Relational Fusion Networks: Graph Convolutional Networks for Road Networks

TL;DR

This paper introduces Relational Fusion Networks, a specialized Graph Convolutional Network for road networks, demonstrating significant performance improvements over existing GCNs in transportation tasks.

Contribution

The paper presents a novel GCN architecture tailored for road networks, addressing limitations of existing models and improving task performance.

Findings

RFN outperforms state-of-the-art GCNs by 21%-40% on key tasks

Existing GCNs may not effectively utilize road network structure

RFN generalizes better across different road networks

Abstract

The application of machine learning techniques in the setting of road networks holds the potential to facilitate many important intelligent transportation applications. Graph Convolutional Networks (GCNs) are neural networks that are capable of leveraging the structure of a network. However, many implicit assumptions of GCNs do not apply to road networks. We introduce the Relational Fusion Network (RFN), a novel type of GCN designed specifically for road networks. In particular, we propose methods that outperform state-of-the-art GCNs by 21%-40% on two machine learning tasks in road networks. Furthermore, we show that state-of-the-art GCNs may fail to effectively leverage road network structure and may not generalize well to other road networks.