Initialisation and Network Effects in Decentralised Federated Learning

TL;DR

This paper investigates how network topology and initial conditions affect decentralized federated learning, proposing an eigenvector centrality-based initialization strategy that improves training efficiency and scalability in distributed neural network training.

Contribution

It introduces a novel uncoordinated initialization method based on network eigenvector centralities, enhancing training efficiency in decentralized federated learning.

Findings

Eigenvector centrality-based initialization improves training efficiency

Network topology significantly influences learning dynamics

Scaling behavior depends on environmental parameters

Abstract

Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the training data localised on each node. This approach avoids central coordination, enhances data privacy and eliminates the risk of a single point of failure. Our research highlights that the effectiveness of decentralised federated learning is significantly influenced by the network topology of connected devices and the learning models' initial conditions. We propose a strategy for uncoordinated initialisation of the artificial neural networks based on the distribution of eigenvector centralities of the underlying communication network, leading to a radically improved training efficiency. Additionally, our study explores the scaling behaviour and the choice of environmental parameters under our proposed initialisation strategy. This work paves the way for more efficient and scalable artificial neural network training in a distributed and uncoordinated environment, offering a deeper understanding of the intertwining roles of network structure and learning dynamics.