Pseudo-Label Similarity Graph-Driven Multi-View Contrastive Clustering
IEEE Transactions on Multimedia · 2026 · 28 · 4786-4798
DOI: 10.1109/tmm.2026.3660170 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2026. Verfasst von Guojie Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Major Key Project of PCL.
Abstract (Originalsprache)
Multi-view clustering has exhibited exceptional performance by harnessing complementary information and extracting shared semantics across diverse views. However, existing methods still encounter substantial obstacles in exploiting high-quality consensus representation: (i) they typically lack effective guidance mechanisms under unsupervised conditions, leading to suboptimal representation learning, and (ii) they overlook the intrinsic cluster structure when forming sample pairs to align representation across views, conflicting with clustering objectives. To address these issues, we propose a contrastive-based method called Pseudo-Label Similarity Graph-driven Multi-View Clustering (PSGVC). Specifically, to uncover the potential semantic relationships between samples, we construct a pseudo-label similarity graph based on the consensus representation. Then, we design a similarity graph-based contrastive loss, which utilizes the pseudo-label similarity graph as a global supervision signal to guide the optimization of cross-view embedded representation, thereby indirectly improving the quality of consensus representation. Additionally, we propose a weighted cluster-aware contrastive loss to align the consensus representation with view-specific representation. It leverages the cluster structure contained in the pseudo-label similarity graph to achieve cluster-level contrastive learning, further enhancing the quality of the consensus representation. Extensive experimental results show that our PSGVC achieves state-of-the-art clustering performance across multiple datasets.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Major Key Project of PCL
Zitieren
APA
Li, G., Yu, Z., Yang, K., Lv, J., & Chen, C. L. P. (2026). Pseudo-Label Similarity Graph-Driven Multi-View Contrastive Clustering. IEEE Transactions on Multimedia, 28, 4786-4798. https://doi.org/10.1109/tmm.2026.3660170
Vancouver
Li G, Yu Z, Yang K, Lv J, Chen CLP. Pseudo-Label Similarity Graph-Driven Multi-View Contrastive Clustering. IEEE Transactions on Multimedia. 2026;28:4786-4798. doi:10.1109/tmm.2026.3660170
BibTeX
@article{Li2026,
author = {Li, Guojie and Yu, Zhiwen and Yang, Kaixiang and Lv, Jianming and Chen, C. L. Philip},
title = {Pseudo-Label Similarity Graph-Driven Multi-View Contrastive Clustering},
journal = {IEEE Transactions on Multimedia},
year = {2026},
volume = {28},
pages = {4786--4798},
doi = {10.1109/tmm.2026.3660170}
}
EUVIMED