Machine learningTime-series forecasting
FreTS：用于时间序列预测的频域MLP
FreTS是由Yi等人于NeurIPS 2023上提出的一种时间序列预测架构。它通过将简单的多层感知器（MLP）完全应用于频域，从而摆脱了基于Transformer的设计。该模型使用离散傅里叶变换转换输入序列，然后通过复值MLP层学习时间和通道依赖性，以显著降低的计算成本实现具有竞争力或更优的长期预测精度。
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
- Yi, K., Zhang, Q., Fan, W., Wang, S., Wang, P., He, H., An, N., Lian, D., Cao, L., & Niu, Z. (2023). Frequency-domain MLPs are more effective learners in time series forecasting. NeurIPS. link ↗
如何引用本页
ScholarGate. (2026, June 2). FreTS (Frequency-domain MLPs for Forecasting). ScholarGate. https://scholargate.app/zh/deep-learning/frets
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.
- FEDformer：频率增强分解Transformer深度学习↔ compare
- FiLM: 频率改进的勒让德记忆模型深度学习↔ compare
- TSMixer：全MLP架构用于时间序列预测深度学习↔ compare