We study the label shift problem between the source and target domains in general domain adaptation (DA) settings. We consider transformations transporting the target to source domains, which enable us to align the source and target examples. Through those transformations, we define the label shift between two domains via optimal transport and develop theory to investigate the properties of DA under various DA settings (e.g., closed-set, partial-set, open-set, and universal settings). Inspired from the developed theory, we propose Label and Data Shift Reduction via Optimal Transport (LDROT) which can mitigate the data and label shifts simultaneously. Finally, we conduct comprehensive experiments to verify our theoretical findings and compare LDROT with state-of-the-art baselines.

翻译：在一般域适应(DA)设置中,我们研究了源和目标域之间的标签转换问题。我们考虑了将目标传送到源域的转换,这使我们能够对源和目标示例进行对齐。通过这些转换,我们定义了两个域之间的标签转换,通过优化运输,我们定义了两个域之间的标签转换,并发展了理论,以调查在各种DA设置(例如封闭设置、部分设置、开放设置和通用设置)下DA的属性。在开发理论的启发下,我们提议通过优化运输(LDROT)减少Label和数据转换,这可以同时减少数据和标签的转换。最后,我们进行了全面实验,以核实我们的理论结论,并将LDROT与最先进的基线进行比较。