KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings

Zhiping Luo, Wentao Xu, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu


Abstract
Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering. In recent years, many research efforts have been proposed for knowledge graph embedding (KGE). However, most previous KGE methods ignore the semantic similarity between the related entities and entity-relation couples in different triples since they separately optimize each triple with the scoring function. To address this problem, we propose a simple yet efficient contrastive learning framework for tensor decomposition based (TDB) KGE, which can shorten the semantic distance of the related entities and entity-relation couples in different triples and thus improve the performance of KGE. We evaluate our proposed method on three standard KGE datasets: WN18RR, FB15k-237 and YAGO3-10. Our method can yield some new state-of-the-art results, achieving 51.2% MRR, 46.8% Hits@1 on the WN18RR dataset, 37.8% MRR, 28.6% Hits@1 on FB15k-237 dataset, and 59.1% MRR, 51.8% Hits@1 on the YAGO3-10 dataset.
Anthology ID:
2022.coling-1.229
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2598–2607
Language:
URL:
https://aclanthology.org/2022.coling-1.229
DOI:
Bibkey:
Cite (ACL):
Zhiping Luo, Wentao Xu, Weiqing Liu, Jiang Bian, Jian Yin, and Tie-Yan Liu. 2022. KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2598–2607, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings (Luo et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.229.pdf
Code
 HELL-TO-HEAVEN/KGE-CL +  additional community code
Data
FB15k-237