Geodesic
PFLIC: A Novel Personalized Federated Learning-Based Iterative Clustering
Computer Science and Information Systems, Tome 22 (2025) no. 3

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

Federated learning (FL) is a machine learning framework that effectively helps multiple organizations perform data usage and machine learning models while meeting the requirements of user privacy protection, data security, and government regulations. However, in practical applications, existing federated learning mechanisms face many challenges, including system inefficiency due to data heterogeneity and how to achieve fairness to incentivize clients to participate in federated training. Due to this fact, we propose PFLIC, a novel personalized federated learning based on an iterative clustering algorithm, to estimate clusters to mitigate data heterogeneity and improve the efficiency of FL. It is combined with sparse sharing to facilitate knowledge sharing within the system for personalized federated learning. To ensure fairness, a client selection strategy is proposed to choose relatively “good” clients to achieve fairer federated learning without sacrificing system efficiency. Extensive experiments demonstrate the superior performance and effectiveness of the proposed PFLIC compared to the baseline.
Keywords: Federated learning; Clustering algorithm; Client Selection; Sparse sharing 
Shiwen Zhang; Shuang Chen; Wei Liang; Kuanching Li; Arcangelo Castiglione; Junsong Yuan. PFLIC: A Novel Personalized Federated Learning-Based Iterative Clustering. Computer Science and Information Systems, Tome 22 (2025) no. 3. http://geodesic.mathdoc.fr/item/CSIS_2025_22_3_a13/
@article{CSIS_2025_22_3_a13,
     author = {Shiwen Zhang and Shuang Chen and Wei Liang and Kuanching Li and Arcangelo Castiglione and Junsong Yuan},
     title = {PFLIC: {A} {Novel} {Personalized} {Federated} {Learning-Based} {Iterative} {Clustering}},
     journal = {Computer Science and Information Systems},
     year = {2025},
     volume = {22},
     number = {3},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2025_22_3_a13/}
}
TY  - JOUR
AU  - Shiwen Zhang
AU  - Shuang Chen
AU  - Wei Liang
AU  - Kuanching Li
AU  - Arcangelo Castiglione
AU  - Junsong Yuan
TI  - PFLIC: A Novel Personalized Federated Learning-Based Iterative Clustering
JO  - Computer Science and Information Systems
PY  - 2025
VL  - 22
IS  - 3
UR  - http://geodesic.mathdoc.fr/item/CSIS_2025_22_3_a13/
ID  - CSIS_2025_22_3_a13
ER  - 
%0 Journal Article
%A Shiwen Zhang
%A Shuang Chen
%A Wei Liang
%A Kuanching Li
%A Arcangelo Castiglione
%A Junsong Yuan
%T PFLIC: A Novel Personalized Federated Learning-Based Iterative Clustering
%J Computer Science and Information Systems
%D 2025
%V 22
%N 3
%U http://geodesic.mathdoc.fr/item/CSIS_2025_22_3_a13/
%F CSIS_2025_22_3_a13