A Spatially Constraint Negative Sample Generation Method for Geographic Knowledge Graph Embedding

doi:10.13209/j.0479-8023.2023.002

Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2023, Vol. 59 ›› Issue (3): 434-444.DOI: 10.13209/j.0479-8023.2023.002

Previous Articles Next Articles

A Spatially Constraint Negative Sample Generation Method for Geographic Knowledge Graph Embedding

GAO Yong^†, MENG Haohan, YE Chao

Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing 100871

Received:2022-04-28 Revised:2022-05-11 Online:2023-05-20 Published:2023-05-20
Contact: GAO Yong, E-mail: gaoyong(at)pku.edu.cn

基于空间约束的地理知识图谱嵌入表示的负样本生成方法

高勇^†, 孟浩瀚, 叶超

北京大学地球与空间科学学院遥感与地理信息系统研究所, 北京 100871

通讯作者: 高勇, E-mail: gaoyong(at)pku.edu.cn
基金资助:
国家自然科学基金(41971331)资助

Abstract

Abstract:

Geographic knowledge graph representation learning requires generating the corresponding negative samples based on the positive ones. However, traditional negative sample generation algorithms suffer from high error rate and poor adaption to geographic knowledge graph. Aimming at this problem, a spatially constraint negative sample generation method was proposed by modifying the modeling of spatial relations. Then the method was applied to different knowledge graph representation learning models to explore its suitability in geographic knowledge graph embedding. Results show that the proposed method has a low error rate and is suitable for two common types of knowledge graph representation models. The spatially constraint negative sample generation method will improve the accuracy of geographic knowledge graph representation learning, which helps to advance geographical research.

Key words: geographic knowledge graph, representation learning, spatial constraint, spatial relationship, place

摘要：

地理知识图谱的表示学习需要根据正样本生成对应的负样本, 然而传统的负样本生成算法存在错误率高、地理知识图谱适配性差的问题。针对这一问题, 调整空间关系在地理知识图谱中的表达方式, 提出基于空间约束的负样本生成方法, 并将该方法应用至不同的知识图谱表示学习模型, 探讨其在地理知识图谱表示学习中的适配性。结果表明, 该算法具有较低的错误率, 同时适用于常见的两类知识图谱表示模型, 能够提高地理知识图谱表示学习的精度, 有助于地理知识图谱在地理研究中发挥更重要的作用。

关键词: 地理知识图谱, 表示学习, 空间约束, 空间关系, 场所

GAO Yong, MENG Haohan, YE Chao. A Spatially Constraint Negative Sample Generation Method for Geographic Knowledge Graph Embedding[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(3): 434-444.

高勇, 孟浩瀚, 叶超. 基于空间约束的地理知识图谱嵌入表示的负样本生成方法[J]. 北京大学学报自然科学版, 2023, 59(3): 434-444.

Add to citation manager EndNote|Ris|BibTeX

URL: https://xbna.pku.edu.cn/EN/10.13209/j.0479-8023.2023.002

https://xbna.pku.edu.cn/EN/Y2023/V59/I3/434

[1]	TIAN Yuan, CHANG Xiaoyin, ZHAO Wenyi, CHENG Chuyun, Bronte Scheuer, DENG Yanglanduo, MA Ruiping, ZHANG Jianxue. Supplemental Evaluation of Landslide Displacement Prediction Models [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(3): 513-520.
[2]	GU Shulun, JIANG Dayong, ZHOU Min. Study of the Tooth Replacement of Chaohusaurus brevifemoralis from the Lower Triassic of Chaohu, Anhui Province [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(2): 239-248.
[3]	XIANG Lanlin, ZHANG Junchu, YAN Yuhan, MA Beibei. Changes of Sense of Place in Historic Conservation Areas under the Representations of Social Perception Data: A Case Study of Nanluoguxiang (2008–2022) [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2024, 60(2): 289-305.
[4]	FENG Jun, YAN Jiyuan, ZHAO Xiaoxia. Preliminary Investigation on the Surface Ruptures of the Turkey M7.8 Earthquake on February 6, 2023 [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(6): 945-950.
[5]	TIAN Yuan, PANG Xiao, ZHAO Wenyi, CHANG Xiaoyin, CHENG Chuyun, ZOU Pei, CAO Xiaocheng. A Transformer-Based Model for Short-Term Landslide Displacement Prediction [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(2): 197-210.
[6]	PENG Xia, WANG Yun, HUANG Zhou. Research on Differences of Image Perception of Beijing Historical and Cultural Districts among Various Cultural Groups [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(5): 949-958.
[7]	XIANG Lanlin, YE Yafei, PAN Jingdong, WANG Zhenlong. Residents’ Place Attachment from the Perspective of Lifeworld in Chinese Historic and Cultural Areas: A Case Study in Qianjin Street in Xinjiang [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2022, 58(3): 488-502.
[8]	LI Jing, LIU Yu, ZOU Lei. A Dynamic Graph Convolutional Network Based on Spatial-Temporal Modeling [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2021, 57(4): 605-613.
[9]	DING Weiming, NING Meng, QIN Shujian, DONG Lin. Sedimentary Characteristics of Dolomite from Gaoyuzhuang Formation in Beipiao Area, North China [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55(6): 1055-1066.
[10]	LIAO Xiangwen, WU Xiaojing, GUI Lin, HUANG Jinhui, CHEN Guolong. Cross-Domain Sentiment Classification Based on Representation Learning and Transfer Learning [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55(1): 37-46.
[11]	LI Xiaojun, SHI Hanxiao, CHEN Nannan, LIU Hong, ZOU Yi. Research on Sentiment Analysis Based on Representation Learning [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2019, 55(1): 105-112.
[12]	Li CONG, Bihu WU, Yujun ZHANG, Newsome Daivd. Research on Place Involvement in Wildlife Tourism: A Case Study of Dolphin Discovery Center in Bunbury, Australia [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(4): 715-721.
[13]	LIU Caishan. The Fundamental Equations in Analytical Mechanics for Nonholonomic Systems [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2016, 52(4): 756-766.
[14]	SHI Jin,TONG Xin,ZHANG Hongmou,TAO Dongyan. Spatial Interaction of Urban Residence and Workplace: An UrbanSim Application in Yichang, China [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2013, 49(6): 1065-1074.
[15]	CHAI Zhi,SHI Yongmin,XU Changsheng,ZHANG Yuguang,LI Hong,WU Wenjuan,XU Hongbo,WANG Lei. Pore-Throat Structure Evaluation of Artificial Cores with Rate-Controlled Porosimetry [J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2012, 48(5): 770-774.

A Spatially Constraint Negative Sample Generation Method for Geographic Knowledge Graph Embedding

基于空间约束的地理知识图谱嵌入表示的负样本生成方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics