@inproceedings{li-etal-2025-exploring,
title = "Exploring the Impacts of Feature Fusion Strategy in Multi-modal Entity Alignment",
author = "Li, Chenxiao and
Cheng, Jingwei and
Tong, Qiang and
Zhang, Fu",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.522/",
pages = "7809--7818",
abstract = "Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs, which consist of structural triples and images associated with entities. Unfortunately, prior works fuse the multi-modal knowledge of all entities only via solely one single fusion strategy. Therefore, the impact of the fusion strategy on individual entities could be largely ignored. To solve this challenge, we propose AMF2SEA, an adaptive multi-modal feature fusion strategy for entity alignment, which dynamically selects the optimal entity-level feature fusion strategy. Additionally, we build a new dataset based on DBP15K, which includes a full set of entity images from multiple inconsistent web sources, making it more representative of the real world. Experimental results demonstrate that our model achieves state-of-the-art (SOTA) performance compared to models using the same modality on DBP15K and its variants with richer image sources and styles. Our code and data are available at https://github.com/ChenxiaoLiJoe/AMFFSEA."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-exploring">
<titleInfo>
<title>Exploring the Impacts of Feature Fusion Strategy in Multi-modal Entity Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenxiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs, which consist of structural triples and images associated with entities. Unfortunately, prior works fuse the multi-modal knowledge of all entities only via solely one single fusion strategy. Therefore, the impact of the fusion strategy on individual entities could be largely ignored. To solve this challenge, we propose AMF2SEA, an adaptive multi-modal feature fusion strategy for entity alignment, which dynamically selects the optimal entity-level feature fusion strategy. Additionally, we build a new dataset based on DBP15K, which includes a full set of entity images from multiple inconsistent web sources, making it more representative of the real world. Experimental results demonstrate that our model achieves state-of-the-art (SOTA) performance compared to models using the same modality on DBP15K and its variants with richer image sources and styles. Our code and data are available at https://github.com/ChenxiaoLiJoe/AMFFSEA.</abstract>
<identifier type="citekey">li-etal-2025-exploring</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.522/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>7809</start>
<end>7818</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Impacts of Feature Fusion Strategy in Multi-modal Entity Alignment
%A Li, Chenxiao
%A Cheng, Jingwei
%A Tong, Qiang
%A Zhang, Fu
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F li-etal-2025-exploring
%X Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs, which consist of structural triples and images associated with entities. Unfortunately, prior works fuse the multi-modal knowledge of all entities only via solely one single fusion strategy. Therefore, the impact of the fusion strategy on individual entities could be largely ignored. To solve this challenge, we propose AMF2SEA, an adaptive multi-modal feature fusion strategy for entity alignment, which dynamically selects the optimal entity-level feature fusion strategy. Additionally, we build a new dataset based on DBP15K, which includes a full set of entity images from multiple inconsistent web sources, making it more representative of the real world. Experimental results demonstrate that our model achieves state-of-the-art (SOTA) performance compared to models using the same modality on DBP15K and its variants with richer image sources and styles. Our code and data are available at https://github.com/ChenxiaoLiJoe/AMFFSEA.
%U https://aclanthology.org/2025.coling-main.522/
%P 7809-7818
Markdown (Informal)
[Exploring the Impacts of Feature Fusion Strategy in Multi-modal Entity Alignment](https://aclanthology.org/2025.coling-main.522/) (Li et al., COLING 2025)
ACL