Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in the target domain, they suffer from the semantic loss: the feature will inevitably lose non-discriminative semantics in source domain, which is however discriminative in target domain. We use a causal view -- transportability theory -- to identify that such loss is in fact a confounding effect, which can only be removed by causal intervention. However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the stratification and representation of an unobserved confounder that is the cause of the domain gap. To this end, we propose a practical solution: Transporting Causal Mechanisms (TCM), to identify the confounder stratum and representations by using the domain-invariant disentangled causal mechanisms, which are discovered in an unsupervised fashion. Our TCM is both theoretically and empirically grounded. Extensive experiments show that TCM achieves state-of-the-art performance on three challenging UDA benchmarks: ImageCLEF-DA, Office-Home, and VisDA-2017. Codes are available in Appendix.

翻译：现有未经监督的域适应(UDA)文献采用了共同变换和有条件的变换假设,这些假设基本上鼓励模型学习不同领域的共同特征,然而,由于目标领域缺乏监督,它们遭受了语义损失:该特征在源域将不可避免地失去非差异性语义,在目标领域,这无论在目标领域如何具有歧视性。我们使用一种因果观点 -- -- 运输可变性理论 -- -- 来确定这种损失事实上是一种混乱效应,只能通过因果干预予以消除。然而,运输提供的理论解决方案对于UDA来说远不实用,因为它要求一个未观测到的共创造者进行分级和代表,这是域间差距的根源。为此,我们提出了一个切实可行的解决方案:运输Causal机制(TCM),通过使用域内不易分解的因果机制,确定交错的因果关系和表述,而这种机制是非由因果性干预发现的。我们的TCM是理论和经验基础。广泛的实验显示,TCM(TCM)实现V-CLA、CFDA、CFDA3号标准。