mlsanityData to 7 Oct 2026

FreDo: Frequency Domain-based Long-Term Time Series Forecasting

arXiv 2205.12301 ↗First posted 24 May 2022cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

The ability to forecast far into the future is highly beneficial to many applications, including but not limited to climatology, energy consumption, and logistics. However, due to noise or measurement error, it is questionable how far into the future one can reasonably predict. In this paper, we first mathematically show that due to error accumulation, sophisticated models might not outperform baseline models for long-term forecasting. To demonstrate, we show that a non-parametric baseline model based on periodicity can actually achieve comparable performance to a state-of-the-art Transformer-based model on various datasets. We further propose FreDo, a frequency domain-based neural network model that is built on top of the baseline model to enhance its performance and which greatly outperforms the state-of-the-art model. Finally, we validate that the frequency domain is indeed better by comparing univariate models trained in the frequency v.s. time domain.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 15 of its 45 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

15 of 45 references.

References · 15

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  3. 2020Reformer: The Efficient Transformercited by 1,658
  4. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  5. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  6. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  8. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  9. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  10. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  11. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 525
  12. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
3 more
  1. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  2. 2021Adjusting for Autocorrelated Errors in Neural Networks for Time Seriescited by 18
  3. 2013Integrated Pre-Processing for Bayesian Nonlinear System Identification with Gaussian Processescited by 8

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 1.

6 papers.

  1. 2023A Survey on Deep Learning based Time Series Analysis with Frequency Transformationcited by 40
  2. 2022First De-Trend then Attend: Rethinking Attention for Time-Series Forecastingcited by 19
  3. 2023Deep Learning based Forecasting: a case study from the online fashion industrycited by 12
  4. 2023TFDNet: Time-Frequency Enhanced Decomposed Network for Long-term Time Series Forecastingcited by 7
  5. 2023A Joint Time-frequency Domain Transformer for Multivariate Time Series Forecastingcited by 5
  6. 2024FSMLP: Modelling Channel Dependencies With Simplex Theory Based Multi-Layer Perceptions In Frequency Domaincited by 0