Multi-information Optimized Entity Alignment Model Based on Graph Neural Network
Entity alignment is a key step in knowledge fusion,which aims to discover entity pairs with corresponding relations between knowledge graphs.Knowledge fusion enables a more extensive and accurate services for further knowledge graph applications.However,the entity names and relations are used insuff...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2023-03-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-3-34.pdf |
| _version_ | 1797845043273269248 |
|---|---|
| author | CHEN Fuqiang, KOU Jiamin, SU Limin, LI Ke |
| author_facet | CHEN Fuqiang, KOU Jiamin, SU Limin, LI Ke |
| author_sort | CHEN Fuqiang, KOU Jiamin, SU Limin, LI Ke |
| collection | DOAJ |
| description | Entity alignment is a key step in knowledge fusion,which aims to discover entity pairs with corresponding relations between knowledge graphs.Knowledge fusion enables a more extensive and accurate services for further knowledge graph applications.However,the entity names and relations are used insufficiently by most of the state-of-the-art models of entity alignment.After obtaining the vector representation of the entity,generally the alignment relations among the entities are obtained through single iterative strategy or direct calculation,while ignoring some valuable information,so that the result of entity alignment is not ideal.In view of the above problems,a multi-information optimized entity alignment model based on graph neural network(MOGNN) is proposed.Firstly,the input of the model fuses word information and character information in the entity name,and the vector representation of relations is learnt through attention mechanism.After transmitting the information by utilizing relations,MOGNN corrects the initial entity alignment matrix based on the pre-alignment results of entities and relations,and finally employs the deferred acceptance algorithm to further correct the misaligned results.The proposed model is validated on three subsets of DBP15K,and compared with the baseline models.Compared with the baseline models,Hits@1 increases by 4.47%,0.82% and 0.46%,Hits@10 and MRR have also achieved impressive results,and the effectiveness of the model is further verifies by ablation experiments.Therefore,more accurate entity alignment results can be obtained with the proposed model. |
| first_indexed | 2024-04-09T17:33:15Z |
| format | Article |
| id | doaj.art-178f3ccc57f9422981d6dd964609e98f |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:33:15Z |
| publishDate | 2023-03-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-178f3ccc57f9422981d6dd964609e98f2023-04-18T02:33:25ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2023-03-01503344110.11896/jsjkx.220700242Multi-information Optimized Entity Alignment Model Based on Graph Neural NetworkCHEN Fuqiang, KOU Jiamin, SU Limin, LI Ke0Smart City College,Beijing Union University,Beijing 100101,ChinaEntity alignment is a key step in knowledge fusion,which aims to discover entity pairs with corresponding relations between knowledge graphs.Knowledge fusion enables a more extensive and accurate services for further knowledge graph applications.However,the entity names and relations are used insufficiently by most of the state-of-the-art models of entity alignment.After obtaining the vector representation of the entity,generally the alignment relations among the entities are obtained through single iterative strategy or direct calculation,while ignoring some valuable information,so that the result of entity alignment is not ideal.In view of the above problems,a multi-information optimized entity alignment model based on graph neural network(MOGNN) is proposed.Firstly,the input of the model fuses word information and character information in the entity name,and the vector representation of relations is learnt through attention mechanism.After transmitting the information by utilizing relations,MOGNN corrects the initial entity alignment matrix based on the pre-alignment results of entities and relations,and finally employs the deferred acceptance algorithm to further correct the misaligned results.The proposed model is validated on three subsets of DBP15K,and compared with the baseline models.Compared with the baseline models,Hits@1 increases by 4.47%,0.82% and 0.46%,Hits@10 and MRR have also achieved impressive results,and the effectiveness of the model is further verifies by ablation experiments.Therefore,more accurate entity alignment results can be obtained with the proposed model.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-3-34.pdfentity alignment|knowledge graph|graph neural network|attention mechanism|global alignment |
| spellingShingle | CHEN Fuqiang, KOU Jiamin, SU Limin, LI Ke Multi-information Optimized Entity Alignment Model Based on Graph Neural Network Jisuanji kexue entity alignment|knowledge graph|graph neural network|attention mechanism|global alignment |
| title | Multi-information Optimized Entity Alignment Model Based on Graph Neural Network |
| title_full | Multi-information Optimized Entity Alignment Model Based on Graph Neural Network |
| title_fullStr | Multi-information Optimized Entity Alignment Model Based on Graph Neural Network |
| title_full_unstemmed | Multi-information Optimized Entity Alignment Model Based on Graph Neural Network |
| title_short | Multi-information Optimized Entity Alignment Model Based on Graph Neural Network |
| title_sort | multi information optimized entity alignment model based on graph neural network |
| topic | entity alignment|knowledge graph|graph neural network|attention mechanism|global alignment |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2023-50-3-34.pdf |
| work_keys_str_mv | AT chenfuqiangkoujiaminsuliminlike multiinformationoptimizedentityalignmentmodelbasedongraphneuralnetwork |