Relational structure-aware knowledge graph representation in complex space

Date

2022

Authors

Sun, K.
Yu, S.
Peng, C.
Wang, Y.
Alfarraj, O.
Tolba, A.
Xia, F.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

Mathematics, 2022; 10(11, article no. 1930):1-16

Statement of Responsibility

Conference Name

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.

School/Discipline

Dissertation Note

Provenance

Description

Data source: Data availability statement, https://doi.org/10.3390/math10111930

Access Status

Rights

Copyright 2022 the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. (https://creativecommons.org/licenses/by/4.0/)

License

Grant ID

Call number

Persistent link to this record