移动边缘网络中联邦学习效率优化综述  

Survey on Optimization of Federated Learning Efficiency in Mobile Edge Networks

作　　者：孙兵 刘艳[1] 王田 彭绍亮 王国军 贾维嘉 Sun Bing;Liu Yan;Wang Tian;Peng Shaoliang;Wang Guojun;Jia Weijia(College of Computer Science and Technology,Huaqiao University,Xiamen,Fujian 361021;Institute of Artificial Intelligence and Future Networks,Beijing Normal University,Zhuhai,Guangdong 519087;Key Laboratory of Artificial Intelligence and Multi Modal Data Processing,Beijing Normal University Hong Kong Baptist University United Intermational College,Zhuhai,Guangdong 519087;College of Computer Science and Electronic Engineering,Hunan University,Changsha 410082;School of Computer Science and Cyber Engineering,Guangzhou University,Guangzhou 510006)

机构地区：[1]华侨大学计算机科学与技术学院,福建厦门361021 [2]北京师范大学人工智能与未来网络研究院,广东珠海519087 [3]北京师范大学香港浸会大学联合国际学院人工智能与多模态数据处理重点实验室,广东珠海519087 [4]湖南大学信息科学与工程学院,长沙410082 [5]广州大学计算机科学与网络工程学院,广州510006

出　　处：《计算机研究与发展》2022年第7期1439-1469,共31页Journal of Computer Research and Development

基　　金：国家重点研发计划项目(2022YFE0201400);国家自然科学基金项目(62172046);福建省自然科学基金项目(2020J06023);广东省教育厅普通高校重点专项(2021ZDZX1063);广东省教育厅人工智能与多模态数据处理重点实验室项目(2020KSYS007);珠海市产学研项目(ZH22017001210133PWC);UIC科研启动经费(R72021202)。

摘　　要：联邦学习(federated learning)将模型训练任务部署在移动边缘设备,参与者只需将训练后的本地模型发送到服务器参与全局聚合而无须发送原始数据,提高了数据隐私性.然而,解决效率问题是联邦学习落地的关键.影响效率的主要因素包括设备与服务器之间的通信消耗、模型收敛速率以及移动边缘网络中存在的安全与隐私风险.在充分调研后,首先将联邦学习的效率优化归纳为通信、训练与安全隐私保护3类.具体来说,从边缘协调与模型压缩的角度讨论分析了通信优化方案;从设备选择、资源协调、聚合控制与数据优化4个方面讨论分析了训练优化方案;从安全与隐私的角度讨论分析了联邦学习的保护机制.其次,通过对比相关技术的创新点与贡献,总结了现有方案的优点与不足,探讨了联邦学习所面临的新挑战.最后,基于边缘计算的思想提出了边缘化的联邦学习解决方案,在数据优化、自适应学习、激励机制和隐私保护等方面给出了创新理念与未来展望.Federated learning deploys deep learning training tasks on mobile edge networks. Mobile devices participating in learning only need to send the trained local models to the server instead of sending personal data, thereby protecting the data privacy of users. To speed up the implementation of federated learning, optimization of efficiency is the key. The main factors affecting efficiency include communication consumption between device and server, model convergence rate, and security and privacy risk of mobile edge networks. Based on thoroughly investigating the existing optimization methods, we summarize the efficiency optimization of federated learning into communication optimization, training optimization, and protection mechanism for the first time. Specifically, we discuss the optimization of federated learning communication from two aspects of edge computing coordination and model compression which can reduce the frequency of communication and resource consumption. Then, we review the optimization of federated learning process from four elements of device selection, resource coordination, model aggregation control, and data optimization similarly, because there are many heterogeneous factors in the mobile edge networks, such as the different computing resources of mobile devices and different data quality. Furthermore, the security and privacy protection mechanisms of federated learning are expounded. After comparing the innovation points and contributions of related technologies, the advantages and disadvantages of the existing solutions are concluded and the new challenges faced by federated learning are discussed. Finally, we propose edge-intelligent federated learning based on the idea of edge computing, provide innovative methods and future research directions in data optimization, adaptive learning, incentive mechanisms, and advanced technology.

关 键 词：联邦学习 深度学习 效率 边缘计算 移动边缘网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]