A Comparison of Global Sensitivity Analysis Methods for Explainable AI with an Application in Genomic Prediction

Abstract

Explainable Artificial Intelligence (XAI) is an increasingly important field of research required to bring AI to the next level in real-world applications. Global sensitivity analysis methods play an important role in XAI, as they can provide an understanding of which (groups of) parameters have high influence in the predictions of machine learning models and the output of simulators and real-world processes. In this paper, we conduct a survey into global sensitivity methods in an XAI context and present both a qualitative and a quantitative analysis of these methods under different conditions. In addition to the overview and comparison, we propose an open source application, GSAreport, that allows you to easily generate extensive reports using a carefully selected set of global sensitivity analysis methods depending on the number of dimensions and samples, to gain a deep understanding of the role of each feature for a given model or data set. We finally present the methods discussed in a complex real-world application of genomic prediction and draw conclusions about when to use which GSA methods.

Authors 6

1. Bas van Stein Aachen

   Leiden University

   Affiliation as printed

   Leiden University

2. Elena Raponi

   Technical University of Munich

   Affiliation as printed

   TUM School of Engineering and Design , Technical University of Munich , Germany

3. Zahra Sadeghi Aachen Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Institute of Advanced Computer Science , University Leiden , The Netherlands

4. Niek J. Bouman
   Affiliation as printed

   Wageningen , The Netherlands

5. Roeland C. H. J. van Ham
6. Thomas Bäck Aachen Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Institute of Advanced Computer Science , University Leiden , The Netherlands