D-PAD: Deep-Shallow Multi-Frequency Patterns Disentangling for Time Series Forecasting
Not on the map. Why?
Abstract (arXiv)
In time series forecasting, effectively disentangling intricate temporal patterns is crucial. While recent works endeavor to combine decomposition techniques with deep learning, multiple frequencies may still be mixed in the decomposed components, e.g., trend and seasonal. Furthermore, frequency domain analysis methods, e.g., Fourier and wavelet transforms, have limitations in resolution in the time domain and adaptability. In this paper, we propose D-PAD, a deep-shallow multi-frequency patterns disentangling neural network for time series forecasting. Specifically, a multi-component decomposing (MCD) block is introduced to decompose the series into components with different frequency ranges, corresponding to the "shallow" aspect. A decomposition-reconstruction-decomposition (D-R-D) module is proposed to progressively extract the information of frequencies mixed in the components, corresponding to the "deep" aspect. After that, an interaction and fusion (IF) module is used to further analyze the components. Extensive experiments on seven real-world datasets demonstrate that D-PAD achieves the state-of-the-art performance, outperforming the best baseline by an average of 9.48% and 7.15% in MSE and MAE, respectively.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 21 of its 46 references that are in the map. First posted on arXiv 26 Mar 2024.
Builds on
21 of 46 references.
References · 21
- 2017Attention Is All You Needcited by 60,361
- 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
- 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
- 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
- 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
- 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
- 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
- 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
- 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 607
9 more
- 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
- 2022N-HiTS: Neural Hierarchical Interpolation for Time Series Forecastingcited by 146
- 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
- 2016Multi-Scale Convolutional Neural Networks for Time Series Classificationcited by 99
- 2022Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecastingcited by 42
- 2022DEPTS: Deep Expansion Learning for Periodic Time Series Forecastingcited by 29
- 2021Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecastingcited by 4
- 2023MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Predictioncited by 2
- 2021DexDeepFM: Ensemble Diversity Enhanced Extreme Deep Factorization Machine Modelcited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.