Personalized Federated Learning with Moreau Envelopes. (arXiv:2006.08848v3 [cs.LG] UPDATED)

Federated learning (FL) is a decentralized and privacy-preserving machine
learning technique in which a group of clients collaborate with a server to
learn a global model without sharing clients' data. One challenge associated
with FL is statistical diversity among clients, which restricts the global
model from delivering good performance on each client's task. To address this,
we propose an algorithm for personalized FL (pFedMe) using Moreau envelopes as
clients' regularized loss functions, which help decouple personalized model
optimization from the …

arxiv federated learning learning personalized