Unknown

Dataset Information

0

Data-Driven Approach to Multiple-Source Domain Adaptation.


ABSTRACT: A key problem in domain adaptation is determining what to transfer across different domains. We propose a data-driven method to represent these changes across multiple source domains and perform unsupervised domain adaptation. We assume that the joint distributions follow a specific generating process and have a small number of identifiable changing parameters, and develop a data-driven method to identify the changing parameters by learning low-dimensional representations of the changing class-conditional distributions across multiple source domains. The learned low-dimensional representations enable us to reconstruct the target-domain joint distribution from unlabeled target-domain data, and further enable predicting the labels in the target domain. We demonstrate the efficacy of this method by conducting experiments on synthetic and real datasets.

SUBMITTER: Stojanov P 

PROVIDER: S-EPMC6730632 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

altmetric image

Publications

Data-Driven Approach to Multiple-Source Domain Adaptation.

Stojanov Petar P   Gong Mingming M   Carbonell Jaime G JG   Zhang Kun K  

Proceedings of machine learning research 20190401


A key problem in domain adaptation is determining what to transfer across different domains. We propose a data-driven method to represent these changes across multiple source domains and perform unsupervised domain adaptation. We assume that the joint distributions follow a specific generating process and have a small number of identifiable changing parameters, and develop a data-driven method to identify the changing parameters by learning low-dimensional representations of the changing class-c  ...[more]

Similar Datasets

| S-EPMC8270218 | biostudies-literature
| S-EPMC6612867 | biostudies-literature
| S-EPMC9665854 | biostudies-literature
| S-EPMC9358785 | biostudies-literature
| S-EPMC2706936 | biostudies-literature
| S-EPMC10805953 | biostudies-literature
| S-EPMC7075308 | biostudies-literature
| S-EPMC9908850 | biostudies-literature
| S-EPMC8096844 | biostudies-literature
| S-EPMC10020569 | biostudies-literature