Computing Abductive Explanations for Boosted Trees

TL;DR

This paper introduces a new method for efficiently generating understandable explanations for boosted trees, making them more suitable for safety-critical applications by improving explanation scalability.

Contribution

The paper proposes the concept of tree-specific explanations that can be computed in polynomial time, enhancing the scalability of abductive explanations for boosted trees.

Findings

Tree-specific explanations can be computed in polynomial time.

Using tree-specific explanations improves the scalability of generating abductive explanations.

Experiments demonstrate computational benefits on various datasets.

Abstract

Boosted trees is a dominant ML model, exhibiting high accuracy. However, boosted trees are hardly intelligible, and this is a problem whenever they are used in safety-critical applications. Indeed, in such a context, rigorous explanations of the predictions made are expected. Recent work have shown how subset-minimal abductive explanations can be derived for boosted trees, using automated reasoning techniques. However, the generation of such well-founded explanations is intractable in the general case. To improve the scalability of their generation, we introduce the notion of tree-specific explanation for a boosted tree. We show that tree-specific explanations are abductive explanations that can be computed in polynomial time. We also explain how to derive a subset-minimal abductive explanation from a tree-specific explanation. Experiments on various datasets show the computational benefits of leveraging tree-specific explanations for deriving subset-minimal abductive explanations.