{"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-decoupled-masked-pre-training","title":"Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting","arxiv_id":"2312.00516","date":"2023-12-01","proceeding":null,"authors":["Haotian Gao","Renhe Jiang","Zheng Dong","Jinliang Deng","Yuxin Ma","Xuan Song"],"abstract":"Spatiotemporal forecasting techniques are significant for various domains such as transportation, energy, and weather. Accurate prediction of spatiotemporal series remains challenging due to the complex spatiotemporal heterogeneity. In particular, current end-to-end models are limited by input length and thus often fall into spatiotemporal mirage, i.e., similar input time series followed by dissimilar future values and vice versa. To address these problems, we propose a novel self-supervised pre-training framework Spatial-Temporal-Decoupled Masked Pre-training (STD-MAE) that employs two decoupled masked autoencoders to reconstruct spatiotemporal series along the spatial and temporal dimensions. Rich-context representations learned through such reconstruction could be seamlessly integrated by downstream predictors with arbitrary architectures to augment their performances. A series of quantitative and qualitative evaluations on six widely used benchmarks (PEMS03, PEMS04, PEMS07, PEMS08, METR-LA, and PEMS-BAY) are conducted to validate the state-of-the-art performance of STD-MAE. Codes are available at https://github.com/Jimmy-7664/STD-MAE.","url_abs":"https://arxiv.org/abs/2312.00516v3","url_pdf":"https://arxiv.org/pdf/2312.00516v3.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-decoupled-masked-pre-training","repo_url":"https://github.com/jimmy-7664/std-mae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"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-expy-tky-1","task":"Traffic Prediction","dataset":"EXPY-TKY","model":"STD-MAE","rank_in_archive_order":1,"of":8,"metrics":{"1 step MAE":"5.73","3 step MAE":"6.41","6 step MAE":"6.75"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-metr-la","task":"Traffic Prediction","dataset":"METR-LA","model":"STD-MAE","rank_in_archive_order":10,"of":20,"metrics":{"12 steps MAE":"3.40","12 steps MAPE":"9.59","12 steps RMSE":"7.07","MAE @ 12 step":"3.40","MAE @ 3 step":"2.62"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pems-bay","task":"Traffic Prediction","dataset":"PEMS-BAY","model":"STD-MAE","rank_in_archive_order":3,"of":16,"metrics":{"MAE @ 12 step":"1.77","RMSE":"4.20"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pems04","task":"Traffic Prediction","dataset":"PeMS04","model":"STD-MAE","rank_in_archive_order":1,"of":12,"metrics":{"12 Steps MAE":"17.80"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pems07","task":"Traffic Prediction","dataset":"PeMS07","model":"STD-MAE","rank_in_archive_order":1,"of":17,"metrics":{"MAE@1h":"18.31"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pemsd3","task":"Traffic Prediction","dataset":"PeMSD3","model":"STD-MAE","rank_in_archive_order":1,"of":6,"metrics":{"12 steps MAE":"13.80","12 steps MAPE":"13.96","12 steps RMSE":"24.43"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pemsd4","task":"Traffic Prediction","dataset":"PeMSD4","model":"STD-MAE","rank_in_archive_order":2,"of":13,"metrics":{"12 steps MAE":"17.80"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pemsd7","task":"Traffic Prediction","dataset":"PeMSD7","model":"STD-MAE","rank_in_archive_order":1,"of":8,"metrics":{"12 steps MAE":"18.31","12 steps MAPE":"7.72","12 steps RMSE":"31.07"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pemsd7-l","task":"Traffic Prediction","dataset":"PeMSD7(L)","model":"STD-MAE","rank_in_archive_order":1,"of":6,"metrics":{"12 steps MAE":"2.64","12 steps MAPE":"6.65","12 steps RMSE":"5.50"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pemsd7-m","task":"Traffic Prediction","dataset":"PeMSD7(M)","model":"STD-MAE","rank_in_archive_order":1,"of":7,"metrics":{"12 steps MAE":"2.52","12 steps MAPE":"6.35","12 steps RMSE":"5.20"},"uses_additional_data":true},{"leaderboard":"/sota/traffic-prediction-on-pemsd8","task":"Traffic Prediction","dataset":"PeMSD8","model":"STD-MAE","rank_in_archive_order":5,"of":13,"metrics":{"12 steps MAE":"13.44","12 steps MAPE":"8.76","12 steps RMSE":"22.47"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.00516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00516"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jimmy-7664/std-mae","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"48469f10c13c505c","entry":"l1_loss","repo":"jimmy-7664/std-mae","repo_kind":"official","path":"basicts/losses/losses.py","file_url":"https://github.com/jimmy-7664/std-mae/blob/HEAD/basicts/losses/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48469f10c13c505c"}},{"code_sha256_prefix":"3492570f7c53230f","entry":"masked_mae","repo":"jimmy-7664/std-mae","repo_kind":"official","path":"basicts/metrics/mae.py","file_url":"https://github.com/jimmy-7664/std-mae/blob/HEAD/basicts/metrics/mae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3492570f7c53230f"}},{"code_sha256_prefix":"e97291c1cbf62cfd","entry":"l2_loss","repo":"jimmy-7664/std-mae","repo_kind":"official","path":"basicts/losses/losses.py","file_url":"https://github.com/jimmy-7664/std-mae/blob/HEAD/basicts/losses/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e97291c1cbf62cfd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}