Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs
Few-shot knowledge graph reasoning is a research focus in the field of knowledge graph reasoning. At present, in order to expand the application scope of knowledge graphs, a large number of researchers are devoted to the study of the multi-shot knowledge graph model. However, as far as we know, the...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/9/4284 |
| _version_ | 1797505725453303808 |
|---|---|
| author | Ruixin Ma Zeyang Li Yunlong Ma Hao Wu Mengfei Yu Liang Zhao |
| author_facet | Ruixin Ma Zeyang Li Yunlong Ma Hao Wu Mengfei Yu Liang Zhao |
| author_sort | Ruixin Ma |
| collection | DOAJ |
| description | Few-shot knowledge graph reasoning is a research focus in the field of knowledge graph reasoning. At present, in order to expand the application scope of knowledge graphs, a large number of researchers are devoted to the study of the multi-shot knowledge graph model. However, as far as we know, the knowledge graph contains a large number of missing relations and entities, and there are not many reference examples at the time of training. In this paper, our goal is to be able to infer the correct entity given a few training instances, or even only one training instance is available. Therefore, we propose an adaptive attentional network for few-shot relational learning of knowledge graphs, extracting knowledge based on traditional embedding methods, using the Transformer mechanism and hierarchical attention mechanism to obtain hidden attributes of entities, and then using a noise checker to filter out unreasonable candidate entities. Our model produces large performance improvements on the NELL-One dataset. |
| first_indexed | 2024-03-10T04:22:34Z |
| format | Article |
| id | doaj.art-1511517f0e3141339971e1e7d882210a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:22:34Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1511517f0e3141339971e1e7d882210a2023-11-23T07:46:52ZengMDPI AGApplied Sciences2076-34172022-04-01129428410.3390/app12094284Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge GraphsRuixin Ma0Zeyang Li1Yunlong Ma2Hao Wu3Mengfei Yu4Liang Zhao5School of Software Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Software Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Software Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Software Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Software Technology, Dalian University of Technology, Dalian 116024, ChinaSchool of Software Technology, Dalian University of Technology, Dalian 116024, ChinaFew-shot knowledge graph reasoning is a research focus in the field of knowledge graph reasoning. At present, in order to expand the application scope of knowledge graphs, a large number of researchers are devoted to the study of the multi-shot knowledge graph model. However, as far as we know, the knowledge graph contains a large number of missing relations and entities, and there are not many reference examples at the time of training. In this paper, our goal is to be able to infer the correct entity given a few training instances, or even only one training instance is available. Therefore, we propose an adaptive attentional network for few-shot relational learning of knowledge graphs, extracting knowledge based on traditional embedding methods, using the Transformer mechanism and hierarchical attention mechanism to obtain hidden attributes of entities, and then using a noise checker to filter out unreasonable candidate entities. Our model produces large performance improvements on the NELL-One dataset.https://www.mdpi.com/2076-3417/12/9/4284few-shotone-shotknowledge graph reasoningTransformer |
| spellingShingle | Ruixin Ma Zeyang Li Yunlong Ma Hao Wu Mengfei Yu Liang Zhao Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs Applied Sciences few-shot one-shot knowledge graph reasoning Transformer |
| title | Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs |
| title_full | Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs |
| title_fullStr | Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs |
| title_full_unstemmed | Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs |
| title_short | Adaptive Attentional Network for Few-Shot Relational Learning of Knowledge Graphs |
| title_sort | adaptive attentional network for few shot relational learning of knowledge graphs |
| topic | few-shot one-shot knowledge graph reasoning Transformer |
| url | https://www.mdpi.com/2076-3417/12/9/4284 |
| work_keys_str_mv | AT ruixinma adaptiveattentionalnetworkforfewshotrelationallearningofknowledgegraphs AT zeyangli adaptiveattentionalnetworkforfewshotrelationallearningofknowledgegraphs AT yunlongma adaptiveattentionalnetworkforfewshotrelationallearningofknowledgegraphs AT haowu adaptiveattentionalnetworkforfewshotrelationallearningofknowledgegraphs AT mengfeiyu adaptiveattentionalnetworkforfewshotrelationallearningofknowledgegraphs AT liangzhao adaptiveattentionalnetworkforfewshotrelationallearningofknowledgegraphs |