Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909418152525824 |
|---|---|
| author | Wang, Cunda Wang, Weihua Liang, Qiuyu Bao, Feilong Gao, Guanglai |
| author_facet | Wang, Cunda Wang, Weihua Liang, Qiuyu Bao, Feilong Gao, Guanglai |
| contents | Entity alignment aims to match identical entities across different knowledge graphs (KGs). Graph neural network-based entity alignment methods have achieved promising results in Euclidean space. However, KGs often contain complex structures, including both local and hierarchical ones, which make it challenging to efficiently represent them within a single space. In this paper, we proposed a novel method UniEA, which unifies dual-space embedding to preserve the intrinsic structure of KGs. Specifically, we learn graph structure embedding in both Euclidean and hyperbolic spaces simultaneously to maximize the consistency between the embedding in both spaces. Moreover, we employ contrastive learning to mitigate the misalignment issues caused by similar entities, where embedding of similar neighboring entities within the KG become too close in distance. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance in structure-based EA. Our code is available at https://github.com/wonderCS1213/UniEA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05028 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning Wang, Cunda Wang, Weihua Liang, Qiuyu Bao, Feilong Gao, Guanglai Computation and Language Entity alignment aims to match identical entities across different knowledge graphs (KGs). Graph neural network-based entity alignment methods have achieved promising results in Euclidean space. However, KGs often contain complex structures, including both local and hierarchical ones, which make it challenging to efficiently represent them within a single space. In this paper, we proposed a novel method UniEA, which unifies dual-space embedding to preserve the intrinsic structure of KGs. Specifically, we learn graph structure embedding in both Euclidean and hyperbolic spaces simultaneously to maximize the consistency between the embedding in both spaces. Moreover, we employ contrastive learning to mitigate the misalignment issues caused by similar entities, where embedding of similar neighboring entities within the KG become too close in distance. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance in structure-based EA. Our code is available at https://github.com/wonderCS1213/UniEA. |
| title | Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.05028 |