Generalized Incomplete Multiview Clustering With Flexible Locality Structure Diffusion

An important underlying assumption that guides the success of the existing multiview learning algorithms is the full observation of the multiview data. However, such rigorous precondition clearly violates the common-sense knowledge in practical applications, where in most cases, only incomplete fractions of the multiview data are given. The presence of the incomplete settings generally disables the conventional multiview clustering methods. In this article, we propose a simple but effective incomplete multiview clustering (IMC) framework, which simultaneously considers the local geometric information and the unbalanced discriminating powers of these incomplete multiview observations. Specifically, a novel graph-regularized matrix factorization model, on the one hand, is developed to preserve the local geometric similarities of the learned common representations from different views. On the other hand, the semantic consistency constraint is introduced to stimulate these view-specific representations toward a unified discriminative representation. Moreover, the importance of different views is adaptively determined to reduce the negative influence of the unbalanced incomplete views. Furthermore, an efficient learning algorithm is proposed to solve the resulting optimization problem. Extensive experimental results performed on several incomplete multiview datasets demonstrate that the proposed method can achieve superior clustering performance in comparison with some state-of-the-art multiview learning methods.

Automated summary

This article introduces a simple and effective incomplete multiview clustering framework that considers incomplete multiview data, taking into account both local geometric information and unbalanced discriminating powers. By developing a novel graph-regularized matrix factorization model and introducing a semantic consistency constraint, the common representations learned from different views can maintain local geometric similarities and achieve a unified discriminative representation. Furthermore, the importance of different views is adaptively determined to reduce the negative influence of unbalanced incomplete views, leading to superior clustering performance compared to state-of-the-art multiview learning methods according to extensive experimental results on several incomplete multiview datasets.