Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation

This paper explores the problem of multi-view spectral clustering (MVSC) based on tensor low-rank modeling. Unlike existing methods that all adopt an off-the-shelf norm without considering special characteristics in MVSC, we design a novel structured tailored to MVSC. Specifically, explicitly impose symmetric constraint and sparse frontal horizontal slices characterize intra-view inter-view relationships, respectively. Moreover, two constraints could be jointly optimized achieve mutual refinement. On basis norm, formulate MVSC as convex recovery problem, which is then efficiently solved with augmented Lagrange multiplier-based method iteratively. Extensive experimental results seven commonly used benchmark datasets show proposed outperforms state-of-the-art significant extent. Impressively, our able produce perfect clustering. In addition, parameters can easily tuned, model robust different datasets, demonstrating its potential practice. The code available at https://github.com/jyh-learning/MVSC-TLRR .