Feature importance methods using unrestricted permutations are flawed due to extrapolation errors; such errors appear in all non-trivial variable importance approaches. We propose three new approaches: conditional model reliance and Knockoffs with Gaussian transformation, and restricted ALE plot designs. Theoretical and numerical results show our strategies reduce/eliminate extrapolation.
@article{arxiv.2604.11253,
title = {Trustworthy Feature Importance Avoids Unrestricted Permutations},
author = {Emanuele Borgonovo and Francesco Cappelli and Xuefei Lu and Elmar Plischke and Cynthia Rudin},
journal= {arXiv preprint arXiv:2604.11253},
year = {2026}
}