A Survey of Methods for Explaining Black Box Models

Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, Dino Pedreschi

ACM Computing Surveys 51(5), 42 pages, article 93, August 2018
Association for Computing Machinery, New York, NY, USA

In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.

(keywords) interpretability, explanations, Open the black box, transparent models
address = {New York, NY, USA},
articleno = 93,
author = {Guidotti, Riccardo and Monreale, Anna and Ruggieri, Salvatore and Turini, Franco and Giannotti, Fosca and Pedreschi, Dino},
doi = {10.1145/3236009},
issn = {0360-0300},
issue_date = {September 2019},
journal = {ACM Comput. Surv.},
keywords = {interpretability, explanations, Open the black box, transparent models},
month = aug,
number = 5,
numpages = 42,
publisher = {Association for Computing Machinery},
title = {A Survey of Methods for Explaining Black Box Models},
url = {https://doi.org/10.1145/3236009},
volume = 51,
year = 2018

Journals & Series

Partita IVA: 01131710376 - Copyright © 2008-2022 APICe@DISI Research Group - PRIVACY