From explanations to feature selection: assessing SHAP values as feature selection mechanism
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/SIBGRAPI51738.2020.00053 http://hdl.handle.net/11449/210335 |
Resumo: | Explainability has become one of the most discussed topics in machine learning research in recent years, and although a lot of methodologies that try to provide explanations to black-box models have been proposed to address such an issue, little discussion has been made on the pre-processing steps involving the pipeline of development of machine learning solutions, such as feature selection. In this work, we evaluate a game-theoretic approach used to explain the output of any machine learning model, SHAP, as a feature selection mechanism. In the experiments, we show that besides being able to explain the decisions of a model, it achieves better results than three commonly used feature selection algorithms. |
id |
UNSP_89baa9f1e570613780d6b909626c5bdd |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/210335 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
From explanations to feature selection: assessing SHAP values as feature selection mechanismExplainability has become one of the most discussed topics in machine learning research in recent years, and although a lot of methodologies that try to provide explanations to black-box models have been proposed to address such an issue, little discussion has been made on the pre-processing steps involving the pipeline of development of machine learning solutions, such as feature selection. In this work, we evaluate a game-theoretic approach used to explain the output of any machine learning model, SHAP, as a feature selection mechanism. In the experiments, we show that besides being able to explain the decisions of a model, it achieves better results than three commonly used feature selection algorithms.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Fundacao de Amparo a Pesquisa do Estudo de Sao Paulo grantSao Paulo State Univ, Dept Math & Comp Sci, Presidente Prudente, SP, BrazilSao Paulo State Univ, Dept Math & Comp Sci, Presidente Prudente, SP, BrazilCAPES: 88887.487331/2020-00Fundacao de Amparo a Pesquisa do Estudo de Sao Paulo grant: 2018/17881-3IeeeUniversidade Estadual Paulista (Unesp)Marcilio Jr, Wilson E. [UNESP]Eler, Danilo M. [UNESP]IEEE2021-06-25T15:05:15Z2021-06-25T15:05:15Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject340-347http://dx.doi.org/10.1109/SIBGRAPI51738.2020.000532020 33rd Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi 2020). New York: Ieee, p. 340-347, 2020.1530-1834http://hdl.handle.net/11449/21033510.1109/SIBGRAPI51738.2020.00053WOS:000651203300045Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2020 33rd Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi 2020)info:eu-repo/semantics/openAccess2024-06-19T14:32:27Zoai:repositorio.unesp.br:11449/210335Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-06T00:04:01.100735Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
From explanations to feature selection: assessing SHAP values as feature selection mechanism |
title |
From explanations to feature selection: assessing SHAP values as feature selection mechanism |
spellingShingle |
From explanations to feature selection: assessing SHAP values as feature selection mechanism Marcilio Jr, Wilson E. [UNESP] |
title_short |
From explanations to feature selection: assessing SHAP values as feature selection mechanism |
title_full |
From explanations to feature selection: assessing SHAP values as feature selection mechanism |
title_fullStr |
From explanations to feature selection: assessing SHAP values as feature selection mechanism |
title_full_unstemmed |
From explanations to feature selection: assessing SHAP values as feature selection mechanism |
title_sort |
From explanations to feature selection: assessing SHAP values as feature selection mechanism |
author |
Marcilio Jr, Wilson E. [UNESP] |
author_facet |
Marcilio Jr, Wilson E. [UNESP] Eler, Danilo M. [UNESP] IEEE |
author_role |
author |
author2 |
Eler, Danilo M. [UNESP] IEEE |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Marcilio Jr, Wilson E. [UNESP] Eler, Danilo M. [UNESP] IEEE |
description |
Explainability has become one of the most discussed topics in machine learning research in recent years, and although a lot of methodologies that try to provide explanations to black-box models have been proposed to address such an issue, little discussion has been made on the pre-processing steps involving the pipeline of development of machine learning solutions, such as feature selection. In this work, we evaluate a game-theoretic approach used to explain the output of any machine learning model, SHAP, as a feature selection mechanism. In the experiments, we show that besides being able to explain the decisions of a model, it achieves better results than three commonly used feature selection algorithms. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 2021-06-25T15:05:15Z 2021-06-25T15:05:15Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/SIBGRAPI51738.2020.00053 2020 33rd Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi 2020). New York: Ieee, p. 340-347, 2020. 1530-1834 http://hdl.handle.net/11449/210335 10.1109/SIBGRAPI51738.2020.00053 WOS:000651203300045 |
url |
http://dx.doi.org/10.1109/SIBGRAPI51738.2020.00053 http://hdl.handle.net/11449/210335 |
identifier_str_mv |
2020 33rd Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi 2020). New York: Ieee, p. 340-347, 2020. 1530-1834 10.1109/SIBGRAPI51738.2020.00053 WOS:000651203300045 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2020 33rd Sibgrapi Conference On Graphics, Patterns And Images (sibgrapi 2020) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
340-347 |
dc.publisher.none.fl_str_mv |
Ieee |
publisher.none.fl_str_mv |
Ieee |
dc.source.none.fl_str_mv |
Web of Science reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808129579307499520 |