MöbiusE: Knowledge Graph Embedding on Möbius ring

Chen, Y; Liu, J; Zhang, Z; Wen, S; Xiong, W

MöbiusE: Knowledge Graph Embedding on Möbius ring

Chen, Y Liu, J Zhang, Z Wen, S

Xiong, W

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Knowledge-Based Systems, 2021, 227, pp. 1-7
Issue Date:: 2021-09-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0950705121004445-main.pdf	Published version	945.89 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Chen, Y
dc.contributor.author	Liu, J
dc.contributor.author	Zhang, Z
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.contributor.author	Xiong, W
dc.date.accessioned	2021-10-30T20:20:46Z
dc.date.available	2021-10-30T20:20:46Z
dc.date.issued	2021-09-01
dc.identifier.citation	Knowledge-Based Systems, 2021, 227, pp. 1-7
dc.identifier.issn	0950-7051
dc.identifier.uri	http://hdl.handle.net/10453/151273
dc.description.abstract	In this work, we propose a novel Knowledge Graph Embedding (KGE) strategy, called MöbiusE, in which the entities and relations are embedded to the surface of a Möbius ring. The proposition of such a strategy is inspired by the classic TorusE, in which the addition of two arbitrary elements is subject to a modulus operation. In this sense, TorusE naturally guarantees the critical boundedness of embedding vectors in KGE. However, the nonlinear property of addition operation on Torus ring is uniquely derived by the modulus operation, which in some extent restricts the expressiveness of TorusE. As a further generalization of TorusE, MöbiusE also uses modulus operation to preserve the closeness of addition on it, but the coordinates on Möbius ring interacts with each other in the following way: any vector attaches to the surface of a Mobius ring becomes its opposite one if it moves along its parametric trace by a cycle. Hence, MöbiusE assumes much more nonlinear representativeness than that of TorusE, and in turn it generates much more precise embedding results. In our experiments, MöbiusE outperforms TorusE and other classic embedding strategies in several key indicators.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Knowledge-Based Systems
dc.relation.isbasedon	10.1016/j.knosys.2021.107181
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences, 15 Commerce, Management, Tourism and Services, 17 Psychology and Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	MöbiusE: Knowledge Graph Embedding on Möbius ring
dc.type	Journal Article
utslib.citation.volume	227
utslib.for	08 Information and Computing Sciences
utslib.for	15 Commerce, Management, Tourism and Services
utslib.for	17 Psychology and Cognitive Sciences
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2021-10-30T20:20:44Z
pubs.publication-status	Published
pubs.volume	227

Abstract:

In this work, we propose a novel Knowledge Graph Embedding (KGE) strategy, called MöbiusE, in which the entities and relations are embedded to the surface of a Möbius ring. The proposition of such a strategy is inspired by the classic TorusE, in which the addition of two arbitrary elements is subject to a modulus operation. In this sense, TorusE naturally guarantees the critical boundedness of embedding vectors in KGE. However, the nonlinear property of addition operation on Torus ring is uniquely derived by the modulus operation, which in some extent restricts the expressiveness of TorusE. As a further generalization of TorusE, MöbiusE also uses modulus operation to preserve the closeness of addition on it, but the coordinates on Möbius ring interacts with each other in the following way: any vector attaches to the surface of a Mobius ring becomes its opposite one if it moves along its parametric trace by a cycle. Hence, MöbiusE assumes much more nonlinear representativeness than that of TorusE, and in turn it generates much more precise embedding results. In our experiments, MöbiusE outperforms TorusE and other classic embedding strategies in several key indicators.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/151273