KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting

arXiv:2404.12846v1 Announce Type: new
Abstract: Although Split Federated Learning (SFL) is good at enabling knowledge sharing among resource-constrained clients, it suffers from the problem of low training accuracy due to the neglect of data heterogeneity and catastrophic forgetting. To address this issue, we propose a novel SFL approach named KoReA-SFL, which adopts a multi-model aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and a knowledge replay strategy to deal with catastrophic forgetting. Specifically, in KoReA-SFL cloud servers (i.e., …

abstract accuracy arxiv catastrophic forgetting cs.lg data enabling federated learning good issue knowledge korea low novel split training type