Enhancing LIME using Neural Decision Trees

TL;DR

This paper introduces NDT-LIME, a novel approach that uses Neural Decision Trees as surrogate models to improve the fidelity of local explanations in interpretable machine learning, especially for complex tabular data.

Contribution

It proposes integrating Neural Decision Trees into LIME to enhance explanation accuracy and interpretability for black-box models on tabular datasets.

Findings

NDT-LIME outperforms traditional LIME surrogates in explanation fidelity.

Neural Decision Trees provide more faithful local explanations.

The approach demonstrates consistent improvements across benchmark datasets.

Abstract

Interpreting complex machine learning models is a critical challenge, especially for tabular data where model transparency is paramount. Local Interpretable Model-Agnostic Explanations (LIME) has been a very popular framework for interpretable machine learning, also inspiring many extensions. While traditional surrogate models used in LIME variants (e.g. linear regression and decision trees) offer a degree of stability, they can struggle to faithfully capture the complex non-linear decision boundaries that are inherent in many sophisticated black-box models. This work contributes toward bridging the gap between high predictive performance and interpretable decision-making. Specifically, we propose the NDT-LIME variant that integrates Neural Decision Trees (NDTs) as surrogate models. By leveraging the structured, hierarchical nature of NDTs, our approach aims at providing more accurate and meaningful local explanations. We evaluate its effectiveness on several benchmark tabular datasets, showing consistent improvements in explanation fidelity over traditional LIME surrogates.