Metalearning traffic assignment for network disruptions with graph convolutional neural networks

TL;DR

This paper introduces a meta-learning approach combined with graph convolutional neural networks to enable rapid adaptation of traffic flow predictions to network disruptions and demand changes, improving accuracy in unforeseen scenarios.

Contribution

The work presents a novel meta-learning architecture that allows GCNs to quickly adapt to new network structures and demand patterns in traffic forecasting, addressing a key limitation of traditional models.

Findings

Achieves R^2 of around 0.85 on unseen disruptions and demand scenarios.

Enables rapid adaptation of traffic predictions to network changes.

Reduces the need for extensive training data covering all scenarios.

Abstract

Building machine-learning models for estimating traffic flows from OD matrices requires an appropriate design of the training process and a training dataset spanning over multiple regimes and dynamics. As machine-learning models rely heavily on historical data, their predictions are typically accurate only when future traffic patterns resemble those observed during training. However, their performance often degrades when there is a significant statistical discrepancy between historical and future conditions. This issue is particularly relevant in traffic forecasting when predictions are required for modified versions of the network, where the underlying graph structure changes due to events such as maintenance, public demonstrations, flooding, or other extreme disruptions. Ironically, these are precisely the situations in which reliable traffic predictions are most needed. In the presented work, we combine a machine-learning model (graph convolutional neural network) with a meta-learning architecture to train the former to quickly adapt to new graph structures and demand patterns, so that it may easily be applied to scenarios in which changes in the road network (the graph) and the demand (the node features) happen simultaneously. Our results show that the use of meta-learning allows the graph neural network to quickly adapt to unseen graphs (network closures) and OD matrixes while easing the burden of designing a training dataset that covers all relevant patterns for the practitioners. The proposed architecture achieves a R^2 of around 0.85 over unseen closures and OD matrixes.