Formally Explaining Decision Tree Models with Answer Set Programming

TL;DR

This paper introduces a flexible ASP-based method for generating various explanations for decision tree models, enhancing interpretability especially in safety-critical contexts, and compares its effectiveness to existing SAT-based approaches.

Contribution

It presents a novel ASP-based framework for generating multiple types of explanations for decision trees, offering greater flexibility and enumeration capabilities over prior SAT-based methods.

Findings

Effective in generating diverse explanations

Supports enumeration of all explanations

Outperforms SAT-based methods in flexibility

Abstract

Decision tree models, including random forests and gradient-boosted decision trees, are widely used in machine learning due to their high predictive performance. However, their complex structures often make them difficult to interpret, especially in safety-critical applications where model decisions require formal justification. Recent work has demonstrated that logical and abductive explanations can be derived through automated reasoning techniques. In this paper, we propose a method for generating various types of explanations, namely, sufficient, contrastive, majority, and tree-specific explanations, using Answer Set Programming (ASP). Compared to SAT-based approaches, our ASP-based method offers greater flexibility in encoding user preferences and supports enumeration of all possible explanations. We empirically evaluate the approach on a diverse set of datasets and demonstrate its effectiveness and limitations compared to existing methods.