Multi‐Objective Optimisation Framework for Heterogeneous Federated Learning

ABSTRACT Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server. Despite rapid progress, federated learning still faces several unsolved challenges. Specifically, communication costs and system heterogeneity, such as nonidentical data distribution, hinder federated learning's progress. Several approaches have recently emerged for federated learning involving heterogeneous clients with varying computational capabilities (namely, heterogeneous federated learning). However, heterogeneous federated learning faces two key challenges: optimising model size and determining client selection ratios. Moreover, efficiently aggregating local models from clients with diverse capabilities is crucial for addressing system heterogeneity and communication efficiency. This paper proposes an evolutionary multiobjective optimisation framework for heterogeneous federated learning (MOHFL) to address these issues. Our approach elegantly formulates and solves a biobjective optimisation problem that minimises communication cost and model error rate. The decision variables in this framework comprise model sizes and client selection ratios for each Q client cluster, yielding a total of 2 Q optimisation parameters to be tuned. We develop a partition‐based strategy for MOHFL that segregates clients into clusters based on their communication and computation capabilities. Additionally, we implement an adaptive model sizing mechanism that dynamically assigns appropriate subnetwork architectures to clients based on their computational constraints. We also propose a unified aggregation framework to combine models of varying sizes from heterogeneous clients effectively. Extensive experiments on multiple datasets demonstrate the effectiveness and superiority of our proposed method compared to existing approaches.