比较三种知识图谱元数据模型在链接预测中的表现差异。
Comparison of Metadata Representation Models for Knowledge Graph Embeddings
- 对比重构、单属性和RDF星三种元数据建模方式。
- 简单知识图谱中重构法效果最好，复杂场景下差异不大。
- 提出新评估框架，确保不同模型公平比较。
超关系知识图谱（HRKGs）将传统二元关系扩展至包含上下文、来源和时间信息的复杂场景，如历史事件、传感器数据、视频内容与叙事。现有元数据表示模型（MRMs）包括重构（REF）、单属性（SGP）和RDF星（RDR）。本文在链接预测（LP）任务中评估这些模型，发现现有评估框架存在偏差，并提出新任务以实现公平比较。同时，构建一个能有效映射三种MRMs知识表示的嵌入框架。在两类数据集上的实验表明：在简单HRKG中，REF表现优异；而SGP效果较差；但在复杂HRKG中，三者在LP任务中的差距极小。研究为HRKG在链接预测中的最优表示策略提供了依据。
原文摘要 · Abstract (English)
Hyper-relational Knowledge Graphs (HRKGs) extend traditional KGs beyond binary relations, enabling the representation of contextual, provenance, and temporal information in domains, such as historical events, sensor data, video content, and narratives. HRKGs can be structured using several Metadata Representation Models (MRMs), including Reification (REF), Singleton Property (SGP), and RDF-star (RDR). However, the effects of different MRMs on KG Embedding (KGE) and Link Prediction (LP) models remain unclear. This study evaluates MRMs in the context of LP tasks, identifies the limitations of existing evaluation frameworks, and introduces a new task that ensures fair comparisons across MRMs. Furthermore, we propose a framework that effectively reflects the knowledge representations of the three MRMs in latent space. Experiments on two types of datasets reveal that REF performs well in simple HRKGs, whereas SGP is less effective. However, in complex HRKGs, the differences among MRMs in the LP tasks are minimal. Our findings contribute to an optimal knowledge representation strategy for HRKGs in LP tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。