Metraipolis › archive › dc_cebea2177f9f

MIDAS: Mutual Information Disentanglement with Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis — arXiv:2608.09986

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09986
License (as archived)
CC0-1.0
Archived
2026-10-19T06:08:08.929Z
SHA-256 of the archived text
af47e5e0f24b8addc9f1ebb89fe2d7c106f25b20cb231f8bed3a9c33efaef129
Stable URL of this page
https://metraipolis.com/documento/dc_cebea2177f9f

How to cite

MIDAS: Mutual Information Disentanglement with Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis — arXiv:2608.09986 — arXiv (en), https://arxiv.org/abs/2608.09986 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cebea2177f9f (Metraipolis archive dc_cebea2177f9f, sha256 af47e5e0f24b8addc9f1ebb89fe2d7c106f25b20cb231f8bed3a9c33efaef129)
BibTeX
@misc{dccebea2177f9f,
  title = {MIDAS: Mutual Information Disentanglement with Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis — arXiv:2608.09986},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09986},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cebea2177f9f; sha256 af47e5e0f24b8addc9f1ebb89fe2d7c106f25b20cb231f8bed3a9c33efaef129},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09986. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Most existing multimodal sentiment analysis approaches assume access to complete multimodal inputs. However, real-world applications frequently encounter incomplete or corrupted modalities, posing a critical challenge. Although several methods have been proposed to tackle this issue, they mainly rely on data imputation and heuristic coordination constraints, which fail to effectively extract and leverage task-relevant information from the incomplete multimodal data. To address this challenge, we propose a unified framework termed Mutual Information Disentanglement with uncertainty-Aware fuSion (MIDAS), which effectively restructures multimodal representations under incomplete conditions. MIDAS adopts a variational modeling strategy to represent each modality with multivariate Gaussian latent variables and further decomposes them into shared and exclusive factors. To obtain reliable representations, we design a minimax objective that minimizes the mutual information between shared and exclusive spaces for stable disentanglement, while maximizing the mutual information among shared spaces across modalities to enhance semantic alignment. In addition, an uncertainty-aware fusion mechanism is introduced, where posterior variance is leveraged as a reliability indicator to adaptively weight latent features during fusion, ensuring robust integration even when modalities are incomplete. Extensive experiments on three widely used datasets show that MIDAS achieves strong and consistent performance gains over competitive baselines across a wide range of incomplete settings, demonstrating its effectiveness and robustness for incomplete data scenarios.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.09986 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:57:28.228Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).