Metric Tools for Sensitivity Analysis with Applications to Neural Networks

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  α-curves is extracted. These  α-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  α-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.