We address one of the main open issues about the use of diversity in multiple classifier systems: the effectiveness of the explicit use of diversity measures for creation of classifier ensembles. So far, diver- sity measures have been mostly used for ensemble pruning, namely, for selecting a subset of classifiers out of an original, larger ensemble. Here we focus on pruning techniques based on forward/backward selection, since they allow a direct comparison with the simple estimation of accu- racy of classifier ensemble. We empirically carry out this comparison for several diversity measures and benchmark data sets, using bagging as the ensemble construction technique, and majority voting as the fusion rule. Our results provide further and more direct evidence to previous observations against the effectiveness of the use of diversity measures for ensemble pruning, but also show that, combined with ensemble accuracy estimated on a validation set, diversity can have a regularization effect when the validation set size is small.

An empirical investigation on the use of diversity for creation of classifier ensembles

AHMED, MUHAMMAD ATTA OTHMAN;DIDACI, LUCA;FUMERA, GIORGIO;ROLI, FABIO
2015-01-01

Abstract

We address one of the main open issues about the use of diversity in multiple classifier systems: the effectiveness of the explicit use of diversity measures for creation of classifier ensembles. So far, diver- sity measures have been mostly used for ensemble pruning, namely, for selecting a subset of classifiers out of an original, larger ensemble. Here we focus on pruning techniques based on forward/backward selection, since they allow a direct comparison with the simple estimation of accu- racy of classifier ensemble. We empirically carry out this comparison for several diversity measures and benchmark data sets, using bagging as the ensemble construction technique, and majority voting as the fusion rule. Our results provide further and more direct evidence to previous observations against the effectiveness of the use of diversity measures for ensemble pruning, but also show that, combined with ensemble accuracy estimated on a validation set, diversity can have a regularization effect when the validation set size is small.
2015
978-3-319-20247-1
978-3-319-20248-8
Diversity; Ensemble pruning; Forward/backward selection; Ensemble construction
File in questo prodotto:
File Dimensione Formato  
An Empirical Investigation on the Use of Diversity for Creation of Classifier Ensembles.pdf

Solo gestori archivio

Tipologia: versione editoriale
Dimensione 216.76 kB
Formato Adobe PDF
216.76 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11584/127683
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 4
social impact