Multiview Consensus Graph Clustering

• Published in: IEEE transactions on image processing Vol. 28; no. 3; pp. 1261 - 1270
• Main Authors: Zhan, Kun, Nie, Feiping, Wang, Jing, Yang, Yi
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-03-2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Affinity; Algorithms; Clustering; Clustering algorithms; Coding; Data points; Eigenvalues and eigenfunctions; graph learning; image retrieval; Iterative methods; Kernel; Laplace equations; Learning systems; Linear programming; multiview clustering; Periodic structures; Post-processing; Unsupervised learning
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2018.2877335

A graph is usually formed to reveal the relationship between data points and graph structure is encoded by the affinity matrix. Most graph-based multiview clustering methods use predefined affinity matrices and the clustering performance highly depends on the quality of graph. We learn a consensus graph with minimizing disagreement between different views and constraining the rank of the Laplacian matrix. Since diverse views admit the same underlying cluster structure across multiple views, we use a new disagreement cost function for regularizing graphs from different views toward a common consensus. Simultaneously, we impose a rank constraint on the Laplacian matrix to learn the consensus graph with exactly k connected components where k is the number of clusters, which is different from using fixed affinity matrices in most existing graph-based methods. With the learned consensus graph, we can directly obtain the cluster labels without performing any post-processing, such as kmeans clustering algorithm in spectral clustering-based methods. A multiview consensus clustering method is proposed to learn such a graph. An efficient iterative updating algorithm is derived to optimize the proposed challenging optimization problem. Experiments on several benchmark datasets have demonstrated the effectiveness of the proposed method in terms of seven metrics.