A Symbolic Approach for Counterfactual Explanations
This work addresses the need for interpretable AI by providing a method to explain predictions through feature changes, but it is incremental as it builds on existing Minimal Correction Subsets techniques.
The paper tackles the problem of generating counterfactual explanations for classifier predictions by proposing a symbolic approach that encodes the decision function into a CNF formula, with preliminary experiments on Bayesian classifiers showing potential across several datasets.
In this paper titled A Symbolic Approach for Counterfactual Explanations we propose a novel symbolic approach to provide counterfactual explanations for a classifier predictions. Contrary to most explanation approaches where the goal is to understand which and to what extent parts of the data helped to give a prediction, counterfactual explanations indicate which features must be changed in the data in order to change this classifier prediction. Our approach is symbolic in the sense that it is based on encoding the decision function of a classifier in an equivalent CNF formula. In this approach, counterfactual explanations are seen as the Minimal Correction Subsets (MCS), a well-known concept in knowledge base reparation. Hence, this approach takes advantage of the strengths of already existing and proven solutions for the generation of MCS. Our preliminary experimental studies on Bayesian classifiers show the potential of this approach on several datasets.