Induction of Non-Monotonic Logic Programs to Explain Boosted Tree Models Using LIME

TL;DR

This paper introduces LIME-FOLD, a heuristic ILP algorithm that explains XGBoost classifiers by inducing non-monotonic logic programs based on local feature importance, improving rule simplicity and classification metrics.

Contribution

The paper presents a novel LIME-based ILP method for global explanation of boosted tree models, reducing rule complexity and enhancing interpretability.

Findings

Significant improvement in classification metrics.

Dramatic reduction in the number of rules.

Effective global explanations of XGBoost models.

Abstract

We present a heuristic based algorithm to induce \textit{nonmonotonic} logic programs that will explain the behavior of XGBoost trained classifiers. We use the technique based on the LIME approach to locally select the most important features contributing to the classification decision. Then, in order to explain the model's global behavior, we propose the LIME-FOLD algorithm ---a heuristic-based inductive logic programming (ILP) algorithm capable of learning non-monotonic logic programs---that we apply to a transformed dataset produced by LIME. Our proposed approach is agnostic to the choice of the ILP algorithm. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics. Meanwhile, the number of induced rules dramatically decreases compared to ALEPH, a state-of-the-art ILP system.