FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning

arXiv:2506.23210v5 Announce Type: replace-cross Abstract: Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, data and system heterogeneity often cause catastrophic forgetting and unbounded drift in model updates, leading...