ETA Prediction with Graph Neural Networks in Google Maps

by   Austin Derrow-Pinion, et al.

Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike. Further, such a task requires accounting for complex spatiotemporal interactions (modelling both the topological properties of the road network and anticipating events – such as rush hours – that may occur in the future). Hence, it is an ideal target for graph representation learning at scale. Here we present a graph neural network estimator for estimated time of arrival (ETA) which we have deployed in production at Google Maps. While our main architecture consists of standard GNN building blocks, we further detail the usage of training schedule methods such as MetaGradients in order to make our model robust and production-ready. We also provide prescriptive studies: ablating on various architectural decisions and training regimes, and qualitative analyses on real-world situations where our model provides a competitive edge. Our GNN proved powerful when deployed, significantly reducing negative ETA outcomes in several regions compared to the previous production baseline (40+


page 1

page 2

page 3

page 4


Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks

Origin-Destination (O-D) travel demand prediction is a fundamental chall...

Uncertainty Quantification of Spatiotemporal Travel Demand with Probabilistic Graph Neural Networks

Recent studies have significantly improved the prediction accuracy of tr...

BRIGHT – Graph Neural Networks in Real-Time Fraud Detection

Detecting fraudulent transactions is an essential component to control r...

Stochastic Graph Neural Networks

Graph neural networks (GNNs) model nonlinear representations in graph da...

Physics-Informed Graph Neural Network for Spatial-temporal Production Forecasting

Production forecast based on historical data provides essential value fo...

Representation Learning with Graph Neural Networks for Speech Emotion Recognition

Learning expressive representation is crucial in deep learning. In speec...

Please sign up or login with your details

Forgot password? Click here to reset