.Trading data for learning:Incentive mechanism for on-device federatedlearning[C]//GLOBECOM 2020－2020 IEEE Global Communications Conference.IEEE,2020:1-6.
[28]LE T H T,TRAN N H,TUN Y K,et al.An incentive mechanism for federated learning in wireless cellular networks:An auction approach[J].IEEE Transactions on Wireless Communications,2021,20(8):4874-4887.
[29]KHAN L U,PANDEY S R,TRAN N H,et al.Federated lear-ning for edge networks:Resource optimization and incentive mechanism[J].IEEE Communications Magazine,2020,58(10):88-93.
[30]PANDEY S R,TRAN N H,BENNIS M,et al.A crowdsourcing framework for on-device federated learning[J].IEEE Transactions on Wireless Communications,2020,19(5):3241-3256.
[31]CONG M,YU H,WENG X,et al.A vcg-based fair incentive mechanism for federated learning[J].arXiv:2008.06680,2020.
[32]LEE J,KIM D,NIYATO D.A Novel Joint Dataset and Incentive Management Mechanism for Federated Learning Over MEC[J].IEEE Access,2022,10:30026-30038.
[33]PANDEY S R,TRAN N H,BENNIS M,et al.Incentivize tobuild:A crowdsourcing framework for federated learning[C]//2019 IEEE Global Communications Conference(GLOBECOM).IEEE,2019:1-6.
[34]YU H,LIU Z,LIU Y,et al.A sustainable incentive scheme for federated learning[J].IEEE Intelligent Systems,2020,35(4):58-69.
[35]LIU Y,AI Z,SUN S,et al.Fedcoin:A peer-to-peer payment system for federated learning[M]//Federated Learning.Cham:Springer,2020:125-138.
[36]ZENG R,ZHANG S,WANG J,et al.Fmore:An incentivescheme of multi-dimensional auction for federated learning in mec[C]//2020 IEEE 40th International Conference on Distri-buted Computing Systems(ICDCS).IEEE,2020:278-288.
[37]ZHANG J,WU Y,PAN R.Auction-Based Ex-Post-Payment Incentive Mechanism Design for Horizontal Federated Learning with Reputation and Contribution Measurement[J].arXiv:2201.02410,2022.
[38]HAN J,KHAN A F,ZAWAD S,et al.Tokenized Incentive for Federated Learning[C]//Proceedings of the Federated Learning Workshop at the Association for the Advancement of Artificial Intelligence(AAAI) Conference.2022.
[39]WANG Z,HU Q,LI R,et al.Incentive Mechanism Design for Joint Resource Allocation in Blockchain-based Federated Lear-ning[J].arXiv:2202.10938,2022.
[40]WANG G,DANG C X,ZHOU Z.Measure contribution of participants in federated learning[C]//2019 IEEE International Conference on Big Data(Big Data).IEEE,2019:2597-2604.
[41]ZHANG J,GUO S,MA X,et al.Parameterized KnowledgeTransfer for Personalized Federated Learning[J].Advances in Neural Information Processing Systems,2021,34:10092-10104.
[42]LE T H T,TRAN N H,TUN Y K,et al.Auction based incentive design for efficient federated learning in cellular wireless networks[C]//2020 IEEE Wireless Communications and Networking Conference(WCNC).IEEE,2020:1-6.
[43]GAO L,LI L,CHEN Y,et al.FGFL:A blockchain-based fair incentive governor for Federated Learning[J].Journal of Parallel and Distributed Computing,2022,163:283-299.
[44]TAHANIAN E,AMOUEI M,FATEH H,et al.A game-theoretic approach for robust federated learning[J].International Journal of Engineering,2021,34(4):832-842.
[1] 鲁晨阳, 邓苏, 马武彬, 吴亚辉, 周浩浩.
基于分层抽样优化的面向异构客户端的联邦学习
Federated Learning Based on Stratified Sampling Optimization for Heterogeneous Clients
计算机科学, 2022, 49(9): 183-193. https://doi.org/10.11896/jsjkx.220500263
[2] 傅彦铭, 朱杰夫, 蒋侃, 黄保华, 孟庆文, 周兴.
移动众包中基于多约束工人择优的激励机制研究
Incentive Mechanism Based on Multi-constrained Worker Selection in Mobile Crowdsourcing
计算机科学, 2022, 49(9): 275-282. https://doi.org/10.11896/jsjkx.210700129
[3] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[4] 陈明鑫, 张钧波, 李天瑞.
联邦学习攻防研究综述
Survey on Attacks and Defenses in Federated Learning
计算机科学, 2022, 49(7): 310-323. https://doi.org/10.11896/jsjkx.211000079
[5] 鲁晨阳, 邓苏, 马武彬, 吴亚辉, 周浩浩.
基于DBSCAN聚类的集群联邦学习方法
Clustered Federated Learning Methods Based on DBSCAN Clustering
计算机科学, 2022, 49(6A): 232-237. https://doi.org/10.11896/jsjkx.211100059
[6] 闫萌, 林英, 聂志深, 曹一凡, 皮欢, 张兰.
一种提高联邦学习模型鲁棒性的训练方法
Training Method to Improve Robustness of Federated Learning
计算机科学, 2022, 49(6A): 496-501. https://doi.org/10.11896/jsjkx.210400298
[7] 王思明, 谭北海, 余荣.
面向6G可信可靠智能的区块链分片与激励机制
Blockchain Sharding and Incentive Mechanism for 6G Dependable Intelligence
计算机科学, 2022, 49(6): 32-38. https://doi.org/10.11896/jsjkx.220400004
[8] 杜辉, 李卓, 陈昕.
基于在线双边拍卖的分层联邦学习激励机制
Incentive Mechanism for Hierarchical Federated Learning Based on Online Double Auction
计算机科学, 2022, 49(3): 23-30. https://doi.org/10.11896/jsjkx.210800051
[9] 王鑫, 周泽宝, 余芸, 陈禹旭, 任昊文, 蒋一波, 孙凌云.
一种面向电能量数据的联邦学习可靠性激励机制
Reliable Incentive Mechanism for Federated Learning of Electric Metering Data
计算机科学, 2022, 49(3): 31-38. https://doi.org/10.11896/jsjkx.210700195
[10] 赵罗成, 屈志昊, 谢在鹏.
面向多层无线边缘环境下的联邦学习通信优化的研究
Study on Communication Optimization of Federated Learning in Multi-layer Wireless Edge Environment
计算机科学, 2022, 49(3): 39-45. https://doi.org/10.11896/jsjkx.210800054
[11] 杨昕宇, 彭长根, 杨辉, 丁红发.
基于演化博弈的理性拜占庭容错共识算法
Rational PBFT Consensus Algorithm with Evolutionary Game
计算机科学, 2022, 49(3): 360-370. https://doi.org/10.11896/jsjkx.210900110
[12] 邹赛兰, 李卓, 陈昕.
面向分层联邦学习的传输优化研究
Study on Transmission Optimization for Hierarchical Federated Learning
计算机科学, 2022, 49(12): 5-16. https://doi.org/10.11896/jsjkx.220300204
[13] 申圳, 赵成贵.
去中心化云存储网络的存储任务分配算法
Storage Task Allocation Algorithm in Decentralized Cloud Storage Network
计算机科学, 2022, 49(12): 17-21. https://doi.org/10.11896/jsjkx.220700131
[14] 杨鸿健, 胡学先, 李可佳, 徐阳, 魏江宏.
隐私保护的非线性联邦支持向量机研究
Study on Privacy-preserving Nonlinear Federated Support Vector Machines
计算机科学, 2022, 49(12): 22-32. https://doi.org/10.11896/jsjkx.220500240
[15] 瞿祥谋, 吴映波, 蒋晓玲.
一种非独立同分布问题下的联邦数据增强算法
Federated Data Augmentation Algorithm for Non-independent and Identical Distributed Data
计算机科学, 2022, 49(12): 33-39. https://doi.org/10.11896/jsjkx.220300031
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发