A Novel Method to Control the Diversity in Cluster Ensembles

Clustering is fundamental to understand the structure of data. In the past decade the cluster ensemble problem has been introduced, which combines a set of partitions (an ensemble) of the data to obtain a single consensus solution that outperforms all the ensemble members. Although disagreement amon...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pividori, Milton, Stegmayer, Georgina, Milone, Diego H.
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2013
Materias:	Ciencias Informáticas consensus clustering ensemble diversity cluster ensemble generation
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/76220 http://42jaiio.sadio.org.ar/proceedings/simposios/Trabajos/ASAI/11.pdf
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-76220
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas consensus clustering ensemble diversity cluster ensemble generation
spellingShingle	Ciencias Informáticas consensus clustering ensemble diversity cluster ensemble generation Pividori, Milton Stegmayer, Georgina Milone, Diego H. A Novel Method to Control the Diversity in Cluster Ensembles
topic_facet	Ciencias Informáticas consensus clustering ensemble diversity cluster ensemble generation
description	Clustering is fundamental to understand the structure of data. In the past decade the cluster ensemble problem has been introduced, which combines a set of partitions (an ensemble) of the data to obtain a single consensus solution that outperforms all the ensemble members. Although disagreement among ensemble partitions (diversity) has been found to be fundamental for success, the literature has arrived to confusing conclusions: some authors suggest that high diversity is beneficial for the final performance, whereas others have indicated that medium is better. While there are several options to measure the diversity, there is no method to control it. This paper introduces a new ensemble generation strategy and a method to smoothly change the ensemble diversity. Experimental results on three datasets suggest that this is an important step towards a more systematic approach to analyze the impact of the ensemble diversity on the overall consensus performance.
format	Objeto de conferencia Objeto de conferencia
author	Pividori, Milton Stegmayer, Georgina Milone, Diego H.
author_facet	Pividori, Milton Stegmayer, Georgina Milone, Diego H.
author_sort	Pividori, Milton
title	A Novel Method to Control the Diversity in Cluster Ensembles
title_short	A Novel Method to Control the Diversity in Cluster Ensembles
title_full	A Novel Method to Control the Diversity in Cluster Ensembles
title_fullStr	A Novel Method to Control the Diversity in Cluster Ensembles
title_full_unstemmed	A Novel Method to Control the Diversity in Cluster Ensembles
title_sort	novel method to control the diversity in cluster ensembles
publishDate	2013
url	http://sedici.unlp.edu.ar/handle/10915/76220 http://42jaiio.sadio.org.ar/proceedings/simposios/Trabajos/ASAI/11.pdf
work_keys_str_mv	AT pividorimilton anovelmethodtocontrolthediversityinclusterensembles AT stegmayergeorgina anovelmethodtocontrolthediversityinclusterensembles AT milonediegoh anovelmethodtocontrolthediversityinclusterensembles AT pividorimilton novelmethodtocontrolthediversityinclusterensembles AT stegmayergeorgina novelmethodtocontrolthediversityinclusterensembles AT milonediegoh novelmethodtocontrolthediversityinclusterensembles
bdutipo_str	Repositorios
_version_	1764820487928545280

A Novel Method to Control the Diversity in Cluster Ensembles

Ejemplares similares