MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations Completion
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 th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/9/493 |
| _version_ | 1797487517155459072 |
|---|---|
| author | Zongcai Huang Peiyuan Qiu Li Yu Feng Lu |
| author_facet | Zongcai Huang Peiyuan Qiu Li Yu Feng Lu |
| author_sort | Zongcai Huang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T23:49:49Z |
| format | Article |
| id | doaj.art-903db1472d6542ac99fd193eae7615f2 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-09T23:49:49Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-903db1472d6542ac99fd193eae7615f22023-11-23T16:37:28ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-09-0111949310.3390/ijgi11090493MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations CompletionZongcai Huang0Peiyuan Qiu1Li Yu2Feng Lu3State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaSchool of Surveying and Geo-Informatics, Shandong Jianzhu University, Jinan 250101, ChinaNational Academy of Safety and Development, Beijing Institute of Technology, Beijing 100081, ChinaState Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaGeographic 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.https://www.mdpi.com/2220-9964/11/9/493geographic knowledge graphrelation completionrepresentation learningsimilarity networkrelation prediction |
| spellingShingle | Zongcai Huang Peiyuan Qiu Li Yu Feng Lu MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations Completion ISPRS International Journal of Geo-Information geographic knowledge graph relation completion representation learning similarity network relation prediction |
| title | MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations Completion |
| title_full | MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations Completion |
| title_fullStr | MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations Completion |
| title_full_unstemmed | MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations Completion |
| title_short | MSEN-GRP: A Geographic Relations Prediction Model Based on Multi-Layer Similarity Enhanced Networks for Geographic Relations Completion |
| title_sort | msen grp a geographic relations prediction model based on multi layer similarity enhanced networks for geographic relations completion |
| topic | geographic knowledge graph relation completion representation learning similarity network relation prediction |
| url | https://www.mdpi.com/2220-9964/11/9/493 |
| work_keys_str_mv | AT zongcaihuang msengrpageographicrelationspredictionmodelbasedonmultilayersimilarityenhancednetworksforgeographicrelationscompletion AT peiyuanqiu msengrpageographicrelationspredictionmodelbasedonmultilayersimilarityenhancednetworksforgeographicrelationscompletion AT liyu msengrpageographicrelationspredictionmodelbasedonmultilayersimilarityenhancednetworksforgeographicrelationscompletion AT fenglu msengrpageographicrelationspredictionmodelbasedonmultilayersimilarityenhancednetworksforgeographicrelationscompletion |