Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
This addresses the challenge of completing knowledge graphs for applications requiring inference from limited data, but it is incremental as it builds on existing meta-learning approaches.
The paper tackles the problem of few-shot link prediction in knowledge graphs, where embedding-based methods struggle with relations having few triples, and proposes a Meta Relational Learning (MetaR) framework that achieves state-of-the-art results on benchmarks.
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.