Causal Autoregressive Flows

TL;DR

This paper establishes a connection between autoregressive normalizing flows and causal models, enabling causal discovery, interventional, and counterfactual inference with improved accuracy over existing methods.

Contribution

It introduces a novel approach linking autoregressive flows to causal inference, demonstrating identifiability and practical utility for causal discovery and prediction tasks.

Findings

Causal models from autoregressive flows are identifiable.

Likelihood ratio measure effectively determines causal direction.

Flows enable direct evaluation of interventional and counterfactual queries.

Abstract

Two apparently unrelated fields -- normalizing flows and causality -- have recently received considerable attention in the machine learning community. In this work, we highlight an intrinsic correspondence between a simple family of autoregressive normalizing flows and identifiable causal models. We exploit the fact that autoregressive flow architectures define an ordering over variables, analogous to a causal ordering, to show that they are well-suited to performing a range of causal inference tasks, ranging from causal discovery to making interventional and counterfactual predictions. First, we show that causal models derived from both affine and additive autoregressive flows with fixed orderings over variables are identifiable, i.e. the true direction of causal influence can be recovered. This provides a generalization of the additive noise model well-known in causal discovery. Second, we derive a bivariate measure of causal direction based on likelihood ratios, leveraging the fact that flow models can estimate normalized log-densities of data. Third, we demonstrate that flows naturally allow for direct evaluation of both interventional and counterfactual queries, the latter case being possible due to the invertible nature of flows. Finally, throughout a series of experiments on synthetic and real data, the proposed method is shown to outperform current approaches for causal discovery as well as making accurate interventional and counterfactual predictions.