In this paper, we introduce a novel GNN-based knowledge graph embedding model, named WGE, to capture entity-focused graph structure and relation-focused graph structure. In particular, given the knowledge graph, WGE builds a single undirected entity-focused graph that views entities as nodes. In addition, WGE also constructs another single undirected graph from relation-focused constraints, which views entities and relations as nodes. WGE then proposes a new architecture of utilizing two vanilla GNNs directly on these two single graphs to better update vector representations of entities and relations, followed by a weighted score function to return the triple scores. Experimental results show that WGE obtains state-of-the-art performances on three new and challenging benchmark datasets CoDEx for knowledge graph completion.

翻译：在本文中,我们引入了一个新的以GNN为基础的知识图形嵌入模型,名为WGE,以捕捉以实体为重点的图表结构和以关系为重点的图表结构,特别是,根据知识图表,WGE建立了一个单一的、以实体为重点的、以实体为节点的无方向的图表,此外,WGE还从以关系为焦点的制约因素中构建了另一个将实体和关系视为节点的无方向的图表。WGE然后提出了一个新的结构,即直接利用这两个单一图表的两个vanilla GNN,以更好地更新实体和关系的矢量表达方式和关系,然后是加权得分函数,以回报三分。实验结果显示,WGE在三个新的、具有挑战性的基准数据集CODEx上取得了最新业绩,以完成知识图表。