Self-Guided Deep Multi-View Subspace Clustering Network

To cluster the data with complex structures, Deep Subspace Clustering Network (DSCN) extracts the subspace relations among non-linear latent features. However, the performance improvement has encountered bottlenecks due to the lack of supervision. Meantime, in multi-view settings, most of DSCN-based methods underestimate the significance of view-fusion, which always adopt simple tactics. To address these issues, we propose a self-supervised model for simultaneous subspace clustering, consensus construction and self-guided learning, named as Self-Guided Deep Multi-view Subspace Clustering Network (SG-DMSC). We utilize DSCN to learn a complex subspace representation for each single-view. Considering their different importance, we design the view-fusion layer to establish the agreement. We construct a novel loss term, the spectral supervisor, so that the consensus can be more clustering-friendly by the self-guidance of pseudo labels. Theoretical support is provided to reflect the validity of this self-guided strategy. An alternate iterative optimization algorithm is presented to handle SG-DMSC. Experiments on real-world datasets confirm its efficacy compared with others.