Multi-modal Knowledge Graph Generation with Semantics-enriched Prompts
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915249977819136 |
|---|---|
| author | Xu, Yajing Liu, Zhiqiang Chen, Jiaoyan Tu, Mingchen Chen, Zhuo Pan, Jeff Z. Zhang, Yichi Zhu, Yushan Zhang, Wen Chen, Huajun |
| author_facet | Xu, Yajing Liu, Zhiqiang Chen, Jiaoyan Tu, Mingchen Chen, Zhuo Pan, Jeff Z. Zhang, Yichi Zhu, Yushan Zhang, Wen Chen, Huajun |
| contents | Multi-modal Knowledge Graphs (MMKGs) have been widely applied across various domains for knowledge representation. However, the existing MMKGs are significantly fewer than required, and their construction faces numerous challenges, particularly in ensuring the selection of high-quality, contextually relevant images for knowledge graph enrichment. To address these challenges, we present a framework for constructing MMKGs from conventional KGs. Furthermore, to generate higher-quality images that are more relevant to the context in the given knowledge graph, we designed a neighbor selection method called Visualizable Structural Neighbor Selection (VSNS). This method consists of two modules: Visualizable Neighbor Selection (VNS) and Structural Neighbor Selection (SNS). The VNS module filters relations that are difficult to visualize, while the SNS module selects neighbors that most effectively capture the structural characteristics of the entity. To evaluate the quality of the generated images, we performed qualitative and quantitative evaluations on two datasets, MKG-Y and DB15K. The experimental results indicate that using the VSNS method to select neighbors results in higher-quality images that are more relevant to the knowledge graph. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_13631 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-modal Knowledge Graph Generation with Semantics-enriched Prompts Xu, Yajing Liu, Zhiqiang Chen, Jiaoyan Tu, Mingchen Chen, Zhuo Pan, Jeff Z. Zhang, Yichi Zhu, Yushan Zhang, Wen Chen, Huajun Artificial Intelligence Multi-modal Knowledge Graphs (MMKGs) have been widely applied across various domains for knowledge representation. However, the existing MMKGs are significantly fewer than required, and their construction faces numerous challenges, particularly in ensuring the selection of high-quality, contextually relevant images for knowledge graph enrichment. To address these challenges, we present a framework for constructing MMKGs from conventional KGs. Furthermore, to generate higher-quality images that are more relevant to the context in the given knowledge graph, we designed a neighbor selection method called Visualizable Structural Neighbor Selection (VSNS). This method consists of two modules: Visualizable Neighbor Selection (VNS) and Structural Neighbor Selection (SNS). The VNS module filters relations that are difficult to visualize, while the SNS module selects neighbors that most effectively capture the structural characteristics of the entity. To evaluate the quality of the generated images, we performed qualitative and quantitative evaluations on two datasets, MKG-Y and DB15K. The experimental results indicate that using the VSNS method to select neighbors results in higher-quality images that are more relevant to the knowledge graph. |
| title | Multi-modal Knowledge Graph Generation with Semantics-enriched Prompts |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2504.13631 |