pFedAFM: Adaptive Feature Mixture for Batch-Level Personalization in Heterogeneous Federated Learning

arXiv:2404.17847v1 Announce Type: new
Abstract: Model-heterogeneous personalized federated learning (MHPFL) enables FL clients to train structurally different personalized models on non-independent and identically distributed (non-IID) local data. Existing MHPFL methods focus on achieving client-level personalization, but cannot address batch-level data heterogeneity. To bridge this important gap, we propose a model-heterogeneous personalized Federated learning approach with Adaptive Feature Mixture (pFedAFM) for supervised learning tasks. It consists of three novel designs: 1) A sharing global homogeneous small feature extractor is assigned alongside …

abstract arxiv bridge client cs.lg data distributed feature federated learning focus gap independent personalization personalized train type