# Incrementally Improving Graph WaveNet Performance on Traffic Prediction

arXiv: https://arxiv.org/abs/1912.07390 · HTML: https://mlsanity.com/paper/1912.07390/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2019.

## Built on by (most cited first, 10 of 10)

- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks](https://mlsanity.com/paper/2203.08852/) (2022)
- [A Survey of Generative Techniques for Spatial-Temporal Data Mining](https://mlsanity.com/paper/2405.09592/) (2024)
- [Efficient Traffic Prediction Through Spatio-Temporal Distillation](https://mlsanity.com/paper/2501.10459/) (2025)
- [Because Every Sensor Is Unique, so Is Every Pair: Handling Dynamicity in Traffic Forecasting](https://mlsanity.com/paper/2302.09956/) (2023)
- [Graph Convolutional Networks for Traffic Forecasting with Missing Values](https://mlsanity.com/paper/2212.06419/) (2022)
- [PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training](https://mlsanity.com/paper/2507.11683/) (2025)
- [RadNet: Incident Prediction in Spatio-Temporal Road Graph Networks Using Traffic Forecasting](https://mlsanity.com/paper/2206.05602/) (2022)
- [Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecasting](https://mlsanity.com/paper/2510.23656/) (2025)
- [Generalising Travel Time Prediction To Varying Route Choices In Urban Networks](https://mlsanity.com/paper/2605.06918/) (2026)

## Abstract (arXiv)

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 https://github.com/sshleifer/Graph-WaveNet .