Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space

The aim of Knowledge Graph Embedding (KGE) is to acquire low-dimensional representations of entities and relationships for the purpose of predicting new valid triples, thereby enhancing the functionality of intelligent networks that rely on accurate data representation. In recommendation systems, fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Longxin Lin, Huaibin Qin, Quan Qi, Rui Gu, Pengxiang Zuo, Yongqiang Cheng
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-01-01
Series:International Journal of Intelligent Networks
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S266660302500003X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725251795025920
author Longxin Lin
Huaibin Qin
Quan Qi
Rui Gu
Pengxiang Zuo
Yongqiang Cheng
author_facet Longxin Lin
Huaibin Qin
Quan Qi
Rui Gu
Pengxiang Zuo
Yongqiang Cheng
author_sort Longxin Lin
collection DOAJ
description The aim of Knowledge Graph Embedding (KGE) is to acquire low-dimensional representations of entities and relationships for the purpose of predicting new valid triples, thereby enhancing the functionality of intelligent networks that rely on accurate data representation. In recommendation systems, for example, the model can enhance personalized suggestions by better understanding user-item relationships, especially when the relationships are hierarchical, such as in the case of user preferences across different product categories. Existing KGE models mostly learn embeddings in Euclidean space, which perform well in high-dimensional settings. However, in low-dimensional scenarios, these models struggle to accurately capture the hierarchical information of relationships in knowledge graphs (KG), a limitation that can adversely affect the performance of intelligent network systems where structured knowledge is critical for decision making and operational efficiency. Recently, the MuRP model was proposed, introducing the use of hyperbolic space for KG embedding. Using the properties of hyperbolic space, where the space near the center is small and the space away from the center is large, the MuRP model achieves effective KG embedding even in low-dimensional training conditions, making it particularly suitable for dynamic environments typical of intelligent networks. Therefore, this paper proposes a method that utilizes the characteristics of hyperbolic geometry to create an embedding model in hyperbolic space, combining translation and multi-dimensional rotation geometric transformations. This model accurately represents various relationship patterns in knowledge graphs, including symmetry, asymmetry, inversion, composition, hierarchy, and multiplicity, which are essential for enabling robust interactions in intelligent network frameworks. Experimental results demonstrate that the proposed model generally outperforms Euclidean space embedding models under low-dimensional training conditions and performs comparably to other hyperbolic KGE models. In experiments using the WN18RR dataset, the Hits@10 metric improved by 0.3% compared to the baseline model, and in experiments using the FB15k-237 dataset, the Hits@3 metric improved by 0.1% compared to the baseline model, validating the reliability of the proposed model and its potential contribution to advancing intelligent network applications.
format Article
id doaj-art-1ff6f08b0cc5481ba4b5f9bb575ebc6c
institution DOAJ
issn 2666-6030
language English
publishDate 2025-01-01
publisher KeAi Communications Co., Ltd.
record_format Article
series International Journal of Intelligent Networks
spelling doaj-art-1ff6f08b0cc5481ba4b5f9bb575ebc6c2025-08-20T03:10:31ZengKeAi Communications Co., Ltd.International Journal of Intelligent Networks2666-60302025-01-016576410.1016/j.ijin.2025.02.002Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic spaceLongxin Lin0Huaibin Qin1Quan Qi2Rui Gu3Pengxiang Zuo4Yongqiang Cheng5School of Information Science and Technology, Shihezi University, Shihezi, 832000, Xinjiang, ChinaSchool of Information Science and Technology, Shihezi University, Shihezi, 832000, Xinjiang, China; Corresponding author.School of Information Science and Technology, Shihezi University, Shihezi, 832000, Xinjiang, ChinaSchool of Rehabilitation Medicine, Capital Medical University, Beijing, 100068, ChinaMedical School, Shihezi University, Shihezi, 832000, Xinjiang, ChinaFaculty of business & technology, University of Sunderland, Sunderland, SR60DD, Britain, United KingdomThe aim of Knowledge Graph Embedding (KGE) is to acquire low-dimensional representations of entities and relationships for the purpose of predicting new valid triples, thereby enhancing the functionality of intelligent networks that rely on accurate data representation. In recommendation systems, for example, the model can enhance personalized suggestions by better understanding user-item relationships, especially when the relationships are hierarchical, such as in the case of user preferences across different product categories. Existing KGE models mostly learn embeddings in Euclidean space, which perform well in high-dimensional settings. However, in low-dimensional scenarios, these models struggle to accurately capture the hierarchical information of relationships in knowledge graphs (KG), a limitation that can adversely affect the performance of intelligent network systems where structured knowledge is critical for decision making and operational efficiency. Recently, the MuRP model was proposed, introducing the use of hyperbolic space for KG embedding. Using the properties of hyperbolic space, where the space near the center is small and the space away from the center is large, the MuRP model achieves effective KG embedding even in low-dimensional training conditions, making it particularly suitable for dynamic environments typical of intelligent networks. Therefore, this paper proposes a method that utilizes the characteristics of hyperbolic geometry to create an embedding model in hyperbolic space, combining translation and multi-dimensional rotation geometric transformations. This model accurately represents various relationship patterns in knowledge graphs, including symmetry, asymmetry, inversion, composition, hierarchy, and multiplicity, which are essential for enabling robust interactions in intelligent network frameworks. Experimental results demonstrate that the proposed model generally outperforms Euclidean space embedding models under low-dimensional training conditions and performs comparably to other hyperbolic KGE models. In experiments using the WN18RR dataset, the Hits@10 metric improved by 0.3% compared to the baseline model, and in experiments using the FB15k-237 dataset, the Hits@3 metric improved by 0.1% compared to the baseline model, validating the reliability of the proposed model and its potential contribution to advancing intelligent network applications.http://www.sciencedirect.com/science/article/pii/S266660302500003XIntelligent networksKnowledge graph embeddingHyperbolic geometryPoincaré ballLink prediction
spellingShingle Longxin Lin
Huaibin Qin
Quan Qi
Rui Gu
Pengxiang Zuo
Yongqiang Cheng
Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space
International Journal of Intelligent Networks
Intelligent networks
Knowledge graph embedding
Hyperbolic geometry
Poincaré ball
Link prediction
title Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space
title_full Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space
title_fullStr Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space
title_full_unstemmed Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space
title_short Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space
title_sort multi relation pattern knowledge graph embeddings for link prediction in hyperbolic space
topic Intelligent networks
Knowledge graph embedding
Hyperbolic geometry
Poincaré ball
Link prediction
url http://www.sciencedirect.com/science/article/pii/S266660302500003X
work_keys_str_mv AT longxinlin multirelationpatternknowledgegraphembeddingsforlinkpredictioninhyperbolicspace
AT huaibinqin multirelationpatternknowledgegraphembeddingsforlinkpredictioninhyperbolicspace
AT quanqi multirelationpatternknowledgegraphembeddingsforlinkpredictioninhyperbolicspace
AT ruigu multirelationpatternknowledgegraphembeddingsforlinkpredictioninhyperbolicspace
AT pengxiangzuo multirelationpatternknowledgegraphembeddingsforlinkpredictioninhyperbolicspace
AT yongqiangcheng multirelationpatternknowledgegraphembeddingsforlinkpredictioninhyperbolicspace