Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifiers

TL;DR

This paper proposes a novel perspective on counterfactual explanations by treating the simulation process as a knowledge source, demonstrated through additive models and naive Bayes classifiers.

Contribution

It introduces a new approach to explainable AI by leveraging counterfactual simulation as a knowledge generation process, especially in additive models and naive Bayes classifiers.

Findings

Counterfactual simulation can be used as a knowledge source.

Naive Bayes classifiers exhibit properties beneficial for this approach.

The method enhances understanding of model decisions.

Abstract

There are now many explainable AI methods for understanding the decisions of a machine learning model. Among these are those based on counterfactual reasoning, which involve simulating features changes and observing the impact on the prediction. This article proposes to view this simulation process as a source of creating a certain amount of knowledge that can be stored to be used, later, in different ways. This process is illustrated in the additive model and, more specifically, in the case of the naive Bayes classifier, whose interesting properties for this purpose are shown.