Hierarchical Cross-View Alignment for Multi-View Clustering via Decoupled Information Distillation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (34) · 29000-29008
DOI: 10.1609/aaai.v40i34.40136 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Taichun Zhou und 8 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
Multi-view clustering aims to uncover shared semantics and complementary information across different views. However, the inherent heterogeneity among views poses significant challenges to effective collaborative modeling and information integration. While recent studies have introduced distillation-based mechanisms to enhance cross-view consistency and alleviate heterogeneity, these approaches often rely on manually defined knowledge transfer paths or fixed fusion weights, which are inflexible in handling complex and dynamic view relationships in practice. To address this issue, we propose HOARD: a novel framework for Hierarchical crOss-view Alignment for multi-view clusteRing via Decoupled information distillation. HOARD structurally decouples multi-view representations into shared and specific components, and performs hierarchical alignment. Specifically, we introduce a granular-ball contrastive alignment to enhance the semantic consistency of shared features, and a prototype collaborative transmission alignment strategy to align specific features while preserving view-specific structural characteristics. Moreover, we design an information distillation unit to adaptively model cross-view knowledge transfer in both feature spaces. An attention mechanism is further employed to integrate shared and specific information. Extensive experiments on benchmark datasets demonstrate that HOARD significantly improves alignment quality and clustering performance, achieving state-of-the-art results.
Zitieren
APA
Zhou, T., Wang, S., Dong, Z., Jin, J., Liang, K., Xiao, B., Li, M., Liu, X., & Zhu, E. (2026). Hierarchical Cross-View Alignment for Multi-View Clustering via Decoupled Information Distillation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(34), 29000-29008. https://doi.org/10.1609/aaai.v40i34.40136
Vancouver
Zhou T, Wang S, Dong Z, Jin J, Liang K, Xiao B, et al. Hierarchical Cross-View Alignment for Multi-View Clustering via Decoupled Information Distillation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(34):29000-29008. doi:10.1609/aaai.v40i34.40136
BibTeX
@article{Zhou2026,
author = {Zhou, Taichun and Wang, Siwei and Dong, Zhibin and Jin, Jiaqi and Liang, Ke and Xiao, Baili and Li, Miaomiao and Liu, Xinwang and Zhu, En},
title = {Hierarchical Cross-View Alignment for Multi-View Clustering via Decoupled Information Distillation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {34},
pages = {29000--29008},
doi = {10.1609/aaai.v40i34.40136}
}
EUVIMED