Unguided structure learning of DAGs for count data

TL;DR

This paper introduces learnDAG, a new algorithm for learning DAG structures from multivariate count data, demonstrating its effectiveness through experiments and real data validation in high-dimensional settings.

Contribution

The paper presents learnDAG, a novel two-step algorithm for structure learning of DAGs specifically tailored for count data, addressing high-dimensional observational data challenges.

Findings

learnDAG outperforms several competitors in structure recovery

The algorithm is effective with moderate sample sizes

Validation on real datasets confirms practical utility

Abstract

Mainly motivated by the problem of modelling directional dependence relationships for multivariate count data in high-dimensional settings, we present a new algorithm, called learnDAG, for learning the structure of directed acyclic graphs (DAGs). In particular, the proposed algorithm tackled the problem of learning DAGs from observational data in two main steps: (i) estimation of candidate parent sets; and (ii) feature selection. We experimentally compare learnDAG to several popular competitors in recovering the true structure of the graphs in situations where relatively moderate sample sizes are available. Furthermore, to make our algorithm is stronger, a validation of the algorithm is presented through the analysis of real datasets.