Abstract. We present a Bayesian variational inference scheme for semi- supervised clustering in which data is supplemented with side information in the form of common labels. There is no mutual exclusion of classes assumption and samples are represented as a combinatorial mixture over multiple clusters. We illustrate performance on six datasets and ¯nd a positive comparison against constrained K-means clustering.
|Translated title of the contribution||A Variational Approach to Semi-Supervised Clustering|
|Title of host publication||ESANN|
|Pages||11 - 16|
|Number of pages||5|
|Publication status||Published - 2009|
Bibliographical noteName and Venue of Event: ESANN2009, Bruges Belgium
Conference Proceedings/Title of Journal: Proceedings ESANN2009