Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916665984286720 |
|---|---|
| author | Chen, Jianfang Zhang, Kai Gan, Aoran Tong, Shiwei Shen, Shuanghong Liu, Qi |
| author_facet | Chen, Jianfang Zhang, Kai Gan, Aoran Tong, Shiwei Shen, Shuanghong Liu, Qi |
| contents | Knowledge Graph Completion (KGC) aims to infer missing information in Knowledge Graphs (KGs) to address their inherent incompleteness. Traditional structure-based KGC methods, while effective, face significant computational demands and scalability challenges due to the need for dense embedding learning and scoring all entities in the KG for each prediction. Recent text-based approaches using language models like T5 and BERT have mitigated these issues by converting KG triples into text for reasoning. However, they often fail to fully utilize contextual information, focusing mainly on the neighborhood of the entity and neglecting the context of the relation. To address this issue, we propose KGC-ERC, a framework that integrates both types of context to enrich the input of generative language models and enhance their reasoning capabilities. Additionally, we introduce a sampling strategy to effectively select relevant context within input token constraints, which optimizes the utilization of contextual information and potentially improves model performance. Experiments on the Wikidata5M, Wiki27K, and FB15K-237-N datasets show that KGC-ERC outperforms or matches state-of-the-art baselines in predictive performance and scalability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23205 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context Chen, Jianfang Zhang, Kai Gan, Aoran Tong, Shiwei Shen, Shuanghong Liu, Qi Computation and Language Artificial Intelligence Databases Knowledge Graph Completion (KGC) aims to infer missing information in Knowledge Graphs (KGs) to address their inherent incompleteness. Traditional structure-based KGC methods, while effective, face significant computational demands and scalability challenges due to the need for dense embedding learning and scoring all entities in the KG for each prediction. Recent text-based approaches using language models like T5 and BERT have mitigated these issues by converting KG triples into text for reasoning. However, they often fail to fully utilize contextual information, focusing mainly on the neighborhood of the entity and neglecting the context of the relation. To address this issue, we propose KGC-ERC, a framework that integrates both types of context to enrich the input of generative language models and enhance their reasoning capabilities. Additionally, we introduce a sampling strategy to effectively select relevant context within input token constraints, which optimizes the utilization of contextual information and potentially improves model performance. Experiments on the Wikidata5M, Wiki27K, and FB15K-237-N datasets show that KGC-ERC outperforms or matches state-of-the-art baselines in predictive performance and scalability. |
| title | Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context |
| topic | Computation and Language Artificial Intelligence Databases |
| url | https://arxiv.org/abs/2503.23205 |