@article{ART003317097},
author={VO VAN PHAP and CHANG, HYOKYUNG},
title={A Study of Personalized Federated Learning Based on Sparse Representations},
journal={ Journal of Software Forensics},
issn={3092-541X},
year={2026},
volume={22},
number={1},
pages={67-75}
TY - JOUR
AU - VO VAN PHAP
AU - CHANG, HYOKYUNG
TI - A Study of Personalized Federated Learning Based on Sparse Representations
JO - Journal of Software Forensics
PY - 2026
VL - 22
IS - 1
PB - Korea Software Assessment and Valuation Society
SP - 67
EP - 75
SN - 3092-541X
AB - Federated Learning (FL) enables collaborative training in distributed environments, but suffers from performance degradation and inter-client disparity under Non-IID data. This paper proposes a personalized federated learning method that combines a sparse representation–based global model with a lightweight personalization layer. The proposed approach maintains computational efficiency and training stability via a k-sparse constraint, while enabling local adaptation without additional communication overhead.
Experiments on CIFAR-10 and CIFAR-100 under various Non-IID settings (α = 0.1, 0.3, 0.5, 1.0) and client scales (10, 20, 50) show that the proposed method preserves global accuracy while reducing inter-client variance. In particular, it significantly improves the performance of low-performing clients in highly heterogeneous environments, demonstrating robust and scalable performance across diverse settings.
KW - Federated learning;Personalized federated learning;Sparse representation;Non-IID data;Performance stability;k-sparse Constraint
DO -
UR -
ER -
VO VAN PHAP and CHANG, HYOKYUNG. (2026). A Study of Personalized Federated Learning Based on Sparse Representations. Journal of Software Forensics, 22(1), 67-75.
VO VAN PHAP and CHANG, HYOKYUNG. 2026, "A Study of Personalized Federated Learning Based on Sparse Representations", Journal of Software Forensics, vol.22, no.1 pp.67-75.
VO VAN PHAP, CHANG, HYOKYUNG "A Study of Personalized Federated Learning Based on Sparse Representations" Journal of Software Forensics 22.1 pp.67-75 (2026) : 67.
VO VAN PHAP, CHANG, HYOKYUNG. A Study of Personalized Federated Learning Based on Sparse Representations. 2026; 22(1), 67-75.
VO VAN PHAP and CHANG, HYOKYUNG. "A Study of Personalized Federated Learning Based on Sparse Representations" Journal of Software Forensics 22, no.1 (2026) : 67-75.
VO VAN PHAP; CHANG, HYOKYUNG. A Study of Personalized Federated Learning Based on Sparse Representations. Journal of Software Forensics, 22(1), 67-75.
VO VAN PHAP; CHANG, HYOKYUNG. A Study of Personalized Federated Learning Based on Sparse Representations. Journal of Software Forensics. 2026; 22(1) 67-75.
VO VAN PHAP, CHANG, HYOKYUNG. A Study of Personalized Federated Learning Based on Sparse Representations. 2026; 22(1), 67-75.
VO VAN PHAP and CHANG, HYOKYUNG. "A Study of Personalized Federated Learning Based on Sparse Representations" Journal of Software Forensics 22, no.1 (2026) : 67-75.
