filename     : Anc19c.pdf
entry        : article
conference   : 
pages        : 169--191
year         : 2019
month        : 
title        : Gradient-Based Attribution Methods
subtitle     : 
author       : Marco Ancona, Enea Ceolini, Cengiz Öztireli, Markus Gross
booktitle    : Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
ISSN/ISBN    : 978-3-030-28954-6
editor       : Samek, Wojciech
publisher    : Springer International Publishing
publ.place   :
volume       :
issue        :
language     : 
keywords     : 
abstract     :  The problem of explaining complex machine learning models, including Deep Neural Networks, has gained increasing attention over the last few years. While several methods have been proposed to explain network predictions, the definition itself of explanation is still debated. Moreover, only a few attempts to compare explanation methods from a theoretical perspective has been done. In this chapter, we discuss the theoretical properties of several attribution methods and show how they share the same idea of using the gradient information as a descriptive factor for the functioning of a model. Finally, we discuss the strengths and limitations of these methods and compare them with available alternatives.