Real-world classification problems must contend with domain shift, the (potential) mismatch between the domain where a model is deployed and the domain(s) where the training data was gathered. Methods to handle such problems must specify what structure is common between the domains and what varies. A natural assumption is that causal (structural) relationships are invariant in all domains. Then, it is tempting to learn a predictor for label $Y$ that depends only on its causal parents. However, many real-world problems are "anti-causal" in the sense that $Y$ is a cause of the covariates $X$ -- in this case, $Y$ has no causal parents and the naive causal invariance is useless. In this paper, we study representation learning under a particular notion of domain shift that both respects causal invariance and that naturally handles the "anti-causal" structure. We show how to leverage the shared causal structure of the domains to learn a representation that both admits an invariant predictor and that also allows fast adaptation in new domains. The key is to translate causal assumptions into learning principles that disentangle "invariant" and "non-stable" features. Experiments on both synthetic and real-world data demonstrate the effectiveness of the proposed learning algorithm. Code is available at https://github.com/ybjiaang/ACTIR.

翻译：真实世界分类问题必须与域变、 模型部署域与培训数据收集域之间的( 潜在)错配问题相争论。 处理此类问题的方法必须说明域间和不同领域之间哪些结构是共同的。 自然的假设是, 因果关系( 结构) 关系在所有领域都是无差异的。 然后, 需要学习一个仅取决于因果父母的“ Y” 标签的预测符。 然而, 许多真实世界问题都是“ 反因果”, 意思是, 美元是造成共变的美元 -- -- 在本案中, $Y没有因果父母, 天真的因果性不一是毫无用处的。 在本文中, 我们研究在特定域变数概念下学习的因果性( 结构) 。 我们展示如何利用域的共同因果性结构来学习一种既承认异性预测, 也允许在新领域快速调整。 关键是要将因果假设转化成“ 变数/ 变数/ 变数” 和“ 变数 变数” 的变法性( ) 和“ 变数法性( ) ( ) 变数) 的变法( ) ( ) ( ) ( ) (变数) (变数) (变数) (变数) (变数) (变数) (变数) (变数) (变数) (变数) (变法) (变法) (变数) (变法) (变法) (变法) (变法) (变法) (变法) ) (变法) (变法) (变数) (变法) (变法) ) (变法) (变法) (变法) (变法) (变法) (变法) (变法) (变法) ) (变法) (变法) (变法) (变法) (变法) ) (变法) (变法) (变法) (变法) (变法) (变法) (变法) (变法) ) (变法) (变法) (变法) (变法) ) (变法) (变法) (变法) (变法) (变法) (变法) (变法) (变法) (