Machine learningTime-series forecasting
TimesNet：面向时间序列的二维时变建模
TimesNet是由Wu等人于ICLR 2023提出的一种通用时间序列模型。其核心思想是通过快速傅里叶变换（FFT）检测到的主导周期性来重塑一维信号，将一元或多元时间序列重新解释为二维时间图的集合。这种一维到二维的转换暴露了周期内模式（一个周期内）和周期间趋势（跨周期），使得强大的二维卷积架构能够对时间变化进行建模。
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.
来源
- Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M. (2023). TimesNet: Temporal 2D-variation modeling for general time series analysis. ICLR. link ↗
如何引用本页
ScholarGate. (2026, June 2). TimesNet (Temporal 2D-Variation Modeling). ScholarGate. https://scholargate.app/zh/deep-learning/timesnet
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.
Compare side by side →