Generating Global and Local Explanations for Tree-Ensemble Learning Methods by Answer Set Programming

TL;DR

This paper introduces a method using Answer Set Programming to generate both global and local rule-based explanations for tree-ensemble models, enhancing interpretability with flexible, user-defined constraints.

Contribution

It presents a novel decompositional approach leveraging ASP for transparent rule extraction from tree-ensembles, accommodating user preferences and applicable to various classification tasks.

Findings

Applicable to a wide range of classification tasks

Demonstrates effectiveness on real-world datasets

Allows flexible, user-defined constraints in explanations

Abstract

We propose a method for generating rule sets as global and local explanations for tree-ensemble learning methods using Answer Set Programming (ASP). To this end, we adopt a decompositional approach where the split structures of the base decision trees are exploited in the construction of rules, which in turn are assessed using pattern mining methods encoded in ASP to extract explanatory rules. For global explanations, candidate rules are chosen from the entire trained tree-ensemble models, whereas for local explanations, candidate rules are selected by only considering rules that are relevant to the particular predicted instance. We show how user-defined constraints and preferences can be represented declaratively in ASP to allow for transparent and flexible rule set generation, and how rules can be used as explanations to help the user better understand the models. Experimental evaluation with real-world datasets and popular tree-ensemble algorithms demonstrates that our approach is applicable to a wide range of classification tasks. Under consideration in Theory and Practice of Logic Programming (TPLP).