label propagation (LPA) and graph convolutional neural networks (GCN) are
both message passing algorithms on graphs. Both solve the task of node
classification but LPA propagates node label information across the
本文从标签传播的角度探索了解耦后的图卷积网络,证明其本质上与两步标签传播是一致的,并揭示了其有效性,提出了一种新的标签传播方法,Propagation then Training Adaptively (PTA),通过动态自适应加权策略克服了解耦后的 GCN 的缺陷。该方法在四个基准数据集上得到经验证明优于现有方法。