{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/segrnn-segment-recurrent-neural-network-for","title":"SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting","arxiv_id":"2308.11200","date":"2023-08-22","proceeding":null,"authors":["Shengsheng Lin","Weiwei Lin","Wentai Wu","Feiyu Zhao","Ruichao Mo","Haotong Zhang"],"abstract":"RNN-based methods have faced challenges in the Long-term Time Series Forecasting (LTSF) domain when dealing with excessively long look-back windows and forecast horizons. Consequently, the dominance in this domain has shifted towards Transformer, MLP, and CNN approaches. The substantial number of recurrent iterations are the fundamental reasons behind the limitations of RNNs in LTSF. To address these issues, we propose two novel strategies to reduce the number of iterations in RNNs for LTSF tasks: Segment-wise Iterations and Parallel Multi-step Forecasting (PMF). RNNs that combine these strategies, namely SegRNN, significantly reduce the required recurrent iterations for LTSF, resulting in notable improvements in forecast accuracy and inference speed. Extensive experiments demonstrate that SegRNN not only outperforms SOTA Transformer-based models but also reduces runtime and memory usage by more than 78%. These achievements provide strong evidence that RNNs continue to excel in LTSF tasks and encourage further exploration of this domain with more RNN-based approaches. The source code is coming soon.","url_abs":"https://arxiv.org/abs/2308.11200v1","url_pdf":"https://arxiv.org/pdf/2308.11200v1.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":"segrnn-segment-recurrent-neural-network-for","repo_url":"https://github.com/lss-1138/SegRNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"segrnn-segment-recurrent-neural-network-for","repo_url":"https://github.com/WenjieDu/PyPOTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"segrnn-segment-recurrent-neural-network-for","repo_url":"https://github.com/hughxx/tsf-new-paper-taste","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"segrnn-segment-recurrent-neural-network-for","repo_url":"https://github.com/thuml/Time-Series-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/time-series-forecasting-on-etth1-192-1","task":"Time Series Forecasting","dataset":"ETTh1 (192) Multivariate","model":"SegRNN","rank_in_archive_order":4,"of":17,"metrics":{"MAE":"0.402","MSE":"0.385"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-192-2","task":"Time Series Forecasting","dataset":"ETTh1 (192) Univariate","model":"SegRNN","rank_in_archive_order":2,"of":5,"metrics":{"MAE":"0.208","MSE":"0.068"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-336-1","task":"Time Series Forecasting","dataset":"ETTh1 (336) Multivariate","model":"SegRNN","rank_in_archive_order":7,"of":72,"metrics":{"MAE":"0.417","MSE":"0.401"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-336-2","task":"Time Series Forecasting","dataset":"ETTh1 (336) Univariate","model":"SegRNN","rank_in_archive_order":1,"of":10,"metrics":{"MAE":"0.215","MSE":"0.073"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-720-1","task":"Time Series Forecasting","dataset":"ETTh1 (720) Multivariate","model":"SegRNN","rank_in_archive_order":3,"of":22,"metrics":{"MAE":"0.447","MSE":"0.434"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-720-2","task":"Time Series Forecasting","dataset":"ETTh1 (720) Univariate","model":"SegRNN","rank_in_archive_order":3,"of":12,"metrics":{"MAE":"0.233","MSE":"0.085"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-96-1","task":"Time Series Forecasting","dataset":"ETTh1 (96) Multivariate","model":"SegRNN","rank_in_archive_order":1,"of":15,"metrics":{"MAE":"0.376","MSE":"0.341"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth1-96-2","task":"Time Series Forecasting","dataset":"ETTh1 (96) Univariate","model":"SegRNN","rank_in_archive_order":1,"of":6,"metrics":{"MAE":"0.18","MSE":"0.053"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-192-1","task":"Time Series Forecasting","dataset":"ETTh2 (192) Multivariate","model":"SegRNN","rank_in_archive_order":4,"of":16,"metrics":{"MAE":"0.36","MSE":"0.321"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-192-2","task":"Time Series Forecasting","dataset":"ETTh2 (192) Univariate","model":"SegRNN","rank_in_archive_order":2,"of":6,"metrics":{"MAE":"0.317","MSE":"0.158"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-336-1","task":"Time Series Forecasting","dataset":"ETTh2 (336) Multivariate","model":"SegRNN","rank_in_archive_order":4,"of":20,"metrics":{"MAE":"0.374","MSE":"0.325"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-336-2","task":"Time Series Forecasting","dataset":"ETTh2 (336) Univariate","model":"SegRNN","rank_in_archive_order":5,"of":10,"metrics":{"MAE":"0.345","MSE":"0.18"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-720-1","task":"Time Series Forecasting","dataset":"ETTh2 (720) Multivariate","model":"SegRNN","rank_in_archive_order":7,"of":20,"metrics":{"MAE":"0.424","MSE":"0.394"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-720-2","task":"Time Series Forecasting","dataset":"ETTh2 (720) Univariate","model":"SegRNN","rank_in_archive_order":3,"of":11,"metrics":{"MAE":"0.365","MSE":"0.205"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-96-1","task":"Time Series Forecasting","dataset":"ETTh2 (96) Multivariate","model":"SegRNN","rank_in_archive_order":5,"of":16,"metrics":{"MAE":"0.32","MSE":"0.263"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-etth2-96-2","task":"Time Series Forecasting","dataset":"ETTh2 (96) Univariate","model":"SegRNN","rank_in_archive_order":2,"of":6,"metrics":{"MAE":"0.272","MSE":"0.121"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-192","task":"Time Series Forecasting","dataset":"Weather (192)","model":"SegRNN","rank_in_archive_order":1,"of":13,"metrics":{"MAE":"0.227","MSE":"0.186"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-336","task":"Time Series Forecasting","dataset":"Weather (336)","model":"SegRNN","rank_in_archive_order":3,"of":11,"metrics":{"MAE":"0.269","MSE":"0.237"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-720","task":"Time Series Forecasting","dataset":"Weather (720)","model":"SegRNN","rank_in_archive_order":3,"of":11,"metrics":{"MAE":"0.32","MSE":"0.31"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-forecasting-on-weather-96","task":"Time Series Forecasting","dataset":"Weather (96)","model":"SegRNN","rank_in_archive_order":1,"of":12,"metrics":{"MAE":"0.181","MSE":"0.142"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.11200","atlas_url":"https://app.syntology.ai/?focus=2308.11200","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2308.11200"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.11200\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.11200"},"call":"get_concepts_for_paper(arxiv_id=\"2308.11200\")"}],"by_repo":[{"repo":"lss-1138/SegRNN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.06625"],"harvested_for_calls":[{"arxiv_id":"2310.06625","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.06625"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.06625\")"}]},{"repo":"WenjieDu/PyPOTS","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":8,"harvested_for":["1706.03762","2012.07436","2101.10318","2103.07719","2106.13008","2211.14730","2312.16427","2404.08472"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"2012.07436","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2012.07436"},"call":"get_harvested_code_for_paper(arxiv_id=\"2012.07436\")"},{"arxiv_id":"2101.10318","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.10318"},"call":"get_harvested_code_for_paper(arxiv_id=\"2101.10318\")"},{"arxiv_id":"2103.07719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.07719"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.07719\")"},{"arxiv_id":"2106.13008","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.13008"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.13008\")"},{"arxiv_id":"2211.14730","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.14730"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.14730\")"},{"arxiv_id":"2312.16427","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.16427"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.16427\")"},{"arxiv_id":"2404.08472","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.08472"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.08472\")"}]},{"repo":"hughxx/tsf-new-paper-taste","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"thuml/Time-Series-Library","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2403.00131","2601.09237","2601.23114"],"harvested_for_calls":[{"arxiv_id":"2403.00131","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.00131"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.00131\")"},{"arxiv_id":"2601.09237","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2601.09237"},"call":"get_harvested_code_for_paper(arxiv_id=\"2601.09237\")"},{"arxiv_id":"2601.23114","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2601.23114"},"call":"get_harvested_code_for_paper(arxiv_id=\"2601.23114\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"eecf7c6c3bb17ca53efd4105caed735128d8dadfb4893c298eed15ca7b9b5ccf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}