论文标题
pathgcn：从路径学习通用图形空间操作员
pathGCN: Learning General Graph Spatial Operators from Paths
论文作者
论文摘要
图形卷积网络（GCN）类似于卷积神经网络（CNNS），通常基于两个主要操作 - 空间和角度卷积。在GCN的背景下，与CNN的不同，通常选择基于图形laplacian的预定的空间操作员，只允许学习点的操作。但是，学习有意义的空间操作员对于开发更具表现力的GCN以提高性能至关重要。在本文中，我们提出了PathGCN，这是一种从图上随机路径学习空间操作员的新型方法。我们分析了我们方法的收敛性及其与现有GCN的差异。此外，我们讨论了将我们所学的空间操作员与重点卷积相结合的几种选择。我们在众多数据集上进行的广泛实验表明，通过适当地学习空间和角度的卷积，可以固有地避免使用诸如过度光滑的现象，并实现新的最先进的性能。
Graph Convolutional Networks (GCNs), similarly to Convolutional Neural Networks (CNNs), are typically based on two main operations - spatial and point-wise convolutions. In the context of GCNs, differently from CNNs, a pre-determined spatial operator based on the graph Laplacian is often chosen, allowing only the point-wise operations to be learnt. However, learning a meaningful spatial operator is critical for developing more expressive GCNs for improved performance. In this paper we propose pathGCN, a novel approach to learn the spatial operator from random paths on the graph. We analyze the convergence of our method and its difference from existing GCNs. Furthermore, we discuss several options of combining our learnt spatial operator with point-wise convolutions. Our extensive experiments on numerous datasets suggest that by properly learning both the spatial and point-wise convolutions, phenomena like over-smoothing can be inherently avoided, and new state-of-the-art performance is achieved.
