SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction

Miao Peng, Ben Liu, Qianqian Xie, Wenjie Xu, Hua Wang, Min Peng


Abstract
Link prediction is the task of inferring missing links between entities in knowledge graphs. Embedding-based methods have shown effectiveness in addressing this problem by modeling relational patterns in triples. However, the link prediction task often requires contextual information in entity neighborhoods, while most existing embedding-based methods fail to capture it. Additionally, little attention is paid to the diversity of entity representations in different contexts, which often leads to false prediction results. In this situation, we consider that the schema of knowledge graph contains the specific contextual information, and it is beneficial for preserving the consistency of entities across contexts. In this paper, we propose a novel Schema-augmented Multi-level contrastive LEarning framework (SMiLE) to conduct knowledge graph link prediction. Specifically, we first exploit network schema as the prior constraint to sample negatives and pre-train our model by employing a multi-level contrastive learning method to yield both prior schema and contextual information. Then we fine-tune our model under the supervision of individual triples to learn subtler representations for link prediction. Extensive experimental results on four knowledge graph datasets with thorough analysis of each component demonstrate the effectiveness of our proposed framework against state-of-the-art baselines. The implementation of SMiLE is available at https://github.com/GKNL/SMiLE.
Anthology ID:
2022.findings-emnlp.307
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4165–4177
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.307
DOI:
10.18653/v1/2022.findings-emnlp.307
Bibkey:
Cite (ACL):
Miao Peng, Ben Liu, Qianqian Xie, Wenjie Xu, Hua Wang, and Min Peng. 2022. SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4165–4177, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction (Peng et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.307.pdf
Software:
 2022.findings-emnlp.307.software.zip
Dataset:
 2022.findings-emnlp.307.dataset.zip
Video:
 https://aclanthology.org/2022.findings-emnlp.307.mp4