Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges - A&O (Apprentissage et Optimisation)
Communication Dans Un Congrès Année : 2024

Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges

Alessandro Leite
Nicolas Chesneau
  • Fonction : Auteur
Marc Schoenauer

Résumé

This paper provides a comprehensive review of deep structural causal models (DSCMs), particularly focusing on their ability to answer counterfactual queries using observational data within known causal structures. It delves into the characteristics of DSCMs by analyzing the hypotheses, guarantees, and applications inherent to the underlying deep learning components and structural causal models, fostering a finer understanding of their capabilities and limitations in addressing different counterfactual queries. Furthermore, it highlights the challenges and open questions in the field of deep structural causal modeling. It sets the stages for researchers to identify future work directions and for practitioners to get an overview in order to find out the most appropriate methods for their needs.
Fichier principal
Vignette du fichier
Survey_SCM.pdf (343.97 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04706985 , version 1 (24-09-2024)

Licence

Identifiants

Citer

Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Michele Sebag, Marc Schoenauer. Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges. IJCAI 2024 - Thirty-Third International Joint Conference on Artificial Intelligence, Aug 2024, Jeju, South Korea. pp.8207-8215, ⟨10.24963/ijcai.2024/907⟩. ⟨hal-04706985⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More