Efficient and Effective One-Step Multiview Clustering

Multiview clustering algorithms have attracted intensive attention and achieved superior performance in various fields recently. Despite the great success of multiview clustering methods in realistic applications, we observe that most of them are difficult to apply to large-scale datasets due to their cubic complexity. Moreover, they usually use a two-stage scheme to obtain the discrete clustering labels, which inevitably causes a suboptimal solution. In light of this, an efficient and effective one-step multiview clustering ((EOMVC)-O-2) method is proposed to directly obtain clustering indicators with a small-time burden. Specifically, according to the anchor graphs, the smaller similarity graph of each view is constructed, from which the low-dimensional latent features are generated to form the latent partition representation. By introducing a label discretization mechanism, the binary indicator matrix can be directly obtained from the unified partition representation which is formed by fusing all latent partition representations from different views. In addition, by coupling the fusion of all latent information and the clustering task into a joint framework, the two processes can help each other and obtain a better clustering result. Extensive experimental results demonstrate that the proposed method can achieve comparable or better performance than the state-of-the-art methods. The demo code of this work is publicly available at https://github.com/WangJun2023/EEOMVC.

Automated summary

Multiview clustering algorithms have achieved superior performance in various fields, but most of them are difficult to apply to large-scale datasets due to their cubic complexity. Moreover, they often rely on a two-stage scheme to obtain clustering labels, which results in suboptimal solutions. Therefore, an efficient and effective one-step multiview clustering method is proposed to directly obtain clustering indicators with a small-time burden. The method constructs smaller similarity graphs and generates low-dimensional latent features to form a unified partition representation, from which a binary indicator matrix can be directly obtained. The fusion of latent information and the clustering task in a joint framework improve the clustering result.