TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns.
Representation learning on a knowledge graph (KG) aims to map entities and relationships into a low-dimensional vector space. Traditional methods for representation learning have predominantly focused on the structural aspects of triples within the KG. While existing approaches have endeavored to in...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0324059 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849469991937638400 |
|---|---|
| author | Xinliang Liu Yanyan Shi Yushi Xu Yanzhao Ren |
| author_facet | Xinliang Liu Yanyan Shi Yushi Xu Yanzhao Ren |
| author_sort | Xinliang Liu |
| collection | DOAJ |
| description | Representation learning on a knowledge graph (KG) aims to map entities and relationships into a low-dimensional vector space. Traditional methods for representation learning have predominantly focused on the structural aspects of triples within the KG. While existing approaches have endeavored to integrate path information and rules to enhance the structural richness of KGs, these efforts have been constrained by the lack of consideration for complex relational representations and contextual information. In this study, we introduce TP-RotatE, an innovative method that leverages the semantic context of triples to effectively capture more intricate relational patterns. Specifically, our model harnesses contextual information surrounding the head entity and distills relevant rules. These rules are then integrated with path information to offer a more holistic perspective on the relationships embedded within complex vector spaces. Furthermore, the synergy between rules and paths empowers the knowledge-embedded model to handle the intricacies of complex relationships. Experimental results on a benchmark dataset confirm that TP-RotatE surpasses current baseline methods in KG inference tasks, achieving state-of-the-art performance. |
| format | Article |
| id | doaj-art-26f848e5f6884a7ca177308e9eeb700e |
| institution | Kabale University |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-26f848e5f6884a7ca177308e9eeb700e2025-08-20T03:25:16ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032405910.1371/journal.pone.0324059TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns.Xinliang LiuYanyan ShiYushi XuYanzhao RenRepresentation learning on a knowledge graph (KG) aims to map entities and relationships into a low-dimensional vector space. Traditional methods for representation learning have predominantly focused on the structural aspects of triples within the KG. While existing approaches have endeavored to integrate path information and rules to enhance the structural richness of KGs, these efforts have been constrained by the lack of consideration for complex relational representations and contextual information. In this study, we introduce TP-RotatE, an innovative method that leverages the semantic context of triples to effectively capture more intricate relational patterns. Specifically, our model harnesses contextual information surrounding the head entity and distills relevant rules. These rules are then integrated with path information to offer a more holistic perspective on the relationships embedded within complex vector spaces. Furthermore, the synergy between rules and paths empowers the knowledge-embedded model to handle the intricacies of complex relationships. Experimental results on a benchmark dataset confirm that TP-RotatE surpasses current baseline methods in KG inference tasks, achieving state-of-the-art performance.https://doi.org/10.1371/journal.pone.0324059 |
| spellingShingle | Xinliang Liu Yanyan Shi Yushi Xu Yanzhao Ren TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns. PLoS ONE |
| title | TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns. |
| title_full | TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns. |
| title_fullStr | TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns. |
| title_full_unstemmed | TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns. |
| title_short | TP-RotatE: A knowledge graph representation learning method combining path information and rules to capture complex relational patterns. |
| title_sort | tp rotate a knowledge graph representation learning method combining path information and rules to capture complex relational patterns |
| url | https://doi.org/10.1371/journal.pone.0324059 |
| work_keys_str_mv | AT xinliangliu tprotateaknowledgegraphrepresentationlearningmethodcombiningpathinformationandrulestocapturecomplexrelationalpatterns AT yanyanshi tprotateaknowledgegraphrepresentationlearningmethodcombiningpathinformationandrulestocapturecomplexrelationalpatterns AT yushixu tprotateaknowledgegraphrepresentationlearningmethodcombiningpathinformationandrulestocapturecomplexrelationalpatterns AT yanzhaoren tprotateaknowledgegraphrepresentationlearningmethodcombiningpathinformationandrulestocapturecomplexrelationalpatterns |