Delay Minimization for Intelligent Reflecting Surface Assisted Federated Learning

• 作 者: Ning Huang Tianshun Wang Yuan Wu Suzhi Bi Liping Qian Bin Lin
• 机 构: State Key Laboratory of Internet of Things for Smart City,University of Macau,Macau,China;Department
• 出 处: 中国通信（英文版）
• 发表日期: 2022年4期
• 关键词: federated learning intelligent reflecting surface latency minimization

Federated learning(FL),which allows multiple mobile devices to cooperatively train a ma-chine learning model without sharing their data with the central server,has received widespread attention.However,the process of FL involves frequent com-munications between the server and mobile devices,which incurs a long latency.Intelligent reflecting sur-face(IRS)provides a promising technology to address this issue,thanks to its capacity to reconfigure the wireless propagation environment.In this paper,we exploit the advantage of IRS to reduce the latency of FL.Specifically,we formulate a latency minimization problem for the IRS assisted FL system,by optimiz-ing the communication resource allocations including the devices\'transmit-powers,the uploading time,the downloading time,the multi-user decomposition ma-trix and the phase shift matrix of IRS.To solve this non-convex problem,we propose an efficient algo-rithm which is based on the Block Coordinate Descent(BCD)and the penalty difference of convex(DC)al-gorithm to compute the solution.Numerical results are provided to validate the efficiency of our proposed al-gorithm and demonstrate the benefit of deploying IRS for reducing the latency of FL.In particular,the results show that our algorithm can outperform the baseline of Majorization-Minimization(MM)algorithm with the fixed transmit-power bv up to 30％.