Learning Functional Causal Models with Generative Neural Networks

Olivier Goudet 1, 2 Diviyan Kalainathan 1, 2 Philippe Caillou 1, 2 David Lopez-Paz 3 Isabelle Guyon 1, 2, 4 Michèle Sebag 1, 2
1 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : We introduce a new approach to functional causal modeling from observational data, called Causal Generative Neural Networks (CGNN). CGNN leverages the power of neural networks to learn a generative model of the joint distribution of the observed variables, by minimizing the Maximum Mean Discrepancy between generated and observed data. An approximate learning criterion is proposed to scale the computational cost of the approach to linear complexity in the number of observations. The performance of CGNN is studied throughout three experiments. Firstly, CGNN is applied to cause-effect inference, where the task is to identify the best causal hypothesis out of $X\rightarrow Y$ and $Y\rightarrow X$. Secondly, CGNN is applied to the problem of identifying v-structures and conditional independences. Thirdly, CGNN is applied to multivariate functional causal modeling: given a skeleton describing the direct dependences in a set of random variables $\textbf{X} = [X_1, \ldots, X_d]$, CGNN orients the edges in the skeleton to uncover the directed acyclic causal graph describing the causal structure of the random variables. On all three tasks, CGNN is extensively assessed on both artificial and real-world data, comparing favorably to the state-of-the-art. Finally, CGNN is extended to handle the case of confounders, where latent variables are involved in the overall causal model.
Type de document :
Chapitre d'ouvrage
Explainable and Interpretable Models in Computer Vision and Machine Learning, Springer International Publishing, 2018, Springer Series on Challenges in Machine Learning, 978-3-319-98131-4. 〈10.1007/978-3-319-98131-4〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01649153
Contributeur : Olivier Goudet <>
Soumis le : lundi 27 novembre 2017 - 11:57:59
Dernière modification le : mardi 8 janvier 2019 - 08:36:01

Lien texte intégral

Identifiants

Citation

Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, David Lopez-Paz, Isabelle Guyon, et al.. Learning Functional Causal Models with Generative Neural Networks. Explainable and Interpretable Models in Computer Vision and Machine Learning, Springer International Publishing, 2018, Springer Series on Challenges in Machine Learning, 978-3-319-98131-4. 〈10.1007/978-3-319-98131-4〉. 〈hal-01649153〉

Partager

Métriques

Consultations de la notice

309