Unsupervised Domain Adaptation Based on Source-guided Discrepancy
Unsupervised Domain Adaptation Based on Source-guided Discrepancy
复制标题
DOI：
10.1609/aaai.v33i01.33014122
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Seiichi Kuroki;Nontawat Charoenphakdee;Han Bao;J. Honda;Issei Sato;Masashi Sugiyama
中科院分区：
文献类型：
--
作者：
Seiichi Kuroki;Nontawat Charoenphakdee;Han Bao;J. Honda;Issei Sato;Masashi Sugiyama
无监督域自适应是一种问题设置，其中源域和目标域中的数据生成分布不同，并且目标域中的标签不可用。无监督域自适应中的一个重要问题是如何度量源域和目标域之间的差异。现有的差异措施无监督域适应要么需要很高的计算成本或没有理论保证。为了缓解这些问题，本文提出了一种新的差异测量称为源引导的差异（S-disc），它利用标签在源域不同于现有的。因此，S盘可以有效地计算有限样本收敛保证。此外，它表明，S-光盘可以提供一个更严格的泛化误差界比一个基于现有的差异措施。最后，实验结果表明，S-光盘的优势，现有的差异措施。
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.