Conference Proceedings

Data-Driven Approach to Multiple-Source Domain Adaptation

Petar Stojanov, Mingming Gong, Jaime Carbonell, Kun Zhang

The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS, CORE Rank A) | PMLR | Published : 2019

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, an..

View full abstract

University of Melbourne Researchers