Multi-View Learning Via Low-Rank Tensor Optimization

In tensor-based multi-view learning methods, the self-representation based subspace clustering is widely researched, which is effective but heavy in high computational complexity. Furthermore, most of approaches learn the low-rank tensor representation and the final affinity matrix separately and ignore the difference between views. In this paper, we construct the target tensor composed of multiple normalized similarity matrices based on the Gaussian kernel function, which is constrained with the t-SVD based tensor nuclear norm to recover the low-rank part. The final affinity matrix is simultaneously learned via weighted multi-view fusion while optimizing the low-rank tensor, which suggests that each view is distributed to an adaptive weight. Moreover, the proposed method can be extended to semi-supervised classification through the collaborative optimization of the similarity tensor and the label indicator matrix. Extensive experiments conducted on four real-world datasets demonstrate the superiority of the proposed method compared with other state-of-the-art methods.