mlsanityData to 7 Oct 2026

Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data

arXiv 2412.13757 ↗First posted 18 Dec 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this problem, we focus on a source-free domain adaptation task, where (1) the server holds a pre-trained model on labeled source domain data, (2) clients possess only unlabeled data from various target domains, and (3) the server and clients cannot access the source data in the adaptation phase. This task is known as Federated source-Free Domain Adaptation (FFREEDA). Specifically, we focus on classification tasks, while the previous work solely studies semantic segmentation. Our contribution is the novel Federated learning with Weighted Cluster Aggregation (FedWCA) method, designed to mitigate both domain shifts and privacy concerns with only unlabeled data. FedWCA comprises three phases: private and parameter-free clustering of clients to obtain domain-specific global models on the server, weighted aggregation of the global models for the clustered clients, and local domain adaptation with pseudo-labeling. Experimental results show that FedWCA surpasses several existing methods and baselines in FFREEDA, establishing its effectiveness and practicality.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 42 of its 62 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

42 of 62 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  6. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  7. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  8. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  9. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  10. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  11. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
  12. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
30 more
  1. 2024The Unreasonable Ineffectiveness of the Deeper Layerscited by 219
  2. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  3. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  4. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
  5. 2019Federated Adversarial Domain Adaptationcited by 140
  6. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  7. 2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
  8. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  9. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
  10. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  11. 2020Federated Unsupervised Representation Learningcited by 92
  12. 2021VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptationcited by 69
  13. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 63
  14. 2022Confidence Score for Source-Free Unsupervised Domain Adaptationcited by 58
  15. 2022Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learningcited by 53
  16. 2021SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Trainingcited by 45
  17. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  18. 2021Federated Multi-Target Domain Adaptationcited by 44
  19. 2021Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Densitycited by 44
  20. 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 43
  21. 2022BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptationcited by 39
  22. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  23. 2022RSCFed: Random Sampling Consensus Federated Semi-supervised Learningcited by 32
  24. 2022Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matchingcited by 24
  25. 2022Feature Distribution Matching for Federated Domain Generalizationcited by 18
  26. 2020FedFMC: Sequential Efficient Federated Learning on Non-iid Datacited by 17
  27. 2023ProtoFL: Unsupervised Federated Learning via Prototypical Distillationcited by 11
  28. 2021FRuDA: Framework for Distributed Adversarial Domain Adaptationcited by 8
  29. 2022Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclientscited by 6
  30. 2022Personalized Federated Learning with Multi-branch Architecturecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025ViLAaD: Enhancing "Attracting and Dispersing'' Source-Free Domain Adaptation with Vision-and-Language Modelcited by 2
  2. 2025Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Modelscited by 0
  3. 2025FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptationcited by 0
  4. 2026Multi-Scale Temporal Domain Alignment for Federated Video Domain Adaptationcited by 0