Machine learning
PatchTST
PatchTST 是一种基于块（patch）的 Transformer 架构，用于时间序列预测。它由 Nie 及其同事于 2023 年提出，该方法将每个时间序列分割成重叠的块，并将这些块视为 token 进行处理，同时独立地处理各个通道（变量）。它在长视界预测方面实现了计算效率和高精度的平衡。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
+4 more
来源
- Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR. link ↗
- Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L. & Jin, R. (2022). FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting. ICML. link ↗
如何引用本页
ScholarGate. (2026, June 1). Patch Time Series Transformer. ScholarGate. https://scholargate.app/zh/deep-learning/patchtst
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- ARIMA（自回归积分滑动平均）模型计量经济学↔ compare
- Conformal Prediction for Time-Series Forecasting计量经济学↔ compare
- 随机森林机器学习↔ compare