Toward Causal Representation Learning


Loading...

Date

2021-05

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

The two fields of machine learning and graphical causality arose and are developed separately. However, there is, now, cross-pollination and increasing interest in both fields to benefit from the advances of the other. In this article, 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, that is, 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.

Publication status

published

Editor

Book title

Volume

109 (5)

Pages / Article No.

612 - 634

Publisher

IEEE

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Artificial intelligence; causality; deep learning; representation learning

Organisational unit

09664 - Schölkopf, Bernhard / Schölkopf, Bernhard check_circle

Notes

Funding

Related publications and datasets