Truthful Meta-Explanations for Local Interpretability of Machine Learning Models

TL;DR

This paper introduces a local meta-explanation method for machine learning models that leverages a faithfulness-based truthfulness metric to improve interpretability in high-stakes applications.

Contribution

It presents a novel meta-explanation technique built on the truthfulness metric, enhancing the selection of interpretability methods for complex ML models.

Findings

The proposed technique effectively identifies truthful explanations.

The truthfulness metric correlates well with explanation quality.

Experimental results validate the approach's usefulness.

Abstract

Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable, they should not be used in critical, high-risk applications where human lives are at risk. To address this issue, researchers and businesses have been focusing on finding ways to improve the interpretability of complex ML systems, and several such methods have been developed. Indeed, there are so many developed techniques that it is difficult for practitioners to choose the best among them for their applications, even when using evaluation metrics. As a result, the demand for a selection tool, a meta-explanation technique based on a high-quality evaluation metric, is apparent. In this paper, we present a local meta-explanation technique which builds on top of the truthfulness metric, which is a faithfulness-based metric. We demonstrate the effectiveness of both the technique and the metric by concretely defining all the concepts and through experimentation.