Empowering over-the-air personalized federated learning via RIS

作     者：Wei SHI Jiacheng YAO Jindan XU Wei XU Lexi XU Chunming ZHAO 

作者机构：National Mobile Communications Research Laboratory Southeast University Purple Mountain Laboratories School of Electrical and Electronics Engineering Nanyang Technological University Research Institute China United Network Communications Corporation 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2024年第67卷第11期

页      面：371-372页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by National Natural Science Foundation of China (Grant No. 62271137) Fundamental Research Funds for the Central Universities(Grant Nos. 2242022k60002, 2242023K5003) 

摘      要：Federated learning(FL) is a promising distributed learning approach due to its privacy-enhancing characteristic [1–3].To enhance communication efficiency of FL, over-the-air computation(AirComp) has emerged as a key technique by exploiting the waveform superposition property of multiple access channels [4, 5]. Although AirComp-enabled FL(AirFL) offers significant performance gains, it does not address the data heterogeneity in most real-life FL scenarios with non-independent and identically distributed local datasets.