SmoothHess: ReLU Network Feature Interactions via Stein's Lemma
Abstract
Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-linear and thus have a zero Hessian almost everywhere. We propose SmoothHess, a method of estimating second-order interactions through Stein's Lemma. In particular, we estimate the Hessian of the network convolved with a Gaussian through an efficient sampling algorithm, requiring only network gradient calls. SmoothHess is applied post-hoc, requires no modifications to the ReLU network architecture, and the extent of smoothing can be controlled explicitly. We provide a non-asymptotic bound on the sample complexity of our estimation procedure. We validate the superior ability of SmoothHess to capture interactions on benchmark datasets and a real-world medical spirometry dataset.
Cite
@article{arxiv.2311.00858,
title = {SmoothHess: ReLU Network Feature Interactions via Stein's Lemma},
author = {Max Torop and Aria Masoomi and Davin Hill and Kivanc Kose and Stratis Ioannidis and Jennifer Dy},
journal= {arXiv preprint arXiv:2311.00858},
year = {2023}
}
Comments
Accepted to NeurIPS 2023 as a conference paper