<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-shimodaira-2024-block">
    <titleInfo>
        <title>Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yihua</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hidetoshi</namePart>
        <namePart type="family">Shimodaira</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The primary aim of Knowledge Graph Embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. While rotation-based methods like RotatE and QuatE perform well in KGE, they face two challenges: limited model flexibility requiring proportional increases in relation size with entity dimension, and difficulties in generalizing the model for higher-dimensional rotations. To address these issues, we introduce OrthogonalE, a novel KGE model employing matrices for entities and block-diagonal orthogonal matrices with Riemannian optimization for relations. This approach not only enhances the generality and flexibility of KGE models but also captures several relation patterns that rotation-based methods can identify. Experimental results indicate that our new KGE model, OrthogonalE, offers generality and flexibility, captures several relation patterns, and significantly outperforms state-of-the-art KGE models while substantially reducing the number of relation parameters.</abstract>
    <identifier type="citekey">zhu-shimodaira-2024-block</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.987</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>16956</start>
            <end>16972</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding
%A Zhu, Yihua
%A Shimodaira, Hidetoshi
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F zhu-shimodaira-2024-block
%X The primary aim of Knowledge Graph Embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. While rotation-based methods like RotatE and QuatE perform well in KGE, they face two challenges: limited model flexibility requiring proportional increases in relation size with entity dimension, and difficulties in generalizing the model for higher-dimensional rotations. To address these issues, we introduce OrthogonalE, a novel KGE model employing matrices for entities and block-diagonal orthogonal matrices with Riemannian optimization for relations. This approach not only enhances the generality and flexibility of KGE models but also captures several relation patterns that rotation-based methods can identify. Experimental results indicate that our new KGE model, OrthogonalE, offers generality and flexibility, captures several relation patterns, and significantly outperforms state-of-the-art KGE models while substantially reducing the number of relation parameters.
%U https://aclanthology.org/2024.findings-emnlp.987
%P 16956-16972

Markdown (Informal)

[Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding](https://aclanthology.org/2024.findings-emnlp.987) (Zhu & Shimodaira, Findings 2024)

• Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding (Zhu & Shimodaira, Findings 2024)

ACL

• Yihua Zhu and Hidetoshi Shimodaira. 2024. Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16956–16972, Miami, Florida, USA. Association for Computational Linguistics.