A Benchmark for Interpretability Methods in Deep Neural Networks

We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature importance that are not better than a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-11
Main Authors: Hooker, Sara, Dumitru Erhan, Pieter-Jan Kindermans, Been, Kim
Format: Article
Language:English
Subjects:
Accuracy
Estimates
Human behavior
Image classification
Neural networks
Production methods
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose an empirical measure of the approximate accuracy of feature importance estimates in deep neural networks. Our results across several large-scale image classification datasets show that many popular interpretability methods produce estimates of feature importance that are not better than a random designation of feature importance. Only certain ensemble based approaches---VarGrad and SmoothGrad-Squared---outperform such a random assignment of importance. The manner of ensembling remains critical, we show that some approaches do no better then the underlying method but carry a far higher computational burden.
ISSN:2331-8422