Weighted clustering ensemble: A review. (April 2022)

• Record Type: Journal Article
• Authors: Zhang, Mimi
• Is Part Of: Pattern recognition. Volume 124(2022)
• Publication Date: 2022-04
• Subjects: Ensemble selection -- Fuzzy clustering -- Labeling correspondence -- Multi-view data -- Temporal data; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108428
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Compile and analyze the state-of-the-art in weighted clustering ensemble research. Provide a unifying framework for weighted clustering ensemble. Identify pros and cons of existing methods, and give suggestions on future research. Abstract: Clustering ensemble, or consensus clustering, has emerged as a powerful tool for improving both the robustness and the stability of results from individual clustering methods. Weighted clustering ensemble arises naturally from clustering ensemble. One of the arguments for weighted clustering ensemble is that elements (clusterings or clusters) in a clustering ensemble are of different quality, or that objects or features are of varying significance. However, it is not possible to directly apply the weighting mechanisms from classification (supervised) domain to clustering (unsupervised) domain, also because clustering is inherently an ill-posed problem. This paper provides an overview of weighted clustering ensemble by discussing different types of weights, major approaches to determining weight values, and applications of weighted clustering ensemble to complex data. The unifying framework presented in this paper will help clustering practitioners select the most appropriate weighting mechanisms for their own problems.