A hybrid constrained semi-supervised clustering algorithm

A hybrid constrained semi-supervised clustering algorithm(HCC) is proposed, both labeled data and pairwise constraints are concerned in clustering a given dataset to get a better clustering result. This paper gives theoretical derivation and experiments on UCI data sets, and the experiments show that the quality of clustering using two kinds of constraint information is better than only one kind of labeled data information. Additionally, HCC is more stable than other algorithms such as CCL and SAP.