---
res:
  bibo_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.@eng'
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Bernhard
      foaf_name: Scholkopf, Bernhard
      foaf_surname: Scholkopf
  - foaf_Person:
      foaf_givenName: Francesco
      foaf_name: Locatello, Francesco
      foaf_surname: Locatello
      foaf_workInfoHomepage: http://www.librecat.org/personId=26cfd52f-2483-11ee-8040-88983bcc06d4
    orcid: 0000-0002-4850-0683
  - foaf_Person:
      foaf_givenName: Stefan
      foaf_name: Bauer, Stefan
      foaf_surname: Bauer
  - foaf_Person:
      foaf_givenName: Nan Rosemary
      foaf_name: Ke, Nan Rosemary
      foaf_surname: Ke
  - foaf_Person:
      foaf_givenName: Nal
      foaf_name: Kalchbrenner, Nal
      foaf_surname: Kalchbrenner
  - foaf_Person:
      foaf_givenName: Anirudh
      foaf_name: Goyal, Anirudh
      foaf_surname: Goyal
  - foaf_Person:
      foaf_givenName: Yoshua
      foaf_name: Bengio, Yoshua
      foaf_surname: Bengio
  bibo_doi: 10.1109/jproc.2021.3058954
  bibo_issue: '5'
  bibo_volume: 109
  dct_date: 2021^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/0018-9219
  - http://id.crossref.org/issn/1558-2256
  dct_language: eng
  dct_publisher: Institute of Electrical and Electronics Engineers@
  dct_subject:
  - Electrical and Electronic Engineering
  dct_title: Toward causal representation learning@
...