EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Three-Way Multimodal Learning with Severely Missing Modalities

Hanrui Wang, Yu Fang, Xin Wang, Fan Min

Information · 19.04.2026 · 17 (4) · 384

DOI: 10.3390/info17040384 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 19.04.2026. Verfasst von Hanrui Wang und 3 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Missing modalities remain a major obstacle to the real-world deployment of multimodal learning systems, as incomplete inputs can substantially degrade model performance. Existing methods often suffer from biased imputation under high missing rates and lack uncertainty-aware, differentiated processing. Inspired by three-way decision, a framework for handling uncertainty by adding a deferment option to acceptance and rejection, we propose three-way multimodal learning with severely missing modalities (3WML-SMMs), a novel framework that introduces a three-way decision mechanism into both missing-modality imputation and feature regularization for the first time. Specifically, 3WML-SMM treats variance not merely as a descriptive measure of uncertainty, but as a decision signal for adaptive processing. Based on this idea, the framework incorporates (1) a variance-guided three-way imputation strategy with accept–delay–reject decisions to reduce unreliable reconstruction when only a limited number of complete samples are available and (2) a dimension-wise adaptive feature enhancement module that performs fine-grained regularization according to perturbation uncertainty. Experiments on the CMU Multimodal Opinion Sentiment Intensity (CMU-MOSI) and Multimodal Internet Movie Database (MM-IMDb) datasets show that 3WML-SMM consistently outperforms representative baselines, including reconstruction-based methods, complete-input multimodal methods, and missing-modality-specific methods under severe missing-modality settings, with statistically significant improvements over the multimodal learning with severely missing modality (SMIL) baseline (p

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, H., Fang, Y., Wang, X., & Min, F. (2026). Three-Way Multimodal Learning with Severely Missing Modalities. Information, 17(4), 384. https://doi.org/10.3390/info17040384

Vancouver

Wang H, Fang Y, Wang X, Min F. Three-Way Multimodal Learning with Severely Missing Modalities. Information. 2026;17(4):384. doi:10.3390/info17040384

BibTeX
@article{Wang2026,
  author = {Wang, Hanrui and Fang, Yu and Wang, Xin and Min, Fan},
  title = {Three-Way Multimodal Learning with Severely Missing Modalities},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {4},
  pages = {384},
  doi = {10.3390/info17040384}
}
Kostenlos starten →