Differentiable Causal Discovery from Interventional Data
Abstract
Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the solution is not always identifiable. A new line of work reformulates this problem as a continuous constrained optimization one, which is solved via the augmented Lagrangian method. However, most methods based on this idea do not make use of interventional data, which can significantly alleviate identifiability issues. This work constitutes a new step in this direction by proposing a theoretically-grounded method based on neural networks that can leverage interventional data. We illustrate the flexibility of the continuous-constrained framework by taking advantage of expressive neural architectures such as normalizing flows. We show that our approach compares favorably to the state of the art in a variety of settings, including perfect and imperfect interventions for which the targeted nodes may even be unknown.
Cite
@article{arxiv.2007.01754,
title = {Differentiable Causal Discovery from Interventional Data},
author = {Philippe Brouillard and Sébastien Lachapelle and Alexandre Lacoste and Simon Lacoste-Julien and Alexandre Drouin},
journal= {arXiv preprint arXiv:2007.01754},
year = {2020}
}
Comments
Appears in: Advances in Neural Information Processing Systems 34 (NeurIPS 2020). 46 pages