Decentralized Federated Learning Over Imperfect Communication Channels

TL;DR

This paper investigates how imperfect communication channels affect decentralized federated learning, deriving optimal local aggregation strategies to improve convergence and accuracy despite communication errors.

Contribution

It introduces a bias and convergence analysis for D-FL under imperfect channels and identifies the optimal number of local aggregations to enhance performance.

Findings

Optimal local aggregation number improves convergence.

Communication errors significantly impact model bias.

D-FL with optimal aggregation outperforms alternatives by over 10% in accuracy.

Abstract

This paper analyzes the impact of imperfect communication channels on decentralized federated learning (D-FL) and subsequently determines the optimal number of local aggregations per training round, adapting to the network topology and imperfect channels. We start by deriving the bias of locally aggregated D-FL models under imperfect channels from the ideal global models requiring perfect channels and aggregations. The bias reveals that excessive local aggregations can accumulate communication errors and degrade convergence. Another important aspect is that we analyze a convergence upper bound of D-FL based on the bias. By minimizing the bound, the optimal number of local aggregations is identified to balance a trade-off with accumulation of communication errors in the absence of knowledge of the channels. With this knowledge, the impact of communication errors can be alleviated, allowing the convergence upper bound to decrease throughout aggregations. Experiments validate our convergence analysis and also identify the optimal number of local aggregations on two widely considered image classification tasks. It is seen that D-FL, with an optimal number of local aggregations, can outperform its potential alternatives by over 10% in training accuracy.