A deep learning architecture for aligning cross-domain geographic knowledge graph
文献类型：期刊论文
| 作者 | Qiu, Qinjun4,5,6,7; Zheng, Shiyu7; Li, Jiali7; Tian, Miao6; Li, Zixuan3; Tao, Liufeng4,5,6,7; Zhu, Yunqiang2; Huang, Yi1; Chen, Zhanlong4,5,6,7; Xie, Zhong4,5,6,7 |
| 刊名 | INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
 |
| 出版日期 | 2025-03-12 |
| 卷号 | N/A |
| 关键词 | Knowledge graph alignment graph neural network geographic text geographic information retrieval deep learning |
| ISSN号 | 1365-8816 |
| DOI | 10.1080/13658816.2025.2477615 |
| 产权排序 | 6 |
| 文献子类 | Article ; Early Access |
| 英文摘要 | Geographic knowledge graph (GeoKG) alignment is important for the integration and knowledge discovery of multisource geographic information and the generation of large-scale and high-quality knowledge graphs (KGs). However, the existing models/technologies face many challenges when dealing with large-scale multisource complex GeoKG alignment tasks, including the inconsistency of attribute and relationship values caused by domain differences, the inability to perceive relationships and entities, and missing geographic domain training data. To address these issues, we propose a GeoKG alignment model based on depth relationships and neighborhood awareness (named DRNA-GCNE). The DRNA-GCNE model adopts a graph neural network as the infrastructure and uses the graph attention technique to evaluate and weight the entity's relationship attributes dynamically, thus enhancing the ability to perceive structural and semantic information in the GeoKG; concurrently, the relationship information and the multihop neighbor characteristics of the entity are effectively integrated, and the representation of the entity is further enriched. Finally, the training technique of normalized loss mining for multiple negative samples is shown. This approach increases the model's capacity for generalization. The DRNA-GCNE model, as evaluated on two public datasets and our GeoEA2024 Chinese dataset, significantly outperforms current GeoKG entity alignment methods across key metrics. |
| URL标识 | 查看原文 |
| WOS研究方向 | Computer Science ; Geography ; Physical Geography ; Information Science & Library Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001445318000001 |
| 出版者 | TAYLOR & FRANCIS LTD |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/213257]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Qiu, Qinjun |
| 作者单位 | 1.Nanjing Univ Posts & Telecommun, Sch Internet Things, Nanjing, Peoples R China 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China; 3.China Univ Geosci, Sch Geog & Informat Engn, Wuhan, Peoples R China; 4.Minist Educ, Engn Res Ctr Nat Resource Informat Management & Di, Wuhan, Peoples R China; 5.Minist Nat Resources, Key Lab Quantitat Resources Assessment & Informat, Wuhan, Peoples R China; 6.China Univ Geosci, Key Lab Geol Survey & Evaluat, Minist Educ, Wuhan, Peoples R China; 7.China Univ Geosci, Sch Comp Sci, Wuhan, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Qiu, Qinjun,Zheng, Shiyu,Li, Jiali,et al. A deep learning architecture for aligning cross-domain geographic knowledge graph[J]. INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,2025,N/A. |
| APA | Qiu, Qinjun.,Zheng, Shiyu.,Li, Jiali.,Tian, Miao.,Li, Zixuan.,...&Xie, Zhong.(2025).A deep learning architecture for aligning cross-domain geographic knowledge graph.INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,N/A. |
| MLA | Qiu, Qinjun,et al."A deep learning architecture for aligning cross-domain geographic knowledge graph".INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE N/A(2025). |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。