mlsanityData to 14 Oct 2026

Collaborative Semantic Aggregation and Calibration for Federated Domain Generalization

arXiv 2110.06736 ↗First posted 13 Oct 2021cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Domain generalization (DG) aims to learn from multiple known source domains a model that can generalize well to unknown target domains. The existing DG methods usually exploit the fusion of shared multi-source data to train a generalizable model. However, tremendous data is distributed across lots of places nowadays that can not be shared due to privacy policies. In this paper, we tackle the problem of federated domain generalization where the source datasets can only be accessed and learned locally for privacy protection. We propose a novel framework called Collaborative Semantic Aggregation and Calibration (CSAC) to enable this challenging problem. To fully absorb multi-source semantic information while avoiding unsafe data fusion, we conduct data-free semantic aggregation by fusing the models trained on the separated domains layer-by-layer. To address the semantic dislocation problem caused by domain shift, we further design cross-layer semantic calibration with an attention mechanism to align each semantic level and enhance domain invariance. We unify multi-source semantic learning and alignment in a collaborative way by repeating the semantic aggregation and calibration alternately, keeping each dataset localized, and the data privacy is carefully protected. Extensive experiments show the significant performance of our method in addressing this challenging problem.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 53 of its 129 references that are in the map. First posted on arXiv 13 Oct 2021.

Builds on

53 of 129 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  4. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  5. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  6. 2019When Does Label Smoothing Help?cited by 988
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  8. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  9. 2018Self-Attention Generative Adversarial Networkscited by 809
  10. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 766
  11. 2021Domain Generalization: A Surveycited by 764
  12. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
38 more
  1. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 722
  2. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  3. 2021Domain Generalization with MixStylecited by 566
  4. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  5. 2021Towards Personalized Federated Learningcited by 464
  6. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  7. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 450
  8. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  9. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  10. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 407
  11. 2017Residual Attention Network for Image Classificationcited by 386
  12. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  13. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 341
  14. 2020Learning to Learn Single Domain Generalizationcited by 296
  15. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  16. 2021A Fourier-based Framework for Domain Generalizationcited by 290
  17. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  18. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  19. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  20. 2019Episodic Training for Domain Generalizationcited by 245
  21. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  22. 2020Universal Source-Free Domain Adaptationcited by 220
  23. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  24. 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 161
  25. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  26. 2019Federated Adversarial Domain Adaptationcited by 140
  27. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  28. 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
  29. 2020Learning to Balance Specificity and Invariance for In and Out of Domain Generalizationcited by 128
  30. 2020Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularizationcited by 123
  31. 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
  32. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  33. 2020Federated Unsupervised Representation Learningcited by 93
  34. 2018Interpreting CNNs via Decision Treescited by 89
  35. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 85
  36. 2019Graph Transfer Learning via Adversarial Domain Adaptation with Graph Convolutioncited by 67
  37. 2021Fast-adapting and Privacy-preserving Federated Recommender Systemcited by 30
  38. 2018Domain Adaptation on Graphs by Learning Aligned Graph Basescited by 24

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 4; 2025: 6; 2026: 2.

16 papers.

Sort:

By area:

  1. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  2. 2023Federated Domain Generalization: A Surveycited by 25
  3. 2025Follow-Your-Preference: Towards Preference-Aligned Image Inpaintingcited by 18
  4. 2024Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalizationcited by 12
  5. 2024MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classescited by 7
  6. 2024FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneitycited by 5
  7. 2025UniTrans: A Unified Vertical Federated Knowledge Transfer Framework for Enhancing Cross-Hospital Collaborationcited by 5
  8. 2022Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptationcited by 4
  9. 2023Exploring Flat Minima for Domain Generalization with Large Learning Ratescited by 4
  10. 2025FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysiscited by 2
  11. 2024Federated Cross-Training Learners for Robust Generalization under Data Heterogeneitycited by 1
  12. 2026FedStain: Modeling Higher-Order Stain Statistics for Federated Domain Generalization in Computational Pathologycited by 1
4 more
  1. 2025Multi-Source Collaborative Style Augmentation and Domain-Invariant Learning for Federated Domain Generalizationcited by 0
  2. 2025ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoningcited by 0
  3. 2025Gains: Fine-grained Federated Domain Adaptation in Open Setcited by 0
  4. 2026What Will Happen Next: Large Models-Driven Deduction for Emergency Instancescited by 0