Generalized Latent Multi-View Subspace Clustering

By Changqing Zhang, Huan Fu, Qinghua Hu, Xiaochun Cao, Yuan Xie, Dacheng Tao, Dong Xu. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020

650 citations recorded by the source corpus.

Subspace clustering is an effective method that has been successfully applied to many applications. Here, we propose a novel subspace clustering model for multi-view data using a latent representation termed Latent Multi-View Subspace Clustering (LMSC). Unlike most existing single-view subspace clustering methods, which directly reconstruct data points using original features, our method explores underlying complementary information from multiple views and simultaneously seeks the underlying latent representation. Using the complementarity of multiple views, the latent representation depicts data more comprehensively than each individual view, accordingly making subspace representation more accurate and robust. We proposed two LMSC formulations: linear LMSC (lLMSC), based on linear correlations between latent representation and each view, and generalized LMSC (gLMSC), based on neural networks to handle general relationships. The proposed method can be efficiently optimized under the Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM-ADM) framework. Extensive experiments on diverse datasets demonstrate the effectiveness of the proposed method.

View Paper: https://www.semanticscholar.org/paper/00fdad35b6e819837d0222effde31a56b2edb508

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jianlong Wu
2. Ling Shao
3. Huan Fu
4. Jianbing Shen
5. Wenguan Wang
6. Tao Zhou
7. Deng-Ping Fan
8. Hongyuan Zha

Citations in the corpus

• Essential Tensor Learning for Multi-View Spectral Clustering (2018, methodology): “epresentation. Zhang et al. [31] jointly learns the underlying latent representation of features and the multi-view low-rank representation, and then generalize it to combine with deep neural network [32]. To explore the complementary property of multi-view representations, [5] utilizes the Hilbert ”
• Scalable Multi-view Subspace Clustering with Unified Anchors (2021, background): “[33, 35] reconstruct the data points in a latent space which could make subspace representation more accurate and robust.”
• Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis (2020, background): “In the multi-view learning field, several studies focus on learning a common latent representation to exploit the correlations among multiple views [50], [51], while other methods explore complementary information.”
• Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance (2021, methodology): “[9], [24] reconstruct the data points in a latent space which could make subspace representation more accurate and robust.”
• Structured Graph Learning for Scalable Subspace Clustering: From Single View to Multiview (2021, unknown): “[47], [52] performed subspace clustering in latent space; and Kang et al.”