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

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

doi:10.18653/v1/d19-1431

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.

Highlights

With Meta Relational Learning (MetaR), we want to figure out following things: 1) can MetaR accomplish few-shot link prediction task and even perform better than previous model? 2) how much relation-specific meta information contributes to few-shot link prediction? 3) is there any requirement for MetaR to work on few-shot link prediction? To do these, we conduct the experiments on two few-shot link prediction datasets and deeply analyze the experiment results 1
The baseline in our experiment is GMatching (Xiong et al, 2018), which made the first trial on few-shot link prediction task and is the only method that we can find as baseline
We propose a meta relational learning framework to do few-shot link prediction in knowledge graphs (KGs), and we design our model to transfer relation-specific meta information from support set to query set