论文标题
重新审视深度GCN中的过度光滑
Revisiting Over-smoothing in Deep GCNs
论文作者
论文摘要
过度厚度已被认为是深图卷积网络（GCN）中性能下降的主要原因。在本文中，我们提出了一种新观点，即深GCN可以在培训期间实际学习反对平滑的观点。这项工作将标准GCN体系结构解释为多层感知器（MLP）和图形正则化的层集成。我们分析并得出结论，在训练之前，深GCN的最终表示会过度光滑，但是，它在训练过程中学习了反对锻炼。根据结论，本文进一步设计了一种廉价但有效的技巧来改善GCN培训。我们验证我们的结论并评估三个引用网络的技巧，并进一步提供有关GCN中邻里聚集的见解。
Oversmoothing has been assumed to be the major cause of performance drop in deep graph convolutional networks (GCNs). In this paper, we propose a new view that deep GCNs can actually learn to anti-oversmooth during training. This work interprets a standard GCN architecture as layerwise integration of a Multi-layer Perceptron (MLP) and graph regularization. We analyze and conclude that before training, the final representation of a deep GCN does over-smooth, however, it learns anti-oversmoothing during training. Based on the conclusion, the paper further designs a cheap but effective trick to improve GCN training. We verify our conclusions and evaluate the trick on three citation networks and further provide insights on neighborhood aggregation in GCNs.
