---
title: "FedCSGA: Client Selection Based on Genetic Algorithm for Federated Learning"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04667v1"
permalink: "https://feed.astralor.com/items/itm_7afe3c387e5c531101251795"
published: "2026-11-03T10:52:35.000Z"
score: 61
channel: "tech"
tags: ["推理效率","RAG","FedCSGA","Client Selection Based","Genetic Algorithm","Federated Learning Federated","Learning","Federated Learning"]
---

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

## 速览

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 co…

## 关键点

- 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 con…
- In heterogeneous edge computing environments, both statistical heterogeneity and system heterogeneity significantly affect convergence efficiency and model performance.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_7afe3c387e5c531101251795