Metric Tools for Sensitivity Analysis with Applications to Neural Networks

Abstract

<p>In this paper, a theoretical framework is proposed to study sensitivities of Machine Learning models using metric techniques. From this metric interpretation, a complete family of new quantitative metrics called <strong>α</strong>-curves is extracted. These <strong>α</strong>-curves provide information with greater depth on the importance of the input variables for a machine learning model than existing XAI methods in the literature. We demonstrate the effectiveness of the <strong>α</strong>-curves using synthetic and real datasets, comparing the results against other XAI methods for variable importance and validating the analysis results with the ground truth or literature information. </p>