Efficient and Less Centralized Federated Learning
Abstract
With the rapid growth in mobile computing, massive amounts of data and computing resources are now located at the edge. To this end, Federated learning (FL) is becoming a widely adopted distributed machine learning (ML) paradigm, which aims to harness this expanding skewed data locally in order to develop rich and informative models. In centralized FL, a collection of devices collaboratively solve a ML task under the coordination of a central server. However, existing FL frameworks make an over-simplistic assumption about network connectivity and ignore the communication bandwidth of the different links in the network. In this paper, we present and study a novel FL algorithm, in which devices mostly collaborate with other devices in a pairwise manner. Our nonparametric approach is able to exploit network topology to reduce communication bottlenecks. We evaluate our approach on various FL benchmarks and demonstrate that our method achieves 10X better communication efficiency and around 8% increase in accuracy compared to the centralized approach.
Cite
Text
Chou et al. "Efficient and Less Centralized Federated Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021. doi:10.1007/978-3-030-86486-6_47Markdown
[Chou et al. "Efficient and Less Centralized Federated Learning." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2021.](https://mlanthology.org/ecmlpkdd/2021/chou2021ecmlpkdd-efficient/) doi:10.1007/978-3-030-86486-6_47BibTeX
@inproceedings{chou2021ecmlpkdd-efficient,
title = {{Efficient and Less Centralized Federated Learning}},
author = {Chou, Li and Liu, Zichang and Wang, Zhuang and Shrivastava, Anshumali},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2021},
pages = {772-787},
doi = {10.1007/978-3-030-86486-6_47},
url = {https://mlanthology.org/ecmlpkdd/2021/chou2021ecmlpkdd-efficient/}
}