# Unsupervised Structural-Counterfactual Generation under Domain Shift

arXiv: https://arxiv.org/abs/2502.12013 · HTML: https://mlsanity.com/paper/2502.12013/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 56 references that are in the map.
- First posted on arXiv 17 Feb 2025.

## Builds on (most cited first, 30 of 34)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [Kernel Mean Embedding of Distributions: A Review and Beyond](https://mlsanity.com/paper/1605.09522/) (2016)
- [Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style](https://mlsanity.com/paper/2106.04619/) (2021)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Learning with a Wasserstein Loss](https://mlsanity.com/paper/1506.05439/) (2015)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Neural Optimal Transport](https://mlsanity.com/paper/2201.12220/) (2022)
- [Unbalanced minibatch Optimal Transport; applications to Domain Adaptation](https://mlsanity.com/paper/2103.03606/) (2021)
- [Interpretability at Scale: Identifying Causal Mechanisms in Alpaca](https://mlsanity.com/paper/2305.08809/) (2023)
- [The Causal-Neural Connection: Expressiveness, Learnability, and Inference](https://mlsanity.com/paper/2107.00793/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [MMD Aggregated Two-Sample Test](https://mlsanity.com/paper/2110.15073/) (2021)
- [Causal machine learning for predicting treatment outcomes](https://mlsanity.com/paper/2410.08770/) (2024)
- [Identifiability Results for Multimodal Contrastive Learning](https://mlsanity.com/paper/2303.09166/) (2023)
- [Neural Causal Models for Counterfactual Identification and Estimation](https://mlsanity.com/paper/2210.00035/) (2022)
- [Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals](https://mlsanity.com/paper/2009.08270/) (2020)
- [High Fidelity Image Counterfactuals with Probabilistic Causal Models](https://mlsanity.com/paper/2306.15764/) (2023)
- [Few-shot Domain Adaptation by Causal Mechanism Transfer](https://mlsanity.com/paper/2002.03497/) (2020)
- [A Causal Lens for Controllable Text Generation](https://mlsanity.com/paper/2201.09119/) (2022)
- [Counterfactual Identifiability of Bijective Causal Models](https://mlsanity.com/paper/2302.02228/) (2023)
- [Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach](https://mlsanity.com/paper/2309.07944/) (2023)
- [Neural Causal Abstractions](https://mlsanity.com/paper/2401.02602/) (2024)
- [Counterfactual Image Editing](https://mlsanity.com/paper/2403.09683/) (2024)
- [Estimating Categorical Counterfactuals via Deep Twin Networks](https://mlsanity.com/paper/2109.01904/) (2021)

## Abstract (arXiv)

Motivated by the burgeoning interest in cross-domain learning, we present a novel generative modeling challenge: generating counterfactual samples in a target domain based on factual observations from a source domain. Our approach operates within an unsupervised paradigm devoid of parallel or joint datasets, relying exclusively on distinct observational samples and causal graphs for each domain. This setting presents challenges that surpass those of conventional counterfactual generation. Central to our methodology is the disambiguation of exogenous causes into effect-intrinsic and domain-intrinsic categories. This differentiation facilitates the integration of domain-specific causal graphs into a unified joint causal graph via shared effect-intrinsic exogenous variables. We propose leveraging Neural Causal models within this joint framework to enable accurate counterfactual generation under standard identifiability assumptions. Furthermore, we introduce a novel loss function that effectively segregates effect-intrinsic from domain-intrinsic variables during model training. Given a factual observation, our framework combines the posterior distribution of effect-intrinsic variables from the source domain with the prior distribution of domain-intrinsic variables from the target domain to synthesize the desired counterfactuals, adhering to Pearl's causal hierarchy. Intriguingly, when domain shifts are restricted to alterations in causal mechanisms without accompanying covariate shifts, our training regimen parallels the resolution of a conditional optimal transport problem. Empirical evaluations on a synthetic dataset show that our framework generates counterfactuals in the target domain that very closely resemble the ground truth.