We argue that interpretations of machine learning (ML) models or the model-building process can be seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental modeling, engineering, or economics. We address both researchers and practitioners, calling attention to the benefits of a unified SA-based view of explanations in ML and the necessity to fully credit related work. We bridge the gap between both fields by formally describing how (a) the ML process is a system suitable for SA, (b) how existing ML interpretation methods relate to this perspective, and (c) how other SA techniques could be applied to ML.
@article{arxiv.2312.13234,
title = {Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis},
author = {Christian A. Scholbeck and Julia Moosbauer and Giuseppe Casalicchio and Hoshin Gupta and Bernd Bischl and Christian Heumann},
journal= {arXiv preprint arXiv:2312.13234},
year = {2024}
}