FedAC: A Adaptive Clustered Federated Learning Framework for Heterogeneous Data

arXiv:2403.16460v1 Announce Type: new
Abstract: Clustered federated learning (CFL) is proposed to mitigate the performance deterioration stemming from data heterogeneity in federated learning (FL) by grouping similar clients for cluster-wise model training. However, current CFL methods struggle due to inadequate integration of global and intra-cluster knowledge and the absence of an efficient online model similarity metric, while treating the cluster count as a fixed hyperparameter limits flexibility and robustness. In this paper, we propose an adaptive CFL framework, named FedAC, …

abstract arxiv cluster cs.ai cs.dc cs.lg current data federated learning framework global however integration knowledge performance stemming struggle training type wise