FedQMIX:Communication-efficient federated learning via multi-agent reinforcement learning

作     者：Shaohua Cao Hanqing Zhang Tian Wen Hongwei Zhao Quancheng Zheng Weishan Zhang Danyang Zheng 

作者机构：Qingdao Institute of SoftwareCollege of Computer Science and TechnologyChina University of Petroleum(East China)Qingdao 266580China School of Computing and Artificial IntelligenceXipu CampusSouthwest Jiaotong UniversityChengdu 611756China 

出 版 物：《High-Confidence Computing》 (高置信计算（英文）)

年 卷 期：2024年第4卷第2期

页      面：96-104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 the National Natural Science Foundation of China(NSFC)(62072469) 

主　　题：Communication efficient Federated learning MARL 

摘      要：Since the data samples on client devices are usually non-independent and non-identically distributed(non-IID),this will challenge the convergence of federated learning(FL)and reduce communication *** paper proposes FedQMIX,a node selection algorithm based on multi-agent reinforcement learning(MARL),to address these ***,we observe a connection between model weights and data distribution,and a clustering algorithm can group clients with similar data distribution into the same ***,we propose a QMIX-based mechanism that learns to select devices from clustering results in each communication round to maximize the reward,penalizing the use of more communication rounds and thereby improving the communication efficiency of ***,experiments show that FedQMIX can reduce the number of communication rounds by 11%and 30%on the MNIST and CIFAR-10 datasets,respectively,compared to the baseline algorithm(Favor).