Parameter-free ensemble clustering with dynamic weighting mechanism

Ensemble clustering (EC) gains more and more attention because it can improve the effectiveness and robustness of single clustering methods. A popular ensemble approach is to construct a co-association matrix which represents the possibility that the sample pair is divided into different clusters by base clusterings. Then, some single clustering methods could be performed on it. However, this approach separates the construction of the co-association matrix from the generation of clustering results. Besides, the importance of base clusterings and clusters are often regarded as the same but their performance or quality is different actually. Although some weighted ensemble clustering methods have been proposed, typically, the weights are calculated based on certain criteria and then fixed. To cope with these issues, we propose a Parameter-Free Ensemble Clustering (PFEC) with dynamic weighting mechanism, which is capable of dynamically adjusting the weights of base clusterings and clusters. Firstly, the self-weighted framework is applied in our method to weight base clusterings automatically. Furthermore, an additional weight is assigned to each cluster in the base clustering, which can also be dynamically adjusted. This can help alleviate the issue of imbalanced clusters as well. Finally, a structured affinity graph is learned from the results of base clusterings through rank constraint and no post-processing is required. The experimental results on synthetic and real datasets illustrate the effectiveness of our proposed method.