Adaptive Configuration for Heterogeneous Participants in Decentralized Federated Learning

TL;DR

This paper introduces FedHP, an adaptive decentralized federated learning method that optimizes local update frequency and network topology to address heterogeneity, achieving faster convergence and better accuracy.

Contribution

FedHP is the first method to adaptively control local updates and network topology in DFL, improving convergence speed and model accuracy in heterogeneous environments.

Findings

Reduces completion time by about 51%.

Improves model accuracy by at least 5%.

Effectively handles system and statistical heterogeneity.

Abstract

Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing (EC). Aided by EC, decentralized federated learning (DFL), which overcomes the single-point-of-failure problem in the parameter server (PS) based federated learning, is becoming a practical and popular approach for machine learning over distributed data. However, DFL faces two critical challenges, \ie, system heterogeneity and statistical heterogeneity introduced by edge devices. To ensure fast convergence with the existence of slow edge devices, we present an efficient DFL method, termed FedHP, which integrates adaptive control of both local updating frequency and network topology to better support the heterogeneous participants. We establish a theoretical relationship between local updating frequency and network topology regarding model training performance and obtain a convergence upper bound. Upon this, we propose an optimization algorithm, that adaptively determines local updating frequencies and constructs the network topology, so as to speed up convergence and improve the model accuracy. Evaluation results show that the proposed FedHP can reduce the completion time by about 51% and improve model accuracy by at least 5% in heterogeneous scenarios, compared with the baselines.