Skip to content
AI News HubLIVE
Original source2 min read

ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis

Summary

ConsMSA explicitly models intra- and inter-modality semantic distribution consistency to produce consistency-aware importance signals used for regularization, token reweighting, and pruning, achieving state-of-the-art results on CMU-MOSI, CMU-MOSEI, and CH-SIMS while retaining comparable accuracy with only 10% of tokens.

SourcearXiv Machine LearningAuthor: Pan Wang, Lipeng Ke, Huajun Ying, Pritish Mohapatra, Rohan Sarkar, Suresh Lakhani, Sankar Venkataraman, Jingtong Hu
ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 22 Oct 2026]

Title:ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis

View a PDF of the paper titled ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis, by Pan Wang and 7 other authors

View PDF HTML (experimental)

Abstract:Multimodal sentiment analysis (MSA) aims to predict human sentiments by integrating signals from different modalities such as text, video, and audio. However, raw multimodal sequences often suffer from semantic inconsistency--exhibiting redundancy or conflicts within and across modalities--which hinders robust understanding and increases computational cost. To this end, we introduce ConsMSA, which explicitly formalizes semantic distribution consistency across both $\textit{intra}$- and $\textit{inter}$-modality, providing a consistency-aware mechanism for robust and efficient multimodal sentiment prediction. Specifically, ConsMSA projects multimodal token features into a shared sentiment space to compute an Intra- and Inter-modality Consistency Score ($I^2CS$). By coupling this score with predictive relevance, we formulate consistency-aware importance signals that are utilized: (i) as a consistency regularizer to align latent distributions during training, (ii) to derive semantic-aware weights for adaptive multimodal token reweighting, and (iii) as a practical criterion to prune redundant or conflicting tokens. Extensive experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS demonstrate that ConsMSA achieves state-of-the-art performance while remaining robust under aggressive token compression--retaining only 10% of tokens yields comparable accuracy. These results establish semantic distribution consistency as a promising foundation for synergizing predictive robustness with computational efficiency.

Comments: ICML 2026

Subjects:

Machine Learning (cs.LG); Multimedia (cs.MM)

Cite as: arXiv:2610.31731 [cs.LG]

(or arXiv:2610.31731v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.31731

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Pan Wang [view email] [v1] Thu, 22 Oct 2026 15:40:23 UTC (2,414 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled ConsMSA: Semantic Distribution Consistency Learning for Multimodal Sentiment Analysis, by Pan Wang and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-10

Change to browse by:

cs cs.MM

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Introduces an Intra- and Inter-modality Consistency Score (I²CS) computed in a shared sentiment space over multimodal token features.
  • Couples consistency with predictive relevance to drive training regularization, adaptive token reweighting, and pruning of redundant or conflicting tokens.
  • Reports state-of-the-art performance on CMU-MOSI, CMU-MOSEI, and CH-SIMS.
  • Maintains comparable accuracy under aggressive compression, retaining only 10% of tokens.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models