A rank-based framework through manifold learning for improved clustering tasks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.ins.2021.08.080 http://hdl.handle.net/11449/229448 |
Resumo: | The relevance of diversified data preprocessing approaches for improving clustering tasks is remarkable. Once the effectiveness is direct impacted by feature representation and similarity definition, considerable attention from the research community has been drawn to this direction. More recently, rank-based manifold learning methods have been successfully explored in unsupervised similarity learning for retrieval scenarios. Such methods consider the underlying dataset manifold to compute a new similarity measure, which increases the separability of data from distinct classes. In this paper, a rank-based framework for clustering tasks is proposed based on contemporary manifold learning methods. A flexible model is employed, where ranking structures are the representation of similarity information among data samples. Subsequently, is made the exploration of unsupervised similarity learning. It is also possible to compute more effective similarity measures and clustering results. To assess the effectiveness of the proposed framework was conducted a comprehensive experimental evaluation. The tests involved various public image datasets, considering different manifold learning and clustering methods. The quantitative experiments take into consideration comparisons with traditional and recent state-of-the-art clustering approaches. |
id |
UNSP_b2ff56b9f43abb3af8d366803576c9d5 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/229448 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A rank-based framework through manifold learning for improved clustering tasksClusteringManifold learningRankingSimilarity learningThe relevance of diversified data preprocessing approaches for improving clustering tasks is remarkable. Once the effectiveness is direct impacted by feature representation and similarity definition, considerable attention from the research community has been drawn to this direction. More recently, rank-based manifold learning methods have been successfully explored in unsupervised similarity learning for retrieval scenarios. Such methods consider the underlying dataset manifold to compute a new similarity measure, which increases the separability of data from distinct classes. In this paper, a rank-based framework for clustering tasks is proposed based on contemporary manifold learning methods. A flexible model is employed, where ranking structures are the representation of similarity information among data samples. Subsequently, is made the exploration of unsupervised similarity learning. It is also possible to compute more effective similarity measures and clustering results. To assess the effectiveness of the proposed framework was conducted a comprehensive experimental evaluation. The tests involved various public image datasets, considering different manifold learning and clustering methods. The quantitative experiments take into consideration comparisons with traditional and recent state-of-the-art clustering approaches.Department of Statistics Applied Mathematics and Computing (DEMAC) São Paulo State University (UNESP)Department of Statistics Applied Mathematics and Computing (DEMAC) São Paulo State University (UNESP)Universidade Estadual Paulista (UNESP)Rozin, Bionda [UNESP]Pereira-Ferrero, Vanessa Helena [UNESP]Lopes, Leonardo Tadeu [UNESP]Guimarães Pedronette, Daniel Carlos [UNESP]2022-04-29T08:32:36Z2022-04-29T08:32:36Z2021-11-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article202-220http://dx.doi.org/10.1016/j.ins.2021.08.080Information Sciences, v. 580, p. 202-220.0020-0255http://hdl.handle.net/11449/22944810.1016/j.ins.2021.08.0802-s2.0-85114150489Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengInformation Sciencesinfo:eu-repo/semantics/openAccess2022-04-29T08:32:36Zoai:repositorio.unesp.br:11449/229448Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T22:05:10.855275Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A rank-based framework through manifold learning for improved clustering tasks |
title |
A rank-based framework through manifold learning for improved clustering tasks |
spellingShingle |
A rank-based framework through manifold learning for improved clustering tasks Rozin, Bionda [UNESP] Clustering Manifold learning Ranking Similarity learning |
title_short |
A rank-based framework through manifold learning for improved clustering tasks |
title_full |
A rank-based framework through manifold learning for improved clustering tasks |
title_fullStr |
A rank-based framework through manifold learning for improved clustering tasks |
title_full_unstemmed |
A rank-based framework through manifold learning for improved clustering tasks |
title_sort |
A rank-based framework through manifold learning for improved clustering tasks |
author |
Rozin, Bionda [UNESP] |
author_facet |
Rozin, Bionda [UNESP] Pereira-Ferrero, Vanessa Helena [UNESP] Lopes, Leonardo Tadeu [UNESP] Guimarães Pedronette, Daniel Carlos [UNESP] |
author_role |
author |
author2 |
Pereira-Ferrero, Vanessa Helena [UNESP] Lopes, Leonardo Tadeu [UNESP] Guimarães Pedronette, Daniel Carlos [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Rozin, Bionda [UNESP] Pereira-Ferrero, Vanessa Helena [UNESP] Lopes, Leonardo Tadeu [UNESP] Guimarães Pedronette, Daniel Carlos [UNESP] |
dc.subject.por.fl_str_mv |
Clustering Manifold learning Ranking Similarity learning |
topic |
Clustering Manifold learning Ranking Similarity learning |
description |
The relevance of diversified data preprocessing approaches for improving clustering tasks is remarkable. Once the effectiveness is direct impacted by feature representation and similarity definition, considerable attention from the research community has been drawn to this direction. More recently, rank-based manifold learning methods have been successfully explored in unsupervised similarity learning for retrieval scenarios. Such methods consider the underlying dataset manifold to compute a new similarity measure, which increases the separability of data from distinct classes. In this paper, a rank-based framework for clustering tasks is proposed based on contemporary manifold learning methods. A flexible model is employed, where ranking structures are the representation of similarity information among data samples. Subsequently, is made the exploration of unsupervised similarity learning. It is also possible to compute more effective similarity measures and clustering results. To assess the effectiveness of the proposed framework was conducted a comprehensive experimental evaluation. The tests involved various public image datasets, considering different manifold learning and clustering methods. The quantitative experiments take into consideration comparisons with traditional and recent state-of-the-art clustering approaches. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-11-01 2022-04-29T08:32:36Z 2022-04-29T08:32:36Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.ins.2021.08.080 Information Sciences, v. 580, p. 202-220. 0020-0255 http://hdl.handle.net/11449/229448 10.1016/j.ins.2021.08.080 2-s2.0-85114150489 |
url |
http://dx.doi.org/10.1016/j.ins.2021.08.080 http://hdl.handle.net/11449/229448 |
identifier_str_mv |
Information Sciences, v. 580, p. 202-220. 0020-0255 10.1016/j.ins.2021.08.080 2-s2.0-85114150489 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Information Sciences |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
202-220 |
dc.source.none.fl_str_mv |
Scopus 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_ |
1808129390916141056 |