Spectral ensemble clustering from graph reconstruction with auto-weighted cluster

Abstract

Ensemble clustering (EC) integrates the base clusterings into a consensus result, which is more robust and effective. A common approach involves constructing a co-association (CA) matrix, and then some individual algorithms are applied to it. However, this approach does not account for the variations in quality across different base clusterings and clusters. Although some weighted ensemble clustering approaches have been introduced, their assigned weights remain fixed once they are determined according to specific principles. Additionally, this method isolates the process of building the co-association matrix from the generation of clustering outcomes. To address these issues, we propose a novel clustering algorithm that adaptively adjust cluster weights. In our method, we define a novel weighted CA matrix and apply a self-weighting framework to automatically assign weights to clusters. Then, the construction of the consensus graph and spectral clustering are integrated into a single framework. Finally, an effective optimization algorithm, the coordinate descent method, is used to directly produce a discrete label matrix. The effectiveness of the proposed approach is validated through experiments on both synthetic and real-world datasets.