mlsanityData to 7 Oct 2026

Unlocking the Power of LSTM for Long Term Time Series Forecasting

arXiv 2408.10006 ↗First posted 19 Aug 2024cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 18 of its 38 references that are in the map. First posted on arXiv 19 Aug 2024.

Builds on

18 of 38 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  5. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  8. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
  9. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  10. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  11. 2022Transformers in Time Series: A Surveycited by 489
  12. 2019Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directionscited by 172
6 more
  1. 2016Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNscited by 62
  2. 2020Do RNN and LSTM have Long Memory?cited by 47
  3. 2024CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variablescited by 25
  4. 2023ST-MLP: A Cascaded Spatio-Temporal Linear Framework with Channel-Independence Strategy for Traffic Forecastingcited by 21
  5. 2018Learning with Interpretable Structure from Gated RNNcited by 13
  6. 2024Hedge Fund Portfolio Construction Using PolyModel Theory and iTransformercited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 12.

29 papers.

Sort:

By area:

  1. 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignmentcited by 22
  2. 2024xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memoriescited by 18
  3. 2026AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discoverycited by 17
  4. 2025Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernelscited by 12
  5. 2025AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Datasetcited by 9
  6. 2025BenchECG and xECG: a benchmark and baseline for ECG foundation modelscited by 8
  7. 2025TimeRecipe: A Time-Series Forecasting Recipe via Benchmarking Module Level Effectivenesscited by 6
  8. 2026TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoningcited by 5
  9. 2024HiPPO-KAN: Efficient KAN Model for Time Series Analysiscited by 3
  10. 2025Semantic-Enhanced Time-Series Forecasting via Large Language Modelscited by 2
  11. 2026Deep Time-series Forecasting Needs Kernelized Moment Balancingcited by 2
  12. 2025Predictive AI with External Knowledge Infusion: Datasets and Benchmarks for Stock Marketscited by 1
17 more
  1. 2025How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcastingcited by 1
  2. 2025TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecastingcited by 1
  3. 2025Directly Learning Stock Trading Strategies Through Profit Guided Loss Functionscited by 0
  4. 2025Hierarchical Stochastic Differential Equation Models for Latent Manifold Learning in Neural Time Seriescited by 0
  5. 2025Filter then Attend: Improving attention-based Time Series Forecasting with Spectral Filteringcited by 0
  6. 2025StoxLSTM: A Stochastic Extended Long Short-Term Memory Network for Time Series Forecastingcited by 0
  7. 2025An overview of neural architectures for self-supervised audio representation learning from masked spectrogramscited by 0
  8. 2025AI-Based Stroke Rehabilitation Domiciliary Assessment System with ST_GCN Attentioncited by 0
  9. 2026Rethinking Recurrent Neural Networks for Time Series Forecasting: A Reinforced Recurrent Encoder with Prediction-Oriented Proximal Policy Optimizationcited by 0
  10. 2026We Need a More Robust Classifier: Dual Causal Learning Empowers Domain-Incremental Time Series Classificationcited by 0
  11. 2026Deep Learning for Financial Time Series: A Large-Scale Benchmark of Risk-Adjusted Performancecited by 0
  12. 2026Role-Aware Conditional Inference for Spatiotemporal Ecosystem Carbon Flux Predictioncited by 0
  13. 2026Deep Time-Series Forecasting in 10 Years: A Surveycited by 0
  14. 2026PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecastingcited by 0
  15. 2026CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Predictioncited by 0
  16. 2026Evaluating Forecasting Techniques for Hardware Errors on a Large-scale HPC Systemcited by 0
  17. 2026Mix&Fix-Net: A Dual-Stage Trajectory Prediction Model for AIS and Vision-Derived Vessel Datacited by 0