HyperCL: A Contrastive Learning Framework for Hyper-Relational Knowledge Graph Embedding with Hierarchical Ontology

Yuhuan Lu, Weijian Yu, Xin Jing, Dingqi Yang


Abstract
Knowledge Graph (KG) embeddings are essential for link prediction over KGs. Compared to triplets, hyper-relational facts consisting of a base triplet and an arbitrary number of key-value pairs, can better characterize real-world facts and have aroused various hyper-relational embedding techniques recently. Nevertheless, existing works seldom consider the ontology of KGs, which is beneficial to link prediction tasks. A few studies attempt to incorporate the ontology information, by either utilizing the ontology as constraints on entity representations or jointly learning from hyper-relational facts and the ontology. However, existing approaches mostly overlook the ontology hierarchy and suffer from the dominance issue of facts over ontology, resulting in suboptimal performance. Against this background, we propose a universal contrastive learning framework for hyper-relational KG embeddings (HyperCL), which is flexible to integrate different hyper-relational KG embedding methods and effectively boost their link prediction performance. HyperCL designs relation-aware Graph Attention Networks to capture the hierarchical ontology and a concept-aware contrastive loss to alleviate the dominance issue. We evaluate HyperCL on three real-world datasets in different link prediction tasks. Experimental results show that HyperCL consistently boosts the performance of state-of-the-art baselines with an average improvement of 3.1-7.4% across the three datasets.
Anthology ID:
2024.findings-acl.171
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2918–2929
Language:
URL:
https://aclanthology.org/2024.findings-acl.171
DOI:
10.18653/v1/2024.findings-acl.171
Bibkey:
Cite (ACL):
Yuhuan Lu, Weijian Yu, Xin Jing, and Dingqi Yang. 2024. HyperCL: A Contrastive Learning Framework for Hyper-Relational Knowledge Graph Embedding with Hierarchical Ontology. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2918–2929, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
HyperCL: A Contrastive Learning Framework for Hyper-Relational Knowledge Graph Embedding with Hierarchical Ontology (Lu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.171.pdf