A Taxonomy of Explainable Bayesian Networks

TL;DR

This paper introduces a comprehensive taxonomy for explainability in Bayesian networks, aiming to improve user understanding and trust by systematically categorizing explanation methods within probabilistic models.

Contribution

It extends existing explainability frameworks to include decision explanations and illustrates the taxonomy with a medical diagnostic example.

Findings

Provides a structured taxonomy for explainability in Bayesian networks

Enhances understanding of how and why predictions are made

Supports better communication and trust in AI decisions

Abstract

Artificial Intelligence (AI), and in particular, the explainability thereof, has gained phenomenal attention over the last few years. Whilst we usually do not question the decision-making process of these systems in situations where only the outcome is of interest, we do however pay close attention when these systems are applied in areas where the decisions directly influence the lives of humans. It is especially noisy and uncertain observations close to the decision boundary which results in predictions which cannot necessarily be explained that may foster mistrust among end-users. This drew attention to AI methods for which the outcomes can be explained. Bayesian networks are probabilistic graphical models that can be used as a tool to manage uncertainty. The probabilistic framework of a Bayesian network allows for explainability in the model, reasoning and evidence. The use of these methods is mostly ad hoc and not as well organised as explainability methods in the wider AI research field. As such, we introduce a taxonomy of explainability in Bayesian networks. We extend the existing categorisation of explainability in the model, reasoning or evidence to include explanation of decisions. The explanations obtained from the explainability methods are illustrated by means of a simple medical diagnostic scenario. The taxonomy introduced in this paper has the potential not only to encourage end-users to efficiently communicate outcomes obtained, but also support their understanding of how and, more importantly, why certain predictions were made.