arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.01933cs.AIcs.CGcs.CLcs.SC
收藏

Concept2Box:用于学习双视图知识图谱的联合几何嵌入

Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs

University of California, Los Angeles(加州大学洛杉矶分校);Amazon.com Inc(亚马逊公司);University of California, San Diego(加州大学圣地亚哥分校);Carnegie Mellon University(卡内基梅隆大学)

Zijie Huang, Daheng Wang, Binxuan Huang, Chenwei Zhang, Jingbo Shang, Yan Liang, Zhengyang Wang, Xian Li, Christos Faloutsos, Yizhou Sun, Wei Wang

AI总结:

Concept2Box提出用盒子嵌入表示本体概念、向量表示实例实体,并通过向量到盒子距离度量联合学习,以捕捉知识图谱双视图的结构差异和概念粒度。

摘要:

知识图谱嵌入(KGE)已被广泛研究,用于为许多现实世界应用嵌入大规模关系数据。现有方法长期忽视了一个事实:许多知识图谱包含两种根本不同的视图:高层本体视图的概念和细粒度实例视图的实体。它们通常将所有节点嵌入到一个潜在空间中的向量。然而,单一的几何表示无法捕捉两种视图之间的结构差异,并且缺乏面向概念粒度的概率语义。我们提出Concept2Box,这是一种利用双重几何表示联合嵌入知识图谱两种视图的新方法。我们使用盒子嵌入对概念进行建模,从而学习概念之间的层次结构以及重叠和不相交等复杂关系。盒子体积可以解释为概念的粒度。与概念不同,我们将实体建模为向量。为了弥合概念盒子嵌入与实体向量嵌入之间的差距,我们提出了一种新的向量到盒子距离度量,并联合学习两种嵌入。在公开的DBpedia知识图谱和一个新创建的工业知识图谱上的实验表明了Concept2Box的有效性。

英文摘要:

Knowledge graph embeddings (KGE) have been extensively studied to embed large-scale relational data for many real-world applications. Existing methods have long ignored the fact many KGs contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities. They usually embed all nodes as vectors in one latent space. However, a single geometric representation fails to capture the structural differences between two views and lacks probabilistic semantics towards concepts' granularity. We propose Concept2Box, a novel approach that jointly embeds the two views of a KG using dual geometric representations. We model concepts with box embeddings, which learn the hierarchy structure and complex relations such as overlap and disjoint among them. Box volumes can be interpreted as concepts' granularity. Different from concepts, we model entities as vectors. To bridge the gap between concept box embeddings and entity vector embeddings, we propose a novel vector-to-box distance metric and learn both embeddings jointly. Experiments on both the public DBpedia KG and a newly-created industrial KG showed the effectiveness of Concept2Box.

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。

↑