Deep Grassmannian multiview subspace clustering with contrastive learning

Abstract

This paper investigated the problem of multiview subspace clustering, focusing on feature learning with submanifold structure and exploring the invariant representations of multiple views. A novel approach was proposed in this study, termed deep Grassmannian multiview subspace clustering with contrastive learning (DGMVCL). The proposed algorithm initially utilized a feature extraction module (FEM) to map the original input samples into a feature subspace. Subsequently, the manifold modeling module (MMM) was employed to map the aforementioned subspace features onto a Grassmannian manifold. Afterward, the designed Grassmannian manifold network was utilized for deep subspace learning. Finally, discriminative cluster assignments were achieved utilizing a contrastive learning mechanism. Extensive experiments conducted on five benchmarking datasets demonstrate the effectiveness of the proposed method. The source code is available at https://github.com/Zoo-LLi/DGMVCL.

Keywords

• multiview clustering
• contrastive learning
• grassmannian manifold
• neural network
• invariant representation