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

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.

arXiv commentAccepted by EMNLP 2019

References in corpus (2)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning

Cited by in corpus (8)

• Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
• Meta-Graph: Few Shot Link Prediction via Meta Learning
• Graph Meta Learning via Local Subgraphs
• Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• Relation Adversarial Network for Low Resource Knowledge Graph Completion
• OntoZSL: Ontology-enhanced Zero-shot Learning
• Sequential Recommendation for Cold-start Users with Meta Transitional Learning