Incrementally Improving Graph WaveNet Performance on Traffic Prediction
Published in
arXiv.org(2019)External Links:
TL
TL;DR
This work improves GWN by using better hyperparameters, adding connections that allow larger gradients to flow back to the early convolutional layers, and pretraining on an easier short-term traffic prediction task, and shows that ensembling separate models for short- and long-term predictions further improves performance.
Abstract
We present a series of modifications which improve upon Graph WaveNet's previously state-of-the-art performance on the METR-LA traffic prediction task. The goal of this task is to predict the future speed of traffic at each sensor in a network using the past hour of sensor readings. Graph WaveNet (GWN) is a spatio-temporal graph neural network which interleaves graph convolution to aggregate information from nearby sensors and dilated convolutions to aggregate information from the past. We improve GWN by (1) using better hyperparameters, (2) adding connections that allow larger gradients to flow back to the early convolutional layers, and (3) pretraining on an easier short-term traffic prediction task. These modifications reduce the mean absolute error by .06 on the METR-LA task, nearly equal to GWN's improvement over its predecessor. These improvements generalize to the PEMS-BAY dataset, with similar relative magnitude. We also show that ensembling separate models for short-and long-term predictions further improves performance. Code is available at this https URL .
References6 items
1
Graph WaveNet for Deep Spatial-Temporal Graph Modeling
2
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
3
WaveNet: A Generative Model for Raw Audio
4
Cyclical Learning Rates for Training Neural Networks
5