Fuzzy Rule-Guided Multiview Differentiable Representation Learning With Dual-Space Information Extraction
IEEE Transactions on Fuzzy Systems · 2026-05 · 34 (5) · 1644-1658
DOI: 10.1109/tfuzz.2026.3669150 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Fuzzy Systems, 2026-05. Verfasst von Wei Zhang und 5 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: NSFC, Basic Research Program of Jiangsu, Natural Science Foundation of the Jiangsu Higher Education Institutions of China.
Abstract (Originalsprache)
Effectively extracting discriminative information from multiview data remains a key challenge in multiview learning. Existing methods typically focus on exploring inter-view consistency via linear or nonlinear transformation. While nonlinear methods tend to yield better performance, their limited transparency and interpretability limit their practical applications. Takagi–Sugeno–Kang fuzzy systems (TSK-FS), as a rule-based model with high interpretability, have been applied to multiview tasks. However, prior methods either rely solely on antecedent components for nonlinear modeling or integrate deep neural networks into the consequent part, thereby compromising model interpretability. To address these challenges, we propose Fuzzy Rule-guided Multiview Differentiable Representation Learning (FRMVDRL). Specifically, in our framework, antecedent parameters of TSK-FS are first used to map data into high-dimensional fuzzy space. Then, during the learning of consequent parameters, a dual information extraction mechanism is proposed to jointly capture shared knowledge across views and view-specific knowledge. Moreover, a second-order geometric structure preservation mechanism is constructed to exploit structural information at both the instance and the instance-pair level. To enhance discriminability of the learned representations, a biorthogonal constraint alongside a Shannon entropy mechanism is introduced. Finally, to balance model performance and interpretability, we introduce a novel multiview differentiable optimization strategy that incorporates learnable parameters to expand the solution space while preserving the structure of traditional optimization. Extensive experiments on benchmark multiview datasets demonstrate the effectiveness of the FRMVDRL.
Förderung
- NSFC
- Basic Research Program of Jiangsu
- Natural Science Foundation of the Jiangsu Higher Education Institutions of China
Zitieren
APA
Zhang, W., Zhou, J., Wang, G., Deng, Z., Ding, W., & Pedrycz, W. (2026). Fuzzy Rule-Guided Multiview Differentiable Representation Learning With Dual-Space Information Extraction. IEEE Transactions on Fuzzy Systems, 34(5), 1644-1658. https://doi.org/10.1109/tfuzz.2026.3669150
Vancouver
Zhang W, Zhou J, Wang G, Deng Z, Ding W, Pedrycz W. Fuzzy Rule-Guided Multiview Differentiable Representation Learning With Dual-Space Information Extraction. IEEE Transactions on Fuzzy Systems. 2026;34(5):1644-1658. doi:10.1109/tfuzz.2026.3669150
BibTeX
@article{Zhang2026,
author = {Zhang, Wei and Zhou, Jun and Wang, Guanjin and Deng, Zhaohong and Ding, Weiping and Pedrycz, Witold},
title = {Fuzzy Rule-Guided Multiview Differentiable Representation Learning With Dual-Space Information Extraction},
journal = {IEEE Transactions on Fuzzy Systems},
year = {2026},
volume = {34},
number = {5},
pages = {1644--1658},
doi = {10.1109/tfuzz.2026.3669150}
}
EUVIMED