@inproceedings{nayyeri-etal-2023-knowledge,
title = "Knowledge Graph Embeddings using Neural {I}to Process: From Multiple Walks to Stochastic Trajectories",
author = "Nayyeri, Mojtaba and
Xiong, Bo and
Mohammadi, Majid and
Akter, Mst. Mahfuja and
Alam, Mirza Mohtashim and
Lehmann, Jens and
Staab, Steffen",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.448",
doi = "10.18653/v1/2023.findings-acl.448",
pages = "7165--7179",
abstract = "Knowledge graphs mostly exhibit a mixture of branching relations, e.g., hasFriend, and complex structures, e.g., hierarchy and loop. Most knowledge graph embeddings have problems expressing them, because they model a specific relation r from a head h to tails by starting at the node embedding of h and transitioning deterministically to exactly one other point in the embedding space. We overcome this issue in our novel framework ItCAREToE by modeling relations between nodes by relation-specific, stochastic transitions. Our framework is based on stochastic ItCARETo processes, which operate on low-dimensional manifolds. ItCAREToE is highly expressive and generic subsuming various state-of-the-art models operating on different, also non-Euclidean, manifolds. Experimental results show the superiority of ItCAREToE over other deterministic embedding models with regard to the KG completion task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nayyeri-etal-2023-knowledge">
<titleInfo>
<title>Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories</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">Bo</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majid</namePart>
<namePart type="family">Mohammadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mst.</namePart>
<namePart type="given">Mahfuja</namePart>
<namePart type="family">Akter</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">Steffen</namePart>
<namePart type="family">Staab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge graphs mostly exhibit a mixture of branching relations, e.g., hasFriend, and complex structures, e.g., hierarchy and loop. Most knowledge graph embeddings have problems expressing them, because they model a specific relation r from a head h to tails by starting at the node embedding of h and transitioning deterministically to exactly one other point in the embedding space. We overcome this issue in our novel framework ItCAREToE by modeling relations between nodes by relation-specific, stochastic transitions. Our framework is based on stochastic ItCARETo processes, which operate on low-dimensional manifolds. ItCAREToE is highly expressive and generic subsuming various state-of-the-art models operating on different, also non-Euclidean, manifolds. Experimental results show the superiority of ItCAREToE over other deterministic embedding models with regard to the KG completion task.</abstract>
<identifier type="citekey">nayyeri-etal-2023-knowledge</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.448</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.448</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7165</start>
<end>7179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories
%A Nayyeri, Mojtaba
%A Xiong, Bo
%A Mohammadi, Majid
%A Akter, Mst. Mahfuja
%A Alam, Mirza Mohtashim
%A Lehmann, Jens
%A Staab, Steffen
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F nayyeri-etal-2023-knowledge
%X Knowledge graphs mostly exhibit a mixture of branching relations, e.g., hasFriend, and complex structures, e.g., hierarchy and loop. Most knowledge graph embeddings have problems expressing them, because they model a specific relation r from a head h to tails by starting at the node embedding of h and transitioning deterministically to exactly one other point in the embedding space. We overcome this issue in our novel framework ItCAREToE by modeling relations between nodes by relation-specific, stochastic transitions. Our framework is based on stochastic ItCARETo processes, which operate on low-dimensional manifolds. ItCAREToE is highly expressive and generic subsuming various state-of-the-art models operating on different, also non-Euclidean, manifolds. Experimental results show the superiority of ItCAREToE over other deterministic embedding models with regard to the KG completion task.
%R 10.18653/v1/2023.findings-acl.448
%U https://aclanthology.org/2023.findings-acl.448
%U https://doi.org/10.18653/v1/2023.findings-acl.448
%P 7165-7179
Markdown (Informal)
[Knowledge Graph Embeddings using Neural Ito Process: From Multiple Walks to Stochastic Trajectories](https://aclanthology.org/2023.findings-acl.448) (Nayyeri et al., Findings 2023)
ACL