Meta-GNN: On Few-shot Node Classification in Graph Meta-learning

TL;DR

Meta-GNN introduces a novel graph meta-learning framework that significantly improves few-shot node classification by leveraging prior knowledge from related tasks, demonstrating superior performance on benchmark datasets.

Contribution

The paper presents Meta-GNN, a general graph meta-learning model that enhances few-shot node classification and can be integrated with existing GNNs.

Findings

Significant performance improvement on three benchmark datasets.

Meta-GNN learns a more general and flexible model for task adaptation.

Effective in few-shot learning scenarios within graph domains.

Abstract

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework -- Meta-GNN -- to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption.