Wei Lai, Li Kexin, Zhou Rigui, Liu Jin
IEEE Trans Cybern. 2025 Apr 8;PP. doi: 10.1109/TCYB.2025.3554901.
Multiview subspace clustering (MVSC) aims to integrate complementary information from different views to accurately reveal the subspace structure of a multiview dataset. Traditional MVSC methods often emphasize the aggregation of samples within the same subspace, while neglecting the separation of samples across different subspaces. In this article, we incorporate contrastive learning techniques into the MVSC framework, developing a contrastive data self-representation module, a contrastive regularizer for the reconstruction coefficient matrix in each view, and a contrastive alignment term to obtain a consensus coefficient matrix that fuses structural information from the reconstruction coefficient matrices. This leads to the framework of a purely contrastive MVSC (PCMVSC) approach. We elaborate on the superiority of the proposed modules in PCMVSC over similar ones in existing methods and show that the consensus reconstruction coefficient matrix obtained by PCMVSC can effectively uncover the underlying subspace structure of multiview datasets. Extensive subspace clustering experiments prove the effectiveness of PCMVSC and reveal that it outperforms various existing multiview clustering algorithms.
多视图子空间聚类（MVSC）旨在整合来自不同视图的互补信息，以准确揭示多视图数据集的子空间结构。传统的MVSC方法通常强调同一子空间内样本的聚合，而忽略了不同子空间间样本的分离。在本文中，我们将对比学习技术纳入MVSC框架，开发了一个对比数据自表示模块、每个视图中用于重建系数矩阵的对比正则化器以及一个对比对齐项，以获得融合来自重建系数矩阵结构信息的共识系数矩阵。这就形成了一种纯对比MVSC（PCMVSC）方法的框架。我们详细阐述了PCMVSC中所提出的模块相对于现有方法中类似模块的优越性，并表明PCMVSC获得的共识重建系数矩阵能够有效地揭示多视图数据集的潜在子空间结构。大量的子空间聚类实验证明了PCMVSC的有效性，并表明它优于各种现有的多视图聚类算法。
