Socially inspired Adaptive Coalition and Client Selection in Federated Learning

TL;DR

This paper presents a novel client-selection algorithm for federated learning that forms dynamic coalitions based on social-network inspired clustering, leading to improved accuracy and convergence.

Contribution

It introduces a social-inspired coalition formation and client selection method with theoretical guarantees, addressing data heterogeneity in federated learning.

Findings

Higher accuracy compared to baseline methods

Faster convergence in federated learning tasks

Effective handling of client data heterogeneity

Abstract

Federated Learning (FL) enables privacy-preserving collaborative model training, but its effectiveness is often limited by client data heterogeneity. We introduce a client-selection algorithm that (i) dynamically forms nonoverlapping coalitions of clients based on asymptotic agreement and (ii) selects one representative from each coalition to minimize the variance of model updates. Our approach is inspired by social-network modeling, leveraging homophily-based proximity matrices for spectral clustering and techniques for identifying the most informative individuals to estimate a group's aggregate opinion. We provide theoretical convergence guarantees for the algorithm under mild, standard FL assumptions. Finally, we validate our approach by benchmarking it against three strong heterogeneity-aware baselines; the results show higher accuracy and faster convergence, indicating that the framework is both theoretically grounded and effective in practice.