Enhancing LIME using Neural Decision Trees
This work addresses interpretability challenges in machine learning for tabular data, offering an incremental improvement over existing LIME methods.
The paper tackled the problem of LIME's surrogate models struggling to capture complex non-linear decision boundaries in black-box models for tabular data, and proposed NDT-LIME using Neural Decision Trees, which showed consistent improvements in explanation fidelity on benchmark datasets.
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.