Meta-Graph: Few Shot Link Prediction via Meta Learning

TL;DR

Meta-Graph introduces a gradient-based meta learning framework for few shot link prediction on graphs, enabling rapid adaptation to new graphs with limited data and outperforming existing methods.

Contribution

The paper proposes Meta-Graph, a novel meta learning approach that uses higher-order gradients and a learned graph signature to improve few shot link prediction.

Findings

Meta-Graph achieves faster adaptation to new graphs.

It outperforms existing link prediction methods on new benchmarks.

Meta-Graph improves results at convergence with limited data.

Abstract

We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current link prediction methods are generally ill-equipped to handle this task. They cannot effectively transfer learned knowledge from one graph to another and are unable to effectively learn from sparse samples of edges. To address this challenge, we introduce a new gradient-based meta learning framework, Meta-Graph. Our framework leverages higher-order gradients along with a learned graph signature function that conditionally generates a graph neural network initialization. Using a novel set of few shot link prediction benchmarks, we show that Meta-Graph can learn to quickly adapt to a new graph using only a small sample of true edges, enabling not only fast adaptation but also improved results at convergence.