FedStale: leveraging stale client updates in federated learning

arXiv:2405.04171v1 Announce Type: new
Abstract: Federated learning algorithms, such as FedAvg, are negatively affected by data heterogeneity and partial client participation. To mitigate the latter problem, global variance reduction methods, like FedVARP, leverage stale model updates for non-participating clients. These methods are effective under homogeneous client participation. Yet, this paper shows that, when some clients participate much less than others, aggregating updates with different levels of staleness can detrimentally affect the training process. Motivated by this observation, we introduce FedStale, …

abstract algorithms arxiv client cs.ai cs.lg data federated learning global paper shows type updates variance