Learning causal representations for robust domain adaptation

Files

9916577344401831_AM.pdf (3.52 MB)
  (Published version)

Date

2023

Authors

Yang, S.
Yu, K.
Cao, F.
Liu, L.
Wang, H.
Li, J.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

IEEE Transactions on Knowledge and Data Engineering, 2023; 35(3):2750-2764

Statement of Responsibility

Conference Name

Abstract

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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

Copyright 2021 ITEE Access Condition Notes: Accepted manuscript available on Open Access

License

Grant ID

Call number

Persistent link to this record