Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction

2020/12/09 by Tijs Maas, Peter Bloem, Maas, Tijs +1 · 1 citation
Engineering · Computer Science · Physics and Astronomy · #Traffic Prediction and Management Techniques #Advanced Graph Neural Networks #Complex Network Analysis Techniques

paper · pdf · doi:10.48550/arxiv.2012.05207

Abstract

Many traffic prediction applications rely on uncertainty estimates instead of the mean prediction. Statistical traffic prediction literature has a complete subfield devoted to uncertainty modelling, but recent deep learning traffic prediction models either lack this feature or make specific assumptions that restrict its practicality. We propose Quantile Graph Wavenet, a Spatio-Temporal neural network that is trained to estimate a density given the measurements of previous timesteps, conditioned on a quantile. Our method of density estimation is fully parameterised by our neural network and does not use a likelihood approximation internally. The quantile loss function is asymmetric and this makes it possible to model skewed densities. This approach produces uncertainty estimates without the need to sample during inference, such as in Monte Carlo Dropout, which makes our method also efficient.

Cited by

• Graph Neural Networks for Vehicular Social Networks: Trends, Challenges, and Opportunities

Related

• Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting
• Adaptive Modeling of Uncertainties for Traffic Forecasting
• Uncertainty Quantification for Traffic Forecasting: A Unified Approach
• Causally-Aware Spatio-Temporal Multi-Graph Convolution Network for Accurate and Reliable Traffic Prediction
• UQGNN: Uncertainty Quantification of Graph Neural Networks for Multivariate Spatiotemporal Prediction