论文标题
领域不变的监督代表学习的因果结构
The Causal Structure of Domain Invariant Supervised Representation Learning
论文作者
论文摘要
当部署在与受过训练的域不同的域中时，机器学习方法可能是不可靠的。在某种意义上，通过学习``不变''的表示表示形式来缓解这个问题的建议都有广泛的建议。但是，这些方法通常相互矛盾，并且没有一个始终如一地改善现实世界中域移动基准的性能。必须解决两个主要问题，以了解何时，如果有的话，我们应该使用每种方法。首先，``不变性''的每个临时概念与现实世界问题的结构有何关系？其次，什么时候学习不变表示实际上会产生强大的模型？为了解决这些问题，我们引入了广泛的正式概念，即它对现实世界中的转变意味着什么，以接纳不变结构。然后，我们表征与这种不变性概念兼容的因果结构。与此同时，我们发现条件在哪种特定方法特定的不变性概念与现实世界不变结构相对应的情况下，我们阐明了与域移位的不变结构与稳健性之间的关系。对于这两个问题，我们发现数据的真正基本因果结构起着至关重要的作用。
Machine learning methods can be unreliable when deployed in domains that differ from the domains on which they were trained. There are a wide range of proposals for mitigating this problem by learning representations that are ``invariant'' in some sense.However, these methods generally contradict each other, and none of them consistently improve performance on real-world domain shift benchmarks. There are two main questions that must be addressed to understand when, if ever, we should use each method. First, how does each ad hoc notion of ``invariance'' relate to the structure of real-world problems? And, second, when does learning invariant representations actually yield robust models? To address these issues, we introduce a broad formal notion of what it means for a real-world domain shift to admit invariant structure. Then, we characterize the causal structures that are compatible with this notion of invariance.With this in hand, we find conditions under which method-specific invariance notions correspond to real-world invariant structure, and we clarify the relationship between invariant structure and robustness to domain shifts. For both questions, we find that the true underlying causal structure of the data plays a critical role.
