选择用于模拟干预的数据增强
Selecting Data Augmentation for Simulating Interventions
摘要：
用纯观察数据和经验风险最小化原则\citep{vapnik_principles_1992}训练的机器学习模型可能无法推广到看不见的领域。在本文中，我们专注于问题出现的情况下，通过虚假的相关性观察到的领域和实际的任务标签。我们发现，许多域泛化方法没有明确考虑到这种虚假的相关性。相反，特别是在更面向应用的研究领域，如医学成像或机器人技术，数据增强技术是基于几何学用于学习域不变特征。为了弥合理论和实践之间的差距，我们开发了一个因果关系的角度来看问题的领域泛化。我们认为，因果关系的概念可以用来解释成功的数据增强描述他们如何可以削弱观察到的领域和任务标签之间的虚假相关性。我们证明了数据增强可以作为模拟介入数据的工具。我们使用这些理论的见解，推导出一个简单的算法，能够选择数据增强技术，这将导致更好的域泛化。
英文摘要：
Machine learning models trained with purely observational data and the principle of empirical risk minimization \citep{vapnik_principles_1992} can fail to generalize to unseen domains. In this paper, we focus on the case where the problem arises through spurious correlation between the observed domains and the actual task labels. We find that many domain generalization methods do not explicitly take this spurious correlation into account. Instead, especially in more application-oriented research areas like medical imaging or robotics, data augmentation techniques that are based on heuristics are used to learn domain invariant features. To bridge the gap between theory and practice, we develop a causal perspective on the problem of domain generalization. We argue that causal concepts can be used to explain the success of data augmentation by describing how they can weaken the spurious correlation between the observed domains and the task labels. We demonstrate that data augmentation can serve as a tool for simulating interventional data. We use these theoretical insights to derive a simple algorithm that is able to select data augmentation techniques that will lead to better domain generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
