English

Learning from a Complementary-label Source Domain: Theory and Algorithms

Machine Learning 2021-03-05 v1 Machine Learning

Abstract

In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain. However, collecting fully-true-label data in the source domain is high-cost and sometimes impossible. Compared to the true labels, a complementary label specifies a class that a pattern does not belong to, hence collecting complementary labels would be less laborious than collecting true labels. Thus, in this paper, we propose a novel setting that the source domain is composed of complementary-label data, and a theoretical bound for it is first proved. We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA). To this end, a complementary label adversarial network} (CLARINET) is proposed to solve CC-UDA and PC-UDA problems. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines on handwritten-digits-recognition and objects-recognition tasks.

Keywords

Cite

@article{arxiv.2008.01454,
  title  = {Learning from a Complementary-label Source Domain: Theory and Algorithms},
  author = {Yiyang Zhang and Feng Liu and Zhen Fang and Bo Yuan and Guangquan Zhang and Jie Lu},
  journal= {arXiv preprint arXiv:2008.01454},
  year   = {2021}
}

Comments

arXiv admin note: text overlap with arXiv:2007.14612

R2 v1 2026-06-23T17:37:43.581Z