Induction of Non-monotonic Logic Programs To Explain Statistical Learning Models

TL;DR

This paper introduces a fast algorithm for inducing non-monotonic logic programs from statistical models by framing the search as a High-Utility Itemset Mining problem, leveraging explainability tools for feature importance.

Contribution

The paper presents a novel scalable approach that combines explainable AI techniques with ILP, improving efficiency and accuracy over existing systems like ALEPH.

Findings

Significant improvement in classification metrics

Faster training times compared to ALEPH

Effective extraction of important features using TreeExplainer

Abstract

We present a fast and scalable algorithm to induce non-monotonic logic programs from statistical learning models. We reduce the problem of search for best clauses to instances of the High-Utility Itemset Mining (HUIM) problem. In the HUIM problem, feature values and their importance are treated as transactions and utilities respectively. We make use of TreeExplainer, a fast and scalable implementation of the Explainable AI tool SHAP, to extract locally important features and their weights from ensemble tree models. Our experiments with UCI standard benchmarks suggest a significant improvement in terms of classification evaluation metrics and running time of the training algorithm compared to ALEPH, a state-of-the-art Inductive Logic Programming (ILP) system.