Frequency Analysis for Graph Convolution Network

In this work, we develop quantitative results to the learnablity of a two-layers Graph Convolutional Network (GCN). Instead of analyzing GCN under some classes of functions, our approach provides a quantitative gap between a two-layers GCN and a two-layers MLP model. Our analysis is based on the graph signal processing (GSP) approach, which can provide much more useful insights than the message-passing computational model. Interestingly, based on our analysis, we have been able to empirically demonstrate a few case when GCN and other state-of-the-art models cannot learn even when true vertex features are extremely low-dimensional. To demonstrate our theoretical findings and propose a solution to the aforementioned adversarial cases, we build a proof of concept graph neural network model with stacked filters named Graph Filters Neural Network (gfNN).