Skip to Main Content
Clustering-combination methods have received considerable attentions in recent years, and many ensemble-based clustering methods have been introduced. However, clustering-combination techniques have been limited to ??flat?? clustering combination, and the combination of hierarchical clusterings has yet to be addressed. In this paper, we address and formalize the concept of hierarchical-clustering combination and introduce an algorithmic framework in which multiple hierarchical clusterings could be easily combined. In this framework, the similarity-based description matrices of input hierarchical clusterings are aggregated into a transitive consensus matrix in which the final hierarchy could be formed. Empirical evaluation, by using popular available datasets, confirms the superiority of combined hierarchical clustering introduced by our method over the standard (single) hierarchical-clustering methods.