mlsanityData to 7 Oct 2026

SWIFT: Mapping Sub-series with Wavelet Decomposition Improves Time Series Forecasting

arXiv 2501.16178 ↗First posted 27 Jan 2025cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

In recent work on time-series prediction, Transformers and even large language models have garnered significant attention due to their strong capabilities in sequence modeling. However, in practical deployments, time-series prediction often requires operation in resource-constrained environments, such as edge devices, which are unable to handle the computational overhead of large models. To address such scenarios, some lightweight models have been proposed, but they exhibit poor performance on non-stationary sequences. In this paper, we propose textitSWIFT, a lightweight model that is not only powerful, but also efficient in deployment and inference for Long-term Time Series Forecasting (LTSF). Our model is based on three key points: (i) Utilizing wavelet transform to perform lossless downsampling of time series. (ii) Achieving cross-band information fusion with a learnable filter. (iii) Using only one shared linear layer or one shallow MLP for sub-series' mapping. We conduct comprehensive experiments, and the results show that textitSWIFT achieves state-of-the-art (SOTA) performance on multiple datasets, offering a promising method for edge computing and deployment in this task. Moreover, it is noteworthy that the number of parameters in textitSWIFT-Linear is only 25% of what it would be with a single-layer linear model for time-domain prediction. Our code is available at https://github.com/LancelotXWX/SWIFT.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 27 Jan 2025.

Builds on

22 of 38 references.

References · 22

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  3. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  4. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  5. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  7. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  8. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  9. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 744
  10. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  11. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  12. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
10 more
  1. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 385
  2. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 327
  3. 2021Multiwavelet-based Operator Learning for Differential Equationscited by 229
  4. 2023FITS: Modeling Time Series with 10k Parameterscited by 185
  5. 2023Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictorscited by 110
  6. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 102
  7. 2024WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecastingcited by 25
  8. 2022Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detectioncited by 16
  9. 2022W-Transformers : A Wavelet-based Transformer Framework for Univariate Time Series Forecastingcited by 12
  10. 2024Wave-Mask/Mix: Exploring Wavelet-Based Augmentations for Time Series Forecastingcited by 4

Built on by

Not cited yet.