Fast Federated Learning via Imprecise Correction in Unreliable Wireless Networks

Due to data heterogeneity and parameter transmission failure, federated learning (FL) usually suffers performance degradation in wireless networks. To address this issue, a novel federated Learning via reusing historical Information (FedRe) is proposed for convergence acceleration and performance enhancement without any additional communication cost. Specifically, an analytical model is first built to characterize the impacts of data heterogeneity and parameter transmission failure on FL performance. Based on this, a local gradient correction method and a statistical aggregation correction method are proposed to deal with data heterogeneity and transmission unreliability problems respectively. Additionally, the convergence of the proposed FedRe is proved and analyzed theoretically. Finally, extensive numerical results are presented with experiments on two public datasets to validate the effectiveness of FedRe with comparisons of baselines.