Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning
Knowledge graph completion is a process of reasoning new triples based on existing entities and relations in knowledge graph. The existing methods usually use the encoder-decoder framework. Encoder uses graph convolutional neural network to get the embeddings of entities and relations. Decoder calcu...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2024-04-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2301038.pdf |
| _version_ | 1827299667490111488 |
|---|---|
| author | QIAO Zifeng, QIN Hongchao, HU Jingjing, LI Ronghua, WANG Guoren |
| author_facet | QIAO Zifeng, QIN Hongchao, HU Jingjing, LI Ronghua, WANG Guoren |
| author_sort | QIAO Zifeng, QIN Hongchao, HU Jingjing, LI Ronghua, WANG Guoren |
| collection | DOAJ |
| description | Knowledge graph completion is a process of reasoning new triples based on existing entities and relations in knowledge graph. The existing methods usually use the encoder-decoder framework. Encoder uses graph convolutional neural network to get the embeddings of entities and relations. Decoder calculates the score of each tail entity according to the embeddings of the entities and relations. The tail entity with the highest score is the inference result. Decoder inferences triples independently, without consideration of graph information. Therefore, this paper proposes a graph completion algorithm based on contrastive learning. This paper adds a multi-view contrastive learning framework into the model to constrain the embedded information at graph level. The comparison of multiple views in the model constructs different distribution spaces for relations. Different distributions of relations fit each other, which is more suitable for completion tasks. Contrastive learning constraints the embedding vectors of entity and subgraph and enhahces peroformance of the task. Experiments are carried out on two datasets. The results show that MRR is improved by 12.6% over method A2N and 0.8% over InteractE on FB15k-237 dataset, and 7.3% over A2N and 4.3% over InteractE on WN18RR dataset. Experimental results demonstrate that this model outperforms other completion methods. |
| first_indexed | 2024-04-24T15:37:37Z |
| format | Article |
| id | doaj.art-a950b7a7a3a645f6a0b166f7049dce74 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-04-24T15:37:37Z |
| publishDate | 2024-04-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-a950b7a7a3a645f6a0b166f7049dce742024-04-02T01:27:22ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182024-04-011841001100910.3778/j.issn.1673-9418.2301038Knowledge Graph Completion Algorithm with Multi-view Contrastive LearningQIAO Zifeng, QIN Hongchao, HU Jingjing, LI Ronghua, WANG Guoren0School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100081, ChinaKnowledge graph completion is a process of reasoning new triples based on existing entities and relations in knowledge graph. The existing methods usually use the encoder-decoder framework. Encoder uses graph convolutional neural network to get the embeddings of entities and relations. Decoder calculates the score of each tail entity according to the embeddings of the entities and relations. The tail entity with the highest score is the inference result. Decoder inferences triples independently, without consideration of graph information. Therefore, this paper proposes a graph completion algorithm based on contrastive learning. This paper adds a multi-view contrastive learning framework into the model to constrain the embedded information at graph level. The comparison of multiple views in the model constructs different distribution spaces for relations. Different distributions of relations fit each other, which is more suitable for completion tasks. Contrastive learning constraints the embedding vectors of entity and subgraph and enhahces peroformance of the task. Experiments are carried out on two datasets. The results show that MRR is improved by 12.6% over method A2N and 0.8% over InteractE on FB15k-237 dataset, and 7.3% over A2N and 4.3% over InteractE on WN18RR dataset. Experimental results demonstrate that this model outperforms other completion methods.http://fcst.ceaj.org/fileup/1673-9418/PDF/2301038.pdfknowledge graph; link prediction; contrastive learning; encoder; decoder |
| spellingShingle | QIAO Zifeng, QIN Hongchao, HU Jingjing, LI Ronghua, WANG Guoren Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning Jisuanji kexue yu tansuo knowledge graph; link prediction; contrastive learning; encoder; decoder |
| title | Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning |
| title_full | Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning |
| title_fullStr | Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning |
| title_full_unstemmed | Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning |
| title_short | Knowledge Graph Completion Algorithm with Multi-view Contrastive Learning |
| title_sort | knowledge graph completion algorithm with multi view contrastive learning |
| topic | knowledge graph; link prediction; contrastive learning; encoder; decoder |
| url | http://fcst.ceaj.org/fileup/1673-9418/PDF/2301038.pdf |
| work_keys_str_mv | AT qiaozifengqinhongchaohujingjinglironghuawangguoren knowledgegraphcompletionalgorithmwithmultiviewcontrastivelearning |