Selective Cross-View Topology for Deep Incomplete Multi-View Clustering
IEEE Transactions on Image Processing · 2025 · 34 · 4792-4805
DOI: 10.1109/tip.2025.3587586 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Zhibin Dong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, National Natural Science Foundation of China Joint Found.
Abstract (Originalsprache)
Incomplete multi-view clustering has gained significant attention due to the prevalence of incomplete multi-view data in real-world scenarios. However, existing methods often overlook the critical role of inter-view relationships. In unsupervised settings, selectively leveraging cross-view topological relationships can effectively guide view completion and representation learning. To address this challenge, we propose a novel framework called Selective Cross-View Topology Incomplete Multi-View Clustering (SCVT). Our approach constructs a view topology graph using the Optimal Transport (OT) distance between view. This graph helps identify neighboring views for those with missing data, enabling the inference of topological relationships and accurate completion of missing samples. Additionally, we introduce the Max View Graph Contrastive Alignment module to facilitate information transfer and alignment across neighboring views. Furthermore, we propose the View Graph Weighted Intra-View Contrastive Learning module, which enhances representation learning by pulling representations of samples within the same cluster closer, while applying varying degrees of enhancement across different views based on the view graph. Our method achieves state-of-the-art performance on seven benchmark datasets, significantly outperforming existing methods for incomplete multi-view clustering and demonstrating its effectiveness.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- National Natural Science Foundation of China Joint Found
Zitieren
APA
Dong, Z., Hu, D., Jin, J., Wang, S., Liu, X., & Zhu, E. (2025). Selective Cross-View Topology for Deep Incomplete Multi-View Clustering. IEEE Transactions on Image Processing, 34, 4792-4805. https://doi.org/10.1109/tip.2025.3587586
Vancouver
Dong Z, Hu D, Jin J, Wang S, Liu X, Zhu E. Selective Cross-View Topology for Deep Incomplete Multi-View Clustering. IEEE Transactions on Image Processing. 2025;34:4792-4805. doi:10.1109/tip.2025.3587586
BibTeX
@article{Dong2025,
author = {Dong, Zhibin and Hu, Dayu and Jin, Jiaqi and Wang, Siwei and Liu, Xinwang and Zhu, En},
title = {Selective Cross-View Topology for Deep Incomplete Multi-View Clustering},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {4792--4805},
doi = {10.1109/tip.2025.3587586}
}
EUVIMED