A Multi-Token Coordinate Descent Method for Vertical Federated Learning
Abstract
Communication efficiency is a major challenge in federated learning. In client-server schemes, the server constitutes a bottleneck, and while decentralized setups spread communications, they do not reduce them. We propose a communication efficient semi-decentralized federated learning algorithm for feature-distributed data. Our multi-token method can be seen as a parallel Markov chain (block) coordinate descent algorithm. In this work, we formalize the multi-token semi-decentralized scheme, which subsumes the client-server and decentralized setups, and design a feature-distributed learning algorithm for this setup. Numerical results show the improved communication efficiency of our algorithm.
Cite
Text
Valdeira et al. "A Multi-Token Coordinate Descent Method for Vertical Federated Learning." NeurIPS 2022 Workshops: Federated_Learning, 2022.Markdown
[Valdeira et al. "A Multi-Token Coordinate Descent Method for Vertical Federated Learning." NeurIPS 2022 Workshops: Federated_Learning, 2022.](https://mlanthology.org/neuripsw/2022/valdeira2022neuripsw-multitoken/)BibTeX
@inproceedings{valdeira2022neuripsw-multitoken,
title = {{A Multi-Token Coordinate Descent Method for Vertical Federated Learning}},
author = {Valdeira, Pedro and Chi, Yuejie and Soares, Claudia and Xavier, Joao},
booktitle = {NeurIPS 2022 Workshops: Federated_Learning},
year = {2022},
url = {https://mlanthology.org/neuripsw/2022/valdeira2022neuripsw-multitoken/}
}