This paper presents a locally decoupled network parameter learning with local
propagation. Three elements are taken into account: (i) sets of nonlinear
transforms that describe the representations at all nodes, (ii) a local
objective at each node related to the corresponding local repr
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。