Copying Machine Learning Classifiers

We study copying of machine learning classifiers, an agnostic technique to replicate the decision behavior of any classifier. We develop the theory behind the problem of copying, highlighting its properties, and propose a framework to copy the decision behavior of any classifier using no prior knowl...

Descripción completa

Detalles Bibliográficos
Autores: Unceta, Irene, Nin, Jordi, Pujol Vila, Oriol
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2020
País:España
Institución:Universidad de Barcelona
Repositorio:Dipòsit Digital de la UB
OAI Identifier:oai:diposit.ub.edu:2445/178922
Acceso en línea:https://hdl.handle.net/2445/178922
Access Level:acceso abierto
Palabra clave:Aprenentatge automàtic
Models matemàtics
Machine learning
Mathematical models
id ES_021a6d30edf8c93e5a785bbca68da5ad
oai_identifier_str oai:diposit.ub.edu:2445/178922
network_acronym_str ES
network_name_str España
repository_id_str
spelling Copying Machine Learning ClassifiersUnceta, IreneNin, JordiPujol Vila, OriolAprenentatge automàticModels matemàticsMachine learningMathematical modelsWe study copying of machine learning classifiers, an agnostic technique to replicate the decision behavior of any classifier. We develop the theory behind the problem of copying, highlighting its properties, and propose a framework to copy the decision behavior of any classifier using no prior knowledge of its parameters or training data distribution. We validate this framework through extensive experiments using data from a series of well-known problems. To further validate this concept, we use three different use cases where desiderata such as interpretability, fairness or productivization constrains need to be addressed. Results show that copies can be exploited to enhance existing solutions and improve them adding new features and characteristics.Institute of Electrical and Electronics Engineers (IEEE)2020info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://hdl.handle.net/2445/178922Articles publicats en revistes (Matemàtiques i Informàtica)reponame:Dipòsit Digital de la UBinstname:Universidad de BarcelonaInglésReproducció del document publicat a: https://doi.org/10.1109/ACCESS.2020.3020638IEEE Access, 2020, vol. 8, p. 160268-160284https://doi.org/10.1109/ACCESS.2020.3020638cc-by (c) Unceta, Irene et al., 2020https://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:diposit.ub.edu:2445/1789222026-05-27T06:46:51Z
dc.title.none.fl_str_mv Copying Machine Learning Classifiers
title Copying Machine Learning Classifiers
spellingShingle Copying Machine Learning Classifiers
Unceta, Irene
Aprenentatge automàtic
Models matemàtics
Machine learning
Mathematical models
title_short Copying Machine Learning Classifiers
title_full Copying Machine Learning Classifiers
title_fullStr Copying Machine Learning Classifiers
title_full_unstemmed Copying Machine Learning Classifiers
title_sort Copying Machine Learning Classifiers
dc.creator.none.fl_str_mv Unceta, Irene
Nin, Jordi
Pujol Vila, Oriol
author Unceta, Irene
author_facet Unceta, Irene
Nin, Jordi
Pujol Vila, Oriol
author_role author
author2 Nin, Jordi
Pujol Vila, Oriol
author2_role author
author
dc.subject.none.fl_str_mv Aprenentatge automàtic
Models matemàtics
Machine learning
Mathematical models
topic Aprenentatge automàtic
Models matemàtics
Machine learning
Mathematical models
description We study copying of machine learning classifiers, an agnostic technique to replicate the decision behavior of any classifier. We develop the theory behind the problem of copying, highlighting its properties, and propose a framework to copy the decision behavior of any classifier using no prior knowledge of its parameters or training data distribution. We validate this framework through extensive experiments using data from a series of well-known problems. To further validate this concept, we use three different use cases where desiderata such as interpretability, fairness or productivization constrains need to be addressed. Results show that copies can be exploited to enhance existing solutions and improve them adding new features and characteristics.
publishDate 2020
dc.date.none.fl_str_mv 2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/2445/178922
url https://hdl.handle.net/2445/178922
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Reproducció del document publicat a: https://doi.org/10.1109/ACCESS.2020.3020638
IEEE Access, 2020, vol. 8, p. 160268-160284
https://doi.org/10.1109/ACCESS.2020.3020638
dc.rights.none.fl_str_mv cc-by (c) Unceta, Irene et al., 2020
https://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv cc-by (c) Unceta, Irene et al., 2020
https://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
dc.source.none.fl_str_mv Articles publicats en revistes (Matemàtiques i Informàtica)
reponame:Dipòsit Digital de la UB
instname:Universidad de Barcelona
instname_str Universidad de Barcelona
reponame_str Dipòsit Digital de la UB
collection Dipòsit Digital de la UB
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869402631065042944
score 15,300719

Similares en LA Referencia