EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federated Learning

2026-06-05

AI Summary

This work addresses the slow convergence and poor robustness in federated learning caused by statistical and system heterogeneity across clients. To tackle this challenge, the authors propose an evolutionary client selection framework based on surrogate models. The approach formulates client selection as a multi-objective combinatorial optimization problem and, for the first time, integrates surrogate modeling with evolutionary algorithms to efficiently identify optimal client subsets that jointly optimize model performance, communication latency, and energy consumption. Experimental results on MNIST, CIFAR-10, CINIC-10, and TinyImageNet demonstrate that the proposed method significantly accelerates convergence, reduces energy usage, and enhances system robustness, outperforming existing client selection strategies.

Abstract

The heterogeneity of client data and systems makes it difficult to achieve satisfactory convergence speed and robustness in federated learning with random client selection. To address this issue, this paper proposes a surrogate-assisted client evolutionary selection framework for federated learning. In this framework, some typical client selection strategies are first used to generate candidate sets, and a metric function that integrates model performance, communication latency, and energy consumption is developed to formulate the client selection problem as a combinatorial optimization one. Subsequently, a surrogate model is constructed using the candidate selections and metric to efficiently approximate the performance of selected client subsets. An evolutionary algorithm is employed to search the combinatorial space of client selections, guided by the surrogate model to accelerate convergence. Experiments on MNIST, CIFAR10, CINIC10, and TinyImageNet demonstrate that the proposed algorithm achieves faster convergence, lower energy consumption, and improved robustness compared to existing methods.

Problem

• federated learning
• client selection
• heterogeneity
• convergence speed
• robustness

Innovation

• surrogate-assisted optimization
• evolutionary algorithm
• client selection
• federated learning
• combinatorial optimization