# FedCSGA: Client Selection Based on Genetic Algorithm for Federated Learning

DevFeed: [FedCSGA: Client Selection Based on Genetic Algorithm for Federated Learning](<https://devfeed.tech/articles/fedcsga-client-selection-based-on-genetic-algorithm-for-federated-learning-116493.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.04667>)

Author: Ghani Haider, Majid Kundroo, Leo Zhang, Jinchul Choi, Taehong Kim

Published: 2026-11-04T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [bias](<https://devfeed.tech/tags/bias.md>), [cifar-10](<https://devfeed.tech/tags/cifar-10.md>), [client](<https://devfeed.tech/tags/client.md>), [communication](<https://devfeed.tech/tags/communication.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [data-privacy](<https://devfeed.tech/tags/data-privacy.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-computing](<https://devfeed.tech/tags/edge-computing.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [faster](<https://devfeed.tech/tags/faster.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [fitness](<https://devfeed.tech/tags/fitness.md>), [function](<https://devfeed.tech/tags/function.md>), [history](<https://devfeed.tech/tags/history.md>), [selection](<https://devfeed.tech/tags/selection.md>)

## AI overview

FedCSGA uses a genetic algorithm to select client subsets for federated learning, jointly accounting for statistical utility, system resources, and clients' participation history. It encodes subsets as chromosomes and scores them with a nonlinear fitness function intended to capture interactions between clients and reduce persistent selection bias. The abstract reports experiments on FMNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet, with improvements of up to 7.0% in accuracy and faster convergence using fewer communication rounds than state-of-the-art baselines across diverse heterogeneity settings. The supplied evidence is an abstract and does not specify the baselines or experimental details.

## Source excerpt

arXiv:2611.04667v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative training of machine learning models across distributed clients while preserving data privacy. In practical deployments, FL relies on selecting a subset of clients in each communication round to reduce communication cost, mitigate stragglers, and improve training efficiency under heterogeneous data and system conditions. In heterogeneous edge computing environments, both statistical heterogeneity and system heterogeneity significantly affect convergence efficiency and model performance. However, existing client selection methods often address these factors independently, overlooking their coupled and dynamic impact across communication rounds. To address this limitation, we propose FedCSGA, a Client Selection method for Federated learning based on a Genetic Algorithm. FedCSGA encodes client subsets as chromosomes and evaluates these subsets through a non-linear fitness function that jointly integrates resource-aware metrics and history-aware participation weighting. This design captures subset-level interactions, mitigates persistent selection bias, and balances statistical utility with system efficiency. Extensive experiments on FMNIST, CIFAR-10, CIFAR- 100, and Tiny-ImageNet demonstrate that FedCSGA consistently outperforms state-of-the-art baselines across diverse heterogeneity settings, achieving accuracy improvements of up to 7.0% and faster convergence with fewer communication rounds. These results validate the effectiveness of jointly modeling statistical and system factors to achieve robust and efficient learning in heterogeneous federated environments.