论文标题
考虑域概括中未观察到的混杂
Accounting for Unobserved Confounding in Domain Generalization
论文作者
论文摘要
本文研究了从多个数据集和有关基础数据生成模型的定性假设的组合结合的学习鲁棒，可推广的预测模型的问题。学习强大模型的挑战的一部分在于未观察到的混杂因素的影响，这些混杂因素使目前用于此问题的许多最小错误的不变和原理。我们的方法是在没有观察到的混杂因素的情况下定义因果溶液的不同不变特性，通过放宽这种不变性，可以通过一组数据分布组合的显式分布强大的优化问题将其连接起来。具体而言，我们的目标采用标准损失的形式，以及一个正规化项，鼓励相对于模型参数的差异衍生物的部分平等。我们证明了来自不同方式的医疗保健数据的方法，包括图像，语音和表格数据。
This paper investigates the problem of learning robust, generalizable prediction models from a combination of multiple datasets and qualitative assumptions about the underlying data-generating model. Part of the challenge of learning robust models lies in the influence of unobserved confounders that void many of the invariances and principles of minimum error presently used for this problem. Our approach is to define a different invariance property of causal solutions in the presence of unobserved confounders which, through a relaxation of this invariance, can be connected with an explicit distributionally robust optimization problem over a set of affine combination of data distributions. Concretely, our objective takes the form of a standard loss, plus a regularization term that encourages partial equality of error derivatives with respect to model parameters. We demonstrate the empirical performance of our approach on healthcare data from different modalities, including image, speech and tabular data.
