Coordination-free Decentralised Federated Learning on Complex Networks: Overcoming Heterogeneity

TL;DR

This paper introduces a decentralized federated learning algorithm that enables devices to collaboratively train models over complex, heterogeneous networks without a central server, improving generalization and communication efficiency.

Contribution

It proposes a novel decentralized FL algorithm suitable for complex networks with heterogeneity, eliminating the need for a central coordinator and enhancing communication efficiency.

Findings

Local models outperform competing approaches in generalization.

The method reduces communication costs compared to centralized FL.

Models maintain accuracy despite network complexity and data heterogeneity.

Abstract

Federated Learning (FL) is a well-known framework for successfully performing a learning task in an edge computing scenario where the devices involved have limited resources and incomplete data representation. The basic assumption of FL is that the devices communicate directly or indirectly with a parameter server that centrally coordinates the whole process, overcoming several challenges associated with it. However, in highly pervasive edge scenarios, the presence of a central controller that oversees the process cannot always be guaranteed, and the interactions (i.e., the connectivity graph) between devices might not be predetermined, resulting in a complex network structure. Moreover, the heterogeneity of data and devices further complicates the learning process. This poses new challenges from a learning standpoint that we address by proposing a communication-efficient Decentralised Federated Learning (DFL) algorithm able to cope with them. Our solution allows devices communicating only with their direct neighbours to train an accurate model, overcoming the heterogeneity induced by data and different training histories. Our results show that the resulting local models generalise better than those trained with competing approaches, and do so in a more communication-efficient way.