论文标题
传递超级关系知识图的消息
Message Passing for Hyper-Relational Knowledge Graphs
论文作者
论文摘要
超关系知识图（kgs）（例如，wikidata）使其他键值对以及主要三重配对将歧义歧义或限制事实的有效性。在这项工作中，我们提出了一个基于消息传递的图形编码器 - 能够对此类超相关KG进行建模。与现有方法不同，凝视可以编码任意数量的其他信息（限定符）以及主要三重信息，同时保持预选赛和三元组的语义角色完整。我们还证明了评估超相关KG的链接预测（LP）性能的现有基准，遭受了基本缺陷，因此开发了一个新的基于Wikidata的数据集-WD50K。我们的实验表明，基于凝视的LP模型的表现优于多个基准的现有方法。我们还确认，与三重表示相比，利用限定符对于与高达25 MRR点的链接预测至关重要。
Hyper-relational knowledge graphs (KGs) (e.g., Wikidata) enable associating additional key-value pairs along with the main triple to disambiguate, or restrict the validity of a fact. In this work, we propose a message passing based graph encoder - StarE capable of modeling such hyper-relational KGs. Unlike existing approaches, StarE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset - WD50K. Our experiments demonstrate that StarE based LP model outperforms existing approaches across multiple benchmarks. We also confirm that leveraging qualifiers is vital for link prediction with gains up to 25 MRR points compared to triple-based representations.
