论文标题
简单而深的图形卷积网络
Simple and Deep Graph Convolutional Networks
论文作者
论文摘要
图形卷积网络（GCN）是用于图形结构数据的强大深度学习方法。最近，GCN和随后的变体在现实世界数据集的各个应用领域表现出卓越的性能。尽管他们成功了，但由于{\ em过度平滑}的问题，当前的大多数GCN模型都是浅的。在本文中，我们研究了设计和分析深图卷积网络的问题。我们建议使用两种简单但有效的技术的香草GCN模型的GCNII：{\ em初始残留}和{\ em Indentity映射}。我们提供了理论和经验证据，表明这两种技术有效地消除了过度平滑的问题。我们的实验表明，Deep GCNII模型在各种半监督任务上的最新方法优于最先进的方法。代码可在https://github.com/chennnm/gcnii上找到。
Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the {\em over-smoothing} problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://github.com/chennnM/GCNII .
