Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applications

作     者：Hu, Shuyan Chen, Xiaojing Ni, Wei Hossain, Ekram Wang, Xin 

作者机构：Fudan Univ Sch Informat Sci & Technol State Key Lab ASIC & Syst Shanghai 200433 Peoples R China Shanghai Univ Shanghai Inst Adv Commun & Data Sci Shanghai 200444 Peoples R China Commonwealth Sci & Ind Res Org Digital Prod & Serv Flagship Sydney NSW 2122 Australia Univ Manitoba Dept Elect & Comp Engn Winnipeg MB R3T 5V6 Canada 

出 版 物：《IEEE COMMUNICATIONS SURVEYS AND TUTORIALS》 (IEEE Commun. Surv. Tutor.)

年 卷 期：2021年第23卷第3期

页      面：1458-1493页

核心收录：

学科分类：0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：China Postdoctoral Science Foundation [2020M681168] National Natural Science Foundation of China [61901251, 62071126] Natural Sciences and Engineering Research Council of Canada (NSERC) Innovation Program of Shanghai Municipal Science and Technology Commission [20JC1416400] 

主　　题：Wireless communication Wireless networks Communication system security Wireless sensor networks Computer architecture Servers Security Distributed machine learning wireless communication networks convergence computation and communication cost architecture and platform data privacy and security 

摘      要：Distributed machine learning (DML) techniques, such as federated learning, partitioned learning, and distributed reinforcement learning, have been increasingly applied to wireless communications. This is due to improved capabilities of terminal devices, explosively growing data volume, congestion in the radio interfaces, and increasing concern of data privacy. The unique features of wireless systems, such as large scale, geographically dispersed deployment, user mobility, and the massive amount of data, give rise to new challenges in the design of DML techniques. There is a clear gap in the existing literature that the DML techniques are yet to be systematically reviewed for their applicability to wireless systems. This survey bridges the gap by providing a contemporary and comprehensive survey of DML techniques with a focus on wireless networks. Specifically, we review the latest applications of DML in power control, spectrum management, user association, and edge cloud computing. The optimality, accuracy, convergence rate, computation cost, and communication overhead of DML are analyzed. We also discuss the potential adversarial attacks faced by DML applications, and describe state-of-the-art countermeasures to preserve privacy and security. Last but not least, we point out a number of key issues yet to be addressed, and collate potentially interesting and challenging topics for future research.