English

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

Computation and Language 2019-09-05 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.1909.01515,
  title  = {Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs},
  author = {Mingyang Chen and Wen Zhang and Wei Zhang and Qiang Chen and Huajun Chen},
  journal= {arXiv preprint arXiv:1909.01515},
  year   = {2019}
}

Comments

Accepted by EMNLP 2019

R2 v1 2026-06-23T11:04:45.681Z