Adaptive Personalized Federated Learning
Abstract
Investigation of the degree of personalization in federated learning algorithms has shown that only maximizing the performance of the global model will confine the capacity of the local models to personalize. In this paper, we advocate an adaptive personalized federated learning (APFL) algorithm, where each client will train their local models while contributing to the global model. We derive the generalization bound of mixture of local and global models, and find the optimal mixing parameter. We also propose a communication-efficient optimization method to collaboratively learn the personalized models and analyze its convergence in both smooth strongly convex and nonconvex settings. The extensive experiments demonstrate the effectiveness of our personalization schema, as well as the correctness of established generalization theories.
Cite
@article{arxiv.2003.13461,
title = {Adaptive Personalized Federated Learning},
author = {Yuyang Deng and Mohammad Mahdi Kamani and Mehrdad Mahdavi},
journal= {arXiv preprint arXiv:2003.13461},
year = {2020}
}
Comments
[v3] Added convergence analysis for nonconvex losses and additional experiments along with new baselines [v2] A new generalization analysis is provided. Also, additional experiments are added