Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Node Classification | Cora | Accuracy72.51 | 583 | |
| Node Classification | Citeseer | Accuracy61.32 | 503 | |
| Node Classification | Cora-ML | Accuracy74.34 | 326 | |
| Node Classification | Ogbn-arxiv | Accuracy45.52 | 304 | |
| Node Classification | Cora Full | Accuracy59.7 | 88 | |
| Node Classification | DBLP | Accuracy66.4 | 78 | |
| few-shot node classification | Coauther CS | Accuracy87.86 | 68 | |
| few-shot node classification | CoraFull | Accuracy59.12 | 68 | |
| Node Classification | CoraFull 5-way 3-shot (test) | Accuracy52.23 | 36 | |
| Node Classification | Cora 2 way 3 shot | Accuracy (%)70.4 | 20 |