Pseudo-Labeling with Graph Active Learning for Few-shot Node Classification
Pseudo-Labeling with Graph Active Learning for Few-shot Node Classification
复制标题
DOI：
10.1109/icdm58522.2023.00133
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Quan Li;Lingwei Chen;Shixiong Jing;Dinghao Wu
中科院分区：
文献类型：
--
作者：
Quan Li;Lingwei Chen;Shixiong Jing;Dinghao Wu
图已经成为许多领域中执行内容分析的最重要和最强大的数据结构之一。在这方面的工作中，节点分类是一个经典的任务，通常使用图神经网络（gnn）来完成。不幸的是，当标记节点很少时，常规gnn不能很好地推广到实际应用场景中。为了解决这一挑战，我们提出了一种利用伪标记和图主动学习的新颖的少射节点分类模型。我们首先提供了一个理论分析，认为额外的未标记数据有利于少射分类。受此启发，我们的模型通过一致性和对比正则化进行多层次数据增强以获得更好的半监督伪标记，并进一步设计图主动学习以促进伪标签选择并提高模型有效性。在四个公共引文网络上进行的大量实验表明，我们的模型可以在相当少的标记数据下有效地提高节点分类精度，显著优于所有最先进的基线。
Graphs have emerged as one of the most important and powerful data structures to perform content analysis in many fields. In this line of work, node classification is a classic task, which is generally performed using graph neural networks (GNNs). Unfortunately, regular GNNs cannot be well generalized into the real-world application scenario when the labeled nodes are few. To address this challenge, we propose a novel few-shot node classification model that leverages pseudo-labeling with graph active learning. We first provide a theoretical analysis to argue that extra unlabeled data benefit few-shot classification. Inspired by this, our model proceeds by performing multi-level data augmentation with consistency and contrastive regularizations for better semi-supervised pseudo-labeling, and further devising graph active learning to facilitate pseudo-label selection and improve model effectiveness. Extensive experiments on four public citation networks have demonstrated that our model can effectively improve node classification accuracy with considerably few labeled data, which significantly outperforms all state-of-the-art baselines by large margins.