The Projective Clustering Ensemble (PCE) problem is a recent clustering advance aimed at combining the two powerful tools of clustering ensembles and projective clustering. PCE has been formalized as either a two-objective or a single-objective optimization problem. Two-objective PCE has been recognized as more accurate than its single-objective counterpart, although it is unable to jointly handle the object-based and feature-based cluster representations. In this paper, we push forward the current PCE research, aiming to overcome the limitations of all existing PCE formulations. We propose a novel single-objective PCE formulation so that (i) the object-based and feature-based cluster representations are jointly considered, and (ii) the resulting optimization strategy follows a metacluster-based methodology borrowed from traditional clustering ensembles. As a result, the proposed formulation features best suitability to the PCE problem, thus guaranteeing improved effectiveness. Experiments on benchmark datasets have shown how the proposed approach achieves better average accuracy than all existing PCE methods, as well as efficiency superior to the most accurate existing metacluster-based PCE method on larger datasets.

Metacluster-based Projective Clustering Ensembles

TAGARELLI, Andrea
2015

Abstract

The Projective Clustering Ensemble (PCE) problem is a recent clustering advance aimed at combining the two powerful tools of clustering ensembles and projective clustering. PCE has been formalized as either a two-objective or a single-objective optimization problem. Two-objective PCE has been recognized as more accurate than its single-objective counterpart, although it is unable to jointly handle the object-based and feature-based cluster representations. In this paper, we push forward the current PCE research, aiming to overcome the limitations of all existing PCE formulations. We propose a novel single-objective PCE formulation so that (i) the object-based and feature-based cluster representations are jointly considered, and (ii) the resulting optimization strategy follows a metacluster-based methodology borrowed from traditional clustering ensembles. As a result, the proposed formulation features best suitability to the PCE problem, thus guaranteeing improved effectiveness. Experiments on benchmark datasets have shown how the proposed approach achieves better average accuracy than all existing PCE methods, as well as efficiency superior to the most accurate existing metacluster-based PCE method on larger datasets.
clustering ensembles; projective clustering; dimensionality reduction
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: http://hdl.handle.net/20.500.11770/136271
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 12
social impact