Graph Neural Networks (GNNs) require a relatively large number of labeled nodes and a reliable/uncorrupted graph connectivity structure in order to obtain good performance on the semi-supervised node classification task. The performance of GNNs can degrade significantly as the number of labeled nodes decreases or the graph connectivity structure is corrupted by adversarial attacks or due to noises in data measurement /collection. Therefore, it is important to develop GNN models that are able to achieve good performance when there is limited supervision knowledge -- a few labeled nodes and noisy graph structures. In this paper, we propose a novel Dual GNN learning framework to address this challenge task. The proposed framework has two GNN based node prediction modules. The primary module uses the input graph structure to induce regular node embeddings and predictions with a regular GNN baseline, while the auxiliary module constructs a new graph structure through fine-grained spectral clusterings and learns new node embeddings and predictions. By integrating the two modules in a dual GNN learning framework, we perform joint learning in an end-to-end fashion. This general framework can be applied on many GNN baseline models. The experimental results validate that the proposed dual GNN framework can greatly outperform the GNN baseline methods when the labeled nodes are scarce and the graph connectivity structure is noisy.
翻译:内建图网络(内建图网络)需要数量相对较多的贴标签节点和可靠/不受干扰的图形连通结构,才能在半监督节点分类任务上取得良好的业绩。 GNN的性能可以随着标签节点数量减少或图形连通结构因对抗性攻击或数据测量/收集中的噪音而腐蚀而显著下降。因此,必须开发能够在监督知识有限时取得良好业绩的GNN模型 -- -- 少数贴标签节点和吵闹的图形结构。在本文中,我们提出了应对这一挑战任务的新型双基GNN学习框架。拟议框架有两个基于GNN的节点预测模块。主要模块使用输入图结构来引导定期节点嵌嵌入和预测,同时使用普通GNN的基线,辅助模块通过精细的光谱光谱组合构建新的图形结构,并学习新的节点嵌和预测。通过将两个模块整合GNNN的双重G学习框架,我们以端到端的节点预测模式进行联合学习,在GNNNN的预测方式上进行联合学习。这个通用的基建图式框架是巨大的GNNNN的基模型。这个通用的模型,可以在大量的G的基式的基式的基建基式的G。