Disentangling Consistent and Specific Information for Double Incomplete Multi-View Multi-Label Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-07 · 48 (7) · 7307-7320
DOI: 10.1109/tpami.2026.3665097 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-07. Verfasst von Jie Wen und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Open Projects of Key Laboratories of the Ministry of Education, Southwest University of Science.
Abstract (Originalsprache)
As a prominent research topic, multi-view multi-label classification (MvMlC) aims to assign multiple labels to samples by integrating information from various perspectives. However, in real-world scenarios, MvMlC frequently faces the learning challenge of data with missing views and labels, typically resulting from sensor malfunctions, or the costly and time-consuming process of manual annotation. In addition, learning robust representations that are both consistent across views and specific to individual views remains a challenge. To address these issues, we propose a novel double incomplete multi-view multi-label classification framework based on Disentangling Consistent and Specific Information (DCSI). Specifically, we employ a dual-channel encoder with identical architecture but distinct objectives to extract cross-view consistent information and view-specific unique information from all views, respectively. Meanwhile, a view discriminator is constructed to decouple these two types of information, facilitating the extraction of pure consistent and specific information. Moreover, we meticulously design fusion strategies tailored to each representation type. Regarding consistent representations, we propose a dynamic-confidence-aware fusion mechanism that assesses the reliability of each view's representations in relation to the classification task, enabling the model to prioritize information from trustworthy representations. For specific representations, in light of their complementary rather than redundant property, we suggest treating such representations from each view equally to ensure fairness. Through experimental validation on five datasets, the results demonstrate that our method outperforms existing state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
- Open Projects of Key Laboratories of the Ministry of Education
- Southwest University of Science
Zitieren
APA
Wen, J., Zhao, L., Lu, X., Liu, C., Shen, L., Huang, C., & Xu, Y. (2026). Disentangling Consistent and Specific Information for Double Incomplete Multi-View Multi-Label Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(7), 7307-7320. https://doi.org/10.1109/tpami.2026.3665097
Vancouver
Wen J, Zhao L, Lu X, Liu C, Shen L, Huang C, et al. Disentangling Consistent and Specific Information for Double Incomplete Multi-View Multi-Label Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(7):7307-7320. doi:10.1109/tpami.2026.3665097
BibTeX
@article{Wen2026,
author = {Wen, Jie and Zhao, Lian and Lu, Xiaohuan and Liu, Chengliang and Shen, Li and Huang, Chao and Xu, Yong},
title = {Disentangling Consistent and Specific Information for Double Incomplete Multi-View Multi-Label Classification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {7},
pages = {7307--7320},
doi = {10.1109/tpami.2026.3665097}
}
EUVIMED