RaDE: A Rank-based Graph Embedding Approach
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/10.5220/0008985901420152 http://hdl.handle.net/11449/210488 |
Resumo: | Due to possibility of capturing complex relationships existing between nodes, many application benefit of being modeled with graphs. However, performance issues can be observed on large scale networks, making it computationally unfeasible to process information in various scenarios. Graph Embedding methods are usually used for finding low-dimensional vector representations for graphs, preserving its original properties such as topological characteristics, affinity and shared neighborhood between nodes. In this way, retrieval and machine learning techniques can be exploited to execute tasks such as classification, clustering, and link prediction. In this work, we propose RaDE (Rank Diffusion Embedding), an efficient and effective approach that considers rank-based graphs for learning a low-dimensional vector. The proposed approach was evaluated on 7 network datasets such as a social, co-reference, textual and image networks, with different properties. Vector representations generated with RaDE achieved effective results in visualization and retrieval tasks when compared to vector representations generated by other recent related methods. |
id |
UNSP_eb0b517da19c3e304d835f6d1efbee20 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/210488 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
RaDE: A Rank-based Graph Embedding ApproachRaDEGraph EmbeddingNetwork Representation LearningRankingDue to possibility of capturing complex relationships existing between nodes, many application benefit of being modeled with graphs. However, performance issues can be observed on large scale networks, making it computationally unfeasible to process information in various scenarios. Graph Embedding methods are usually used for finding low-dimensional vector representations for graphs, preserving its original properties such as topological characteristics, affinity and shared neighborhood between nodes. In this way, retrieval and machine learning techniques can be exploited to execute tasks such as classification, clustering, and link prediction. In this work, we propose RaDE (Rank Diffusion Embedding), an efficient and effective approach that considers rank-based graphs for learning a low-dimensional vector. The proposed approach was evaluated on 7 network datasets such as a social, co-reference, textual and image networks, with different properties. Vector representations generated with RaDE achieved effective results in visualization and retrieval tasks when compared to vector representations generated by other recent related methods.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)PetrobrasUNESP Sao Paulo State Univ, Inst Geosci & Exact Sci, Rio Claro, SP, BrazilUNESP Sao Paulo State Univ, Inst Geosci & Exact Sci, Rio Claro, SP, BrazilFAPESP: 2017/25908-6FAPESP: 2018/15597-6CNPq: 308194/2017-9Petrobras: 2014/00545-0Petrobras: 2017/00285-6ScitepressUniversidade Estadual Paulista (Unesp)Fernando, Filipe Alves de [UNESP]Guimaraes Pedronette, Daniel Carlos [UNESP]Sousa, Gustavo Jose de [UNESP]Valem, Lucas Pascotti [UNESP]Guilherme, Ivan Rizzo [UNESP]Farinella, G. M.Radeva, P.Braz, J.2021-06-25T17:45:24Z2021-06-25T17:45:24Z2020-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject142-152http://dx.doi.org/10.5220/0008985901420152Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp. Setubal: Scitepress, p. 142-152, 2020.http://hdl.handle.net/11449/21048810.5220/0008985901420152WOS:000576655800014Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visappinfo:eu-repo/semantics/openAccess2021-10-23T20:18:08Zoai:repositorio.unesp.br:11449/210488Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T21:12:40.326738Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
RaDE: A Rank-based Graph Embedding Approach |
title |
RaDE: A Rank-based Graph Embedding Approach |
spellingShingle |
RaDE: A Rank-based Graph Embedding Approach Fernando, Filipe Alves de [UNESP] RaDE Graph Embedding Network Representation Learning Ranking |
title_short |
RaDE: A Rank-based Graph Embedding Approach |
title_full |
RaDE: A Rank-based Graph Embedding Approach |
title_fullStr |
RaDE: A Rank-based Graph Embedding Approach |
title_full_unstemmed |
RaDE: A Rank-based Graph Embedding Approach |
title_sort |
RaDE: A Rank-based Graph Embedding Approach |
author |
Fernando, Filipe Alves de [UNESP] |
author_facet |
Fernando, Filipe Alves de [UNESP] Guimaraes Pedronette, Daniel Carlos [UNESP] Sousa, Gustavo Jose de [UNESP] Valem, Lucas Pascotti [UNESP] Guilherme, Ivan Rizzo [UNESP] Farinella, G. M. Radeva, P. Braz, J. |
author_role |
author |
author2 |
Guimaraes Pedronette, Daniel Carlos [UNESP] Sousa, Gustavo Jose de [UNESP] Valem, Lucas Pascotti [UNESP] Guilherme, Ivan Rizzo [UNESP] Farinella, G. M. Radeva, P. Braz, J. |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Fernando, Filipe Alves de [UNESP] Guimaraes Pedronette, Daniel Carlos [UNESP] Sousa, Gustavo Jose de [UNESP] Valem, Lucas Pascotti [UNESP] Guilherme, Ivan Rizzo [UNESP] Farinella, G. M. Radeva, P. Braz, J. |
dc.subject.por.fl_str_mv |
RaDE Graph Embedding Network Representation Learning Ranking |
topic |
RaDE Graph Embedding Network Representation Learning Ranking |
description |
Due to possibility of capturing complex relationships existing between nodes, many application benefit of being modeled with graphs. However, performance issues can be observed on large scale networks, making it computationally unfeasible to process information in various scenarios. Graph Embedding methods are usually used for finding low-dimensional vector representations for graphs, preserving its original properties such as topological characteristics, affinity and shared neighborhood between nodes. In this way, retrieval and machine learning techniques can be exploited to execute tasks such as classification, clustering, and link prediction. In this work, we propose RaDE (Rank Diffusion Embedding), an efficient and effective approach that considers rank-based graphs for learning a low-dimensional vector. The proposed approach was evaluated on 7 network datasets such as a social, co-reference, textual and image networks, with different properties. Vector representations generated with RaDE achieved effective results in visualization and retrieval tasks when compared to vector representations generated by other recent related methods. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 2021-06-25T17:45:24Z 2021-06-25T17:45:24Z |
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/10.5220/0008985901420152 Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp. Setubal: Scitepress, p. 142-152, 2020. http://hdl.handle.net/11449/210488 10.5220/0008985901420152 WOS:000576655800014 |
url |
http://dx.doi.org/10.5220/0008985901420152 http://hdl.handle.net/11449/210488 |
identifier_str_mv |
Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp. Setubal: Scitepress, p. 142-152, 2020. 10.5220/0008985901420152 WOS:000576655800014 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings Of The 15th International Joint Conference On Computer Vision, Imaging And Computer Graphics Theory And Applications, Vol 5: Visapp |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
142-152 |
dc.publisher.none.fl_str_mv |
Scitepress |
publisher.none.fl_str_mv |
Scitepress |
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_ |
1808129297833000960 |