联邦学习激励机制研究综述  

Survey of Incentive Mechanism for Federated Learning

作　　者：梁文雅 刘波[1] 林伟伟[2,3] 严远超 LIANG Wen-ya;LIU Bo;LIN Wei-wei;YAN Yuan-chao(School of Computer Science,South China Normal University,Guangzhou 510631,China;School of Computer Science and Engineering,South China University of Technology,Guangzhou 510640,China;Pengcheng Laboratory,Shenzhen,Guangdong 518066,China)

机构地区：[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

出　　处：《计算机科学》2022年第12期46-52,共7页Computer Science

基　　金：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)。

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。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.

关 键 词：联邦学习 激励机制 贡献测量 客户选择 支付分配 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP309[自动化与计算机技术—控制科学与工程]