Graph refinement and consistency self-supervision for tensorized incomplete multi-view clustering

In practical multi-view applications, some data in each view are missing. Although recent incomplete multi-view clustering (IMC) approaches have achieved encouraging performance, two challenges remain. They utilize the tensor nuclear norm to explore the high-order correlations among view-specific similarity graphs. Moreover, they only infer the missing views but do not recover the consensus cluster structure across complete views. To address these issues, we propose a new method called graph Refinement and consistency Self-Supervision for Tensorized Incomplete Multi-view Clustering (RS-TIMC). Specifically, RS-TIMC introduces graph decomposition to remove the diverse similarities from the view-specific graphs and utilizes the tensor Schatten-p norm to model the consistent parts. Additionally, by extracting features from the original observable data and inferring the missing instances, RS-TIMC enables the cluster structure of each complete view to be adjusted. Finally, RS-TIMC utilizes consistent similarity graphs to recover the shared local geometric structure across all complete views. Experimental evaluations on several datasets indicate that our method outperforms the start-of-the-art approaches. • Improving two defects of the tensorized IMC method based on missing-view recovery. • Enhancing multi-view high-order consistency by refining view-specific similarity. • Recovering complete multi-view data with flexible cluster structures. • Ensuring the recovered multiple views share the same underlying cluster structure.