Dual-Weighted Multiview Clustering Based on Anchor

In the field of multiview clustering, how to make full use of information from multiple data sources to improve the clustering performance has become a hot research topic. However, the rapid growth of high-dimensional multiview data brings great challenges to the research of multiview clustering algorithms, especially the time and space complexity of the algorithms. As an effective solution, anchor-based technique has gained wide attention in large-scale multiview clustering tasks. Nevertheless, the current anchor-based methods fail to fully take into account the importance of different views and the difference and diversity of anchors at the same time, which limits the clustering performance to some extent. To address these problems, we propose a dual-weighted multiview clustering based on anchor (DwMVCA). First, we effectively distinguish the different impacts of high-quality and low-quality views on clustering by adaptively learning the weights of different views. Second, by introducing the adaptive weighting matrix of anchors and self-correlation matrix regularization term, the difference and diversity of anchors are fully considered to effectively reduce the effect of redundant information on clustering. Furthermore, we design a three-step alternating optimization algorithm to solve the resultant optimization problem and prove its convergence. Extensive experimental results show that the proposed DwMVCA has obvious advantages in clustering performance on large-scale datasets, especially on datasets with more than 100,000 samples that still maintain linear time complexity.