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

被引：0
作者：
Gao Y. [1 ]
Meng H. [1 ]
Ye C. [1 ]
机构：
[1] Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing
来源：
Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis | 2023年 / 59卷 / 03期
关键词：
geographic knowledge graph; place; representation learning; spatial constraint; spatial relationship;
D O I：
10.13209/j.0479-8023.2023.002
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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. © 2023 Peking University. All rights reserved.
引用
收藏
页码：434 / 444
页数：10
相关论文
共 28 条
  • [1] Relph E., Place and placelessness, (1976)
  • [2] Tuan Y F., Space and place: humanistic perspective, Progress in Human Geography, 6, pp. 233-246, (1974)
  • [3] Purves R S, Winter S, Kuhn W., Places in Information Science, Journal of the Association for Information Science and Technology, 70, 11, pp. 1173-1182, (2019)
  • [4] Goodchild M F., Formalizing place in geographic information systems, Communities, neighborhoods, and health, pp. 21-33, (2011)
  • [5] Scheider S, Janowicz K., Place reference systems: a constructive activity model of reference to places, Applied Ontology, 9, 2, pp. 97-127, (2014)
  • [6] Paulheim H., Knowledge graph refinement: a survey of approaches and evaluation methods, Semantic Web Journal, 8, 3, pp. 489-508, (2017)
  • [7] Yan B, Janowicz K, Mai G, Et al., A spatially explicit reinforcement learning model for geographic knowledge graph summarization, Transactions in GIS, 23, 3, pp. 620-640, (2019)
  • [8] Mai G, Janowicz K, Cai L, Et al., SE-KGE: a location-aware knowledge graph embedding model for geographic question answering and spatial semantic lifting, Transactions in GIS, 24, pp. 623-655, (2020)
  • [9] Qiu P, Gao J, Yu L, Et al., Knowledge embedding with geospatial distance restriction for geographic knowledge graph completion, ISPRS International Journal of Geo-Information, 8, 6, pp. 254-277, (2019)
  • [10] Wang Q, Mao Z, Wang B, Et al., Knowledge graph embedding: a survey of approaches and applications, IEEE Transactions on Knowledge and Data Engineering, 29, 12, pp. 2724-2743, (2017)
123