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

Code

lss-1138/SegRNN officialmentioned on GitHubpytorchApache-2.0 report
WenjieDu/PyPOTS mentioned on GitHubpytorch report
hughxx/tsf-new-paper-taste mentioned on GitHubpytorch report
thuml/Time-Series-Library mentioned on GitHubpytorch 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.

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