GFlowCausal: Generative Flow Networks for Causal Discovery

Abstract

Causal discovery aims to uncover causal structure among a set of variables. Scorebased approaches mainly focus on searching for the best Directed Acyclic Graph (DAG) based on a predefined score function. However, most of them are not applicable on a large scale due to the limited searchability. Inspired by the active learning in generative flow networks, we propose a novel approach to learning a DAG from observational data called GFlowCausal. It converts the graph search problem to a generation problem, in which direct edges are added gradually. GFlowCausal aims to learn the best policy to generate high-reward DAGs by sequential actions with probabilities proportional to predefined rewards. We propose a plug-and-play module based on transitive closure to ensure efficient sampling. Theoretical analysis shows that this module could guarantee acyclicity properties effectively and the consistency between final states and fully-connected graphs. We conduct extensive experiments on both synthetic and real datasets, and results show the proposed approach to be superior and also performs well in a large-scale setting. The codes are available at

DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks

“…The approach also differs from RL, which aims to maximize the expected return and only generates a single sequence of actions with the highest reward. GFlowNets has been applied in molecule generation Bengio et al (2021a); , discrete probabilistic modeling Zhang et al (2022), bayesian structure learning Deleu et al (2022), causal discovery Li et al (2022) and continuous control tasks Li et al (2023).…”