Enabling Regional Explainability by Automatic and Model-agnostic Rule Extraction

TL;DR

This paper introduces a novel, model-agnostic rule extraction method that improves regional explainability in imbalanced datasets by automatically generating rules for subgroups and selecting features efficiently.

Contribution

It presents the first approach for extracting rules from specific data subgroups with automatic numerical feature rule generation, enhancing regional explainability.

Findings

Effective rule extraction demonstrated across multiple datasets.

Improved regional explainability over existing methods.

Reduced computational costs in high-dimensional spaces.

Abstract

In Explainable AI, rule extraction translates model knowledge into logical rules, such as IF-THEN statements, crucial for understanding patterns learned by black-box models. This could significantly aid in fields like disease diagnosis, disease progression estimation, or drug discovery. However, such application domains often contain imbalanced data, with the class of interest underrepresented. Existing methods inevitably compromise the performance of rules for the minor class to maximise the overall performance. As the first attempt in this field, we propose a model-agnostic approach for extracting rules from specific subgroups of data, featuring automatic rule generation for numerical features. This method enhances the regional explainability of machine learning models and offers wider applicability compared to existing methods. We additionally introduce a new method for selecting features to compose rules, reducing computational costs in high-dimensional spaces. Experiments across various datasets and models demonstrate the effectiveness of our methods.