Empowering over-the-air personalized federated learning via RIS  

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

机构地区：[1]National Mobile Communications Research Laboratory,Southeast University,Nanjing 210096,China [2]Purple Mountain Laboratories,Nanjing 211111,China [3]School of Electrical and Electronics Engineering,Nanyang Technological University,Singapore 639798,Singapore [4]Research Institute,China United Network Communications Corporation,Beijing 100048,China

出　　处：《Science China(Information Sciences)》2024年第11期367-368,共2页中国科学（信息科学）（英文版）

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.

关 键 词：AIR LEARNING POWER 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]