Personalized Federated Learning via Stacking

arXiv:2404.10957v2 Announce Type: replace
Abstract: Traditional Federated Learning (FL) methods typically train a single global model collaboratively without exchanging raw data. In contrast, Personalized Federated Learning (PFL) techniques aim to create multiple models that are better tailored to individual clients' data. We present a novel personalization approach based on stacked generalization where clients directly send each other privacy-preserving models to be used as base models to train a meta-model on private data. Our approach is flexible, accommodating various privacy-preserving techniques …

abstract aim arxiv contrast create cs.cr cs.dc cs.lg data federated learning global multiple novel personalization personalized raw train type via