mlsanityData to 14 Oct 2026

Few-shot Domain Adaptation by Causal Mechanism Transfer

arXiv 2002.03497 ↗First posted 10 Feb 2020cs.LG stat.MLcited by 47

Not on the map. Why?

Abstract (arXiv)

We study few-shot supervised domain adaptation (DA) for regression problems, where only a few labeled target domain data and many labeled source domain data are available. Many of the current DA methods base their transfer assumptions on either parametrized distribution shift or apparent distribution similarities, e.g., identical conditionals or small distributional discrepancies. However, these assumptions may preclude the possibility of adaptation from intricately shifted and apparently very different distributions. To overcome this problem, we propose mechanism transfer, a meta-distributional scenario in which a data generating mechanism is invariant among domains. This transfer assumption can accommodate nonparametric shifts resulting in apparently different distributions while providing a solid statistical basis for DA. We take the structural equations in causal modeling as an example and propose a novel DA method, which is shown to be useful both theoretically and experimentally. Our method can be seen as the first attempt to fully leverage the structural causal models for DA.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 8; 2023: 11; 2024: 4; 2025: 4; 2026: 3.

47 papers.

Sort:

  1. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  2. 2021Zero-Shot Recommender Systemscited by 46
  3. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 39
  4. 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
  5. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37
  6. 2023Subspace Identification for Multi-Source Domain Adaptationcited by 37
  7. 2022Universal approximation property of invertible neural networkscited by 30
  8. 2022Certified Robustness Against Natural Language Attacks by Causal Interventioncited by 24
  9. 2021Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Datacited by 18
  10. 2021Discrepancy-Based Active Learning for Domain Adaptationcited by 17
  11. 2021TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptationcited by 17
  12. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
35 more
  1. 2023Generative Causal Representation Learning for Out-of-Distribution Motion Forecastingcited by 13
  2. 2022Adapting to Latent Subgroup Shifts via Concepts and Proxiescited by 12
  3. 2021Rethinking Importance Weighting for Transfer Learningcited by 11
  4. 2021Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentationcited by 10
  5. 2021On the Statistical Benefits of Curriculum Learningcited by 10
  6. 2022Active Source Free Domain Adaptationcited by 10
  7. 2022Few-Shot Learning by Dimensionality Reduction in Gradient Spacecited by 8
  8. 2022Causal Inference via Style Transfer for Out-of-distribution Generalisationcited by 8
  9. 2023Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptationcited by 7
  10. 2023Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Datacited by 7
  11. 2021Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encodingcited by 5
  12. 2021TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentationcited by 5
  13. 2025Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigationcited by 5
  14. 2021Representation learning for maximization of MI, nonlinear ICA and nonlinear subspaces with robust density ratio estimationcited by 4
  15. 2021Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledgecited by 4
  16. 2021Dynamic Feature Alignment for Semi-supervised Domain Adaptationcited by 4
  17. 2022PatchMix Augmentation to Identify Causal Features in Few-shot Learningcited by 4
  18. 2023Out-of-Variable Generalization for Discriminative Modelscited by 4
  19. 2023Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptationcited by 4
  20. 2024COD: Learning Conditional Invariant Representation for Domain Adaptation Regressioncited by 4
  21. 2025Bridging Data Gaps of Rare Conditions in ICU: A Multi-Disease Adaptation Approach for Clinical Predictioncited by 4
  22. 2023A Survey of Deep Visual Cross-Domain Few-Shot Learningcited by 3
  23. 2023Dynamic landslide susceptibility mapping over recent three decades to uncover variations in landslide causes in subtropical urban mountainous areascited by 2
  24. 2024Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systemscited by 2
  25. 2024Get Your Embedding Space in Order: Domain-Adaptive Regression for Forest Monitoringcited by 2
  26. 2026A General Representation-Based Approach to Multi-Source Domain Adaptationcited by 2
  27. 2023Few-Shot Domain Adaptation for Charge Prediction on Unprofessional Descriptionscited by 1
  28. 2023Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuningcited by 1
  29. 2025A Weakly Supervised Transformer for Rare Disease Diagnosis and Subphenotyping from EHRs with Pulmonary Case Studiescited by 1
  30. 2021Adaptive Multi-Source Causal Inferencecited by 0
  31. 2021MetaXT: Meta Cross-Task Transfer between Disparate Label Spacescited by 0
  32. 2024Identifiability of a statistical model with two latent vectors: Importance of the dimensionality relation and application to graph embeddingcited by 0
  33. 2025Unsupervised Structural-Counterfactual Generation under Domain Shiftcited by 0
  34. 2026An Expectation-Maximization Algorithm for Domain Adaptation in Gaussian Causal Modelscited by 0
  35. 2026Causal Transfer in Medical Image Analysiscited by 0