TF-Mamba: Text-enhanced Fusion Mamba with Missing Modalities for Robust Multimodal Sentiment Analysis

TL;DR

TF-Mamba is a novel framework that enhances multimodal sentiment analysis by effectively handling missing modalities through text-aware modules, improving robustness and efficiency in multimodal fusion.

Contribution

The paper introduces a new framework combining three modules to improve robustness and efficiency in multimodal sentiment analysis with missing data.

Findings

Outperforms existing methods on three MSA datasets

Effective in scenarios with missing modalities

Demonstrates improved computational efficiency

Abstract

Multimodal Sentiment Analysis (MSA) with missing modalities has attracted increasing attention recently. While current Transformer-based methods leverage dense text information to maintain model robustness, their quadratic complexity hinders efficient long-range modeling and multimodal fusion. To this end, we propose a novel and efficient Text-enhanced Fusion Mamba (TF-Mamba) framework for robust MSA with missing modalities. Specifically, a Text-aware Modality Enhancement (TME) module aligns and enriches non-text modalities, while reconstructing the missing text semantics. Moreover, we develop Text-based Context Mamba (TC-Mamba) to capture intra-modal contextual dependencies under text collaboration. Finally, Text-guided Query Mamba (TQ-Mamba) queries text-guided multimodal information and learns joint representations for sentiment prediction. Extensive experiments on three MSA datasets demonstrate the effectiveness and efficiency of the proposed method under missing modality scenarios. Our code is available at https://github.com/codemous/TF-Mamba.