Learning Causal Representations for Robust Domain Adaptation

doi:10.1109/TKDE.2021.3119185

Learning Causal Representations for Robust Domain Adaptation

2021-01-01

18

OA

AI

DOI：10.1109/TKDE.2021.3119185

Original

Original request for help

Save

Abstract

En 中文

In this study, we investigate a challenging problem, namely, robust domain adaptation, where data from only a single well-labeled source domain are available in the training phase. To address this problem, assuming that the causal relationships between the features and the class variable are robust across domains, we propose a novel causal autoencoder (CAE), which integrates a deep autoencoder and a causal structure learning model to learn causal representations using data from a single source domain. Specifically, a deep autoencoder model is adopted to learn the low-dimensional representations, and a causal structure learning model is designed to separate the low-dimensional representations into two groups: causal representations and task-irrelevant representations. Using three real-world datasets, the experiments have validated the effectiveness of CAE, in comparison with eleven state-of-the-art methods.

Keywords:

Dogs

Data models

Predictive models

Markov processes

Adaptation models

Training

Sentiment analysis

Domain adaptation

causal discovery

autoencoder

Learning Causal Representations for Robust Domain Adaptation

Abstract

Journal

Organization