Communication-Efficient Federated Learning with Accelerated Client Gradient

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Geeho, Kim, Jinkyu, Han, Bohyung
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910393544212480
author Kim, Geeho
Kim, Jinkyu
Han, Bohyung
author_facet Kim, Geeho
Kim, Jinkyu
Han, Bohyung
contents Federated learning often suffers from slow and unstable convergence due to the heterogeneous characteristics of participating client datasets. Such a tendency is aggravated when the client participation ratio is low since the information collected from the clients has large variations. To address this challenge, we propose a simple but effective federated learning framework, which improves the consistency across clients and facilitates the convergence of the server model. This is achieved by making the server broadcast a global model with a lookahead gradient. This strategy enables the proposed approach to convey the projected global update information to participants effectively without additional client memory and extra communication costs. We also regularize local updates by aligning each client with the overshot global model to reduce bias and improve the stability of our algorithm. We provide the theoretical convergence rate of our algorithm and demonstrate remarkable performance gains in terms of accuracy and communication efficiency compared to the state-of-the-art methods, especially with low client participation rates. The source code is available at our project page.
format Preprint
id arxiv_https___arxiv_org_abs_2201_03172
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Communication-Efficient Federated Learning with Accelerated Client Gradient
Kim, Geeho
Kim, Jinkyu
Han, Bohyung
Machine Learning
Artificial Intelligence
Federated learning often suffers from slow and unstable convergence due to the heterogeneous characteristics of participating client datasets. Such a tendency is aggravated when the client participation ratio is low since the information collected from the clients has large variations. To address this challenge, we propose a simple but effective federated learning framework, which improves the consistency across clients and facilitates the convergence of the server model. This is achieved by making the server broadcast a global model with a lookahead gradient. This strategy enables the proposed approach to convey the projected global update information to participants effectively without additional client memory and extra communication costs. We also regularize local updates by aligning each client with the overshot global model to reduce bias and improve the stability of our algorithm. We provide the theoretical convergence rate of our algorithm and demonstrate remarkable performance gains in terms of accuracy and communication efficiency compared to the state-of-the-art methods, especially with low client participation rates. The source code is available at our project page.
title Communication-Efficient Federated Learning with Accelerated Client Gradient
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2201.03172