Current studentsExisting staffContact us
 

Learning causal representations for robust domain adaptation

Simple item page
dc.contributor.authorYang, S.
dc.contributor.authorYu, K.
dc.contributor.authorCao, F.
dc.contributor.authorLiu, L.
dc.contributor.authorWang, H.
dc.contributor.authorLi, J.
dc.date.issued2023
dc.description.abstractIn 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.
dc.identifier.citationIEEE Transactions on Knowledge and Data Engineering, 2023; 35(3):2750-2764
dc.identifier.doi10.1109/TKDE.2021.3119185
dc.identifier.issn1041-4347
dc.identifier.issn1558-2191
dc.identifier.urihttps://hdl.handle.net/11541.2/26111
dc.language.isoen
dc.publisherITEE
dc.relation.fundingNational Key Research and Development Program of China 2020AAA0106100
dc.relation.fundingNational Natural Science Foundation of China 61876206
dc.rightsCopyright 2021 ITEE Access Condition Notes: Accepted manuscript available on Open Access
dc.source.urihttps://doi.org/10.1109/TKDE.2021.3119185
dc.subjectdogs
dc.subjectdata models
dc.subjectpredictive models
dc.subjectmarkov processes
dc.subjectadaptation models
dc.subjecttraining
dc.subjectsentiment analysis
dc.titleLearning causal representations for robust domain adaptation
dc.typeJournal article
pubs.publication-statusPublished
ror.fileinfo12235833030001831 13235833020001831 9916577344401831_AM
ror.mmsid9916577344401831

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
9916577344401831_AM.pdf
Size:
3.52 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections