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

2026-08-06

AI Summary

This work addresses the performance degradation in multimodal sentiment analysis under real-world conditions where modalities may be missing or corrupted. To enhance robustness, the authors propose a variational modeling approach that represents each modality as a Gaussian latent variable, decomposed into shared and modality-specific factors. Semantic alignment is strengthened through a min-max optimization of mutual information between these factors, while a posterior variance–based uncertainty-aware fusion mechanism improves the reliability of the learned representations. Evaluated across three benchmark datasets under diverse modality-missing scenarios, the proposed method consistently outperforms existing models, demonstrating superior robustness and generalization capability.

Abstract

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.

Problem

• incomplete multimodal sentiment analysis
• missing modalities
• multimodal representation
• uncertainty-aware fusion
• mutual information disentanglement

Innovation

• mutual information disentanglement
• uncertainty-aware fusion
• incomplete multimodal learning
• variational modeling
• semantic alignment