Back to Search
Start Over
Correlation alignment with attention mechanism for unsupervised domain adaptation
- Source :
- Web Intelligence. 18:261-267
- Publication Year :
- 2021
- Publisher :
- IOS Press, 2021.
-
Abstract
- Domain adaptation aims to solve the problems of lacking labels. Most existing works of domain adaptation mainly focus on aligning the feature distributions between the source and target domain. However, in the field of Natural Language Processing, some of the words in different domains convey different sentiment. Thus not all features of the source domain should be transferred, and it would cause negative transfer when aligning the untransferable features. To address this issue, we propose a Correlation Alignment with Attention mechanism for unsupervised Domain Adaptation (CAADA) model. In the model, an attention mechanism is introduced into the transfer process for domain adaptation, which can capture the positively transferable features in source and target domain. Moreover, the CORrelation ALignment (CORAL) loss is utilized to minimize the domain discrepancy by aligning the second-order statistics of the positively transferable features extracted by the attention mechanism. Extensive experiments on the Amazon review dataset demonstrate the effectiveness of CAADA method.
- Subjects :
- Domain adaptation
Computer Networks and Communications
business.industry
Computer science
Pattern recognition
02 engineering and technology
Correlation
Artificial Intelligence
020204 information systems
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
business
Software
Mechanism (sociology)
Subjects
Details
- ISSN :
- 24056464 and 24056456
- Volume :
- 18
- Database :
- OpenAIRE
- Journal :
- Web Intelligence
- Accession number :
- edsair.doi...........0a43102ee479c3054a9c94d7376e416a