Relational Structure-Aware Knowledge Graph Representation in Complex Space

Ke Sun, Shuo Yu, Ciyuan Peng, Yueru Wang, Osama Alfarraj, Amr Tolba and Feng Xia
Additional contact information
Ke Sun: School of Software, Dalian University of Technology, Dalian 116620, China
Shuo Yu: School of Software, Dalian University of Technology, Dalian 116620, China
Ciyuan Peng: Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC 3353, Australia
Yueru Wang: Department of Mathematics, National Tsing Hua University, Hsinchu 30013, Taiwan
Osama Alfarraj: Computer Science Department, Community College, King Saud University, Riyadh 11437, Saudi Arabia
Amr Tolba: Computer Science Department, Community College, King Saud University, Riyadh 11437, Saudi Arabia
Feng Xia: Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC 3353, Australia

Mathematics, 2022, vol. 10, issue 11, 1-16

Abstract: Relations in knowledge graphs have rich relational structures and various binary relational patterns. Various relation modelling strategies are proposed for embedding knowledge graphs, but they fail to fully capture both features of relations, rich relational structures and various binary relational patterns. To address the problem of insufficient embedding due to the complexity of the relations, we propose a novel knowledge graph representation model in complex space, namely MARS, to exploit complex relations to embed knowledge graphs. MARS takes the mechanisms of complex numbers and message-passing and then embeds triplets into relation-specific complex hyperplanes. Thus, MARS can well preserve various relation patterns, as well as structural information in knowledge graphs. In addition, we find that the scores generated from the score function approximate a Gaussian distribution. The scores in the tail cannot effectively represent triplets. To address this particular issue and improve the precision of embeddings, we use the standard deviation to limit the dispersion of the score distribution, resulting in more accurate embeddings of triplets. Comprehensive experiments on multiple benchmarks demonstrate that our model significantly outperforms existing state-of-the-art models for link prediction and triple classification.

Keywords: message passing; complex space; knowledge representation learning; link prediction; triple classification (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/11/1930/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/11/1930/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:11:p:1930-:d:831550

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().