Bayesian Network Structure Learning with Permutation Tests

TL;DR

This paper explores how replacing parametric tests with permutation tests in Bayesian network structure learning impacts performance, including an overview of shrinkage tests for discrete data.

Contribution

It introduces the use of permutation and shrinkage tests in Bayesian network structure learning, expanding beyond traditional parametric methods.

Findings

Permutation tests influence learning performance

Shrinkage tests offer a robust alternative

Performance varies with data type and test choice

Abstract

In literature there are several studies on the performance of Bayesian network structure learning algorithms. The focus of these studies is almost always the heuristics the learning algorithms are based on, i.e. the maximisation algorithms (in score-based algorithms) or the techniques for learning the dependencies of each variable (in constraint-based algorithms). In this paper we investigate how the use of permutation tests instead of parametric ones affects the performance of Bayesian network structure learning from discrete data. Shrinkage tests are also covered to provide a broad overview of the techniques developed in current literature.