mlsanityData to 13 Oct 2026

Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching

arXiv 2203.12285 ↗First posted 23 Mar 2022cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

In federated learning (FL), clients may have diverse objectives, and merging all clients' knowledge into one global model will cause negative transfer to local performance. Thus, clustered FL is proposed to group similar clients into clusters and maintain several global models. In the literature, centralized clustered FL algorithms require the assumption of the number of clusters and hence are not effective enough to explore the latent relationships among clients. In this paper, without assuming the number of clusters, we propose a peer-to-peer (P2P) FL algorithm named PANM. In PANM, clients communicate with peers to adaptively form an effective clustered topology. Specifically, we present two novel metrics for measuring client similarity and a two-stage neighbor matching algorithm based Monte Carlo method and Expectation Maximization under the Gaussian Mixture Model assumption. We have conducted theoretical analyses of PANM on the probability of neighbor estimation and the error gap to the clustered optimum. We have also implemented extensive experiments under both synthetic and real-world clustered heterogeneity. Theoretical analysis and empirical experiments show that the proposed algorithm is superior to the P2P FL counterparts, and it achieves better performance than the centralized cluster FL method. PANM is effective even under extremely low communication budgets.

Key facts. Cited by 24 papers in the map (data through 13 Oct 2026). Builds on 28 of its 47 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

28 of 47 references.

References · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
  3. 2019Advances and Open Problems in Federated Learningcited by 3,040
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,909
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  6. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  7. 2020An Efficient Framework for Clustered Federated Learningcited by 508
  8. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 502
  9. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 500
  10. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  11. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 251
  12. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
16 more
  1. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  2. 2019Federated Adversarial Domain Adaptationcited by 140
  3. 2019Peer-to-peer Federated Learning on Graphscited by 85
  4. 2019Multi-source Distilling Domain Adaptationcited by 73
  5. 2021Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Datacited by 69
  6. 2017Personalized and Private Peer-to-Peer Machine Learningcited by 54
  7. 2021Consensus Control for Decentralized Deep Learningcited by 49
  8. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  9. 2020Decentralized Federated Learning via Mutual Knowledge Transfercited by 43
  10. 2020Throughput-Optimal Topology Design for Cross-Silo Federated Learningcited by 39
  11. 2021Decentralized federated learning of deep neural networks on non-iid datacited by 25
  12. 2020Communication-Efficient Decentralized Learning with Sparsification and Adaptive Peer Selectioncited by 20
  13. 2021Optimal Rate Adaption in Federated Learning with Compressed Communicationscited by 15
  14. 2020Self-organizing Democratized Learning: Towards Large-scale Distributed Learning Systemscited by 14
  15. 2021Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updatescited by 10
  16. 2021Ensemble Federated Adversarial Training with Non-IID datacited by 5

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 13; 2025: 6.

24 papers.

Sort:

By area:

  1. 2023Revisiting Weighted Aggregation in Federated Learning with Neural Networkscited by 58
  2. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  3. 2023A Survey on Decentralized Federated Learningcited by 27
  4. 2024Unleashing the Power of Continual Learning on Non-Centralized Devices: A Surveycited by 23
  5. 2024Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalizationcited by 10
  6. 2025dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysiscited by 8
  7. 2023Edge-cloud Collaborative Learning with Federated and Centralized Featurescited by 5
  8. 2023FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learningcited by 5
  9. 2024Proximity-based Self-Federated Learningcited by 5
  10. 2025ProFed: a Benchmark for Proximity-based non-IID Federated Learningcited by 5
  11. 2024Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Datacited by 4
  12. 2025A survey on Clustered Federated Learning: Taxonomy, Analysis and Applicationscited by 2
12 more
  1. 2024OCD-FL: A Novel Communication-Efficient Peer Selection-based Decentralized Federated Learningcited by 1
  2. 2024PeerFL: A Simulator for Peer-to-Peer Federated Learning at Scalecited by 1
  3. 2024Decentralized Personalized Federated Learningcited by 1
  4. 2024Privacy-Preserved Taxi Demand Prediction System Utilizing Distributed Datacited by 1
  5. 2024On the effects of similarity metrics in decentralized deep learning under distributional shiftcited by 1
  6. 2025Sparse Self-Federated Learning for Energy Efficient Cooperative Intelligence in Society 5.0cited by 1
  7. 2024FedSiKD: Clients Similarity and Knowledge Distillation: Addressing Non-i.i.d. and Constraints in Federated Learningcited by 0
  8. 2024FedGuCci: Making Local Models More Connected in Landscape for Federated Learningcited by 0
  9. 2024P4: Towards private, personalized, and Peer-to-Peer learningcited by 0
  10. 2024Sequence-to-sequence models in peer-to-peer learning: A practical applicationcited by 0
  11. 2025Query-based Knowledge Transfer for Heterogeneous Learning Environmentscited by 0
  12. 2025Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learningcited by 0