A survey on Clustered Federated Learning: Taxonomy, Analysis and Applications
Not on the map. Why?
Abstract (arXiv)
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, real-world applications in IoT, Mobility, and Energy overwhelmingly favor Metadata-based efficiency. 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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 53 of its 150 references that are in the map. First posted on arXiv 29 Jan 2025.
Builds on
53 of 150 references.
References · 53
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2018Federated Learning with Non-IID Datacited by 1,099
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
- 2020Federated Learning with Matched Averagingcited by 564
- 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
- 2020An Efficient Framework for Clustered Federated Learningcited by 505
- 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
- 2021Towards Personalized Federated Learningcited by 462
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
- 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
- 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
38 more
- 2015Inverting Visual Representations with Convolutional Networkscited by 168
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
- 2021Federated Graph Classification over Non-IID Graphscited by 113
- 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
- 2019Robust Federated Learning in a Heterogeneous Environmentcited by 88
- 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
- 2020Privacy-preserving Traffic Flow Prediction: A Federated Learning Approachcited by 82
- 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
- 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
- 2021FedSoft: Soft Clustered Federated Learning with Proximal Local Updatingcited by 46
- 2020FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measurecited by 45
- 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
- 2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
- 2022Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspacescited by 36
- 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
- 2021Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networkscited by 35
- 2022Federated Learning under Distributed Concept Driftcited by 35
- 2020Adaptive Federated Learning and Digital Twin for Industrial Internet of Thingscited by 27
- 2022Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matchingcited by 24
- 2022FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distributioncited by 22
- 2021Federated Learning with Taskonomy for Non-IID Datacited by 21
- 2022Clustered Vehicular Federated Learning: Process and Optimizationcited by 15
- 2023FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clusteringcited by 15
- 2021Federated Learning for Short-term Residential Load Forecastingcited by 13
- 2021Clustered Federated Learning via Generalized Total Variation Minimizationcited by 7
- 2023Clustered Federated Learning Architecture for Network Anomaly Detection in Large Scale Heterogeneous IoT Networkscited by 7
- 2023FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimizationcited by 7
- 2021Genetic CFL: Optimization of Hyper-Parameters in Clustered Federated Learningcited by 6
- 2022Social-Aware Clustered Federated Learning with Customized Privacy Preservationcited by 5
- 2023Contrastive encoder pre-training-based clustered federated learning for heterogeneous datacited by 5
- 2024Federated brain tumor segmentation: an extensive benchmarkcited by 5
- 2022Clustered Federated Learning based on Nonconvex Pairwise Fusioncited by 4
- 2023StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participationcited by 4
- 2024Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigationcited by 4
- 2023Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologiescited by 3
- 2023Federated Learning with Uncertainty-Based Client Clustering for Fleet-Wide Fault Diagnosiscited by 2
- 2024Rethinking Clustered Federated Learning in NOMA Enhanced Wireless Networkscited by 2
- 2024CRSFL: Cluster-based Resource-aware Split Federated Learning for Continuous Authenticationcited by 2
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.