mlsanityData to 7 Oct 2026

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

arXiv 2308.11200 ↗First posted 22 Aug 2023cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 22 Aug 2023.

Builds on

35 of 61 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  8. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  9. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  10. 2021ViViT: A Video Vision Transformercited by 1,610
  11. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  12. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
23 more
  1. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  2. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  3. 2021Transformers in Vision: A Surveycited by 1,009
  4. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  5. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  6. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  7. 2022Transformers in Time Series: A Surveycited by 489
  8. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  9. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  10. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 327
  11. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  12. 2015A Critical Review of Recurrent Neural Networks for Sequence Learningcited by 223
  13. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  14. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 149
  15. 2023TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecastingcited by 136
  16. 2023The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecastingcited by 100
  17. 2021Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSxcited by 63
  18. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 52
  19. 2022DEPTS: Deep Expansion Learning for Periodic Time Series Forecastingcited by 28
  20. 2023PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformercited by 22
  21. 2019Towards Better Forecasting by Fusing Near and Distant Future Visionscited by 14
  22. 2023SageFormer: Series-Aware Framework for Long-term Multivariate Time Series Forecastingcited by 10
  23. 2023Neural Differential Recurrent Neural Network with Adaptive Time Stepscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 17; 2025: 23; 2026: 11.

53 papers.

Sort:

By area:

  1. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  2. 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusioncited by 75
  3. 2024Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysiscited by 65
  4. 2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
  5. 2024Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspectivecited by 17
  6. 2024MambaTS: Improved Selective State Space Models for Long-term Time Series Forecastingcited by 13
  7. 2025TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systemscited by 13
  8. 2024Continual Learning for Smart City: A Surveycited by 9
  9. 2025CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlationscited by 8
  10. 2024Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecastingcited by 6
  11. 2024DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecastingcited by 6
  12. 2024Are KANs Effective for Multivariate Time Series Forecasting?cited by 6
38 more
  1. 2026From Observations to States: Latent Time Series Forecastingcited by 6
  2. 2025ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecastingcited by 5
  3. 2024PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecastingcited by 4
  4. 2026Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learningcited by 4
  5. 2024Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarkingcited by 3
  6. 2024Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecastingcited by 3
  7. 2025FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecastingcited by 3
  8. 2023Sparsity-Aware Distributed Learning for Gaussian Processes with Linear Multiple Kernelcited by 2
  9. 2024Partial-Multivariate Model for Forecastingcited by 2
  10. 2024Approximation Bounds for Recurrent Neural Networks with Application to Regressioncited by 2
  11. 2025ModelRadar: Aspect-based Forecast Evaluationcited by 2
  12. 2025Foundation Models Knowledge Distillation For Battery Capacity Degradation Forecastcited by 2
  13. 2025Continuous Evolution Pool: Taming Recurring Concept Drift in Online Time Series Forecastingcited by 2
  14. 2025PAX-TS: Model-agnostic multi-granular explanations for time series forecasting via localized perturbationscited by 2
  15. 2026Enhancing Multivariate Time Series Forecasting with Global Temporal Retrievalcited by 2
  16. 2025HADL Framework for Noise Resilient Long-Term Time Series Forecastingcited by 1
  17. 2025Time Series Domain Adaptation via Latent Invariant Causal Mechanismcited by 1
  18. 2025MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecastingcited by 1
  19. 2025Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecastingcited by 1
  20. 2025ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecastingcited by 1
  21. 2025How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcastingcited by 1
  22. 2025Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistencycited by 1
  23. 2025UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecastingcited by 1
  24. 2025TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecastingcited by 1
  25. 2024ISMRNN: An Implicitly Segmented RNN Method with Mamba for Long-Term Time Series Forecastingcited by 0
  26. 2024Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Predictioncited by 0
  27. 2024PIAD-SRNN: Physics-Informed Adaptive Decomposition in State-Space RNNcited by 0
  28. 2025Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusioncited by 0
  29. 2025IRNN: Innovation-driven Recurrent Neural Network for Time-Series Data Modeling and Predictioncited by 0
  30. 2025Post-Training Corrections for Improved Time-Series Forecastingcited by 0
  31. 2025TSGym: Design Choices for Deep Multivariate Time-Series Forecastingcited by 0
  32. 2025Echo Flow Networkscited by 0
  33. 2025DB2-TransF: All You Need Is Learnable Daubechies Wavelets for Time Series Forecastingcited by 0
  34. 2026DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysiscited by 0
  35. 2026Federated Weather Modeling on Sensor Datacited by 0
  36. 2026Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamicscited by 0
  37. 2026PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecastingcited by 0
  38. 2026TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecastingcited by 0

50 most cited of 53 All 53 (JSON)