论文标题
基于标签的基于标签的图形神经网络，用于半监督节点分类
Label-Consistency based Graph Neural Networks for Semi-supervised Node Classification
论文作者
论文摘要
图形神经网络（GNN）在基于图的半监督节点分类中取得了显着成功，利用来自相邻节点的信息来改善目标节点的表示形式学习。 GNN在节点分类中的成功取决于以下假设：连接节点倾向于具有相同的标签。但是，这样的假设并不总是可行，从而限制了GNN在节点分类中的性能。在本文中，我们提出了基于标签的图形神经网络（LC-GNN），利用节点对未连接，但具有相同的标签来扩大GNN中节点的接受场。基准数据集上的实验证明了所提出的LC-GNN在基于图的半监督节点分类中优于传统GNN。在稀疏场景中，LC-GNN的优越性仅具有少数标记的节点。
Graph neural networks (GNNs) achieve remarkable success in graph-based semi-supervised node classification, leveraging the information from neighboring nodes to improve the representation learning of target node. The success of GNNs at node classification depends on the assumption that connected nodes tend to have the same label. However, such an assumption does not always work, limiting the performance of GNNs at node classification. In this paper, we propose label-consistency based graph neural network(LC-GNN), leveraging node pairs unconnected but with the same labels to enlarge the receptive field of nodes in GNNs. Experiments on benchmark datasets demonstrate the proposed LC-GNN outperforms traditional GNNs in graph-based semi-supervised node classification.We further show the superiority of LC-GNN in sparse scenarios with only a handful of labeled nodes.
