Extracting Optimal Explanations for Ensemble Trees via Logical Reasoning

TL;DR

This paper introduces OptExplain and ProClass, methods that use logical reasoning and MAX-SAT to generate faithful, simplified explanations for large ensemble decision trees, improving interpretability over existing approaches.

Contribution

The paper presents novel explanation techniques, OptExplain and ProClass, that enhance the interpretability of ensemble trees through logical reasoning and optimization.

Findings

High-quality explanations for large ensemble models

Outperforms recent top explanation methods

Effective simplification of complex ensemble explanations

Abstract

Ensemble trees are a popular machine learning model which often yields high prediction performance when analysing structured data. Although individual small decision trees are deemed explainable by nature, an ensemble of large trees is often difficult to understand. In this work, we propose an approach called optimised explanation (OptExplain) that faithfully extracts global explanations of ensemble trees using a combination of logical reasoning, sampling and optimisation. Building on top of this, we propose a method called the profile of equivalent classes (ProClass), which uses MAX-SAT to simplify the explanation even further. Our experimental study on several datasets shows that our approach can provide high-quality explanations to large ensemble trees models, and it betters recent top-performers.