Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 19 min ago
Peer-reviewedCC BY 4.0Mathematics

PA-CFL: Privacy-Preserving Adaptive Clustered Federated Learning Under Heterogeneous Data

  • Taihao Zhang1
  • Wenting Shen1
  • Hanlin Zhang1
  • Chenbin Zhao2
  1. 1College of Computer Science and Technology, Qingdao University, Qingdao 266071, China
  2. 2School of Mathematics and Big Data, Anhui University of Science and Technology, Huainan 232001, China
Open at sourceDOICite

Abstract

Clustered federated learning (CFL) addresses data heterogeneity by grouping clients with similar data distributions and training personalized models for each cluster. However, existing CFL schemes depend on clustering-related parameters that require prior knowledge of client data distributions. Such information is often unavailable in federated learning due to privacy constraints and the lack of efficient global coordination. This limitation becomes more severe under highly heterogeneous data distributions. In addition, privacy protection remains a major challenge since existing techniques often introduce substantial computational and communication overhead or significantly degrade model utility. To address these challenges, we propose PA-CFL, a novel privacy-preserving adaptive CFL framework under heterogeneous data. We introduce a novel structure-aware similarity metric to partition users based on their data distributions and decompose the clustering process into pre-clustering and fine clustering phases, thereby eliminating the need for manually specified clustering-related parameters. Furthermore, we propose a lightweight structure-aware privacy-preserving mechanism that decomposes each gradient into important and less important subvectors and applies differentiated protection to them. The less important subvector is protected through local randomization and intra-cluster shuffling with a formal differential privacy guarantee, whereas the important subvector is protected through permutation-based coordinate obfuscation under the non-collusion assumption. Extensive experimental results demonstrate that PA-CFL outperforms state-of-the-art methods in terms of model accuracy and efficiency while maintaining a favorable privacy–utility trade-off.

Related

  1. The Dynamics of Collapse and Recovery in Clustered Federated Learning
    Priyanka Sinha, Snigdhansu Chatterjee
    arXivPreprintarXiv licenceFull textDynamical systemsarXiv
  2. Large Stepsizes Federated Learning on Logistic Regression with Linearly Separable Data: The Case of Heterogeneous Devices
    Hok Fong Wong, Hoi-To Wai, Chung-Yiu Yau
    arXivPreprintCC BY-NC-ND 4.0Full textOptimisation & controlarXiv
  3. Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks
    Ming Xiang, Nicolò Michelusi, Yonina C. Eldar +1
    arXivPreprintCC BY 4.0Full textOptimisation & controlarXiv
  4. Privacy-Preserving Over-the-Air Federated Learning over Cell-Free Massive MIMO System with User-Centric Clustering
    Manobendu Sarker, Soumaya Cherkaoui
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  5. Mathematical Analysis of Backdoor-Induced Melanoma Risk in Modality-Heterogeneous Federated Learning
    Ziyu Wang, Xinyu Li, Hongmei Chen +2
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref

Cite

BibTeXRIS
BibTeX
@article{zhang2026pacfl,
  title = {{PA-CFL: Privacy-Preserving Adaptive Clustered Federated Learning Under Heterogeneous Data}},
  author = {Taihao Zhang and Wenting Shen and Hanlin Zhang and Chenbin Zhao},
  journal = {Mathematics},
  year = {2026},
  month = oct,
  doi = {10.3390/math14203673},
  url = {https://www.mdpi.com/2227-7390/14/20/3673},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - PA-CFL: Privacy-Preserving Adaptive Clustered Federated Learning Under Heterogeneous Data
AU  - Taihao Zhang
AU  - Wenting Shen
AU  - Hanlin Zhang
AU  - Chenbin Zhao
PY  - 2026
DA  - 2026/10/10
JO  - Mathematics
DO  - 10.3390/math14203673
UR  - https://www.mdpi.com/2227-7390/14/20/3673
AB  - Clustered federated learning (CFL) addresses data heterogeneity by grouping clients with similar data distributions and training personalized models for each cluster. However, existing CFL schemes depend on clustering-related parameters that require prior knowledge of client data distributions. Such information is often unavailable in federated learning due to privacy constraints and the lack of efficient global coordination. This limitation becomes more severe under highly heterogeneous data distributions. In addition, privacy protection remains a major challenge since existing techniques often introduce substantial computational and communication overhead or significantly degrade model utility. To address these challenges, we propose PA-CFL, a novel privacy-preserving adaptive CFL framework under heterogeneous data. We introduce a novel structure-aware similarity metric to partition users based on their data distributions and decompose the clustering process into pre-clustering and fine clustering phases, thereby eliminating the need for manually specified clustering-related parameters. Furthermore, we propose a lightweight structure-aware privacy-preserving mechanism that decomposes each gradient into important and less important subvectors and applies differentiated protection to them. The less important subvector is protected through local randomization and intra-cluster shuffling with a formal differential privacy guarantee, whereas the important subvector is protected through permutation-based coordinate obfuscation under the non-collusion assumption. Extensive experimental results demonstrate that PA-CFL outperforms state-of-the-art methods in terms of model accuracy and efficiency while maintaining a favorable privacy–utility trade-off.
SN  - 2227-7390
ER  -