mlsanityData to 7 Oct 2026

FreDF: Learning to Forecast in the Frequency Domain

arXiv 2402.02399 ↗First posted 4 Feb 2024cs.LG cs.AI stat.APcited by 77

Not on the map. Why?

Abstract (arXiv)

Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences. While current research predominantly addresses autocorrelation within historical data, the correlations among future labels are often overlooked. Specifically, modern forecasting models primarily adhere to the Direct Forecast (DF) paradigm, generating multi-step forecasts independently and disregarding label autocorrelation over time. In this work, we demonstrate that the learning objective of DF is biased in the presence of label autocorrelation. To address this issue, we propose the Frequency-enhanced Direct Forecast (FreDF), which mitigates label autocorrelation by learning to forecast in the frequency domain, thereby reducing estimation bias. Our experiments show that FreDF significantly outperforms existing state-of-the-art methods and is compatible with a variety of forecast models. Code is available at https://github.com/Master-PLC/FreDF.

Key facts. Cited by 77 papers in the map (data through 7 Oct 2026). Builds on 25 of its 48 references that are in the map. First posted on arXiv 4 Feb 2024.

Builds on

25 of 48 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  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. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  7. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  8. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  9. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  10. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  11. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  12. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
13 more
  1. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 335
  2. 2023Long-term Forecasting with TiDE: Time-series Dense Encodercited by 327
  3. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  4. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 170
  5. 2023FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspectivecited by 126
  6. 2018Connecting the Dots: Identifying Network Structure via Graph Signal Processingcited by 111
  7. 2019Shape and Time Distortion Loss for Training Deep Time Series Forecasting Modelscited by 66
  8. 2022Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecastingcited by 54
  9. 2020From Fourier to Koopman: Spectral Methods for Long-term Time Series Predictioncited by 50
  10. 2023Optimal Transport for Treatment Effect Estimationcited by 32
  11. 2022Entire Space Counterfactual Learning for Reliable Content Recommendationscited by 13
  12. 2020Double machine learning for sample selection modelscited by 8
  13. 2022Towards Better Long-range Time Series Forecasting using Generative Forecastingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 35; 2026: 37.

77 papers.

Sort:

By area:

  1. 2024CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patchingcited by 91
  2. 2025TAB: Unified Benchmarking of Time Series Anomaly Detection Methodscited by 58
  3. 2025DBLoss: Decomposition-based Loss Function for Time Series Forecastingcited by 44
  4. 2025Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspectivecited by 34
  5. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  6. 2025OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domaincited by 25
  7. 2025Time-o1: Time-Series Forecasting Needs Transformed Label Alignmentcited by 22
  8. 2025Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecastingcited by 19
  9. 2025FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecastingcited by 18
  10. 2025PPGF: Probability Pattern-Guided Time Series Forecastingcited by 16
  11. 2025Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecastingcited by 13
  12. 2025DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignmentcited by 13
38 more
  1. 2025TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decodingcited by 12
  2. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  3. 2026GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variablescited by 11
  4. 2025FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detectioncited by 10
  5. 2025Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Modelscited by 10
  6. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  7. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 7
  8. 2024Modeling Temporal Dependencies within the Target for Long-Term Time Series Forecastingcited by 6
  9. 2026From Observations to States: Latent Time Series Forecastingcited by 6
  10. 2025DeepFilter: A Transformer-style Framework for Accurate and Efficient Process Monitoringcited by 5
  11. 2024FTMixer: Frequency and Time Domain Representations Fusion for Time Series Modelingcited by 4
  12. 2025Multi-Order Wavelet Derivative Transform for Deep Time Series Forecastingcited by 4
  13. 2026Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecastingcited by 4
  14. 2024Disentangled Parameter-Efficient Linear Model for Long-Term Time Series Forecastingcited by 3
  15. 2025KANMixer: a minimal KAN-centered mixer for long-term time series forecastingcited by 3
  16. 2025TimeSense:Making Large Language Models Proficient in Time-Series Analysiscited by 3
  17. 2025FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decompositioncited by 3
  18. 2025LoFT-LLM: Low-Frequency Time-Series Forecasting with Large Language Modelscited by 3
  19. 2026TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuningcited by 3
  20. 2026Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecastingcited by 3
  21. 2025Time Series Forecasting via Direct Per-Step Probability Distribution Modelingcited by 2
  22. 2026PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecastingcited by 2
  23. 2026Deep Time-series Forecasting Needs Kernelized Moment Balancingcited by 2
  24. 2026TEFL: Prediction-Residual-Guided Rolling Forecasting for Multi-Horizon Time Seriescited by 2
  25. 2025KARMA: A Multilevel Decomposition Hybrid Mamba Framework for Multivariate Long-Term Time Series Forecastingcited by 1
  26. 2026To See Far, Look Close: Evolutionary Forecasting for Long-term Time Seriescited by 1
  27. 2026ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologiescited by 1
  28. 2026TIFO: Time-Invariant Frequency Operator for Stationarity-Aware Representation Learning in Time Seriescited by 1
  29. 2026PAMNet: Cycle-aware Phase-Amplitude Modulation Network for Multivariate Time Series Forecastingcited by 1
  30. 2026PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecastingcited by 1
  31. 2026Multivariate Time Series Forecasting needs Cross Variable Losscited by 1
  32. 2024FSMLP: Modelling Channel Dependencies With Simplex Theory Based Multi-Layer Perceptions In Frequency Domaincited by 0
  33. 2025BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecastingcited by 0
  34. 2025Ellipsoidal Time Series Forecastingcited by 0
  35. 2025Multivariate Long-term Time Series Forecasting with Fourier Neural Filtercited by 0
  36. 2025KFS: KAN based adaptive Frequency Selection learning architecture for long term time series forecastingcited by 0
  37. 2025Dynamic Relational Priming Improves Transformer in Multivariate Time Seriescited by 0
  38. 2025Transformer Modeling for Both Scalability and Performance in Multivariate Time Seriescited by 0

50 most cited of 77 All 77 (JSON)