arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.00720cs.CLcs.AIcs.LGcs.SI
收藏

知识图谱中是否存在更多模式?面向知识图谱嵌入的邻近模式研究

Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embedding

Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);National Computer Network Emergency Response Technical Team/Coordination Center of China(国家计算机网络应急技术处理协调中心)

Ren Li, Yanan Cao, Qiannan Zhu, Xiaoxue Li, Fang Fang

摘要:

关系模式的建模是知识图谱嵌入研究的核心内容,它表示一个实体与另一个实体之间的显式语义关系。然而,实体之间还有一种更自然、更直观的关联性,即一个实体在语义上如何接近另一个实体,却往往被忽略,而没有考虑任何显式的关系。我们将这种知识图谱中的语义现象称为邻近模式。在这项工作中,我们探讨了如何定义和表示邻近模式,以及如何利用它来帮助知识图谱嵌入的问题。首先,我们定义了任何两个实体的接近度,根据他们的统计共享查询,然后我们构建了一个派生的图结构,并表示从全局视图的接近模式。此外,在原有知识图谱的基础上,设计了一种链式耦合GNN(CP-GNN)结构,将两种模式(图谱)深度融合在一起,实现了更全面的知识嵌入。在FB 15 k-237和WN 18 RR数据集上进行了测试,CP-GNN在知识图谱补全任务上取得了最好的效果,尤其是对于包含多个答案实体的复杂查询,可以提高建模能力,证明了引入邻近模式的有效性。

英文摘要:

Modeling of relation pattern is the core focus of previous Knowledge Graph Embedding works, which represents how one entity is related to another semantically by some explicit relation. However, there is a more natural and intuitive relevancy among entities being always ignored, which is that how one entity is close to another semantically, without the consideration of any explicit relation. We name such semantic phenomenon in knowledge graph as proximity pattern. In this work, we explore the problem of how to define and represent proximity pattern, and how it can be utilized to help knowledge graph embedding. Firstly, we define the proximity of any two entities according to their statistically shared queries, then we construct a derived graph structure and represent the proximity pattern from global view. Moreover, with the original knowledge graph, we design a Chained couPle-GNN (CP-GNN) architecture to deeply merge the two patterns (graphs) together, which can encode a more comprehensive knowledge embedding. Being evaluated on FB15k-237 and WN18RR datasets, CP-GNN achieves state-of-the-art results for Knowledge Graph Completion task, and can especially boost the modeling capacity for complex queries that contain multiple answer entities, proving the effectiveness of introduced proximity pattern.

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。

↑