In the field of representation learning on knowledge graphs (KGs), a hyper-relational fact consists of a main triple and several auxiliary attribute-value descriptions, which is considered more comprehensive and specific than a triple-based fact. However, currently available hyper-relational KG embedding methods in a single view are limited in application because they weaken the hierarchical structure that represents the affiliation between entities. To overcome this limitation, we propose a dual-view hyper-relational KG structure (DH-KG) that contains a hyper-relational instance view for entities and a hyper-relational ontology view for concepts that are abstracted hierarchically from the entities. This paper defines link prediction and entity typing tasks on DH-KG for the first time and constructs two DH-KG datasets, JW44K-6K, extracted from Wikidata, and HTDM based on medical data. Furthermore, we propose DHGE, a DH-KG embedding model based on GRAN encoders, HGNNs, and joint learning. DHGE outperforms baseline models on DH-KG, according to experimental results. Finally, we provide an example of how this technology can be used to treat hypertension. Our model and new datasets are publicly available.

翻译：摘要：在知识图谱表示学习领域，超关系事实由主三元组及若干辅助属性值描述构成，其信息综合性与特异性被公认优于传统三元组事实。然而，现有基于单一视图的超关系知识图谱嵌入方法因弱化了表征实体间隶属关系的层级结构，导致应用范围受限。为克服这一局限，本文提出双视图超关系知识图谱结构（DH-KG），该结构包含面向实体的超关系实例视图与面向从实体抽象出的层级概念的超关系本体视图。本文首次在DH-KG上定义了链接预测与实体类型推断任务，并构建了两个DH-KG数据集：从维基数据抽取的JW44K-6K与基于医疗数据的HTDM。此外，我们提出基于GRAN编码器、HGNN与联合学习的DH-KG嵌入模型DHGE。实验结果表明，DHGE在DH-KG上优于基线模型。最后，以高血压治疗方案为例展示该技术的应用价值。本模型与新数据集均已开源。