ReaLitE: Enrichment of Relation Embeddings in Knowledge Graphs using Numeric Literals
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915222252421120 |
|---|---|
| author | Klironomos, Antonis Zhou, Baifan Zheng, Zhuoxun Mohamed, Gad-Elrab Paulheim, Heiko Kharlamov, Evgeny |
| author_facet | Klironomos, Antonis Zhou, Baifan Zheng, Zhuoxun Mohamed, Gad-Elrab Paulheim, Heiko Kharlamov, Evgeny |
| contents | Most knowledge graph embedding (KGE) methods tailored for link prediction focus on the entities and relations in the graph, giving little attention to other literal values, which might encode important information. Therefore, some literal-aware KGE models attempt to either integrate numerical values into the embeddings of the entities or convert these numerics into entities during preprocessing, leading to information loss. Other methods concerned with creating relation-specific numerical features assume completeness of numerical data, which does not apply to real-world graphs. In this work, we propose ReaLitE, a novel relation-centric KGE model that dynamically aggregates and merges entities' numerical attributes with the embeddings of the connecting relations. ReaLitE is designed to complement existing conventional KGE methods while supporting multiple variations for numerical aggregations, including a learnable method.
We comprehensively evaluated the proposed relation-centric embedding using several benchmarks for link prediction and node classification tasks. The results showed the superiority of ReaLitE over the state of the art in both tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00852 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReaLitE: Enrichment of Relation Embeddings in Knowledge Graphs using Numeric Literals Klironomos, Antonis Zhou, Baifan Zheng, Zhuoxun Mohamed, Gad-Elrab Paulheim, Heiko Kharlamov, Evgeny Machine Learning Artificial Intelligence Most knowledge graph embedding (KGE) methods tailored for link prediction focus on the entities and relations in the graph, giving little attention to other literal values, which might encode important information. Therefore, some literal-aware KGE models attempt to either integrate numerical values into the embeddings of the entities or convert these numerics into entities during preprocessing, leading to information loss. Other methods concerned with creating relation-specific numerical features assume completeness of numerical data, which does not apply to real-world graphs. In this work, we propose ReaLitE, a novel relation-centric KGE model that dynamically aggregates and merges entities' numerical attributes with the embeddings of the connecting relations. ReaLitE is designed to complement existing conventional KGE methods while supporting multiple variations for numerical aggregations, including a learnable method. We comprehensively evaluated the proposed relation-centric embedding using several benchmarks for link prediction and node classification tasks. The results showed the superiority of ReaLitE over the state of the art in both tasks. |
| title | ReaLitE: Enrichment of Relation Embeddings in Knowledge Graphs using Numeric Literals |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.00852 |