Li, C., Peng, X. orcid.org/0000-0001-5787-9982, Niu, Y. et al. (4 more authors) (2021) Learning graph attention-aware knowledge graph embedding. Neurocomputing, 461. pp. 516-529. ISSN 0925-2312
Abstract
The knowledge graph, which utilizes graph structure to represent multi-relational data, has been widely used in the reasoning and prediction tasks, attracting considerable research efforts recently. However, most existing works still concentrate on learning knowledge graph embeddings straightforwardly and intuitively without subtly considering the context of knowledge. Specifically, recent models deal with each single triple independently or consider contexts indiscriminately, which is one-sided as each knowledge unit (i.e., triple) can be derived from its partial surrounding triples. In this paper, we propose a graph-attention-based model to encode entities, which formulates a knowledge graph as an irregular graph and explores a number of concrete and interpretable knowledge compositions by integrating the graph-structured information via multiple independent channels. To measure the correlation between entities from different angles (i.e., entity pair, relation, and structure), we respectively develop three attention metrics. By making use of our enhanced entity embeddings, we further introduce several improved factorization functions for updating relation embeddings and evaluating candidate triples. We conduct extensive experiments on downstream tasks including entity classification, entity typing, and link prediction to validate our methods. Empirical results validate the importance of our introduced attention metrics and demonstrate that our proposed method can improve the performance of factorization models on large-scale knowledge graphs.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 Elsevier B.V. This is an author produced version of a paper subsequently published in Neurocomputing. Uploaded in accordance with the publisher's self-archiving policy. Article available under the terms of the CC-BY-NC-ND licence (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
Keywords: | Knowledge graph embedding; Graph attention mechanism; Entity typing; Link prediction |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 25 Nov 2021 10:43 |
Last Modified: | 21 Jul 2022 00:13 |
Status: | Published |
Publisher: | Elsevier BV |
Refereed: | Yes |
Identification Number: | 10.1016/j.neucom.2021.01.139 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:180853 |
Download
Filename: Learning graph attention-aware knowledge graph embedding.pdf
Licence: CC-BY-NC-ND 4.0