An attention-based representation learning model for multiple relational knowledge graph

doi:10.1111/exsy.13234

2023-01-22

PRE

韩忠明 (Zhongming Han) *

陈富于 (Fuyu Chen)

Hui Zhang

Yang Zhiyu (Zhiyu Yang)

Wenwen Liu

Zequan Shen

Haitao Xiong

DOI：10.1111/exsy.13234

原文链接

原文求助

摘要

En 中文

Knowledge graph embedding models are used to learn low-dimensional representations of entities and relations in knowledge graphs. In this paper, we propose Multi-RAttE, an attention-based learning method for multiple relational knowledge graph embedding representation, which divides the information transfer in the knowledge graph into cross-relational information transfer and relation-specific information transfer, and divides the embedding of knowledge graph entities into structural embedding and multi-relational embedding for joint learning. To objectively analyse the performance of the Multi-RAttE model, we select two typical datasets and different representative baseline models for experimental evaluation on several tasks such as link prediction, multi-relation prediction and node classification. The experimental results show that the Multi-RAttE model improves 8% over the state-of-the-art model Composition-based Multi-Relational Graph Convolutional Networks (CompGCN) in terms of Hits@1 metric on the link prediction task on FB15k-237 dataset; on the multi-relation prediction task, the accuracy improves by 1.8% and 3.7% in the auc metric and F1 metric, respectively. The experimental results have proved that the Multi-RAttE model can effectively perform the representation of multiple relations.

Keyword:

attention

GNN

knowledge graph embedding

representation learning