Unsupervised Domain Adaptation Based on Source-Guided Discrepancy


  • Seiichi Kuroki The University of Tokyo
  • Nontawat Charoenphakdee The University of Tokyo
  • Han Bao The University of Tokyo
  • Junya Honda The University of Tokyo
  • Issei Sato The University of Tokyo
  • Masashi Sugiyama The University of Tokyo




Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different and labels in the target domain are unavailable. An important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. Existing discrepancy measures for unsupervised domain adaptation either require high computation costs or have no theoretical guarantee. To mitigate these problems, this paper proposes a novel discrepancy measure called source-guided discrepancy (S-disc), which exploits labels in the source domain unlike the existing ones. As a consequence, S-disc can be computed efficiently with a finitesample convergence guarantee. In addition, it is shown that S-disc can provide a tighter generalization error bound than the one based on an existing discrepancy measure. Finally, experimental results demonstrate the advantages of S-disc over the existing discrepancy measures.




How to Cite

Kuroki, S., Charoenphakdee, N., Bao, H., Honda, J., Sato, I., & Sugiyama, M. (2019). Unsupervised Domain Adaptation Based on Source-Guided Discrepancy. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 4122-4129. https://doi.org/10.1609/aaai.v33i01.33014122



AAAI Technical Track: Machine Learning