Heterogeneous Graph Sequence Neural Networks for Dynamic Traffic Assignment

TL;DR

This paper introduces HSTGSN, a novel heterogeneous graph neural network that models long-range dependencies between origin-destination pairs to improve traffic flow prediction beyond sensor locations.

Contribution

The paper proposes a heterogeneous spatio-temporal graph sequence network that captures implicit OD demand relationships and predicts traffic flows more accurately than existing sensor-based methods.

Findings

Achieves high accuracy in traffic flow prediction on real-world networks.

Effectively models long-range OD dependencies.

Demonstrates strong generalization to incomplete OD data.

Abstract

Traffic assignment and traffic flow prediction provide critical insights for urban planning, traffic management, and the development of intelligent transportation systems. An efficient model for calculating traffic flows over the entire transportation network could provide a more detailed and realistic understanding of traffic dynamics. However, existing traffic prediction approaches, such as those utilizing graph neural networks, are typically limited to locations where sensors are deployed and cannot predict traffic flows beyond sensor locations. To alleviate this limitation, inspired by fundamental relationship that exists between link flows and the origin-destination (OD) travel demands, we proposed the Heterogeneous Spatio-Temporal Graph Sequence Network (HSTGSN). HSTGSN exploits dependency between origin and destination nodes, even when it is long-range, and learns implicit vehicle route choices under different origin-destination demands. This model is based on a heterogeneous graph which consists of road links, OD links (virtual links connecting origins and destinations) and a spatio-temporal graph encoder-decoder that captures the spatio-temporal relationship between OD demands and flow distribution. We will show how the graph encoder-decoder is able to recover the incomplete information in the OD demand, by using node embedding from the graph decoder to predict the temporal changes in flow distribution. Using extensive experimental studies on real-world networks with complete/incomplete OD demands, we demonstrate that our method can not only capture the implicit spatio-temporal relationship between link traffic flows and OD demands but also achieve accurate prediction performance and generalization capability.