Comparison of Metadata Representation Models for Knowledge Graph Embeddings
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910899499958272 |
|---|---|
| author | Egami, Shusaku Matsushita, Kyoumoto Ugai, Takanori Fukuda, Ken |
| author_facet | Egami, Shusaku Matsushita, Kyoumoto Ugai, Takanori Fukuda, Ken |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21804 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comparison of Metadata Representation Models for Knowledge Graph Embeddings Egami, Shusaku Matsushita, Kyoumoto Ugai, Takanori Fukuda, Ken Machine Learning Artificial Intelligence Information Retrieval I.2.4; I.2.7 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. |
| title | Comparison of Metadata Representation Models for Knowledge Graph Embeddings |
| topic | Machine Learning Artificial Intelligence Information Retrieval I.2.4; I.2.7 |
| url | https://arxiv.org/abs/2503.21804 |