# Few-shot Domain Adaptation by Causal Mechanism Transfer

arXiv: https://arxiv.org/abs/2002.03497 · HTML: https://mlsanity.com/paper/2002.03497/

## Key facts

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

## Built on by (most cited first, 30 of 47)

- [Active Learning for Domain Adaptation: An Energy-Based Approach](https://mlsanity.com/paper/2112.01406/) (2021)
- [Zero-Shot Recommender Systems](https://mlsanity.com/paper/2105.08318/) (2021)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing](https://mlsanity.com/paper/2203.12175/) (2022)
- [CausalAdv: Adversarial Robustness through the Lens of Causality](https://mlsanity.com/paper/2106.06196/) (2021)
- [Subspace Identification for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2310.04723/) (2023)
- [Universal approximation property of invertible neural networks](https://mlsanity.com/paper/2204.07415/) (2022)
- [Certified Robustness Against Natural Language Attacks by Causal Intervention](https://mlsanity.com/paper/2205.12331/) (2022)
- [Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data](https://mlsanity.com/paper/2109.06486/) (2021)
- [Discrepancy-Based Active Learning for Domain Adaptation](https://mlsanity.com/paper/2103.03757/) (2021)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey](https://mlsanity.com/paper/2303.08557/) (2023)
- [Generative Causal Representation Learning for Out-of-Distribution Motion Forecasting](https://mlsanity.com/paper/2302.08635/) (2023)
- [Adapting to Latent Subgroup Shifts via Concepts and Proxies](https://mlsanity.com/paper/2212.11254/) (2022)
- [Rethinking Importance Weighting for Transfer Learning](https://mlsanity.com/paper/2112.10157/) (2021)
- [Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation](https://mlsanity.com/paper/2103.00136/) (2021)
- [On the Statistical Benefits of Curriculum Learning](https://mlsanity.com/paper/2111.07126/) (2021)
- [Active Source Free Domain Adaptation](https://mlsanity.com/paper/2205.10711/) (2022)
- [Few-Shot Learning by Dimensionality Reduction in Gradient Space](https://mlsanity.com/paper/2206.03483/) (2022)
- [Causal Inference via Style Transfer for Out-of-distribution Generalisation](https://mlsanity.com/paper/2212.03063/) (2022)
- [Augmenting and Aligning Snippets for Few-Shot Video Domain Adaptation](https://mlsanity.com/paper/2303.10451/) (2023)
- [Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data](https://mlsanity.com/paper/2312.06091/) (2023)
- [Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding](https://mlsanity.com/paper/2108.02953/) (2021)
- [TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2109.04813/) (2021)
- [Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation](https://mlsanity.com/paper/2510.08962/) (2025)
- [Representation learning for maximization of MI, nonlinear ICA and nonlinear subspaces with robust density ratio estimation](https://mlsanity.com/paper/2101.02083/) (2021)
- [Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledge](https://mlsanity.com/paper/2102.06271/) (2021)
- [Dynamic Feature Alignment for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2110.09641/) (2021)
- [PatchMix Augmentation to Identify Causal Features in Few-shot Learning](https://mlsanity.com/paper/2211.16019/) (2022)
- [Out-of-Variable Generalization for Discriminative Models](https://mlsanity.com/paper/2304.07896/) (2023)

## 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.