Anchor-based incomplete multi-view clustering with graph convolution network

Anchor-based method has proved to be effective in recent incomplete multi-view clustering literature. Although existing methods have achieved significant success in various fields (e.g., digital treatment), they still have several limitations: (1) The construction of anchor graph insufficiently considers the graph structural information inherent in the original data. (2) Most studies are unable to sufficiently explore the correlation between the non-linear structures of representation space and the original space. In this paper, we propose a Anchor-based Incomplete Multi-view Clustering with Graph Convolution Network (AIMCG) method to address the above issues. Specifically, we first adopt graph convolution networks to extract graph information from multi-view data, and employ manifold regularization to constrain the generation of common graph representation. Subsequently, we employ an anchor-based data reconstruction method to generate anchor g raph, combining previous graph information into this process to further enhance the clustering capability. Finally, spectral clustering is applied to the anchor graph to obtain the clustering results. Experiments on 9 benchmark datasets compared with 13 advanced baselines verify the effectiveness of our AIMCG method on incomplete multi-view data.