Discrepancy-Aware Clustered Federated Learning

Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm, yet heterogeneous data often degrades the performance of shared global models. Clustered FL methods, which group clients with similar data distributions and train separate models, help mitigate this issue. However, existing clustered FL algorithms typically rely on local model-related information, leading to computational and communication overhead, and require pre-specifying the number of clusters, which is impractical in real-world scenarios. To overcome these limitations, this work explores an affinity propagation-based clustered FL framework, DACFL, which is directly aware of data discrepancies and infers cluster structures without prior knowledge. It incorporates a set of metrics to characterize feature distribution shift, label distribution shift, and their cooccurrence, aiming to improve the clustering process. Additionally, to protect label-related information during clustering, DACFL includes a novel scheme using fully homomorphic encryption to ensure secure use of label information. Experiments on public datasets suggest that the proposed approach performs favorably compared with several recent FL methods under heterogeneous settings.

Authors

Institutions

Publication Details

Journal
International Journal of Interactive Multimedia and Artificial Intelligence
Published
2026-11-18
DOI
https://doi.org/10.9781/ijimai.2026.6494
Primary Topic
Privacy-Preserving Technologies in Data
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Discrepancy-Aware Clustered Federated Learning

Peifeng Zhang, Chen Jiahui, Wensheng Gan
3 links
International Journal of Interactive Multimedia and Artificial Intelligence
Privacy-Preserving Technologies in Data
article

Discrepancy-Aware Clustered Federated Learning

Peifeng Zhang, Chen Jiahui, Wensheng Gan
article en

Abstract

Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm, yet heterogeneous data often degrades the performance of shared global models. Clustered FL methods, which group clients with similar data distributions and train separate models, help mitigate this issue. However, existing clustered FL algorithms typically rely on local model-related information, leading to computational and communication overhead, and require pre-specifying the number of clusters, which is impractical in real-world scenarios. To overcome these limitations, this work explores an affinity propagation-based clustered FL framework, DACFL, which is directly aware of data discrepancies and infers cluster structures without prior knowledge. It incorporates a set of metrics to characterize feature distribution shift, label distribution shift, and their cooccurrence, aiming to improve the clustering process. Additionally, to protect label-related information during clustering, DACFL includes a novel scheme using fully homomorphic encryption to ensure secure use of label information. Experiments on public datasets suggest that the proposed approach performs favorably compared with several recent FL methods under heterogeneous settings.

International Journal of Interactive Multimedia and Artificial IntelligenceVol. 10(2)
Guangdong University of Technology (CN), Jinan University (CN), Zhengzhou University of Aeronautics (CN)
Privacy-Preserving Technologies in Data
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon