TMDA: Task-Specific Multi-source Domain Adaptation via Clustering Embedded Adversarial Training.
Haotian WangWenjing YangZhipeng LinYue YuPublished in: ICDM (2019)
Keyphrases
- domain adaptation
- multi source
- multiple sources
- soft clustering
- covariate shift
- clustering algorithm
- data sources
- data fusion
- target domain
- cross domain
- test data
- data integration
- information fusion
- learning algorithm
- labeled data
- training set
- semi supervised learning
- training samples
- co training
- k means
- transfer learning
- unsupervised learning
- query processing
- document classification
- data model
- data analysis
- sentiment classification
- training data
- similarity measure
- database systems
- database