FMvC: Fast Multi-View Clustering

In multi-view clustering, an eigen-decomposition of the Laplacian matrix graph is usually necessary. This leads to a significant increase in time cost and also requires post-processing such as $k$ -means. addition, some methods require learning uniform matrix. large-scale data, this process significantly memory costs. To address these problems, paper proposes Fast Multi-view Clustering (FMvC). First, non-negative constraints are added objective function from unified view relaxed normalized ratio cuts. Then, reconstruction performed on similarity using indication ensure that obtained has robust intra-cluster weak inter-cluster connectivity. Besides, operation speed method can be further enhanced by setting common labeling Finally, problem solved optimally based strategy alternating directional multipliers. Experimental results eight real-world datasets demonstrate effectiveness proposed algorithm, which always outperform eleven existing baseline algorithms.