Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs

Mingyang Chen, Wen Zhang, Wei Zhang, Qiang Chen, Huajun Chen

Abstract
Link prediction is an important way to complete knowledge graphs (KGs), while embedding-based methods, effective for link prediction in KGs, perform poorly on relations that only have a few associative triples. In this work, we propose a Meta Relational Learning (MetaR) framework to do the common but challenging few-shot link prediction in KGs, namely predicting new triples about a relation by only observing a few associative triples. We solve few-shot link prediction by focusing on transferring relation-specific meta information to make model learn the most important knowledge and learn faster, corresponding to relation meta and gradient meta respectively in MetaR. Empirically, our model achieves state-of-the-art results on few-shot link prediction KG benchmarks.
Anthology ID:
D19-1431
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4217–4226
Language:
URL:
https://aclanthology.org/D19-1431
DOI:
10.18653/v1/D19-1431
Bibkey:
Cite (ACL):
Mingyang Chen, Wen Zhang, Wei Zhang, Qiang Chen, and Huajun Chen. 2019. Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4217–4226, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs (Chen et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/D19-1431.pdf
Code
 AnselCmy/MetaR
Data
Wiki-One
PDF Search Code