Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

U-Mixer: An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting (2401.02236v1)

Published 4 Jan 2024 in cs.LG

Abstract: Time series forecasting is a crucial task in various domains. Caused by factors such as trends, seasonality, or irregular fluctuations, time series often exhibits non-stationary. It obstructs stable feature propagation through deep layers, disrupts feature distributions, and complicates learning data distribution changes. As a result, many existing models struggle to capture the underlying patterns, leading to degraded forecasting performance. In this study, we tackle the challenge of non-stationarity in time series forecasting with our proposed framework called U-Mixer. By combining Unet and Mixer, U-Mixer effectively captures local temporal dependencies between different patches and channels separately to avoid the influence of distribution variations among channels, and merge low- and high-levels features to obtain comprehensive data representations. The key contribution is a novel stationarity correction method, explicitly restoring data distribution by constraining the difference in stationarity between the data before and after model processing to restore the non-stationarity information, while ensuring the temporal dependencies are preserved. Through extensive experiments on various real-world time series datasets, U-Mixer demonstrates its effectiveness and robustness, and achieves 14.5\% and 7.7\% improvements over state-of-the-art (SOTA) methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271.
  2. NHITS: Neural Hierarchical Interpolation for Time Series Forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, 6989–6997.
  3. Cohen, L. 1998. The generalization of the Wiener-Khinchin theorem. In Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP’98 (Cat. No. 98CH36181), volume 3, 1577–1580. IEEE.
  4. Fukushima, K. 1980. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics, 36(4): 193–202.
  5. Efficiently Modeling Long Sequences with Structured State Spaces. In The International Conference on Learning Representations (ICLR).
  6. CATN: Cross attentive tree-aware network for multivariate time series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 4030–4038.
  7. Long short-term memory. Neural computation, 9(8): 1735–1780.
  8. Reversible instance normalization for accurate time-series forecasting against distribution shift. In International Conference on Learning Representations.
  9. Reformer: The Efficient Transformer. In International Conference on Learning Representations.
  10. Modeling long-and short-term temporal patterns with deep neural networks. In The 41st international ACM SIGIR conference on research & development in information retrieval, 95–104.
  11. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. Advances in neural information processing systems, 32.
  12. Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In International conference on learning representations.
  13. A stock price prediction method based on meta-learning and variational mode decomposition. Knowledge-Based Systems, 252: 109324.
  14. Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting.
  15. Fuzzy hypergraph network for recommending top-K profitable stocks. Information Sciences, 613: 239–255.
  16. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. In International Conference on Learning Representations.
  17. N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. In International Conference on Learning Representations.
  18. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems, 34: 24261–24272.
  19. Attention is all you need. Advances in neural information processing systems, 30.
  20. Etsformer: Exponential smoothing transformers for time-series forecasting. arXiv preprint arXiv:2202.01381.
  21. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In International Conference on Learning Representations.
  22. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems, 34: 22419–22430.
  23. Are transformers effective for time series forecasting? In Proceedings of the AAAI conference on artificial intelligence, volume 37, 11121–11128.
  24. DFNet: Decomposition fusion model for long sequence time-series forecasting. Knowledge-Based Systems, 277: 110794.
  25. Less is more: Fast multivariate time series forecasting with light sampling-oriented mlp structures. arXiv preprint arXiv:2207.01186.
  26. MPR-Net:Multi-Scale Pattern Reproduction Guided Universality Time Series Interpretable Forecasting. arXiv:2307.06736.
  27. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI conference on artificial intelligence, volume 35, 11106–11115.
  28. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International Conference on Machine Learning, 27268–27286. PMLR.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Xiang Ma (95 papers)
  2. Xuemei Li (18 papers)
  3. Lexin Fang (3 papers)
  4. Tianlong Zhao (4 papers)
  5. Caiming Zhang (14 papers)
Citations (4)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets