Open access

Resilient federated learning under data and system heterogeneity via genetic algorithm-based group client selection

Sani Umar Ahmed Alagha R. Mizouni Shakti Singh Jamal Bentahar Hadi Otrok

Jul 2026 · Evolutionary Intelligence · Vol 19 · 0 citations · 51 references

Computer Science

TL;DR

A Genetic-Algorithm (GA) based client selection mechanism that is applicable to both horizontal FL (HFL) and vertical FL (VFL) and improves global model accuracy and accelerates convergence is proposed.

Abstract

The process of selecting suitable clients to participate in Federated Learning (FL) remains a critical challenge due to non-IID heterogeneity in data distributions and heterogeneity in computational resources among participating clients. Existing client selection approaches typically assess clients individually using attributes such as model accuracy. Such individual-based client assessment ignores group effects, which are paramount for global model performance. In this paper, we propose a Genetic-Algorithm (GA) based client selection mechanism that is applicable to both horizontal FL (HFL) and vertical FL (VFL). Candidate client groups are evaluated by a multi-criteria fitness function that jointly models group data size, feature coverage, label coverage, class balance, feature-distribution divergence, feature importance, computational power, reputation, accuracy, and outlier proportion. The GA performs an efficient search over the combinatorial space of client subsets. The proposed approach is evaluated using image classification, diabetes prediction, and rain prediction tasks. The proposed approach improves global model accuracy and accelerates convergence. On the MNIST dataset, it peaks at 98.37%, outperforming DSCS (97.27%) and FedMCCS (97.07%). On the diabetes dataset, it achieves 88.37%, while DSCS and FedMCCS achieve 87.15% and 86.64%, respectively. On the rain prediction task, it attains a peak accuracy of 83.57% and converges to 83.36%, compared with 81.98% for FedMCCS and 80.38% for DSCS.

DOI Semantic Scholar

Read PDF

Similar papers

#federated learning Open access Sep 2026

History-Aware Multi-Objective Client Selection for Federated Learning under Statistical and System Heterogeneity

Federated learning reduces raw-data movement, but partial participation under statistical and system heterogeneity makes the selected client cohort a major source of optimisation bias and delay. This study proposes a history-aware multi-objective selector that combines opt-in data-quality metadata, exponentially smoothed training utility, marginal label-balance gain, participation deficit, and an online latency penalty without querying every client's current private loss. A paired protocol compares Random FedAvg, Power-of-Choice, an Oort-inspired policy, a class-balance greedy policy, and the proposed method on Digits, MNIST, and CIFAR-10. The confirmatory benchmark uses 50 clients, three Dirichlet non-IID levels, ten fresh seeds, and Holm-adjusted Wilcoxon tests. Relative to Random FedAvg, the proposed method improves final-five-round accuracy in all six MNIST/CIFAR-10 conditions by 1.11–5.53 percentage points, with four adjusted-significant conditions. Component ablations show distinct roles. Label balance improves accuracy AUC in all six conditions, the adaptive penalty reduces simulated synchronous latency, and the fairness term improves participation uniformity without eliminating all dataset-dependent concentration. Accuracy gains remain positive when 6%, 10%, or 20% of clients participate per round. The evidence supports a practical accuracy–balance–latency trade-off rather than universal dominance, and the study defines clear boundaries for privacy and hardware claims.

Haoxuan Geng · Applied and Computational En... · 0 citations

Parameter-Efﬁcient Personalized Federated Learning for Accurate Cellular Trafﬁc Prediction

Xing-Yu Tian, Ci-Tong Que, F. Nadeem et al. · 0 citations

Preprint Aug 2026

Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning

Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space using an NTK-based agreement score to characterize predictive behavior and determine a personalized aggregation set for each client.

Mirko Konstantin, S. Zachow, Anirban Mukhopadhyay · 0 citations

Aug 2026

The GAO-based federated learning framework with adaptive client selection for resource-efficient edge-IoT systems

The Federated Green Anaconda Optimizer (FedGAO), an innovative FL framework inspired by the behavioral patterns of the Green Anaconda Optimizer (GAO), is proposed, demonstrating superior performance in terms of accuracy, convergence speed, and resource efficiency.

Elahe Eslami, S. A. Shahzadeh Fazeli, J. Abouei et al. · Cluster Computing · 0 citations

Review Open access Aug 2026

Federated Learning with SVMs: Dynamic SGD for Efficient Hyperparameter Optimization

Empirical evaluations on benchmark datasets show that federated SVM framework provides effective results comparable to NN-based FL approaches while significantly less computational and communication overhead.

Deebakkarthi Chinnasame Rani, Gowtham Ramesh, Sountharrajan Sehar et al. · Journal of Computational and... · 0 citations

Aug 2026

Prototype-based federated learning for one-time soft clustering

Experiments under representative Non-IID settings on benchmark datasets show that PFLS-One achieves improved accuracy and faster convergence compared with representative baseline methods, and the convergence analysis under a non-convex objective provides theoretical support for the proposed method.

Ping Xie, Xiang-Rui Gao, Jingyan Wu et al. · Cluster Computing · 0 citations