University of Waterloo

Graph representation learning of road network

Zahra Gharaee, PDF

June 3, 2022, 11:30am EC4-2101A

I will present learning-based approaches to graph representations based on the state-of-the-art convolutional neural networks. This includes a scenario where GCNs models are employed to address a classification problem related to realistic road networks from Open Street Map. While edge features are crucial to generate descriptive graph representations of road networks, graph convolutional networks usually rely on node features only. We show that the highly representative edge features can still be integrated into such networks by applying a line graph transformation. We also propose a method for neighborhood sampling based on a topological neighbor[1]hood composed of both local and global neighbors. We compare the performance of learning representations using different types of neighborhood aggregation functions in transductive and inductive tasks and in supervised and unsupervised learning. Furthermore, we propose a novel aggregation approach, Graph Attention Isomorphism Network, GAIN. Our results show that GAIN outperforms state-of-the-art methods on the road type classification problem.