Personalized Federated Learning with Moreau Envelopes
This addresses the problem of poor model performance on individual clients in federated learning due to data heterogeneity, offering a solution for privacy-preserving decentralized machine learning.
The paper tackles the challenge of statistical diversity in federated learning by proposing pFedMe, a personalized federated learning algorithm using Moreau envelopes, which achieves state-of-the-art convergence rates and outperforms FedAvg and Per-FedAvg in empirical performance.
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 global model learning in a bi-level problem stylized for personalized FL. Theoretically, we show that pFedMe's convergence rate is state-of-the-art: achieving quadratic speedup for strongly convex and sublinear speedup of order 2/3 for smooth nonconvex objectives. Experimentally, we verify that pFedMe excels at empirical performance compared with the vanilla FedAvg and Per-FedAvg, a meta-learning based personalized FL algorithm.