Meta Propagation Networks for Graph Few-shot Semi-supervised Learning
Meta Propagation Networks for Graph Few-shot Semi-supervised Learning
复制标题
DOI：
10.1609/aaai.v36i6.20605
复制
发表时间：
2021-12
期刊：
影响因子：
--
通讯作者：
Kaize Ding;Jianling Wang;James Caverlee;Huan Liu
中科院分区：
文献类型：
--
作者：
Kaize Ding;Jianling Wang;James Caverlee;Huan Liu
受深度学习广泛成功的启发，图神经网络（GNN）被提出来学习表达节点表示，并在各种图学习任务中表现出了良好的性能。然而，现有的努力主要集中在传统的半监督环境中，提供相对丰富的金标节点。然而，由于数据标记非常费力并且需要大量的领域知识，特别是在考虑图结构数据的异构性时，这通常是不切实际的。在少样本半监督环境下，大多数现有 GNN 的性能不可避免地会受到过度拟合和过度平滑问题的影响，这很大程度上是由于标记数据的缺乏。在本文中，我们提出了一种配备新颖元学习算法的解耦网络架构来解决这个问题。本质上，我们的框架 Meta-PN 通过元学习的标签传播策略在未标记节点上推断出高质量的伪标签，这有效地增加了稀缺的标记数据，同时在训练期间实现了大的感受野。大量的实验表明，与各种基准数据集上的现有技术相比，我们的方法提供了简单而显着的性能提升。这项工作的实现和扩展手稿可在 https://github.com/kaize0409/Meta-PN 上公开获取。
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. The implementation and extended manuscript of this work are publicly available at https://github.com/kaize0409/Meta-PN.