Joint Resource Allocation and User Scheduling Scheme for Federated Learning

This paper investigates the impact of communication factors on the convergence performance of federated learning (FL) in wireless networks. Considering the limited communication resources in wireless networks, it is difficult to schedule all users to participate in a comprehensive training and the convergence performance of training model relies much on the user scheduling scheme. To minimize the maximum update delay of user training, we propose a joint resource allocation and user scheduling scheme in this paper. Particularly, the user communication delay and user training results are jointly considered to dynamically schedule users and allocate communication resources. Simulation results show that the convergence time can be reduced by 41.6% compared with the random scheduling allocation scheme.