PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction
Abstract Link prediction in knowledge hypergraphs is essential for various knowledge-based applications, including question answering and recommendation systems. However, many current approaches simply extend binary relation methods from knowledge graphs to n-ary relations, which does not allow for...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-05-01
|
| Series: | Data Science and Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s41019-023-00214-x |
| _version_ | 1797822758413926400 |
|---|---|
| author | Zirui Chen Xin Wang Chenxu Wang Zhao Li |
| author_facet | Zirui Chen Xin Wang Chenxu Wang Zhao Li |
| author_sort | Zirui Chen |
| collection | DOAJ |
| description | Abstract Link prediction in knowledge hypergraphs is essential for various knowledge-based applications, including question answering and recommendation systems. However, many current approaches simply extend binary relation methods from knowledge graphs to n-ary relations, which does not allow for capturing entity positional and role information in n-ary tuples. To address this issue, we introduce PosKHG, a method that considers entities’ positions and roles within n-ary tuples. PosKHG uses an embedding space with basis vectors to represent entities’ positional and role information through a linear combination, which allows for similar representations of entities with related roles and positions. Additionally, PosKHG employs a relation matrix to capture the compatibility of both information with all associated entities and a scoring function to measure the plausibility of tuples made up of entities with specific roles and positions. PosKHG achieves full expressiveness and high prediction efficiency. In experimental results, PosKHG achieved an average improvement of 4.1% on MRR compared to other state-of-the-art knowledge hypergraph embedding methods. Our code is available at https://anonymous.4open.science/r/PosKHG-C5B3/ . |
| first_indexed | 2024-03-13T10:13:53Z |
| format | Article |
| id | doaj.art-b9b74d8ad3194eae8d9741c67555fd0f |
| institution | Directory Open Access Journal |
| issn | 2364-1185 2364-1541 |
| language | English |
| last_indexed | 2024-03-13T10:13:53Z |
| publishDate | 2023-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Data Science and Engineering |
| spelling | doaj.art-b9b74d8ad3194eae8d9741c67555fd0f2023-05-21T11:22:31ZengSpringerOpenData Science and Engineering2364-11852364-15412023-05-018213514510.1007/s41019-023-00214-xPosKHG: A Position-Aware Knowledge Hypergraph Model for Link PredictionZirui Chen0Xin Wang1Chenxu Wang2Zhao Li3College of Intelligence and Computing, Tianjin UniversityCollege of Intelligence and Computing, Tianjin UniversityCollege of Intelligence and Computing, Tianjin UniversityCollege of Intelligence and Computing, Tianjin UniversityAbstract Link prediction in knowledge hypergraphs is essential for various knowledge-based applications, including question answering and recommendation systems. However, many current approaches simply extend binary relation methods from knowledge graphs to n-ary relations, which does not allow for capturing entity positional and role information in n-ary tuples. To address this issue, we introduce PosKHG, a method that considers entities’ positions and roles within n-ary tuples. PosKHG uses an embedding space with basis vectors to represent entities’ positional and role information through a linear combination, which allows for similar representations of entities with related roles and positions. Additionally, PosKHG employs a relation matrix to capture the compatibility of both information with all associated entities and a scoring function to measure the plausibility of tuples made up of entities with specific roles and positions. PosKHG achieves full expressiveness and high prediction efficiency. In experimental results, PosKHG achieved an average improvement of 4.1% on MRR compared to other state-of-the-art knowledge hypergraph embedding methods. Our code is available at https://anonymous.4open.science/r/PosKHG-C5B3/ .https://doi.org/10.1007/s41019-023-00214-xLink predictionKnowledge hypergraphPositional embeddingRole |
| spellingShingle | Zirui Chen Xin Wang Chenxu Wang Zhao Li PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction Data Science and Engineering Link prediction Knowledge hypergraph Positional embedding Role |
| title | PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction |
| title_full | PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction |
| title_fullStr | PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction |
| title_full_unstemmed | PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction |
| title_short | PosKHG: A Position-Aware Knowledge Hypergraph Model for Link Prediction |
| title_sort | poskhg a position aware knowledge hypergraph model for link prediction |
| topic | Link prediction Knowledge hypergraph Positional embedding Role |
| url | https://doi.org/10.1007/s41019-023-00214-x |
| work_keys_str_mv | AT ziruichen poskhgapositionawareknowledgehypergraphmodelforlinkprediction AT xinwang poskhgapositionawareknowledgehypergraphmodelforlinkprediction AT chenxuwang poskhgapositionawareknowledgehypergraphmodelforlinkprediction AT zhaoli poskhgapositionawareknowledgehypergraphmodelforlinkprediction |