@inproceedings{zhang-etal-2024-unleashing-power,
title = "Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion",
author = "Zhang, Yichi and
Chen, Zhuo and
Liang, Lei and
Chen, Huajun and
Zhang, Wen",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1487",
pages = "17120--17130",
abstract = "Multi-modal knowledge graph completion (MMKGC) aims to predict the missing triples in the multi-modal knowledge graphs by incorporating structural, visual, and textual information of entities into the discriminant models. The information from different modalities will work together to measure the triple plausibility. Existing MMKGC methods overlook the imbalance problem of modality information among entities, resulting in inadequate modal fusion and inefficient utilization of the raw modality information. To address the mentioned problems, we propose Adaptive Multi-modal Fusion and Modality Adversarial Training (AdaMF-MAT) to unleash the power of imbalanced modality information for MMKGC. AdaMF-MAT achieves multi-modal fusion with adaptive modality weights and further generates adversarial samples by modality-adversarial training to enhance the imbalanced modality information. Our approach is a co-design of the MMKGC model and training strategy which can outperform 19 recent MMKGC methods and achieve new state-of-the-art results on three public MMKGC benchmarks. Our code and data have been released at https://github.com/zjukg/AdaMF-MAT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-unleashing-power">
<titleInfo>
<title>Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yichi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huajun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multi-modal knowledge graph completion (MMKGC) aims to predict the missing triples in the multi-modal knowledge graphs by incorporating structural, visual, and textual information of entities into the discriminant models. The information from different modalities will work together to measure the triple plausibility. Existing MMKGC methods overlook the imbalance problem of modality information among entities, resulting in inadequate modal fusion and inefficient utilization of the raw modality information. To address the mentioned problems, we propose Adaptive Multi-modal Fusion and Modality Adversarial Training (AdaMF-MAT) to unleash the power of imbalanced modality information for MMKGC. AdaMF-MAT achieves multi-modal fusion with adaptive modality weights and further generates adversarial samples by modality-adversarial training to enhance the imbalanced modality information. Our approach is a co-design of the MMKGC model and training strategy which can outperform 19 recent MMKGC methods and achieve new state-of-the-art results on three public MMKGC benchmarks. Our code and data have been released at https://github.com/zjukg/AdaMF-MAT.</abstract>
<identifier type="citekey">zhang-etal-2024-unleashing-power</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1487</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17120</start>
<end>17130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion
%A Zhang, Yichi
%A Chen, Zhuo
%A Liang, Lei
%A Chen, Huajun
%A Zhang, Wen
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhang-etal-2024-unleashing-power
%X Multi-modal knowledge graph completion (MMKGC) aims to predict the missing triples in the multi-modal knowledge graphs by incorporating structural, visual, and textual information of entities into the discriminant models. The information from different modalities will work together to measure the triple plausibility. Existing MMKGC methods overlook the imbalance problem of modality information among entities, resulting in inadequate modal fusion and inefficient utilization of the raw modality information. To address the mentioned problems, we propose Adaptive Multi-modal Fusion and Modality Adversarial Training (AdaMF-MAT) to unleash the power of imbalanced modality information for MMKGC. AdaMF-MAT achieves multi-modal fusion with adaptive modality weights and further generates adversarial samples by modality-adversarial training to enhance the imbalanced modality information. Our approach is a co-design of the MMKGC model and training strategy which can outperform 19 recent MMKGC methods and achieve new state-of-the-art results on three public MMKGC benchmarks. Our code and data have been released at https://github.com/zjukg/AdaMF-MAT.
%U https://aclanthology.org/2024.lrec-main.1487
%P 17120-17130
Markdown (Informal)
[Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion](https://aclanthology.org/2024.lrec-main.1487) (Zhang et al., LREC-COLING 2024)
ACL