mlsanityData to 14 Oct 2026

Omni-Dimensional Frequency Learner for General Time Series Analysis

arXiv 2407.10419 ↗First posted 15 Jul 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Frequency domain representation of time series feature offers a concise representation for handling real-world time series data with inherent complexity and dynamic nature. However, current frequency-based methods with complex operations still fall short of state-of-the-art time domain methods for general time series analysis. In this work, we present Omni-Dimensional Frequency Learner (ODFL) model based on a in depth analysis among all the three aspects of the spectrum feature: channel redundancy property among the frequency dimension, the sparse and un-salient frequency energy distribution among the frequency dimension, and the semantic diversity among the variable dimension. Technically, our method is composed of a semantic-adaptive global filter with attention to the un-salient frequency bands and partial operation among the channel dimension. Empirical results show that ODFL achieves consistent state-of-the-art in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection, offering a promising foundation for time series analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 47 of its 77 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

47 of 77 references.

References · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2016Layer Normalizationcited by 5,669
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2022A ConvNet for the 2020scited by 3,579
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  9. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  10. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  11. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  12. 2020Rethinking Attention with Performerscited by 1,601
35 more
  1. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  2. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  3. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  7. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  8. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 700
  9. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  10. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
  11. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  12. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  13. 2019GhostNet: More Features from Cheap Operationscited by 410
  14. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  15. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 356
  16. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 345
  17. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 339
  18. 2018The UEA multivariate time series classification archive, 2018cited by 338
  19. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  20. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  21. 2021Monash Time Series Forecasting Archivecited by 267
  22. 2021Global Filter Networks for Image Classificationcited by 260
  23. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 250
  24. 2023Looped Transformers as Programmable Computerscited by 237
  25. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 172
  26. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
  27. 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
  28. 2017Conditional Time Series Forecasting with Convolutional Neural Networkscited by 123
  29. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  30. 2022Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusioncited by 96
  31. 2022What Makes Convolutional Models Great on Long Sequence Modeling?cited by 87
  32. 2022Learning strides in convolutional neural networkscited by 26
  33. 2022Dynamic Sparse Network for Time Series Classification: Learning What to "see''cited by 22
  34. 2022Revisiting Sparse Convolutional Model for Visual Recognitioncited by 14
  35. 2021GhostSR: Learning Ghost Features for Efficient Image Super-Resolutioncited by 8

Built on by

Not cited yet.