mlsanityData to 14 Oct 2026

Aggregating From Multiple Target-Shifted Sources

arXiv 2105.04051 ↗First posted 9 May 2021cs.LG stat.MLcited by 24

Not on the map. Why?

Abstract (arXiv)

Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In this paper, we analyzed the problem for aggregating source domains with different label distributions, where most recent source selection approaches fail. Our proposed algorithm differs from previous approaches in two key ways: the model aggregates multiple sources mainly through the similarity of semantic conditional distribution rather than marginal distribution; the model proposes a unified framework to select relevant sources for three popular scenarios, i.e., domain adaptation with limited label on target domain, unsupervised domain adaptation and label partial unsupervised domain adaption. We evaluate the proposed method through extensive experiments. The empirical results significantly outperform the baselines.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 41 of its 87 references that are in the map. First posted on arXiv 9 May 2021.

Builds on

41 of 87 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2017Improved Training of Wasserstein GANscited by 2,235
  5. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  7. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  8. 2017A Survey on Multi-Task Learningcited by 840
  9. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
  10. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  11. 2017Wasserstein GANcited by 639
  12. 2019Transfusion: Understanding Transfer Learning for Medical Imagingcited by 368
29 more
  1. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  2. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
  3. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  4. 2018Multi-Adversarial Domain Adaptationcited by 196
  5. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  6. 2018An overview of deep learning in medical imaging focusing on MRIcited by 140
  7. 2018Partial Adversarial Domain Adaptationcited by 127
  8. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 125
  9. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 120
  10. 2020A Unified View of Label Shift Estimationcited by 119
  11. 2019DIVA: Domain Invariant Variational Autoencoderscited by 115
  12. 2018Importance Weighted Adversarial Nets for Partial Domain Adaptationcited by 90
  13. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
  14. 2019Learning to Transfer Examples for Partial Domain Adaptationcited by 87
  15. 2019Multi-source Distilling Domain Adaptationcited by 73
  16. 2018Optimal Transport for Multi-source Domain Adaptation under Target Shiftcited by 68
  17. 2019Domain Adaptation with Asymmetrically-Relaxed Distribution Alignmentcited by 61
  18. 2018Algorithms and Theory for Multiple-Source Adaptationcited by 54
  19. 2020Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Surveycited by 47
  20. 2019Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalizationcited by 43
  21. 2019Domain Aggregation Networks for Multi-Source Domain Adaptationcited by 37
  22. 2019A Principled Approach for Learning Task Similarity in Multitask Learningcited by 32
  23. 2019Robust Learning from Untrusted Sourcescited by 27
  24. 2019Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptationcited by 23
  25. 2020A Theory of Multiple-Source Adaptation with Limited Target Labeled Datacited by 18
  26. 2020Multi-source Domain Adaptation for Visual Sentiment Classificationcited by 16
  27. 2019On Target Shift in Adversarial Domain Adaptationcited by 12
  28. 2019Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptationcited by 11
  29. 2019Tackling Partial Domain Adaptation with Self-Supervisioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 4; 2023: 7; 2024: 4; 2025: 3; 2026: 2.

24 papers.

Sort:

  1. 2023Subspace Identification for Multi-Source Domain Adaptationcited by 37
  2. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  3. 2022Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalizationcited by 22
  4. 2021Variational Disentanglement for Domain Generalizationcited by 18
  5. 2021Mapping conditional distributions for domain adaptation under generalized target shiftcited by 18
  6. 2021Transferable Time-Series Forecasting under Causal Conditional Shiftcited by 18
  7. 2024A Short Survey on Importance Weighting for Machine Learningcited by 15
  8. 2024Generalizing across Temporal Domains with Koopman Operatorscited by 13
  9. 2024More is Better: Deep Domain Adaptation with Multiple Sourcescited by 9
  10. 2022Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptationcited by 7
  11. 2023Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptationcited by 7
  12. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
12 more
  1. 2023H-ensemble: An Information Theoretic Approach to Reliable Few-Shot Multi-Source-Free Transfercited by 6
  2. 2023UFDA: Universal Federated Domain Adaptation with Practical Assumptionscited by 5
  3. 2025A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learningcited by 5
  4. 2022Gap Minimization for Knowledge Sharing and Transfercited by 4
  5. 2023Multi-source domain adaptation for regressioncited by 2
  6. 2025Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergiescited by 2
  7. 2026A General Representation-Based Approach to Multi-Source Domain Adaptationcited by 2
  8. 2022Evolving Domain Generalizationcited by 1
  9. 2025Time Series Domain Adaptation via Latent Invariant Causal Mechanismcited by 1
  10. 2026Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Frameworkcited by 1
  11. 2023Source-free Domain Adaptation Requires Penalized Diversitycited by 0
  12. 2024Theory-inspired Label Shift Adaptation via Aligned Distribution Mixturecited by 0