Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting

04/04/2022
by   Tanwi Mallick, et al.
2

Deep-learning-based data-driven forecasting methods have produced impressive results for traffic forecasting. A major limitation of these methods, however, is that they provide forecasts without estimates of uncertainty, which are critical for real-time deployments. We focus on a diffusion convolutional recurrent neural network (DCRNN), a state-of-the-art method for short-term traffic forecasting. We develop a scalable deep ensemble approach to quantify uncertainties for DCRNN. Our approach uses a scalable Bayesian optimization method to perform hyperparameter optimization, selects a set of high-performing configurations, fits a generative model to capture the joint distributions of the hyperparameter configurations, and trains an ensemble of models by sampling a new set of hyperparameter configurations from the generative model. We demonstrate the efficacy of the proposed methods by comparing them with other uncertainty estimation techniques. We show that our generic and scalable approach outperforms the current state-of-the-art Bayesian and a number of other commonly used frequentist techniques.

READ FULL TEXT

page 4

page 10

page 11

page 12

page 13

page 14

page 15

research
02/20/2023

Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles

Classical problems in computational physics such as data-driven forecast...
research
04/17/2020

Transfer Learning with Graph Neural Networks for Short-Term Highway Traffic Forecasting

Highway traffic modeling and forecasting approaches are critical for int...
research
09/24/2019

Graph-Partitioning-Based Diffusion Convolution Recurrent Neural Network for Large-Scale Traffic Forecasting

Traffic forecasting approaches are critical to developing adaptive strat...
research
02/06/2018

Scalable Meta-Learning for Bayesian Optimization

Bayesian optimization has become a standard technique for hyperparameter...
research
10/28/2022

Measuring the Confidence of Traffic Forecasting Models: Techniques, Experimental Comparison and Guidelines towards Their Actionability

The estimation of the amount of uncertainty featured by predictive machi...
research
01/08/2020

Nonlinear Traffic Prediction as a Matrix Completion Problem with Ensemble Learning

We focus on short-term traffic forecasting for traffic operations manage...

Please sign up or login with your details

Forgot password? Click here to reset