mlsanityData to 14 Oct 2026

Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients

arXiv 2405.16304 ↗First posted 25 May 2024cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised federated learning and show that aligning the gradients at both client and server levels can facilitate the generalization of the model to new (target) domains. Building on this insight, we propose a novel method named FedGaLA, which performs gradient alignment at the client level to encourage clients to learn domain-invariant features, as well as global gradient alignment at the server to obtain a more generalized aggregated model. To empirically evaluate our method, we perform various experiments on four commonly used multi-domain datasets, PACS, OfficeHome, DomainNet, and TerraInc. The results demonstrate the effectiveness of our method which outperforms comparable baselines. Ablation and sensitivity studies demonstrate the impact of different components and parameters in our approach. The source code is available at: https://github.com/MahdiyarMM/FedGaLA.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 42 of its 58 references that are in the map. First posted on arXiv 25 May 2024.

Builds on

42 of 58 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  10. 2020In Search of Lost Domain Generalizationcited by 1,054
  11. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  12. 2021Model-Contrastive Federated Learningcited by 766
30 more
  1. 2018Recognition in Terra Incognitacited by 658
  2. 2020Federated Learning with Matched Averagingcited by 564
  3. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  4. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  5. 2021Gradient Matching for Domain Generalizationcited by 258
  6. 2019Revisiting Self-Supervised Visual Representation Learningcited by 251
  7. 2016Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Predictioncited by 217
  8. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
  9. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  10. 2021Learning to Diversify for Single Domain Generalizationcited by 170
  11. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
  12. 2020Federated Unsupervised Representation Learningcited by 93
  13. 2020Normalization Techniques in Training DNNs: Methodology, Analysis and Applicationcited by 90
  14. 2020AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversariescited by 90
  15. 2021On Large-Cohort Training for Federated Learningcited by 74
  16. 2022Divergence-aware Federated Self-Supervised Learningcited by 73
  17. 2021Collaborative Unsupervised Visual Representation Learning from Decentralized Datacited by 69
  18. 2021Domain Generalization via Gradient Surgerycited by 60
  19. 2021Federated Learning with Domain Generalizationcited by 41
  20. 2021Towards Unsupervised Domain Generalizationcited by 40
  21. 2022FedX: Unsupervised Federated Learning with Cross Knowledge Distillationcited by 40
  22. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  23. 2020Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospectivecited by 27
  24. 2023Federated Domain Generalization: A Surveycited by 25
  25. 2023StableFDG: Style and Attention Based Learning for Federated Domain Generalizationcited by 21
  26. 2022PACS: A Dataset for Physical Audiovisual CommonSense Reasoningcited by 18
  27. 2022Feature Distribution Matching for Federated Domain Generalizationcited by 18
  28. 2023Benchmarking Algorithms for Federated Domain Generalizationcited by 14
  29. 2020Learning to Cluster under Domain Shiftcited by 8
  30. 2022Normalization effects on deep neural networkscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 1.

7 papers.

  1. 2024Federated Domain Generalization with Label Smoothing and Balanced Decentralized Trainingcited by 2
  2. 2025FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentationcited by 2
  3. 2025One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labelingcited by 0
  4. 2025Cooperative Pseudo Labeling for Unsupervised Federated Classificationcited by 0
  5. 2025FedHUG: Federated Heterogeneous Unsupervised Generalization for Remote Physiological Measurementscited by 0
  6. 2025Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformerscited by 0
  7. 2026FedSAP: Federated Learning with Structured Adaptive Partitioning for Multi-Domain Heterogeneous Edge Devicescited by 0