为还未出版的Proceedings of the IEEE特刊 Advances in Machine Learning and Deep Neural Networks撰写的文章。作者阵容很强。

摘要

The two fields of machine learning and graphical causality arose and developed separately. However, there is now cross-pollination and increasing interest in both fields to benefit from the advances of the other. In the present paper, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.

机器学习和图因果这两个领域是分别出现和发展的。 然而，这两个领域现在出现了异花授粉的现象，彼此互相之间的兴趣日增，互相促进。 在本文中，我们回顾了因果推理的一些基本概念，并将它们与机器学习的关键未解决问题（包括迁移和泛化）关联起来，从而分析了因果关系如何有助于现代机器学习研究。 这也适用于相反的方向：我们注意到大多数因果关系的工作都始于因果变量是给定这一前提。 因此，AI和因果关系的中心问题是因果表示学习，即从低层观察中发现高层因果变量。 最后，我们描述了因果关系对机器学习的一些影响，并提出了两个社区相交叉的关键研究领域。

点击下面的“阅读原文”进入arxiv链接。

内容中包含的图片若涉及版权问题，请及时与我们联系删除