mlsanityData to 7 Oct 2026

SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters

arXiv 2405.00946 ↗First posted 2 May 2024cs.LGcited by 103

Not on the map. Why?

Abstract (arXiv)

This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by decoupling the periodicity and trend in time series data. This technique involves downsampling the original sequences to focus on cross-period trend prediction, effectively extracting periodic features while minimizing the model's complexity and parameter count. Based on this technique, the SparseTSF model uses fewer than *1k* parameters to achieve competitive or superior performance compared to state-of-the-art models. Furthermore, SparseTSF showcases remarkable generalization capabilities, making it well-suited for scenarios with limited computational resources, small samples, or low-quality data. The code is publicly available at this repository: https://github.com/lss-1138/SparseTSF.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

24 of 37 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  7. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  8. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  9. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  10. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  11. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  12. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
12 more
  1. 2022Transformers in Time Series: A Surveycited by 489
  2. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  3. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 327
  4. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 242
  5. 2023FITS: Modeling Time Series with 10k Parameterscited by 185
  6. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  7. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 158
  8. 2022FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecastingcited by 147
  9. 2023LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasterscited by 127
  10. 2023The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecastingcited by 100
  11. 2023PETformer: Long-term Time Series Forecasting via Placeholder-enhanced Transformercited by 22
  12. 2023OneShotSTL: One-Shot Seasonal-Trend Decomposition For Online Time Series Anomaly Detection And Forecastingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 18; 2025: 52; 2026: 33.

103 papers.

Sort:

By area:

  1. 2024Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Expertscited by 280
  2. 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 104
  3. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  4. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 91
  5. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 87
  6. 2025Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baselinecited by 54
  7. 2025DBLoss: Decomposition-based Loss Function for Time Series Forecastingcited by 44
  8. 2024TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecastingcited by 38
  9. 2025Patch-wise Structural Loss for Time Series Forecastingcited by 34
  10. 2025Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspectivecited by 34
  11. 2025Temporal Query Network for Efficient Multivariate Time Series Forecastingcited by 29
  12. 2025LightGTS: A Lightweight General Time Series Forecasting Modelcited by 28
38 more
  1. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  2. 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecastingcited by 27
  3. 2025Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecastingcited by 23
  4. 2025CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variablescited by 21
  5. 2025Improving Time Series Forecasting via Instance-aware Post-hoc Revisioncited by 14
  6. 2025TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillationcited by 12
  7. 2025Vision-Enhanced Time Series Forecasting via Latent Diffusion Modelscited by 9
  8. 2025Empowering Time Series Forecasting with LLM-Agentscited by 9
  9. 2024MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K Parameterscited by 8
  10. 2025CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlationscited by 8
  11. 2025Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecastingcited by 8
  12. 2024On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecastingcited by 7
  13. 2025K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecastingcited by 7
  14. 2025From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?cited by 7
  15. 2025PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecastingcited by 7
  16. 2025Learning General Causal Structures with Hidden Dynamic Process for Climate Analysiscited by 6
  17. 2025TS-LIF: A Temporal Segment Spiking Neuron Network for Time Series Forecastingcited by 6
  18. 2025Predicting the Future by Retrieving the Pastcited by 6
  19. 2024Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecastingcited by 5
  20. 2025U-Cast: Learning Hierarchical Structures for High-Dimensional Time Series Forecastingcited by 5
  21. 2025Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecastingcited by 4
  22. 2025DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classificationcited by 4
  23. 2025Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detectioncited by 4
  24. 2024Toward Physics-guided Time Series Embeddingcited by 3
  25. 2024LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecastingcited by 3
  26. 2024Disentangled Parameter-Efficient Linear Model for Long-Term Time Series Forecastingcited by 3
  27. 2025Retrieval Augmented Time Series Forecastingcited by 3
  28. 2025Augur: Modeling Covariate Causal Associations in Time Series via Large Language Modelscited by 3
  29. 2025FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decompositioncited by 3
  30. 2024DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecastingcited by 2
  31. 2025TGT: A Temporal Gating Transformer for Smartphone App Usage Predictioncited by 2
  32. 2025PENGUIN: Enhancing Transformer with Periodic-Nested Group Attention for Long-term Time Series Forecastingcited by 2
  33. 2025Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecastingcited by 2
  34. 2025Task-Aware Mixture-of-Experts for Time Series Analysiscited by 2
  35. 2025SVTime: Small Time Series Forecasting Models Informed by "Physics" of Large Vision Model Forecasterscited by 2
  36. 2026PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecastingcited by 2
  37. 2026Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classificationcited by 2
  38. 2026Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gainscited by 2

50 most cited of 103 All 103 (JSON)