Node classification on attributed networks is a semi-supervised task that is crucial for network analysis. By decoupling two critical operations in Graph Convolutional Networks (GCNs), namely feature transformation and neighborhood aggregation, some recent works of decoupled GCNs could support the information to propagate deeper and achieve advanced performance. However, they follow the traditional structure-aware propagation strategy of GCNs, making it hard to capture the attribute correlation of nodes and sensitive to the structure noise described by edges whose two endpoints belong to different categories. To address these issues, we propose a new method called the itshape Propagation with Adaptive Mask then Training (PAMT). The key idea is to integrate the attribute similarity mask into the structure-aware propagation process. In this way, PAMT could preserve the attribute correlation of adjacent nodes during the propagation and effectively reduce the influence of structure noise. Moreover, we develop an iterative refinement mechanism to update the similarity mask during the training process for improving the training performance. Extensive experiments on four real-world datasets demonstrate the superior performance and robustness of PAMT.
翻译:配给网络的节点分类是一项半监督任务,对网络分析至关重要。通过分解图变异网络(GCNs)中的两种关键操作,即地貌变换和邻里聚合,最近一些分解的GCNs最近的一些作品可以支持信息,以更深入地传播和取得先进的性能。然而,它们遵循的是GCNs传统的结构认知传播战略,因此难以捕捉节点的属性相关性和对两个端点属于不同类别的边缘描述的结构噪音的敏感度。为了解决这些问题,我们提议了一种名为“用适应性面具和适应性面具传播”的新方法(PAMT)。关键的想法是将属性相似性遮罩纳入结构适应性传播进程。这样,PAMT就可以在传播过程中保持相邻节点的属性相关性,有效减少结构噪音的影响。此外,我们开发了一个迭代改进机制,以便在培训过程中更新相似性的遮罩。在四个真实世界数据集上的广泛实验显示了PAMT的优性和稳健性。