Personalized Cross-Silo Federated Learning on Non-IID Data
Abstract
Non-IID data present a tough challenge for federated learning. In this paper, we explore a novel idea of facilitating pairwise collaborations between clients with similar data. We propose FedAMP, a new method employing federated attentive message passing to facilitate similar clients to collaborate more. We establish the convergence of FedAMP for both convex and non-convex models, and propose a heuristic method to further improve the performance of FedAMP when clients adopt deep neural networks as personalized models. Our extensive experiments on benchmark data sets demonstrate the superior performance of the proposed methods.
Cite
Text
Huang et al. "Personalized Cross-Silo Federated Learning on Non-IID Data." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I9.16960Markdown
[Huang et al. "Personalized Cross-Silo Federated Learning on Non-IID Data." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/huang2021aaai-personalized/) doi:10.1609/AAAI.V35I9.16960BibTeX
@inproceedings{huang2021aaai-personalized,
title = {{Personalized Cross-Silo Federated Learning on Non-IID Data}},
author = {Huang, Yutao and Chu, Lingyang and Zhou, Zirui and Wang, Lanjun and Liu, Jiangchuan and Pei, Jian and Zhang, Yong},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {7865-7873},
doi = {10.1609/AAAI.V35I9.16960},
url = {https://mlanthology.org/aaai/2021/huang2021aaai-personalized/}
}