Axiomatic Attribution for Deep Networks

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution methods ought to satisfy. We show that they are not satisfi...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Sundararajan, Mukund, Taly, Ankur, Yan, Qiqi
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 13.06.2017
Subjects
Axioms
Debugging
Identification methods
Methods
Organic chemistry
Online AccessGet full text

Cover

More Information
Summary:We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution methods ought to satisfy. We show that they are not satisfied by most known attribution methods, which we consider to be a fundamental weakness of those methods. We use the axioms to guide the design of a new attribution method called Integrated Gradients. Our method requires no modification to the original network and is extremely simple to implement; it just needs a few calls to the standard gradient operator. We apply this method to a couple of image models, a couple of text models and a chemistry model, demonstrating its ability to debug networks, to extract rules from a network, and to enable users to engage with models better.
ISSN:2331-8422