Since data is presented long-tailed in reality, it is challenging for Federated Learning (FL) to train across decentralized clients as practical applications. We present Global-Regularized Personalization (GRP-FED) to tackle the data imbalanced issue by considering a single global model and multiple local models for each client. With adaptive aggregation, the global model treats multiple clients fairly and mitigates the global long-tailed issue. Each local model is learned from the local data and aligns with its distribution for customization. To prevent the local model from just overfitting, GRP-FED applies an adversarial discriminator to regularize between the learned global-local features. Extensive results show that our GRP-FED improves under both global and local scenarios on real-world MIT-BIH and synthesis CIFAR-10 datasets, achieving comparable performance and addressing client imbalance.
@article{arxiv.2108.13858,
title = {GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization},
author = {Yen-Hsiu Chou and Shenda Hong and Chenxi Sun and Derun Cai and Moxian Song and Hongyan Li},
journal= {arXiv preprint arXiv:2108.13858},
year = {2021}
}
Comments
(FL-ICML'21) International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021