{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/incrementally-improving-graph-wavenet","title":"Incrementally Improving Graph WaveNet Performance on Traffic Prediction","arxiv_id":"1912.07390","date":"2019-12-11","proceeding":null,"authors":["Sam Shleifer","Clara McCreery","Vamsi Chitters"],"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 https://github.com/sshleifer/Graph-WaveNet .","url_abs":"https://arxiv.org/abs/1912.07390v1","url_pdf":"https://arxiv.org/pdf/1912.07390v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"incrementally-improving-graph-wavenet","repo_url":"https://github.com/sshleifer/Graph-WaveNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"incrementally-improving-graph-wavenet","repo_url":"https://github.com/david-amirault/amhs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"incrementally-improving-graph-wavenet","repo_url":"https://github.com/josegg05/eRGWnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"incrementally-improving-graph-wavenet","repo_url":"https://github.com/nnzhan/Graph-WaveNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"wavenet","method_name":"WaveNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/traffic-prediction-on-metr-la","task":"Traffic Prediction","dataset":"METR-LA","model":"Finetune from t1-6 checkpoint","rank_in_archive_order":14,"of":20,"metrics":{"MAE @ 12 step":"3.47"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.07390","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}