Multi-view spectral clustering via sparse graph learning

Although numerous multi-view spectral clustering algorithms have been developed, most of them generally encounter the following two deficiencies. First, high time cost. Second, inferior operability. To this end, in this work we provide a simple yet effective method for multi-view spectral clustering. The main idea is to learn a consistent similarity matrix with sparse structure from multiple views. We show that proposed method is fast, straightforward to implement, and can achieve comparable or better clustering results compared to several state-of-the-art algorithms. Furthermore, the computation complexity of proposed method is approximately equivalent to the single-view spectral clustering. For these advantages, it can be considered as a baseline for multi-view spectral clustering.