Knowledge Graph Embedding by Bias Vectors

Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the resu...

Full description

Saved in:
Bibliographic Details
Main Authors: Ding, Minjie, Tong, Weiqin, Ding, Xuehai, Zhi, Xiaoli, Wang, Xiao, Zhang, Guoqing
Format: Conference Proceeding
Language:English
Subjects:
knowledge completion
knowledge embedding
link prediction
triplets
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Knowledge graph completion can predict the possible relation between entities. Previous work such as TransE, TransR, TransPES and GTrans embed knowledge graph into vector space and treat relations between entities as translations. In most cases, the more complex the algorithm is, the better the result will be, but it is difficult to apply to large-scale knowledge graphs. Therefore, we propose TransB, an efficient model, in this paper. We avoid the complex matrix or vector multiplication operation. Meanwhile, we make the representation of entities not too simple, which can satisfy the operation in the case of non-one-to-one relation. We use link prediction to evaluate the performance of our model in the experiment. The experimental results show that our model is valid and has low time complexity.
ISSN:2375-0197
DOI:10.1109/ICTAI.2019.00180