Domain generalization (DG) aims to learn from multiple source domains a model that can generalize well on unseen target domains. Existing DG methods mainly learn the representations with invariant marginal distribution of the input features, however, the invariance of the conditional distribution of the labels given the input features is more essential for unknown domain prediction. Meanwhile, the existing of unobserved confounders which affect the input features and labels simultaneously cause spurious correlation and hinder the learning of the invariant relationship contained in the conditional distribution. Interestingly, with a causal view on the data generating process, we find that the input features of one domain are valid instrumental variables for other domains. Inspired by this finding, we propose an instrumental variable-driven DG method (IV-DG) by removing the bias of the unobserved confounders with two-stage learning. In the first stage, it learns the conditional distribution of the input features of one domain given input features of another domain. In the second stage, it estimates the relationship by predicting labels with the learned conditional distribution. Theoretical analyses and simulation experiments show that it accurately captures the invariant relationship. Extensive experiments on real-world datasets demonstrate that IV-DG method yields state-of-the-art results.

翻译：领域泛化（Domain Generalization, DG）旨在从多个源域中学习一个能够在未见目标域上良好泛化的模型。现有DG方法主要学习输入特征不变边际分布的表示，然而，在未知域预测中，标签条件分布的不变性更为关键。同时，未观测混杂因素（同时影响输入特征和标签）的存在会导致虚假相关，并阻碍条件分布中包含的不变关系的学习。有趣的是，从数据生成过程的因果视角出发，我们发现一个域的输入特征是另一个域的有效工具变量。受此启发，我们提出一种基于工具变量的领域泛化方法（IV-DG），通过两阶段学习消除未观测混杂因素的偏差。第一阶段，学习一个域的输入特征在另一个域输入特征下的条件分布；第二阶段，利用该条件分布预测标签以估计关系。理论分析和模拟实验表明，该方法能准确捕获不变关系。在真实数据集上的大量实验证明，IV-DG方法取得了最先进的结果。