{"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/revisiting-long-term-time-series-forecasting","title":"Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping","arxiv_id":"2305.10721","date":"2023-05-18","proceeding":null,"authors":["Zhe Li","shiyi qi","Yiduo Li","Zenglin Xu"],"abstract":"Long-term time series forecasting has gained significant attention in recent years. While there are various specialized designs for capturing temporal dependency, previous studies have demonstrated that a single linear layer can achieve competitive forecasting performance compared to other complex architectures. In this paper, we thoroughly investigate the intrinsic effectiveness of recent approaches and make three key observations: 1) linear mapping is critical to prior long-term time series forecasting efforts; 2) RevIN (reversible normalization) and CI (Channel Independent) play a vital role in improving overall forecasting performance; and 3) linear mapping can effectively capture periodic features in time series and has robustness for different periods across channels when increasing the input horizon. We provide theoretical and experimental explanations to support our findings and also discuss the limitations and future works. Our framework's code is available at \\url{https://github.com/plumprc/RTSF}.","url_abs":"https://arxiv.org/abs/2305.10721v1","url_pdf":"https://arxiv.org/pdf/2305.10721v1.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":"revisiting-long-term-time-series-forecasting","repo_url":"https://github.com/plumprc/rtsf","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":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"linear-layer","method_name":"Linear Layer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/time-series-forecasting-on-etth1-192-1","task":"Time Series Forecasting","dataset":"ETTh1 (192) Multivariate","model":"RLinear","rank_in_archive_order":9,"of":17,"metrics":{"MAE":"0.412","MSE":"0.404"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-336-1","task":"Time Series Forecasting","dataset":"ETTh1 (336) Multivariate","model":"RLinear","rank_in_archive_order":16,"of":72,"metrics":{"MAE":"0.423","MSE":"0.42"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-720-1","task":"Time Series Forecasting","dataset":"ETTh1 (720) Multivariate","model":"RLinear","rank_in_archive_order":7,"of":22,"metrics":{"MAE":"0.456","MSE":"0.442"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-96-1","task":"Time Series Forecasting","dataset":"ETTh1 (96) Multivariate","model":"RLinear","rank_in_archive_order":7,"of":15,"metrics":{"MAE":"0.391","MSE":"0.366"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-192-1","task":"Time Series Forecasting","dataset":"ETTh2 (192) Multivariate","model":"RLinear","rank_in_archive_order":3,"of":16,"metrics":{"MAE":"0.374","MSE":"0.319"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-336-1","task":"Time Series Forecasting","dataset":"ETTh2 (336) Multivariate","model":"RLinear","rank_in_archive_order":3,"of":20,"metrics":{"MAE":"0.386","MSE":"0.325"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-720-1","task":"Time Series Forecasting","dataset":"ETTh2 (720) Multivariate","model":"RLinear","rank_in_archive_order":1,"of":20,"metrics":{"MAE":"0.421","MSE":"0.372"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-96-1","task":"Time Series Forecasting","dataset":"ETTh2 (96) Multivariate","model":"RLinear","rank_in_archive_order":3,"of":16,"metrics":{"MAE":"0.331","MSE":"0.262"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm1-192-1","task":"Time Series Forecasting","dataset":"ETTm1 (192) Multivariate","model":"RLinear","rank_in_archive_order":7,"of":9,"metrics":{"MAE":"0.363","MSE":"0.335"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm1-336-1","task":"Time Series Forecasting","dataset":"ETTm1 (336) Multivariate","model":"RLinear","rank_in_archive_order":6,"of":8,"metrics":{"MAE":"0.383","MSE":"0.37"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm1-720-1","task":"Time Series Forecasting","dataset":"ETTm1 (720) Multivariate","model":"RLinear","rank_in_archive_order":5,"of":8,"metrics":{"MAE":"0.414","MSE":"0.425"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm1-96-1","task":"Time Series Forecasting","dataset":"ETTm1 (96) Multivariate","model":"RLinear","rank_in_archive_order":7,"of":9,"metrics":{"MAE":"0.342","MSE":"0.301"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm2-192-1","task":"Time Series Forecasting","dataset":"ETTm2 (192) Multivariate","model":"RLinear","rank_in_archive_order":3,"of":9,"metrics":{"MAE":"0.29","MSE":"0.219"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm2-336-1","task":"Time Series Forecasting","dataset":"ETTm2 (336) Multivariate","model":"RLinear","rank_in_archive_order":5,"of":8,"metrics":{"MAE":"0.326","MSE":"0.273"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm2-720-1","task":"Time Series Forecasting","dataset":"ETTm2 (720) Multivariate","model":"RLinear","rank_in_archive_order":6,"of":8,"metrics":{"MAE":"0.385","MSE":"0.366"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-ettm2-96-1","task":"Time Series Forecasting","dataset":"ETTm2 (96) Multivariate","model":"RLinear","rank_in_archive_order":6,"of":9,"metrics":{"MAE":"0.253","MSE":"0.164"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-192","task":"Time Series Forecasting","dataset":"Weather (192)","model":"RLinear-CI","rank_in_archive_order":6,"of":13,"metrics":{"Accuracy":"0.235","MSE":"0.189"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-192","task":"Time Series Forecasting","dataset":"Weather (192)","model":"RLinear","rank_in_archive_order":11,"of":13,"metrics":{"MAE":"0.26","MSE":"0.218"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-336","task":"Time Series Forecasting","dataset":"Weather (336)","model":"RLinear-CI","rank_in_archive_order":5,"of":11,"metrics":{"Accuracy":"0.275","MSE":"0.241"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-336","task":"Time Series Forecasting","dataset":"Weather (336)","model":"RLinear","rank_in_archive_order":9,"of":11,"metrics":{"MAE":"0.294","MSE":"0.265"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-720","task":"Time Series Forecasting","dataset":"Weather (720)","model":"RLinear-CI","rank_in_archive_order":4,"of":11,"metrics":{"Accuracy":"0.327","MSE":"0.314"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-720","task":"Time Series Forecasting","dataset":"Weather (720)","model":"RLinear","rank_in_archive_order":10,"of":11,"metrics":{"MAE":"0.339","MSE":"0.329"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-96","task":"Time Series Forecasting","dataset":"Weather (96)","model":"RLinear-CI","rank_in_archive_order":6,"of":12,"metrics":{"MAE":"0.194","MSE":"0.146"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-96","task":"Time Series Forecasting","dataset":"Weather (96)","model":"RLinear","rank_in_archive_order":10,"of":12,"metrics":{"MAE":"0.225","MSE":"0.175"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.10721","atlas_url":"https://app.syntology.ai/?focus=2305.10721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10721"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/plumprc/rtsf","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{},"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":2,"samples":[{"code_sha256_prefix":"9a5fcd4ebfc55d03","entry":"time_features","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"9a5fcd4ebfc55d03"}},{"code_sha256_prefix":"f8544563682146e5","entry":"time_features_from_frequency_str","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f8544563682146e5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}