arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.07396cs.CLcs.LG
收藏

基于节点共生的图神经网络知识图谱链接预测

Node Co-occurrence based Graph Neural Networks for Knowledge Graph Link Prediction

Oracle Labs, Australia(甲骨文实验室(澳大利亚));VinAI Research, Vietnam(VinAI 研究院(越南));Monash University, Australia(莫纳什大学(澳大利亚))

Dai Quoc Nguyen, Vinh Tong, Dinh Phung, Dat Quoc Nguyen

摘要:

我们引入了一种新的嵌入模型,称为NoGE,其目的是将实体和关系之间的共现集成到图神经网络中,以提高知识图谱的完备性(即,链接预测)。给定一个知识图谱,NoGE将实体和关系视为单个节点来构建单个图。然后,NoGE基于实体和关系的共现来计算节点之间的边的权重。接下来,NoGE提出了双四元数图神经网络(DualQGNN),并利用DualQGNN更新实体和关系节点的矢量表示。然后,NoGE采用评分函数来产生三重评分。综合实验结果表明,NoGE获得了国家的最先进的结果在三个新的和困难的基准数据集CoDEx的知识图谱完成。

英文摘要:

We introduce a novel embedding model, named NoGE, which aims to integrate co-occurrence among entities and relations into graph neural networks to improve knowledge graph completion (i.e., link prediction). Given a knowledge graph, NoGE constructs a single graph considering entities and relations as individual nodes. NoGE then computes weights for edges among nodes based on the co-occurrence of entities and relations. Next, NoGE proposes Dual Quaternion Graph Neural Networks (DualQGNN) and utilizes DualQGNN to update vector representations for entity and relation nodes. NoGE then adopts a score function to produce the triple scores. Comprehensive experimental results show that NoGE obtains state-of-the-art results on three new and difficult benchmark datasets CoDEx for knowledge graph completion.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑