Few-Shot Knowledge Graph Completion Model Based on Relation Learning
Considering the complexity of entity pair relations and the information contained in the target neighborhood in few-shot knowledge graphs (KG), existing few-shot KG completion methods generally suffer from insufficient relation representation learning capabilities and neglecting the contextual seman...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/17/9513 |
| _version_ | 1797582865530093568 |
|---|---|
| author | Weijun Li Jianlai Gu Ang Li Yuxiao Gao Xinyong Zhang |
| author_facet | Weijun Li Jianlai Gu Ang Li Yuxiao Gao Xinyong Zhang |
| author_sort | Weijun Li |
| collection | DOAJ |
| description | Considering the complexity of entity pair relations and the information contained in the target neighborhood in few-shot knowledge graphs (KG), existing few-shot KG completion methods generally suffer from insufficient relation representation learning capabilities and neglecting the contextual semantics of entities. To tackle the above problems, we propose a Few-shot Relation Learning-based Knowledge Graph Completion model (FRL-KGC). First, a gating mechanism is introduced during the aggregation of higher-order neighborhoods of entities in formation, enriching the central entity representation while reducing the adverse effects of noisy neighbors. Second, during the relation representation learning stage, a more accurate relation representation is learned by using the correlation between entity pairs in the reference set. Finally, an LSTM structure is incorporated into the Transformer learner to enhance its ability to learn the contextual semantics of entities and relations and predict new factual knowledge. We conducted comparative experiments on the publicly available NELL-One and Wiki-One datasets, comparing FRL-KGC with six few-shot knowledge graph completion models and five traditional knowledge graph completion models for five-shot link prediction. The results showed that FRL-KGC outperformed all comparison models in terms of MRR, Hits@10, Hits@5, and Hits@1 metrics. |
| first_indexed | 2024-03-10T23:28:35Z |
| format | Article |
| id | doaj.art-597be201bf2142408ab0298b85852be3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T23:28:35Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-597be201bf2142408ab0298b85852be32023-11-19T07:48:06ZengMDPI AGApplied Sciences2076-34172023-08-011317951310.3390/app13179513Few-Shot Knowledge Graph Completion Model Based on Relation LearningWeijun Li0Jianlai Gu1Ang Li2Yuxiao Gao3Xinyong Zhang4The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaConsidering the complexity of entity pair relations and the information contained in the target neighborhood in few-shot knowledge graphs (KG), existing few-shot KG completion methods generally suffer from insufficient relation representation learning capabilities and neglecting the contextual semantics of entities. To tackle the above problems, we propose a Few-shot Relation Learning-based Knowledge Graph Completion model (FRL-KGC). First, a gating mechanism is introduced during the aggregation of higher-order neighborhoods of entities in formation, enriching the central entity representation while reducing the adverse effects of noisy neighbors. Second, during the relation representation learning stage, a more accurate relation representation is learned by using the correlation between entity pairs in the reference set. Finally, an LSTM structure is incorporated into the Transformer learner to enhance its ability to learn the contextual semantics of entities and relations and predict new factual knowledge. We conducted comparative experiments on the publicly available NELL-One and Wiki-One datasets, comparing FRL-KGC with six few-shot knowledge graph completion models and five traditional knowledge graph completion models for five-shot link prediction. The results showed that FRL-KGC outperformed all comparison models in terms of MRR, Hits@10, Hits@5, and Hits@1 metrics.https://www.mdpi.com/2076-3417/13/17/9513knowledge graphcomplete the knowledge graphfew-shot relationneighborhood aggregationlink prediction |
| spellingShingle | Weijun Li Jianlai Gu Ang Li Yuxiao Gao Xinyong Zhang Few-Shot Knowledge Graph Completion Model Based on Relation Learning Applied Sciences knowledge graph complete the knowledge graph few-shot relation neighborhood aggregation link prediction |
| title | Few-Shot Knowledge Graph Completion Model Based on Relation Learning |
| title_full | Few-Shot Knowledge Graph Completion Model Based on Relation Learning |
| title_fullStr | Few-Shot Knowledge Graph Completion Model Based on Relation Learning |
| title_full_unstemmed | Few-Shot Knowledge Graph Completion Model Based on Relation Learning |
| title_short | Few-Shot Knowledge Graph Completion Model Based on Relation Learning |
| title_sort | few shot knowledge graph completion model based on relation learning |
| topic | knowledge graph complete the knowledge graph few-shot relation neighborhood aggregation link prediction |
| url | https://www.mdpi.com/2076-3417/13/17/9513 |
| work_keys_str_mv | AT weijunli fewshotknowledgegraphcompletionmodelbasedonrelationlearning AT jianlaigu fewshotknowledgegraphcompletionmodelbasedonrelationlearning AT angli fewshotknowledgegraphcompletionmodelbasedonrelationlearning AT yuxiaogao fewshotknowledgegraphcompletionmodelbasedonrelationlearning AT xinyongzhang fewshotknowledgegraphcompletionmodelbasedonrelationlearning |