Quality-aware and Soft Consistency Driven Representation Fusion for Incomplete Multi-view Multi-label Classification
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (28) · 23882-23890
DOI: 10.1609/aaai.v40i28.39564 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yadong Liu und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Multi-view multi-label classification aims to utilize the rich information contained in multiple views for accurate classification. However, in real-world applications, its performance is often severely constrained by the concurrent missingness of both views and labels. To address this problem, this paper first targets the drawback of representation degradation in traditional feature disentanglement methods caused by strong consistency constraints and proposes a soft consistency constraint. This constraint not only effectively aligns the shared information and maximally avoids the compression of information beneficial to the classification task, but it also enhances the aggregation effect of high-quality representations on other representations. Furthermore, to address the coarse-grained problem of traditional fusion strategies, we designed a quality assessment network that achieves instance-level dynamic weighted fusion in a data-driven manner. Extensive experiments on multiple benchmark datasets demonstrate that our method achieves state-of-the-art performance in both incomplete and complete data scenarios, showcasing its robustness and generality.
Zitieren
APA
Liu, Y., Wong, W., Chen, Y., & Wen, J. (2026). Quality-aware and Soft Consistency Driven Representation Fusion for Incomplete Multi-view Multi-label Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 40(28), 23882-23890. https://doi.org/10.1609/aaai.v40i28.39564
Vancouver
Liu Y, Wong W, Chen Y, Wen J. Quality-aware and Soft Consistency Driven Representation Fusion for Incomplete Multi-view Multi-label Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(28):23882-23890. doi:10.1609/aaai.v40i28.39564
BibTeX
@article{Liu2026,
author = {Liu, Yadong and Wong, Waikeung and Chen, Yulong and Wen, Jie},
title = {Quality-aware and Soft Consistency Driven Representation Fusion for Incomplete Multi-view Multi-label Classification},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {28},
pages = {23882--23890},
doi = {10.1609/aaai.v40i28.39564}
}
EUVIMED