arXiv (Cornell University) · 2020 · 56 citations · 33 references
ComputingComputer ScienceFeature EngineeringKnowledge NetworksMachine LearningDeep LearningGraph-based LearningNeural NetworksConvolutional Neural NetworksGraph Convolutional NetworksGraph Neural NetworksMultilayer PerceptronNeighborhood AggregationPerceptronRegularizationTraining
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.
33
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
A Global Geometric Framework for Nonlinear Dimensionality Reduction
Joshua B. Tenenbaum, Vin de Silva, John Langford · Science · 2000 · 13.7K citations
A tutorial on spectral clustering
Ulrike von Luxburg · Statistics and Computing · 2007 · 10.3K citations · Full text