Learning Functional Causal Models with Generative Neural Networks

TL;DR

This paper introduces Causal Generative Neural Networks (CGNN), a neural network-based method for learning causal models from observational data, capable of cause-effect inference, structure discovery, and handling confounders, with favorable performance on artificial and real data.

Contribution

The paper presents CGNN, a scalable neural network approach for functional causal modeling that extends to confounders and outperforms existing methods in various causal inference tasks.

Findings

CGNN accurately infers causal directions in cause-effect tasks.

It effectively identifies causal structures and v-structures.

The method scales linearly with data size and handles confounders.

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.