Socially inspired Adaptive Coalition and Client Selection in Federated Learning
This addresses data heterogeneity issues in Federated Learning for privacy-preserving collaborative training, representing an incremental improvement with novel method elements.
The paper tackled client data heterogeneity in Federated Learning by introducing a client-selection algorithm that dynamically forms coalitions and selects representatives to minimize update variance, resulting in higher accuracy and faster convergence compared to baselines.
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.