# Causal Generative Domain Adaptation Networks

arXiv: https://arxiv.org/abs/1804.04333 · HTML: https://mlsanity.com/paper/1804.04333/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2018.

## Built on by (most cited first, 9 of 9)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization under Conditional and Label Shifts via Variational Bayesian Inference](https://mlsanity.com/paper/2107.10931/) (2021)
- [Adapting to Latent Subgroup Shifts via Concepts and Proxies](https://mlsanity.com/paper/2212.11254/) (2022)
- [Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization](https://mlsanity.com/paper/2507.02288/) (2025)
- [Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation](https://mlsanity.com/paper/2204.02111/) (2022)
- [CaMU: Disentangling Causal Effects in Deep Model Unlearning](https://mlsanity.com/paper/2401.17504/) (2024)
- [Preserving Semantic Consistency in Unsupervised Domain Adaptation Using Generative Adversarial Networks](https://mlsanity.com/paper/2104.13725/) (2021)
- [A Survey on Computational Intelligence-based Transfer Learning](https://mlsanity.com/paper/2206.10593/) (2022)
- [Causal Discovery by Kernel Deviance Measures with Heterogeneous Transforms](https://mlsanity.com/paper/2401.18017/) (2024)

## Abstract (arXiv)

An essential problem in domain adaptation is to understand and make use of distribution changes across domains. For this purpose, we first propose a flexible Generative Domain Adaptation Network (G-DAN) with specific latent variables to capture changes in the generating process of features across domains. By explicitly modeling the changes, one can even generate data in new domains using the generating process with new values for the latent variables in G-DAN. In practice, the process to generate all features together may involve high-dimensional latent variables, requiring dealing with distributions in high dimensions and making it difficult to learn domain changes from few source domains. Interestingly, by further making use of the causal representation of joint distributions, we then decompose the joint distribution into separate modules, each of which involves different low-dimensional latent variables and can be learned separately, leading to a Causal G-DAN (CG-DAN). This improves both statistical and computational efficiency of the learning procedure. Finally, by matching the feature distribution in the target domain, we can recover the target-domain joint distribution and derive the learning machine for the target domain. We demonstrate the efficacy of both G-DAN and CG-DAN in domain generation and cross-domain prediction on both synthetic and real data experiments.