Kernel multi-attention neural network for knowledge graph embedding

作者:

Highlights:

摘要

Link prediction is the problem of predicting missing link between entities and relations for knowledge graph. In recent years, some tasks have achieved great success for link prediction, but these tasks are far from expanding entity relation vectors, and cannot predict missing links more efficiently. In this paper, we propose a novel link prediction method called kernel multi-attention neural network for knowledge graph embedding (KMAE) which is able to extend kernel separately in entity and relation attributes. The kernel function uses Gaussian kernel function to expand into more robust entity kernel and relation kernel. In addition, we constructed a novel multi-attention neural network that acts on the entity kernel and relation kernel which can capture local important characteristics. Experiments on FB15k-237 and WN18RR, show that multi-attention fully reflect excellent performance in the task of knowledge graph embedding. Our proposed KMAE achieves better results than previous state-of-the-art link prediction methods.

论文关键词:Link prediction,Entity kernel,Relation kernel,Multi-attention neural network,Knowledge graph embedding

论文评审过程:Received 28 November 2020, Revised 28 May 2021, Accepted 30 May 2021, Available online 4 June 2021, Version of Record 9 June 2021.

论文官网地址:https://doi.org/10.1016/j.knosys.2021.107188