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
July 2023
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.
.
(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
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
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
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