Causal Generative Domain Adaptation Networks

By Mingming Gong, Kun Zhang, Biwei Huang, Clark Glymour, Dacheng Tao, Kayhan Batmanghelich. 2018

22 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cancer Research, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bernhard Schölkopf
2. Kun Zhang
3. Clark Glymour
4. Jan Peters
5. Biwei Huang
6. Jiji Zhang
7. Dominik Janzing
8. J. Ramsey

In Cancer Research

1. Cuiling Lan
2. Kun Zhang
3. Jindong Wang
4. Bernhard Schölkopf

In Computer Vision and Pattern Recognition

1. Kun Zhang
2. Feng Liu
3. Tao Qin
4. Bernhard Schölkopf
5. Jindong Wang
6. Cuiling Lan
7. Zhen Fang
8. Jie Lu

Citations in the corpus

• Causal Discovery from Heterogeneous/Nonstationary Data (2019, background): “due to the changes in the data-generating processes of only a few variables, and thus, it is only necessary to adapt a small proportion of variables in domain adaptation problems (Zhang et al., 2013; Gong et al., 2018). There are several open questions that we aim to answer in the future work. First”
• Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, background): “There are a number of works [202], [203], [204], [205] that exploited causality for domain adaptation.”
• Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation (2020, background): “, 2019a] and unsupervised DA (UDA) [Gong et al., 2018; Liu et al., 2020; Saito et al., 2017; Fang et al., 2019].”