On Computing Relevant Features for Explaining NBCs

TL;DR

This paper investigates the computation of relevant feature sets for Naive Bayes Classifiers, demonstrating that these sets are computationally feasible and can be succinct, offering a practical alternative to more complex explanation methods.

Contribution

It shows that relevant feature sets for NBCs are easy to compute in practice and can be made succinct, addressing complexity issues in explanation methods.

Findings

Relevant feature sets for NBCs are computationally feasible.

Succinct sets of relevant features can be obtained with NBCs.

The approach offers a practical alternative to complex explanation methods.

Abstract

Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations. One alternative are the so-called formal approaches to XAI, that include PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. The computation of relevant features serves to trade off probabilistic precision for the number of features in an explanation. However, even for very simple classifiers, the complexity of computing sets of relevant features is prohibitive. This paper investigates the computation of relevant sets for Naive Bayes Classifiers (NBCs), and shows that, in practice, these are easy to compute. Furthermore, the experiments confirm that succinct sets of relevant features can be obtained with NBCs.