Beyond Linear Surrogates: High-Fidelity Local Explanations for Black-Box Models

TL;DR

This paper introduces a novel local explanation method using MARS and N-ball sampling to produce high-fidelity, model-agnostic explanations for complex black-box models, significantly improving local surrogate accuracy.

Contribution

It presents a new explanation approach combining MARS and N-ball sampling, enhancing local fidelity over existing methods for black-box models.

Findings

Achieves 32% reduction in RMSE compared to baselines

Statistically significant improvements across five datasets

Provides more accurate local approximations of black-box models

Abstract

With the increasing complexity of black-box machine learning models and their adoption in high-stakes areas, it is critical to provide explanations for their predictions. Existing local explanation methods lack in generating high-fidelity explanations. This paper proposes a novel local model agnostic explanation method to generate high-fidelity explanations using multivariate adaptive regression splines (MARS) and N-ball sampling strategies. MARS is used to model non-linear local boundaries that effectively captures the underlying behavior of the reference model, thereby enhancing the local fidelity. The N-ball sampling technique samples perturbed samples directly from a desired distribution instead of reweighting, leading to further improvement in the faithfulness. The performance of the proposed method was computed in terms of root mean squared error (RMSE) and evaluated on five different benchmark datasets with different kernel width. Experimental results show that the proposed method achieves higher local surrogate fidelity compared to baseline local explanation methods, with an average reduction of 32% in root mean square error, indicating more accurate local approximations of the black-box model. Additionally, statistical analysis shows that across all benchmark datasets, the proposed approach results were statistically significantly better. This paper advances the field of explainable AI by providing insights that can benefit the broader research and practitioner community.