In the last 10 years, semi-supervised clustering (SSC) or clustering with side information has received significant attention from researchers because of its success in many applications like document, image clustering, etc. SSC has been shown to improve the clustering performance substantially with just few constraints or labelled data points as side information which are provided by an expert or an oracle system. Most works have been done so far can be classified into one of two SSC schemes: the a-prior scheme, and the interactive scheme. This survey will cover these two schemes together with the important algorithms in each scheme. Finally, the open issues will also be summarized in the survey.
A Survey of Semi-Supervised Clustering Algorithms: from a priori scheme to interactive scheme and open issues / Battiti, Roberto; Truong, Duy Tin. - ELETTRONICO. - (2013).
A Survey of Semi-Supervised Clustering Algorithms: from a priori scheme to interactive scheme and open issues
Battiti, RobertoUltimo
;Truong, Duy TinPrimo
2013-01-01
Abstract
In the last 10 years, semi-supervised clustering (SSC) or clustering with side information has received significant attention from researchers because of its success in many applications like document, image clustering, etc. SSC has been shown to improve the clustering performance substantially with just few constraints or labelled data points as side information which are provided by an expert or an oracle system. Most works have been done so far can be classified into one of two SSC schemes: the a-prior scheme, and the interactive scheme. This survey will cover these two schemes together with the important algorithms in each scheme. Finally, the open issues will also be summarized in the survey.File | Dimensione | Formato | |
---|---|---|---|
TechnicalReport_SSC.pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
815.2 kB
Formato
Adobe PDF
|
815.2 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione