ServiceNow Research

Typing assumptions improve identification in causal discovery - Report and comments on future directions

Abstract

Causal discovery from observational data is a challenging task that can only be solved up to a set of equivalent solutions, called an equivalence class. Such classes, which are often large in size, encode uncertainties about the orientation of some edges in the causal graph. In this work, we propose a new set of assumptions that constrain possible causal relationships based on the nature of variables, thus circumscribing the equivalence class. Namely, we introduce typed directed acyclic graphs, in which variable types are used to determine the validity of causal relationships. We demonstrate, both theoretically and empirically, that the proposed assumptions can result in significant gains in the identification of the causal graph. We also propose causal discovery algorithms that make use of these assumptions and demonstrate their benefits on simulated and pseudo-real data.

Publication
Workshop at the Neural Information Processing Systems (NeurIPS)
Philippe Brouillard
Philippe Brouillard
Visiting Researcher

Visiting Researcher at Human Decision Support located at Montreal, QC, Canada.

Perouz Taslakian
Perouz Taslakian
Research Lead

Research Lead at Low Data Learning located at Montreal, QC, Canada.

Alexandre Lacoste
Alexandre Lacoste
Research Scientist

Research Scientist at Human Decision Support located at Montreal, QC, Canada.

Alexandre Drouin
Alexandre Drouin
Research Lead

Research Lead at Human Decision Support located at Montreal, QC, Canada.