English

Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation

Machine Learning 2019-10-23 v3 Machine Learning

Abstract

Appropriately evaluating the discrepancy between domains is essential for the success of unsupervised domain adaptation. In this paper, we first point out that existing discrepancy measures are less informative when complex models such as deep neural networks are used, in addition to the facts that they can be computationally highly demanding and their range of applications is limited only to binary classification. We then propose a novel domain discrepancy measure, called the paired hypotheses discrepancy (PHD), to overcome these shortcomings. PHD is computationally efficient and applicable to multi-class classification. Through generalization error bound analysis, we theoretically show that PHD is effective even for complex models. Finally, we demonstrate the practical usefulness of PHD through experiments.

Keywords

Cite

@article{arxiv.1901.10654,
  title  = {Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation},
  author = {Jongyeong Lee and Nontawat Charoenphakdee and Seiichi Kuroki and Masashi Sugiyama},
  journal= {arXiv preprint arXiv:1901.10654},
  year   = {2019}
}

Comments

21 pages

R2 v1 2026-06-23T07:26:34.876Z