{"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/spatio-temporal-adaptive-embedding-makes","title":"STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting","arxiv_id":"2308.10425","date":"2023-08-21","proceeding":null,"authors":["Hangchen Liu","Zheng Dong","Renhe Jiang","Jiewen Deng","Jinliang Deng","Quanjun Chen","Xuan Song"],"abstract":"With the rapid development of the Intelligent Transportation System (ITS), accurate traffic forecasting has emerged as a critical challenge. The key bottleneck lies in capturing the intricate spatio-temporal traffic patterns. In recent years, numerous neural networks with complicated architectures have been proposed to address this issue. However, the advancements in network architectures have encountered diminishing performance gains. In this study, we present a novel component called spatio-temporal adaptive embedding that can yield outstanding results with vanilla transformers. Our proposed Spatio-Temporal Adaptive Embedding transformer (STAEformer) achieves state-of-the-art performance on five real-world traffic forecasting datasets. Further experiments demonstrate that spatio-temporal adaptive embedding plays a crucial role in traffic forecasting by effectively capturing intrinsic spatio-temporal relations and chronological information in traffic time series.","url_abs":"https://arxiv.org/abs/2308.10425v5","url_pdf":"https://arxiv.org/pdf/2308.10425v5.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":"spatio-temporal-adaptive-embedding-makes","repo_url":"https://github.com/xdzhelheim/staeformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/traffic-prediction-on-metr-la","task":"Traffic Prediction","dataset":"METR-LA","model":"STAEformer","rank_in_archive_order":6,"of":20,"metrics":{"MAE @ 12 step":"3.34","MAE @ 3 step":"2.65"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems-bay","task":"Traffic Prediction","dataset":"PEMS-BAY","model":"STAEformer","rank_in_archive_order":11,"of":16,"metrics":{"MAE @ 12 step":"1.91"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems04","task":"Traffic Prediction","dataset":"PeMS04","model":"STAEformer","rank_in_archive_order":5,"of":12,"metrics":{"12 Steps MAE":"18.22"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems07","task":"Traffic Prediction","dataset":"PeMS07","model":"STAEformer","rank_in_archive_order":2,"of":17,"metrics":{"MAE@1h":"19.14"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems08","task":"Traffic Prediction","dataset":"PeMS08","model":"STAEformer","rank_in_archive_order":5,"of":13,"metrics":{"MAE@1h":"13.46"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pemsd7","task":"Traffic Prediction","dataset":"PeMSD7","model":"STAEformer","rank_in_archive_order":2,"of":8,"metrics":{"12 steps MAE":"19.14","12 steps MAPE":"8.01","12 steps RMSE":"32.60"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}