@inproceedings{zhu-etal-2025-multimodal,
title = "Multimodal Invariant Sentiment Representation Learning",
author = "Zhu, Aoqiang and
Hu, Min and
Wang, Xiaohua and
Yang, Jiaoyun and
Tang, Yiming and
An, Ning",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.761/",
doi = "10.18653/v1/2025.findings-acl.761",
pages = "14743--14755",
ISBN = "979-8-89176-256-5",
abstract = "Multimodal Sentiment Analysis (MSA) integrates diverse modalities to overcome the limitations of unimodal data. However, existing MSA datasets commonly exhibit significant sentiment distribution imbalances and cross-modal sentiment conflicts, which hinder performance improvement. This paper shows that distributional discrepancies and sentiment conflicts can be incorporated into the model training to learn stable multimodal invariant sentiment representation. To this end, we propose a Multimodal Invariant Sentiment Representation Learning (MISR) method. Specifically, we first learn a stable and consistent multimodal joint representation in the latent space of Gaussian distribution based on distributional constraints Then, under invariance constraint, we further learn multimodal invariant sentiment representations from multiple distributional environments constructed by the joint representation and unimodal data, achieving robust and efficient MSA performance. Extensive experiments demonstrate that MISR significantly enhances MSA performance and achieves new state-of-the-art."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-multimodal">
<titleInfo>
<title>Multimodal Invariant Sentiment Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aoqiang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaohua</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaoyun</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Multimodal Sentiment Analysis (MSA) integrates diverse modalities to overcome the limitations of unimodal data. However, existing MSA datasets commonly exhibit significant sentiment distribution imbalances and cross-modal sentiment conflicts, which hinder performance improvement. This paper shows that distributional discrepancies and sentiment conflicts can be incorporated into the model training to learn stable multimodal invariant sentiment representation. To this end, we propose a Multimodal Invariant Sentiment Representation Learning (MISR) method. Specifically, we first learn a stable and consistent multimodal joint representation in the latent space of Gaussian distribution based on distributional constraints Then, under invariance constraint, we further learn multimodal invariant sentiment representations from multiple distributional environments constructed by the joint representation and unimodal data, achieving robust and efficient MSA performance. Extensive experiments demonstrate that MISR significantly enhances MSA performance and achieves new state-of-the-art.</abstract>
<identifier type="citekey">zhu-etal-2025-multimodal</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.761</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.761/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>14743</start>
<end>14755</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Invariant Sentiment Representation Learning
%A Zhu, Aoqiang
%A Hu, Min
%A Wang, Xiaohua
%A Yang, Jiaoyun
%A Tang, Yiming
%A An, Ning
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhu-etal-2025-multimodal
%X Multimodal Sentiment Analysis (MSA) integrates diverse modalities to overcome the limitations of unimodal data. However, existing MSA datasets commonly exhibit significant sentiment distribution imbalances and cross-modal sentiment conflicts, which hinder performance improvement. This paper shows that distributional discrepancies and sentiment conflicts can be incorporated into the model training to learn stable multimodal invariant sentiment representation. To this end, we propose a Multimodal Invariant Sentiment Representation Learning (MISR) method. Specifically, we first learn a stable and consistent multimodal joint representation in the latent space of Gaussian distribution based on distributional constraints Then, under invariance constraint, we further learn multimodal invariant sentiment representations from multiple distributional environments constructed by the joint representation and unimodal data, achieving robust and efficient MSA performance. Extensive experiments demonstrate that MISR significantly enhances MSA performance and achieves new state-of-the-art.
%R 10.18653/v1/2025.findings-acl.761
%U https://aclanthology.org/2025.findings-acl.761/
%U https://doi.org/10.18653/v1/2025.findings-acl.761
%P 14743-14755
Markdown (Informal)
[Multimodal Invariant Sentiment Representation Learning](https://aclanthology.org/2025.findings-acl.761/) (Zhu et al., Findings 2025)
ACL
- Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, and Ning An. 2025. Multimodal Invariant Sentiment Representation Learning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14743–14755, Vienna, Austria. Association for Computational Linguistics.