mlsanityData to 7 Oct 2026

On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources

arXiv 2111.13822 ↗First posted 27 Nov 2021cs.LG cs.AI stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

Domain adaptation (DA) benefits from the rigorous theoretical works that study its insightful characteristics and various aspects, e.g., learning domain-invariant representations and its trade-off. However, it seems not the case for the multiple source DA and domain generalization (DG) settings which are remarkably more complicated and sophisticated due to the involvement of multiple source domains and potential unavailability of target domain during training. In this paper, we develop novel upper-bounds for the target general loss which appeal to us to define two kinds of domain-invariant representations. We further study the pros and cons as well as the trade-offs of enforcing learning each domain-invariant representation. Finally, we conduct experiments to inspect the trade-off of these representations for offering practical hints regarding how to use them in practice and explore other interesting properties of our developed theory.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 32 of its 60 references that are in the map. First posted on arXiv 27 Nov 2021.

Builds on

32 of 60 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2019Invariant Risk Minimizationcited by 1,832
  5. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  6. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  7. 2020In Search of Lost Domain Generalizationcited by 1,042
  8. 2019When Does Label Smoothing Help?cited by 985
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  10. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  11. 2013Domain Generalization via Invariant Feature Representationcited by 622
  12. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
20 more
  1. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  2. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  3. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  4. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  5. 2019Episodic Training for Domain Generalizationcited by 245
  6. 2020Improve Unsupervised Domain Adaptation with Mixup Trainingcited by 185
  7. 2020Universal Domain Adaptation through Self Supervisioncited by 172
  8. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  9. 2020Learning to Balance Specificity and Invariance for In and Out of Domain Generalizationcited by 128
  10. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  11. 2018Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shiftcited by 109
  12. 2019Generalizing to unseen domains via distribution matchingcited by 109
  13. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  14. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
  15. 2019Multi-source Distilling Domain Adaptationcited by 73
  16. 2018Optimal Transport for Multi-source Domain Adaptation under Target Shiftcited by 67
  17. 2018Algorithms and Theory for Multiple-Source Adaptationcited by 53
  18. 2021Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improvecited by 46
  19. 2019A Generalization Error Bound for Multi-class Domain Generalizationcited by 26
  20. 2020A Theory of Multiple-Source Adaptation with Limited Target Labeled Datacited by 18

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 4; 2025: 4.

15 papers.

Sort:

By area:

  1. 2022Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representationscited by 57
  2. 2023Fairness and Accuracy under Domain Generalizationcited by 24
  3. 2023Energy-Based Test Sample Adaptation for Domain Generalizationcited by 14
  4. 2022Global-Local Regularization Via Distributional Robustnesscited by 11
  5. 2024Physics-Informed Neural Networks for High-Frequency and Multi-Scale Problems using Transfer Learningcited by 9
  6. 2024Enhancing Domain Adaptation through Prompt Gradient Alignmentcited by 8
  7. 2025Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigationcited by 5
  8. 2024Deep Transfer Learning: Model Framework and Error Analysiscited by 4
  9. 2023CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shiftcited by 3
  10. 2023Out-Of-Domain Unlabeled Data Improves Generalizationcited by 3
  11. 2024Non-stationary Domain Generalization: Theory and Algorithmcited by 3
  12. 2025Why Domain Generalization Fail? A View of Necessity and Sufficiencycited by 2
3 more
  1. 2022A Survey of Learning on Small Data: Generalization, Optimization, and Challengecited by 1
  2. 2025Fair Domain Generalization: An Information-Theoretic Viewcited by 1
  3. 2025ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extractioncited by 0