{"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/when-spatio-temporal-meet-wavelets","title":"When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks","arxiv_id":null,"date":"2023-07-26","proceeding":"IEEE 39th International Conference on Data Engineering (ICDE) 2023 7","authors":["Yuchen Fang","Yanjun Qin","Haiyong Luo","Fang Zhao","Bingbing Xu","Liang Zeng","Chenxing Wang"],"abstract":"Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to the temporal changes and the dynamic spatial correlations of the traffic data. To capture these intricate dependencies, spatio-temporal networks, such as recurrent neural networks with graph convolution networks, graph convolution networks with temporal convolution networks, and temporal attention networks with full graph attention networks, are applied. However, previous spatiotemporal networks are based on end-to-end training and thus fail to handle the distribution shift in the non-stationary traffic time series. On the other hand, the efficient and effective algorithm for modeling spatial correlations is still lacking in prior networks. In this paper, rather than proposing yet another end-to-end model, we aim to provide a novel disentangle fusion framework STWave to mitigate the distribution shift issue. The framework first decouples the complex traffic data into stable trends and fluctuating events, followed by a dual-channel spatio-temporal network to model trends and events, respectively. Finally, reasonable future traffic can be predicted through the fusion of trends and events. Besides, we incorporate a novel query sampling strategy and graph wavelet-based graph positional encoding into the full graph attention network to efficiently and effectively model dynamic spatial correlations. Extensive experiments on six traffic datasets show the superiority of our approach, i.e., the higher forecasting accuracy with lower computational cost.","url_abs":"https://ieeexplore.ieee.org/document/10184591","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10184591","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":"when-spatio-temporal-meet-wavelets","repo_url":"https://github.com/lmissher/stwave","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"traffic-prediction","task_name":"Traffic Prediction"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/traffic-prediction-on-largest","task":"Traffic Prediction","dataset":"LargeST","model":"STWave","rank_in_archive_order":4,"of":6,"metrics":{"CA MAE":"19.69","GBA MAE":"20.81","GLA MAE":"20.96","SD MAE":"18.22"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems07","task":"Traffic Prediction","dataset":"PeMS07","model":"STWave","rank_in_archive_order":11,"of":17,"metrics":{"MAE@1h":"19.94"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pems08","task":"Traffic Prediction","dataset":"PeMS08","model":"STWave","rank_in_archive_order":4,"of":13,"metrics":{"MAE@1h":"13.42"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pemsd3","task":"Traffic Prediction","dataset":"PeMSD3","model":"STWave","rank_in_archive_order":4,"of":6,"metrics":{"12 steps MAE":"14.93"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pemsd4","task":"Traffic Prediction","dataset":"PeMSD4","model":"STWave","rank_in_archive_order":10,"of":13,"metrics":{"12 steps MAE":"18.50"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-prediction-on-pemsd8","task":"Traffic Prediction","dataset":"PeMSD8","model":"STWave","rank_in_archive_order":4,"of":13,"metrics":{"12 steps MAE":"13.42"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}