NIPS Proceedingsβ

A Benchmark for Interpretability Methods in Deep Neural Networks

Part of: Advances in Neural Information Processing Systems 32 (NIPS 2019) pre-proceedings

[PDF] [BibTeX] [Supplemental]

Authors

Conference Event Type: Poster

Abstract

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.