Dynamic Generation of Subordinate Clusters Based on Bayesian Information Criterion for Must-Link Constrained K-Means

抄録

This paper proposes a constrained K-means clustering method that dynamically generates subordinate clusters based on Bayesian information criterion (BIC). COP K-means, which considers a pairwise constraints in partition-based clustering, have difficulty in handling the case that a must-link is given to instances located far away from each other. To address this problem, the proposed method generates subordinate clusters that have a must-link to a master cluster during a clustering process. The final clustering result is obtained by merging the subordinate clusters. The proposed method determines whether to generate subordinate clusters or not based on the BIC. This paper also introduces an idea of mitigating the sensitivity to initial position of subordinate clusters. The effectiveness of the proposed methods is shown through the experiment with two synthetic datasets.