The University of Southampton
University of Southampton Institutional Repository

Knowledge graph embeddings using neural itô process: from multiple walks to stochastic trajectories

Knowledge graph embeddings using neural itô process: from multiple walks to stochastic trajectories
Knowledge graph embeddings using neural itô process: from multiple walks to stochastic trajectories
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.
7165–7179
Nayyeri, Mojtaba
476e5009-e6fc-45e6-ac7f-c07fe0898632
Xiong, Bo
d8c3ce0a-07ac-43f8-bd67-f230c6cbc1ec
Mohammadi, Majid
b6573731-029c-4219-aba9-bf770b5ba264
Akter, Mst. Mahfuja
d1dd6208-8631-4e61-a684-97bb460c20e5
Alam, Mirza Mohtashim
9cf33707-07d0-45a9-b9ea-c4bfba8484b1
Lehmann, Jens
314cdd18-fe27-4296-8e92-add6e359ba26
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
Nayyeri, Mojtaba
476e5009-e6fc-45e6-ac7f-c07fe0898632
Xiong, Bo
d8c3ce0a-07ac-43f8-bd67-f230c6cbc1ec
Mohammadi, Majid
b6573731-029c-4219-aba9-bf770b5ba264
Akter, Mst. Mahfuja
d1dd6208-8631-4e61-a684-97bb460c20e5
Alam, Mirza Mohtashim
9cf33707-07d0-45a9-b9ea-c4bfba8484b1
Lehmann, Jens
314cdd18-fe27-4296-8e92-add6e359ba26
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49

Nayyeri, Mojtaba, Xiong, Bo, Mohammadi, Majid, Akter, Mst. Mahfuja, Alam, Mirza Mohtashim, Lehmann, Jens and Staab, Steffen (2023) Knowledge graph embeddings using neural itô process: from multiple walks to stochastic trajectories. Findings of the Association for Computational Linguistics: ACL 2023, , Toronto, Canada. 09 - 14 Jul 2023. 7165–7179 . (doi:10.18653/v1/2023.findings-acl.448).

Record type: Conference or Workshop Item (Paper)

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.

Text
ItoProcessEmbedding-CameraReadyCopy - Accepted Manuscript
Download (1MB)

More information

Accepted/In Press date: 1 June 2023
Published date: July 2023
Venue - Dates: Findings of the Association for Computational Linguistics: ACL 2023, , Toronto, Canada, 2023-07-09 - 2023-07-14

Identifiers

Local EPrints ID: 478327
URI: http://eprints.soton.ac.uk/id/eprint/478327
PURE UUID: affc3f1c-8416-4958-9484-49b0d8adaab0
ORCID for Steffen Staab: ORCID iD orcid.org/0000-0002-0780-4154

Catalogue record

Date deposited: 28 Jun 2023 16:33
Last modified: 02 Sep 2025 01:49

Export record

Altmetrics

Contributors

Author: Mojtaba Nayyeri
Author: Bo Xiong
Author: Majid Mohammadi
Author: Mst. Mahfuja Akter
Author: Mirza Mohtashim Alam
Author: Jens Lehmann
Author: Steffen Staab ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×