Learning Low-dimensional Multi-domain Knowledge Graph Embedding via Dual Archimedean Spirals

Jiang Li, Xiangdong Su, Fujun Zhang, Guanglai Gao

Abstract
Knowledge graph embedding (KGE) is extensively employed for link prediction by representing entities and relations as low-dimensional vectors. In real-world scenarios, knowledge graphs (KGs) usually encompass diverse domains, which poses challenges to KG representations. However, existing KGE methods rarely make domain constraints on the embedding distribution of multi-domain KGs, leading to the embedding overlapping of different domains and performance degradation of link prediction. To address this challenge, we propose Dual Archimedean Spiral Knowledge Graph Embedding (DuASE), a low-dimensional KGE model for multi-domain KGs. DuASE is inspired by our discovery that relation types can distinguish entities from different domains. Specifically, DuASE encodes entities with the same relation on the same Archimedean spiral, allowing it to differentiate the entities from different domains. To avoid embedding overlapping across domains, DuASE further makes the head and the tail spirals in the same triplet cluster to their respective domain space by a regularization function. Thus, DuASE can better capture the domain information and the dependencies between entities when modeling the multi-domain KGs, leading to improved KG representations. We validate the effectiveness of DuASE on the novel multi-domain dataset (n-MDKG) introduced in this study and three other benchmark datasets.
Anthology ID:
2024.findings-acl.118
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1982–1994
Language:
URL:
https://aclanthology.org/2024.findings-acl.118
DOI:
10.18653/v1/2024.findings-acl.118
Bibkey:
Cite (ACL):
Jiang Li, Xiangdong Su, Fujun Zhang, and Guanglai Gao. 2024. Learning Low-dimensional Multi-domain Knowledge Graph Embedding via Dual Archimedean Spirals. In Findings of the Association for Computational Linguistics ACL 2024, pages 1982–1994, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Learning Low-dimensional Multi-domain Knowledge Graph Embedding via Dual Archimedean Spirals (Li et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-acl.118.pdf
PDF Search