Toward Causal Representation Learning

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 th...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the IEEE Vol. 109; no. 5; pp. 612 - 634
Main Authors: Scholkopf, Bernhard, Locatello, Francesco, Bauer, Stefan, Ke, Nan Rosemary, Kalchbrenner, Nal, Goyal, Anirudh, Bengio, Yoshua
Format: Journal Article
Language:English
Published: New York IEEE 01.05.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Adaptation models
Artificial intelligence
Causality
Data models
deep learning
Differential equations
Inference algorithms
Machine learning
Mathematical model
Representation learning
Representations
Training data
ISSN:0018-9219, 1558-2256
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9219
1558-2256
DOI:10.1109/JPROC.2021.3058954