Formally Explaining Decision Tree Models with Answer Set Programming
This work addresses the need for formal justification of model decisions in safety-critical applications, offering an incremental improvement over SAT-based approaches with greater flexibility and support for enumerating all explanations.
The paper tackled the problem of interpreting complex decision tree models by proposing a method using Answer Set Programming (ASP) to generate various types of explanations, such as sufficient and contrastive ones, and demonstrated its effectiveness and limitations compared to existing methods on diverse datasets.
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.