Context-Specific Refinements of Bayesian Network Classifiers

TL;DR

This paper introduces new Bayesian network classifiers using staged tree models that capture complex, context-specific dependencies, leading to improved classification accuracy in supervised learning tasks.

Contribution

It extends traditional Bayesian network classifiers like TAN by incorporating staged tree models for more flexible, context-specific dependence patterns.

Findings

Models with asymmetric information improve accuracy

Data-driven learning routines are effective

Extended classifiers outperform traditional ones in experiments

Abstract

Supervised classification is one of the most ubiquitous tasks in machine learning. Generative classifiers based on Bayesian networks are often used because of their interpretability and competitive accuracy. The widely used naive and TAN classifiers are specific instances of Bayesian network classifiers with a constrained underlying graph. This paper introduces novel classes of generative classifiers extending TAN and other famous types of Bayesian network classifiers. Our approach is based on staged tree models, which extend Bayesian networks by allowing for complex, context-specific patterns of dependence. We formally study the relationship between our novel classes of classifiers and Bayesian networks. We introduce and implement data-driven learning routines for our models and investigate their accuracy in an extensive computational study. The study demonstrates that models embedding asymmetric information can enhance classification accuracy.