# Tri-Subspaces Disentanglement for Multimodal Sentiment Analysis

arXiv: https://arxiv.org/abs/2602.19585 · HTML: https://mlsanity.com/paper/2602.19585/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 19 of 19)

- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?](https://mlsanity.com/paper/2407.01284/) (2024)
- [Efficient Low-rank Multimodal Fusion with Modality-Specific Factors](https://mlsanity.com/paper/1806.00064/) (2018)
- [MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2005.03545/) (2020)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)
- [Decoupled Multimodal Distilling for Emotion Recognition](https://mlsanity.com/paper/2303.13802/) (2023)
- [MIntRec: A New Dataset for Multimodal Intent Recognition](https://mlsanity.com/paper/2209.04355/) (2022)
- [Classifier-guided Gradient Modulation for Enhanced Multimodal Learning](https://mlsanity.com/paper/2411.01409/) (2024)
- [Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2310.05804/) (2023)
- [DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis](https://mlsanity.com/paper/2412.12225/) (2024)
- [Enriching Multimodal Sentiment Analysis through Textual Emotional Descriptions of Visual-Audio Content](https://mlsanity.com/paper/2412.10460/) (2024)
- [Fine-grained Disentangled Representation Learning for Multimodal Emotion Recognition](https://mlsanity.com/paper/2312.13567/) (2023)
- [Semi-IIN: Semi-supervised Intra-inter modal Interaction Learning Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2412.09784/) (2024)
- [Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs](https://mlsanity.com/paper/2505.01068/) (2025)
- [CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction](https://mlsanity.com/paper/2410.11428/) (2024)
- [MInD: Improving Multimodal Sentiment Analysis via Multimodal Information Disentanglement](https://mlsanity.com/paper/2401.11818/) (2024)
- [Temporal-Spatial Decouple before Act: Disentangled Representation Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2601.13659/) (2026)

## Built on by (most cited first, 6 of 6)

- [FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction](https://mlsanity.com/paper/2604.13453/) (2026)
- [Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration](https://mlsanity.com/paper/2605.00370/) (2026)
- [An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation](https://mlsanity.com/paper/2606.00987/) (2026)
- [AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis](https://mlsanity.com/paper/2607.15755/) (2026)
- [Hierarchical Contrastive Learning for Multimodal Data](https://mlsanity.com/paper/2604.05462/) (2026)
- [Adapting Vision Foundation Models with Cascaded Semantics](https://mlsanity.com/paper/2608.05393/) (2026)

## Abstract (arXiv)

Multimodal Sentiment Analysis (MSA) integrates language, visual, and acoustic modalities to infer human sentiment. Most existing methods either focus on globally shared representations or modality-specific features, while overlooking signals that are shared only by certain modality pairs. This limits the expressiveness and discriminative power of multimodal representations. To address this limitation, we propose a Tri-Subspace Disentanglement (TSD) framework that explicitly factorizes features into three complementary subspaces: a common subspace capturing global consistency, submodally-shared subspaces modeling pairwise cross-modal synergies, and private subspaces preserving modality-specific cues. To keep these subspaces pure and independent, we introduce a decoupling supervisor together with structured regularization losses. We further design a Subspace-Aware Cross-Attention (SACA) fusion module that adaptively models and integrates information from the three subspaces to obtain richer and more robust representations. Experiments on CMU-MOSI and CMU-MOSEI demonstrate that TSD achieves state-of-the-art performance across all key metrics, reaching 0.691 MAE on CMU-MOSI and 54.9% ACC-7 on CMU-MOSEI, and also transfers well to multimodal intent recognition tasks. Ablation studies confirm that tri-subspace disentanglement and SACA jointly enhance the modeling of multi-granular cross-modal sentiment cues.