Graph Neural Networks (GNNs) have achieved unprecedented success in identifying categorical labels of graphs. However, most existing graph classification problems with GNNs follow the protocol of balanced data splitting, which misaligns with many real-world scenarios in which some classes have much fewer labels than others. Directly training GNNs under this imbalanced scenario may lead to uninformative representations of graphs in minority classes, and compromise the overall classification performance, which signifies the importance of developing effective GNNs towards handling imbalanced graph classification. Existing methods are either tailored for non-graph structured data or designed specifically for imbalanced node classification while few focus on imbalanced graph classification. To this end, we introduce a novel framework, Graph-of-Graph Neural Networks (G$^2$GNN), which alleviates the graph imbalance issue by deriving extra supervision globally from neighboring graphs and locally from stochastic augmentations of graphs. Globally, we construct a graph of graphs (GoG) based on kernel similarity and perform GoG propagation to aggregate neighboring graph representations. Locally, we employ topological augmentation via masking node features or dropping edges with self-consistency regularization to generate stochastic augmentations of each graph that improve the model generalibility. Extensive graph classification experiments conducted on seven benchmark datasets demonstrate our proposed G$^2$GNN outperforms numerous baselines by roughly 5\% in both F1-macro and F1-micro scores. The implementation of G$^2$GNN is available at https://github.com/YuWVandy/G2GNN}{https://github.com/YuWVandy/G2GNN
翻译:内建图网络(GNNS)在确定图表绝对标签方面取得了前所未有的成功。然而,GNNS的现有图表分类问题大多遵循了平衡数据分解协议,这与许多真实世界的情景不相符,有些类的标签比其他类少得多。在这一不平衡的假设情景下直接培训GNNS可能导致少数类图的无信息代表性,并损害总体分类性能,这表明开发有效的GNNS对于处理不平衡的图形分类十分重要。现有的方法要么是专门为非图结构数据定制的,要么是专门为不平衡节点分类设计的,而很少注重偏差的图表分类。为此,我们引入了一个新颖的框架,即GGG-G-G-Nal网络(G$2GNNNN),通过全球相邻图表的外建图和GG-G-GO_G_G_G_G_G_G_Bral_G_G_G_G_G_G_Bral_G_G_Bral_Bral_G_G_G_G_G_G_G_BAR_G_G_G_BAR_BAR_G_G_BAR_BAR_BAR_G_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_G_G_G_G_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_BAR_G_G_G_G_G_G_G_G_G_G_G_G_G_G_G_G_BAR_BAR_G_G_G_BAR_G_G_G_G_G_G_G_G_G_BAR_G_G_G_G_BAR_G_G_G_G_G_BAR_G_BAR_BAR_BAR_G_G_G_G_BAR_BAR_BAR_BAR_G_BAR_G_G_BAR_G_G_G_G_G_G_G_G_G_G_G_G_G_