Journal
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
Volume 11, Issue 9, Pages -Publisher
MDPI
DOI: 10.3390/ijgi11090493
Keywords
geographic knowledge graph; relation completion; representation learning; similarity network; relation prediction
Funding
- National Natural Science Foundation of China [41631177, 41801320, 42001341]
Ask authors/readers for more resources
Geographic relation completion is crucial for improving the quality of large-scale geographic knowledge graphs (GeoKGs). This study proposes a geographic relation prediction model based on multi-layer similarity enhanced networks, which effectively enhances the implicit semantic associations between existing geographic entities. Experimental results demonstrate the high accuracy of this method in geo-relations prediction.
Geographic relation completion contributes greatly to improving the quality of large-scale geographic knowledge graphs (GeoKGs). However, the internal features of a GeoKG used in large-scale GeoKGs embedding are often limited by the weak connectivity between geographic entities (geo-entities). If there is no proper choice in the method of external semantic enhancement, this will often interfere with the representation and learning of the KG. Therefore, we here propose a geographic relation (geo-relation) prediction model based on multi-layer similarity enhanced networks for geo-relations completion (MSEN-GRP). The MSEN-GRP comprises three parts: enhancer, encoder, and decoder. The enhancer constructs semantic, spatial, structural, and attribute-similarity networks for geo-entities, which can explicitly and effectively enhance the implicit semantic associations between existing geo-entities. The encoder can obtain the long path relation dependency characteristics of geo-entities using a mixed-path sampling strategy and can support different optimization schemes for external semantic enhancement. Geo-relations prediction experiments show that the mean reciprocal ranking of this method is significantly higher than those of the traditional TransE DisMult and methods, and Hits@10 is improved by up to 57.57%. Furthermore, the spatial-similarity network has the most significant enhancement effect on geo-relations prediction. The proposed method provides a new way to perform relation completion in sparse GeoKGs.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available