An Unpooling Layer for Graph Generation

Abstract

We propose a novel and trainable graph unpooling layer for effective graph generation. The unpooling layer receives an input graph with features and outputs an enlarged graph with desired structure and features. We prove that the output graph of the unpooling layer remains connected and for any connected graph there exists a series of unpooling layers that can produce it from a 3-node graph. We apply the unpooling layer within the generator of a generative adversarial network as well as the decoder of a variational autoencoder. We give extensive experimental evidence demonstrating the competitive performance of our proposed method on synthetic and real data.