Meta Propagation Networks for Graph Few-shot Semi-supervised Learning

TL;DR

This paper introduces Meta Propagation Networks, a meta-learning based approach to improve graph neural network performance in few-shot semi-supervised learning by generating pseudo labels and leveraging large receptive fields.

Contribution

It proposes a novel decoupled network architecture with a meta-learning algorithm for label propagation to address overfitting and oversmoothing in few-shot graph semi-supervised learning.

Findings

Significant performance improvements over existing methods on benchmark datasets.

Effective pseudo label generation enhances learning with limited labeled data.

Large receptive fields contribute to better node representation.

Abstract

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.