Using parallel pivot vs. clustering-based techniques for web engines

Autores
Gil Costa, Graciela Verónica; Printista, Alicia Marcela
Año de publicación
2007
Idioma
inglés
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
Web Engines are a useful tool for searching information in the Web. But a great part of this information is non-textual and for that case a metric space is used. A metric space is a set where a notion of distance (called a metric) between elements of the set is defined. In this paper we present an efficient parallelization of a pivot-based method devised for this purpose which is called the Sparse Spatial Selection (SSS) strategy and we compare it with a clustering-based method, a parallel implementation of the Spatial Approximation Tree (SAT). We show that SAT compares favourably against the pivot data structures SSS. The experimental results were obtained on a highperformance cluster and using several metric spaces, that shows load balance parallel strategies for the SAT. The implementations are built upon the BSP parallel computing model, which shows efficient performance for this application domain and allows a precise evaluation of algorithms.
VIII Workshop de Procesamiento Distribuido y Paralelo
Red de Universidades con Carreras en Informática (RedUNCI)
Materia
Ciencias Informáticas
Informática
Clustering
Search process
Parallel algorithms
metric spaces
parallel search
distance computations
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/22974

id SEDICI_1d4a418174eb329df2cca53e510a4db6
oai_identifier_str oai:sedici.unlp.edu.ar:10915/22974
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Using parallel pivot vs. clustering-based techniques for web enginesGil Costa, Graciela VerónicaPrintista, Alicia MarcelaCiencias InformáticasInformáticaClusteringSearch processParallel algorithmsmetric spacesparallel searchdistance computationsWeb Engines are a useful tool for searching information in the Web. But a great part of this information is non-textual and for that case a metric space is used. A metric space is a set where a notion of distance (called a metric) between elements of the set is defined. In this paper we present an efficient parallelization of a pivot-based method devised for this purpose which is called the Sparse Spatial Selection (SSS) strategy and we compare it with a clustering-based method, a parallel implementation of the Spatial Approximation Tree (SAT). We show that SAT compares favourably against the pivot data structures SSS. The experimental results were obtained on a highperformance cluster and using several metric spaces, that shows load balance parallel strategies for the SAT. The implementations are built upon the BSP parallel computing model, which shows efficient performance for this application domain and allows a precise evaluation of algorithms.VIII Workshop de Procesamiento Distribuido y ParaleloRed de Universidades con Carreras en Informática (RedUNCI)2007-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf1310-1322http://sedici.unlp.edu.ar/handle/10915/22974enginfo:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/2.5/ar/Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T10:55:16Zoai:sedici.unlp.edu.ar:10915/22974Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 10:55:16.96SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Using parallel pivot vs. clustering-based techniques for web engines
title Using parallel pivot vs. clustering-based techniques for web engines
spellingShingle Using parallel pivot vs. clustering-based techniques for web engines
Gil Costa, Graciela Verónica
Ciencias Informáticas
Informática
Clustering
Search process
Parallel algorithms
metric spaces
parallel search
distance computations
title_short Using parallel pivot vs. clustering-based techniques for web engines
title_full Using parallel pivot vs. clustering-based techniques for web engines
title_fullStr Using parallel pivot vs. clustering-based techniques for web engines
title_full_unstemmed Using parallel pivot vs. clustering-based techniques for web engines
title_sort Using parallel pivot vs. clustering-based techniques for web engines
dc.creator.none.fl_str_mv Gil Costa, Graciela Verónica
Printista, Alicia Marcela
author Gil Costa, Graciela Verónica
author_facet Gil Costa, Graciela Verónica
Printista, Alicia Marcela
author_role author
author2 Printista, Alicia Marcela
author2_role author
dc.subject.none.fl_str_mv Ciencias Informáticas
Informática
Clustering
Search process
Parallel algorithms
metric spaces
parallel search
distance computations
topic Ciencias Informáticas
Informática
Clustering
Search process
Parallel algorithms
metric spaces
parallel search
distance computations
dc.description.none.fl_txt_mv Web Engines are a useful tool for searching information in the Web. But a great part of this information is non-textual and for that case a metric space is used. A metric space is a set where a notion of distance (called a metric) between elements of the set is defined. In this paper we present an efficient parallelization of a pivot-based method devised for this purpose which is called the Sparse Spatial Selection (SSS) strategy and we compare it with a clustering-based method, a parallel implementation of the Spatial Approximation Tree (SAT). We show that SAT compares favourably against the pivot data structures SSS. The experimental results were obtained on a highperformance cluster and using several metric spaces, that shows load balance parallel strategies for the SAT. The implementations are built upon the BSP parallel computing model, which shows efficient performance for this application domain and allows a precise evaluation of algorithms.
VIII Workshop de Procesamiento Distribuido y Paralelo
Red de Universidades con Carreras en Informática (RedUNCI)
description Web Engines are a useful tool for searching information in the Web. But a great part of this information is non-textual and for that case a metric space is used. A metric space is a set where a notion of distance (called a metric) between elements of the set is defined. In this paper we present an efficient parallelization of a pivot-based method devised for this purpose which is called the Sparse Spatial Selection (SSS) strategy and we compare it with a clustering-based method, a parallel implementation of the Spatial Approximation Tree (SAT). We show that SAT compares favourably against the pivot data structures SSS. The experimental results were obtained on a highperformance cluster and using several metric spaces, that shows load balance parallel strategies for the SAT. The implementations are built upon the BSP parallel computing model, which shows efficient performance for this application domain and allows a precise evaluation of algorithms.
publishDate 2007
dc.date.none.fl_str_mv 2007-10
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/22974
url http://sedici.unlp.edu.ar/handle/10915/22974
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)
dc.format.none.fl_str_mv application/pdf
1310-1322
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844615811440836608
score 13.070432