Graph Convolutional Networks (GCNs) are one of the most popular architectures that are used to solve classification problems accompanied by graphical information. We present a rigorous theoretical understanding of the effects of graph convolutions in multi-layer networks. We study these effects through the node classification problem of a non-linearly separable Gaussian mixture model coupled with a stochastic block model. First, we show that a single graph convolution expands the regime of the distance between the means where multi-layer networks can classify the data by a factor of at least $1/\sqrt[4]{\mathbb{E}{\rm deg}}$, where $\mathbb{E}{\rm deg}$ denotes the expected degree of a node. Second, we show that with a slightly stronger graph density, two graph convolutions improve this factor to at least $1/\sqrt[4]{n}$, where $n$ is the number of nodes in the graph. Finally, we provide both theoretical and empirical insights into the performance of graph convolutions placed in different combinations among the layers of a network, concluding that the performance is mutually similar for all combinations of the placement. We present extensive experiments on both synthetic and real-world data that illustrate our results.
翻译:图形革命网络(GCNs)是用来用图形信息解决分类问题的最受欢迎的结构之一。我们对多层网络中的图形革命的影响提出了严格的理论理解。我们通过非线性分离高斯混合模型的节点分类问题,加上一个随机区块模型来研究这些影响。首先,我们显示一个单一的图形革命扩大了多层网络能够将数据以至少1美元/斯克特[4] /#mathbb{Eunrm deg ⁇ $来分类的方法之间的距离制度。最后,我们从理论上和实验上都了解了在多层网络中的图形革命表现,其中$\mathb{Eunrm deg}$表示一个节点的预期程度。第二,我们显示,如果图形密度稍强一点,两个图形革命将这一系数提高到至少1美元/斯克特[4]/n}美元,其中美元是图中节点的数量。最后,我们提供了在不同的合成网络中放置的图像变异性表现的理论和经验洞察力和实验结果,我们目前所有合成网络的相形形变的组合都是两个层次。