Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers

Data-driven classification algorithms have proven highly effective in a range of complex tasks. However, their output is sometimes questioned, as the reasoning behind it may remain unclear due to a high number of poorly interpretable parameters used during training. Evidence-based (factual) explanat...

ver descrição completa

Detalhes bibliográficos
Autores: Stepin, Ilia, Alonso Moral, José María, Catalá Bolós, Alejandro, Pereira Fariña, Martín
Formato: capítulo de livro
Fecha de publicación:2020
País:España
Recursos:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:minerva.usc.gal:10347/42577
Acesso em linha:https://hdl.handle.net/10347/42577
Access Level:acceso abierto
id ES_ad85ebfc79351a2e08f7a6df9031e4e9
oai_identifier_str oai:minerva.usc.gal:10347/42577
network_acronym_str ES
network_name_str España
repository_id_str
spelling Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiersStepin, IliaAlonso Moral, José MaríaCatalá Bolós, AlejandroPereira Fariña, MartínData-driven classification algorithms have proven highly effective in a range of complex tasks. However, their output is sometimes questioned, as the reasoning behind it may remain unclear due to a high number of poorly interpretable parameters used during training. Evidence-based (factual) explanations for single classifications answer the question why a particular class is selected in terms of the given observations. On the contrary, counterfactual explanations pay attention to why the rest of classes are not selected. Accordingly, we hypothesize that providing classifiers with a combination of both factual and counterfactual explanations is likely to make them more trustworthy. In order to investigate how such explanations can be produced, we introduce a new method to generate factual and counterfactual explanations for the output of pretrained decision trees and fuzzy rule-based classifiers. Experimental results show that unification of factual and counterfactual explanations under the paradigm of fuzzy inference systems proves promising for explaining the reasoning of classification algorithms.IEEEUniversidade de Santiago de Compostela. Departamento de Electrónica e Computación20202020-01-0120202020-01-01book parthttp://purl.org/coar/resource_type/c_3248AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/bookPartapplication/pdfhttps://hdl.handle.net/10347/42577reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostelainstname:Universidad de Santiago de Compostela (USC)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 RTI2018-099646-B-I00 MODELOS, TECNICAS Y METODOLOGIAS BASADAS EN LA INTELIGENCIA ARTIFICIAL PARA LA MEJORA DE LA ADHERENCIA TERAPEUTICAAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-84796-C2-1-R APORTANDO INTELIGENCIA A LOS PROCESOS DE NEGOCIO MEDIANTE SOFT COMPUTING EN ESCENARIOS DE DATOS MASIVOSopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:minerva.usc.gal:10347/425772026-06-15T12:47:27Z
dc.title.none.fl_str_mv Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
title Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
spellingShingle Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
Stepin, Ilia
title_short Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
title_full Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
title_fullStr Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
title_full_unstemmed Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
title_sort Generation and evaluation of factual and counterfactual explanations for decision trees and fuzzy rule-based classifiers
dc.creator.none.fl_str_mv Stepin, Ilia
Alonso Moral, José María
Catalá Bolós, Alejandro
Pereira Fariña, Martín
author Stepin, Ilia
author_facet Stepin, Ilia
Alonso Moral, José María
Catalá Bolós, Alejandro
Pereira Fariña, Martín
author_role author
author2 Alonso Moral, José María
Catalá Bolós, Alejandro
Pereira Fariña, Martín
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade de Santiago de Compostela. Departamento de Electrónica e Computación
description Data-driven classification algorithms have proven highly effective in a range of complex tasks. However, their output is sometimes questioned, as the reasoning behind it may remain unclear due to a high number of poorly interpretable parameters used during training. Evidence-based (factual) explanations for single classifications answer the question why a particular class is selected in terms of the given observations. On the contrary, counterfactual explanations pay attention to why the rest of classes are not selected. Accordingly, we hypothesize that providing classifiers with a combination of both factual and counterfactual explanations is likely to make them more trustworthy. In order to investigate how such explanations can be produced, we introduce a new method to generate factual and counterfactual explanations for the output of pretrained decision trees and fuzzy rule-based classifiers. Experimental results show that unification of factual and counterfactual explanations under the paradigm of fuzzy inference systems proves promising for explaining the reasoning of classification algorithms.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020-01-01
2020
2020-01-01
dc.type.none.fl_str_mv book part
http://purl.org/coar/resource_type/c_3248
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/bookPart
format bookPart
dc.identifier.none.fl_str_mv https://hdl.handle.net/10347/42577
url https://hdl.handle.net/10347/42577
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 RTI2018-099646-B-I00 MODELOS, TECNICAS Y METODOLOGIAS BASADAS EN LA INTELIGENCIA ARTIFICIAL PARA LA MEJORA DE LA ADHERENCIA TERAPEUTICA
Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-84796-C2-1-R APORTANDO INTELIGENCIA A LOS PROCESOS DE NEGOCIO MEDIANTE SOFT COMPUTING EN ESCENARIOS DE DATOS MASIVOS
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv IEEE
publisher.none.fl_str_mv IEEE
dc.source.none.fl_str_mv reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
instname:Universidad de Santiago de Compostela (USC)
instname_str Universidad de Santiago de Compostela (USC)
reponame_str Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
collection Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416464836984832
score 15.811543

Registos relacionados