Papers › SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting

SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting

22 Aug 2023arXiv:2308.11200archive 2025-07-28

Shengsheng Lin, Weiwei Lin, Wentai Wu, Feiyu Zhao, Ruichao Mo, Haotong Zhang

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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

lss-1138/SegRNN officialmentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (arXiv:2310.06625; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 4 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
WenjieDu/PyPOTS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (arXiv:2012.07436; that paper's own run record: 62 ran (of which 53 constructed an object rather than computing a result; 62 with no instrument failure: 0 honoured, 1 violated, 61 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified), Multi-Time Attention Networks for Irregularly Sampled Time Series (arXiv:2101.10318; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified) and 5 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
hughxx/tsf-new-paper-taste mentioned on GitHubpytorchSyntology: not harvested report
thuml/Time-Series-Library mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniTS: A Unified Multi-Task Time Series Model (arXiv:2403.00131; that paper's own run record: 19 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified), XLinear: A Lightweight and Accurate MLP-Based Model for Long-Term Time Series... (arXiv:2601.09237; that paper's own run record: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 7 samples that ran constructed an object rather than computing a result) and To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series (arXiv:2601.23114; that paper's own run record: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Time SeriesTime Series Forecasting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Time Series Forecasting ETTh1 (192) Multivariate SegRNN MAE 0.402 #4 of 17 Archive leaderboard report
Time Series Forecasting ETTh1 (192) Multivariate SegRNN MSE 0.385 #4 of 17 Archive leaderboard report
Time Series Forecasting ETTh1 (192) Univariate SegRNN MAE 0.208 #2 of 5 Archive leaderboard report
Time Series Forecasting ETTh1 (192) Univariate SegRNN MSE 0.068 #2 of 5 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate SegRNN MAE 0.417 #7 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate SegRNN MSE 0.401 #7 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Univariate SegRNN MAE 0.215 #1 of 10 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Univariate SegRNN MSE 0.073 #1 of 10 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Multivariate SegRNN MAE 0.447 #3 of 22 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Multivariate SegRNN MSE 0.434 #3 of 22 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Univariate SegRNN MAE 0.233 #3 of 12 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Univariate SegRNN MSE 0.085 #3 of 12 Archive leaderboard report
Time Series Forecasting ETTh1 (96) Multivariate SegRNN MAE 0.376 #1 of 15 Archive leaderboard report
Time Series Forecasting ETTh1 (96) Multivariate SegRNN MSE 0.341 #1 of 15 Archive leaderboard report
Time Series Forecasting ETTh1 (96) Univariate SegRNN MAE 0.18 #1 of 6 Archive leaderboard report
Time Series Forecasting ETTh1 (96) Univariate SegRNN MSE 0.053 #1 of 6 Archive leaderboard report
Time Series Forecasting ETTh2 (192) Multivariate SegRNN MAE 0.36 #4 of 16 Archive leaderboard report
Time Series Forecasting ETTh2 (192) Multivariate SegRNN MSE 0.321 #4 of 16 Archive leaderboard report
Time Series Forecasting ETTh2 (192) Univariate SegRNN MAE 0.317 #2 of 6 Archive leaderboard report
Time Series Forecasting ETTh2 (192) Univariate SegRNN MSE 0.158 #2 of 6 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Multivariate SegRNN MAE 0.374 #4 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Multivariate SegRNN MSE 0.325 #4 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Univariate SegRNN MAE 0.345 #5 of 10 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Univariate SegRNN MSE 0.18 #5 of 10 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Multivariate SegRNN MAE 0.424 #7 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Multivariate SegRNN MSE 0.394 #7 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Univariate SegRNN MAE 0.365 #3 of 11 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Univariate SegRNN MSE 0.205 #3 of 11 Archive leaderboard report
Time Series Forecasting ETTh2 (96) Multivariate SegRNN MAE 0.32 #5 of 16 Archive leaderboard report
Time Series Forecasting ETTh2 (96) Multivariate SegRNN MSE 0.263 #5 of 16 Archive leaderboard report
Time Series Forecasting ETTh2 (96) Univariate SegRNN MAE 0.272 #2 of 6 Archive leaderboard report
Time Series Forecasting ETTh2 (96) Univariate SegRNN MSE 0.121 #2 of 6 Archive leaderboard report
Time Series Forecasting Weather (192) SegRNN MAE 0.227 #1 of 13 Archive leaderboard report
Time Series Forecasting Weather (192) SegRNN MSE 0.186 #1 of 13 Archive leaderboard report
Time Series Forecasting Weather (336) SegRNN MAE 0.269 #3 of 11 Archive leaderboard report
Time Series Forecasting Weather (336) SegRNN MSE 0.237 #3 of 11 Archive leaderboard report
Time Series Forecasting Weather (720) SegRNN MAE 0.32 #3 of 11 Archive leaderboard report
Time Series Forecasting Weather (720) SegRNN MSE 0.31 #3 of 11 Archive leaderboard report
Time Series Forecasting Weather (96) SegRNN MAE 0.181 #1 of 12 Archive leaderboard report
Time Series Forecasting Weather (96) SegRNN MSE 0.142 #1 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections