Hybrid attention mechanism for few‐shot relational learning of knowledge graphs
Abstract Few‐shot knowledge graph (KG) reasoning is the main focus in the field of knowledge graph reasoning. In order to expand the application fields of the knowledge graph, a large number of studies are based on a large number of training samples. However, we have learnt that there are actually m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-12-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cvi2.12066 |
| _version_ | 1811214759601635328 |
|---|---|
| author | Ruixin Ma Zeyang Li Fangqing Guo Liang Zhao |
| author_facet | Ruixin Ma Zeyang Li Fangqing Guo Liang Zhao |
| author_sort | Ruixin Ma |
| collection | DOAJ |
| description | Abstract Few‐shot knowledge graph (KG) reasoning is the main focus in the field of knowledge graph reasoning. In order to expand the application fields of the knowledge graph, a large number of studies are based on a large number of training samples. However, we have learnt that there are actually many missing relationships or entities in the knowledge graph, and in most cases, there are not many training instances when implementing new relationships. To tackle it, in this study, the authors aim to predict a new entity given few reference instances, even only one training instance. A few‐shot learning framework based on a hybrid attention mechanism is proposed. The framework employs traditional embedding models to extract knowledge, and uses an attenuated attention network and a self‐attention mechanism to obtain the hidden attributes of entities. Thus, it can learn a matching metric by considering both the learnt embeddings and one‐hop graph structures. The experimental results present that the model has achieved significant performance improvements on the NELL‐One and Wiki‐One datasets. |
| first_indexed | 2024-04-12T06:10:06Z |
| format | Article |
| id | doaj.art-fef0aa29287d403881b40f8429ee2da5 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-04-12T06:10:06Z |
| publishDate | 2021-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-fef0aa29287d403881b40f8429ee2da52022-12-22T03:44:44ZengWileyIET Computer Vision1751-96321751-96402021-12-0115856157210.1049/cvi2.12066Hybrid attention mechanism for few‐shot relational learning of knowledge graphsRuixin Ma0Zeyang Li1Fangqing Guo2Liang Zhao3School of Software Technology Dalian University of Technology Dalian ChinaSchool of Software Technology Dalian University of Technology Dalian ChinaSchool of Software Technology Dalian University of Technology Dalian ChinaSchool of Software Technology Dalian University of Technology Dalian ChinaAbstract Few‐shot knowledge graph (KG) reasoning is the main focus in the field of knowledge graph reasoning. In order to expand the application fields of the knowledge graph, a large number of studies are based on a large number of training samples. However, we have learnt that there are actually many missing relationships or entities in the knowledge graph, and in most cases, there are not many training instances when implementing new relationships. To tackle it, in this study, the authors aim to predict a new entity given few reference instances, even only one training instance. A few‐shot learning framework based on a hybrid attention mechanism is proposed. The framework employs traditional embedding models to extract knowledge, and uses an attenuated attention network and a self‐attention mechanism to obtain the hidden attributes of entities. Thus, it can learn a matching metric by considering both the learnt embeddings and one‐hop graph structures. The experimental results present that the model has achieved significant performance improvements on the NELL‐One and Wiki‐One datasets.https://doi.org/10.1049/cvi2.12066learning (artificial intelligence)semantic networksinference mechanisms |
| spellingShingle | Ruixin Ma Zeyang Li Fangqing Guo Liang Zhao Hybrid attention mechanism for few‐shot relational learning of knowledge graphs IET Computer Vision learning (artificial intelligence) semantic networks inference mechanisms |
| title | Hybrid attention mechanism for few‐shot relational learning of knowledge graphs |
| title_full | Hybrid attention mechanism for few‐shot relational learning of knowledge graphs |
| title_fullStr | Hybrid attention mechanism for few‐shot relational learning of knowledge graphs |
| title_full_unstemmed | Hybrid attention mechanism for few‐shot relational learning of knowledge graphs |
| title_short | Hybrid attention mechanism for few‐shot relational learning of knowledge graphs |
| title_sort | hybrid attention mechanism for few shot relational learning of knowledge graphs |
| topic | learning (artificial intelligence) semantic networks inference mechanisms |
| url | https://doi.org/10.1049/cvi2.12066 |
| work_keys_str_mv | AT ruixinma hybridattentionmechanismforfewshotrelationallearningofknowledgegraphs AT zeyangli hybridattentionmechanismforfewshotrelationallearningofknowledgegraphs AT fangqingguo hybridattentionmechanismforfewshotrelationallearningofknowledgegraphs AT liangzhao hybridattentionmechanismforfewshotrelationallearningofknowledgegraphs |