<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nayyeri-etal-2021-knowledge">
    <titleInfo>
        <title>Knowledge Graph Representation Learning using Ordinary Differential Equations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mojtaba</namePart>
        <namePart type="family">Nayyeri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chengjin</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Franca</namePart>
        <namePart type="family">Hoffmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mirza</namePart>
        <namePart type="given">Mohtashim</namePart>
        <namePart type="family">Alam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jens</namePart>
        <namePart type="family">Lehmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sahar</namePart>
        <namePart type="family">Vahdati</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a knowledge graph into a geometric space. The capability of KGEs in preserving graph characteristics including structural aspects and semantics, highly depends on the design of their score function, as well as the inherited abilities from the underlying geometry. Many KGEs use the Euclidean geometry which renders them incapable of preserving complex structures and consequently causes wrong inferences by the models. To address this problem, we propose a neuro differential KGE that embeds nodes of a KG on the trajectories of Ordinary Differential Equations (ODEs). To this end, we represent each relation (edge) in a KG as a vector field on several manifolds. We specifically parameterize ODEs by a neural network to represent complex manifolds and complex vector fields on the manifolds. Therefore, the underlying embedding space is capable to assume the shape of various geometric forms to encode heterogeneous subgraphs. Experiments on synthetic and benchmark datasets using state-of-the-art KGE models justify the ODE trajectories as a means to enable structure preservation and consequently avoiding wrong inferences.</abstract>
    <identifier type="citekey">nayyeri-etal-2021-knowledge</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.750</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.750</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>9529</start>
            <end>9548</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Knowledge Graph Representation Learning using Ordinary Differential Equations
%A Nayyeri, Mojtaba
%A Xu, Chengjin
%A Hoffmann, Franca
%A Alam, Mirza Mohtashim
%A Lehmann, Jens
%A Vahdati, Sahar
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F nayyeri-etal-2021-knowledge
%X Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a knowledge graph into a geometric space. The capability of KGEs in preserving graph characteristics including structural aspects and semantics, highly depends on the design of their score function, as well as the inherited abilities from the underlying geometry. Many KGEs use the Euclidean geometry which renders them incapable of preserving complex structures and consequently causes wrong inferences by the models. To address this problem, we propose a neuro differential KGE that embeds nodes of a KG on the trajectories of Ordinary Differential Equations (ODEs). To this end, we represent each relation (edge) in a KG as a vector field on several manifolds. We specifically parameterize ODEs by a neural network to represent complex manifolds and complex vector fields on the manifolds. Therefore, the underlying embedding space is capable to assume the shape of various geometric forms to encode heterogeneous subgraphs. Experiments on synthetic and benchmark datasets using state-of-the-art KGE models justify the ODE trajectories as a means to enable structure preservation and consequently avoiding wrong inferences.
%R 10.18653/v1/2021.emnlp-main.750
%U https://aclanthology.org/2021.emnlp-main.750
%U https://doi.org/10.18653/v1/2021.emnlp-main.750
%P 9529-9548

Markdown (Informal)

[Knowledge Graph Representation Learning using Ordinary Differential Equations](https://aclanthology.org/2021.emnlp-main.750) (Nayyeri et al., EMNLP 2021)

• Knowledge Graph Representation Learning using Ordinary Differential Equations (Nayyeri et al., EMNLP 2021)

ACL

• Mojtaba Nayyeri, Chengjin Xu, Franca Hoffmann, Mirza Mohtashim Alam, Jens Lehmann, and Sahar Vahdati. 2021. Knowledge Graph Representation Learning using Ordinary Differential Equations. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9529–9548, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.