Benchmarking and Survey of Explanation Methods for Black Box Models
Artificial Intelligence
2021-02-26 v1 Computers and Society
Machine Learning
Abstract
The widespread adoption of black-box models in Artificial Intelligence has enhanced the need for explanation methods to reveal how these obscure models reach specific decisions. Retrieving explanations is fundamental to unveil possible biases and to resolve practical or ethical issues. Nowadays, the literature is full of methods with different explanations. We provide a categorization of explanation methods based on the type of explanation returned. We present the most recent and widely used explainers, and we show a visual comparison among explanations and a quantitative benchmarking.
Keywords
Cite
@article{arxiv.2102.13076,
title = {Benchmarking and Survey of Explanation Methods for Black Box Models},
author = {Francesco Bodria and Fosca Giannotti and Riccardo Guidotti and Francesca Naretto and Dino Pedreschi and Salvatore Rinzivillo},
journal= {arXiv preprint arXiv:2102.13076},
year = {2021}
}
Comments
This work is currently under review on an international journal