Simpler is better: Multilevel Abstraction with Graph Convolutional Recurrent Neural Network Cells for Traffic Prediction

TL;DR

This paper introduces a simplified multilevel GNN-RNN architecture for traffic prediction that effectively captures spatiotemporal dependencies, improves accuracy, and reduces computational costs, especially for complex urban street networks.

Contribution

It proposes a novel multilevel abstraction sequence-to-sequence GNN-RNN model with sparse architecture and introduces a new Montreal street-level traffic dataset.

Findings

Improves one-hour prediction accuracy by over 7% on benchmarks.

Reduces training resource requirements by more than 50%.

Effectively models complex urban traffic patterns.

Abstract

In recent years, graph neural networks (GNNs) combined with variants of recurrent neural networks (RNNs) have reached state-of-the-art performance in spatiotemporal forecasting tasks. This is particularly the case for traffic forecasting, where GNN models use the graph structure of road networks to account for spatial correlation between links and nodes. Recent solutions are either based on complex graph operations or avoiding predefined graphs. This paper proposes a new sequence-to-sequence architecture to extract the spatiotemporal correlation at multiple levels of abstraction using GNN-RNN cells with sparse architecture to decrease training time compared to more complex designs. Encoding the same input sequence through multiple encoders, with an incremental increase in encoder layers, enables the network to learn general and detailed information through multilevel abstraction. We further present a new benchmark dataset of street-level segment traffic data from Montreal, Canada. Unlike highways, urban road segments are cyclic and characterized by complicated spatial dependencies. Experimental results on the METR-LA benchmark highway and our MSLTD street-level segment datasets demonstrate that our model improves performance by more than 7% for one-hour prediction compared to the baseline methods while reducing computing resource requirements by more than half compared to other competing methods.