A Survey on Clustered Federated Learning: Taxonomy, Analysis and Applications
Open Access
- 26 September 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (16) , 1-35
Abstract
As Federated Learning (FL) expands, the challenge of non-independent and identically distributed (non-IID) data becomes critical. Clustered Federated Learning (CFL) addresses this by training multiple specialized models, each representing a group of clients with similar data distributions. However, the term “CFL” has increasingly been applied to operational strategies unrelated to data heterogeneity, creating significant ambiguity. This survey provides a systematic review of the CFL literature and introduces a principled taxonomy that classifies algorithms into Server-side, Client-side, and Metadata-based approaches. Our analysis reveals a distinct dichotomy: while theoretical research prioritizes privacy-preserving Server/Client-side methods, applied papers overwhelmingly favor Metadata-based approaches, prioritizing efficiency over privacy. Furthermore, we explicitly distinguish “Core CFL” (grouping clients for non-IID data) from “Clustered X FL” (operational variants for system heterogeneity). Finally, we outline lessons learned and future directions to bridge the gap between theoretical privacy and practical efficiency.Keywords
This publication has 126 references indexed in Scilit:
- CFL-ICCV: Clustered federated learning framework with an intra-cluster cross-validation mechanism for DER forecastingApplied Energy, 2024
- A clustered federated learning framework for collaborative fault diagnosis of wind turbinesApplied Energy, 2024
- Emerging trends in federated learning: from model fusion to federated X learningInternational Journal of Machine Learning and Cybernetics, 2024
- Model optimization techniques in personalized federated learning: A surveyExpert Systems with Applications, 2023
- Federated deep contrastive learning for mid-term natural gas demand forecastingApplied Energy, 2023
- Clustered federated learning architecture for network anomaly detection in large scale heterogeneous IoT networksComputers & Security, 2023
- Detection of Cache Pollution Attack Based on Federated Learning in Ultra-Dense NetworkComputers & Security, 2022
- Multi-center federated learning: clients clustering for better personalizationWorld Wide Web, 2022
- A Survey on Some Recent Developments of Alternating Direction Method of MultipliersJournal of the Operations Research Society of China, 2022
- A survey on security and privacy of federated learningFuture Generation Computer Systems, 2021