Meta Propagation Networks for Graph Few-shot Semi-supervised Learning
This addresses the challenge of data labeling being laborious and domain-specific in graph learning, though it is incremental as it builds on existing GNN and meta-learning techniques.
The paper tackles the problem of few-shot semi-supervised learning on graphs, where limited labeled data leads to overfitting and oversmoothing in GNNs, and proposes Meta-PN, a decoupled network with meta-learned label propagation, which achieves substantial performance gains on benchmark datasets.
Inspired by the extensive success of deep learning, graph neural networks (GNNs) have been proposed to learn expressive node representations and demonstrated promising performance in various graph learning tasks. However, existing endeavors predominately focus on the conventional semi-supervised setting where relatively abundant gold-labeled nodes are provided. While it is often impractical due to the fact that data labeling is unbearably laborious and requires intensive domain knowledge, especially when considering the heterogeneity of graph-structured data. Under the few-shot semi-supervised setting, the performance of most of the existing GNNs is inevitably undermined by the overfitting and oversmoothing issues, largely owing to the shortage of labeled data. In this paper, we propose a decoupled network architecture equipped with a novel meta-learning algorithm to solve this problem. In essence, our framework Meta-PN infers high-quality pseudo labels on unlabeled nodes via a meta-learned label propagation strategy, which effectively augments the scarce labeled data while enabling large receptive fields during training. Extensive experiments demonstrate that our approach offers easy and substantial performance gains compared to existing techniques on various benchmark datasets.