Learning Linear Non-Gaussian Causal Models in the Presence of Latent Variables

TL;DR

This paper introduces a method for learning causal models with latent variables from observational data, identifying possible causal effects and conditions for unique causal inference in linear non-Gaussian settings.

Contribution

It proposes a novel approach to determine causal paths and effects among observed variables, accounting for latent variables and non-Gaussian noise, with conditions for unique identification.

Findings

Effective algorithm for causal path detection

Sets of possible causal effects identified

Structural conditions for unique causal effect estimation

Abstract

We consider the problem of learning causal models from observational data generated by linear non-Gaussian acyclic causal models with latent variables. Without considering the effect of latent variables, one usually infers wrong causal relationships among the observed variables. Under faithfulness assumption, we propose a method to check whether there exists a causal path between any two observed variables. From this information, we can obtain the causal order among them. The next question is then whether or not the causal effects can be uniquely identified as well. It can be shown that causal effects among observed variables cannot be identified uniquely even under the assumptions of faithfulness and non-Gaussianity of exogenous noises. However, we will propose an efficient method to identify the set of all possible causal effects that are compatible with the observational data. Furthermore, we present some structural conditions on the causal graph under which we can learn causal effects among observed variables uniquely. We also provide necessary and sufficient graphical conditions for unique identification of the number of variables in the system. Experiments on synthetic data and real-world data show the effectiveness of our proposed algorithm on learning causal models.