Deep Learning of Causal Structures in High Dimensions

TL;DR

This paper introduces a deep neural network architecture that combines convolutional and graph neural networks to learn causal relationships from high-dimensional data, demonstrating scalability and effectiveness in biological applications.

Contribution

It presents a novel deep learning framework integrating empirical data and prior causal knowledge for scalable causal discovery in high dimensions.

Findings

Successful application to linear and nonlinear simulations

Effective learning of causal networks in high-dimensional biological data

Validation against unseen experiments confirms model reliability

Abstract

Recent years have seen rapid progress at the intersection between causality and machine learning. Motivated by scientific applications involving high-dimensional data, in particular in biomedicine, we propose a deep neural architecture for learning causal relationships between variables from a combination of empirical data and prior causal knowledge. We combine convolutional and graph neural networks within a causal risk framework to provide a flexible and scalable approach. Empirical results include linear and nonlinear simulations (where the underlying causal structures are known and can be directly compared against), as well as a real biological example where the models are applied to high-dimensional molecular data and their output compared against entirely unseen validation experiments. These results demonstrate the feasibility of using deep learning approaches to learn causal networks in large-scale problems spanning thousands of variables.