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

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 (GSA) methods play an important role in XAI, as they can provide an understanding of which (groups of) parameters ha...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2022, Vol.10, p.103364-103381
Main Authors: Stein, Bas Van, Raponi, Elena, Sadeghi, Zahra, Bouman, Niek, Van Ham, Roeland C. H. J., Back, Thomas
Format: Article
Language:English
Subjects:
Analytical models
Artificial intelligence
Biological system modeling
Explainable artificial intelligence
genomic prediction
global sensitivity analysis
Machine learning
plant breeding
Predictive models
Qualitative analysis
Robustness
Sensitivity analysis
Simulators
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 (GSA) 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.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2022.3210175