This paper addresses intra-client and inter-client covariate shifts in federated learning (FL) with a focus on the overall generalization performance. To handle covariate shifts, we formulate a new global model training paradigm and propose Federated Importance-Weighted Empirical Risk Minimization (FTW-ERM) along with improving density ratio matching methods without requiring perfect knowledge of the supremum over true ratios. We also propose the communication-efficient variant FITW-ERM with the same level of privacy guarantees as those of classical ERM in FL. We theoretically show that FTW-ERM achieves smaller generalization error than classical ERM under certain settings. Experimental results demonstrate the superiority of FTW-ERM over existing FL baselines in challenging imbalanced federated settings in terms of data distribution shifts across clients.
@article{arxiv.2306.05325,
title = {Federated Learning under Covariate Shifts with Generalization Guarantees},
author = {Ali Ramezani-Kebrya and Fanghui Liu and Thomas Pethick and Grigorios Chrysos and Volkan Cevher},
journal= {arXiv preprint arXiv:2306.05325},
year = {2023}
}
Comments
Published in Transactions on Machine Learning Research (TMLR)