Generative Graph Transformer

Deep generative models for graphs have shown great promise in the area of drug design, but have so far found little application beyond generating graph-structured molecules. In this work, we demonstrate a proof of concept for the challenging task of road network extraction from image data introducing the Generative Graph Transformer (GGT): a deep autoregressive model based on state-of-the-art attention mechanisms. In road network extraction, the goal is to learn to reconstruct graphs representing the road networks pictured in satellite images. A PyTorch implementation of GGT is available here. The proposed GGT model is designed for the recurrent generation of graphs, conditioned on other data such as an image, by means of the encoder-decoder architecture outlined in Figure 1.