Machine learningTime-series forecasting
Pyraformer：用于长程时间序列预测的金字塔注意力Transformer
Pyraformer是由Liu等人于2022年在ICLR上提出的一种基于Transformer的长程时间序列预测模型。其核心创新是金字塔注意力模块（Pyramidal Attention Module, PAM），该模块将序列点组织成多分辨率的层级结构，使模型能够在保持O(L log L)的时间和内存复杂度（而非标准自注意力机制的二次方复杂度）的同时，捕捉多尺度的时间依赖关系。
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
- Liu, S., Yu, H., Liao, C., Li, J., Lin, W., Liu, A. X., & Dustdar, S. (2022). Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. ICLR. link ↗
如何引用本页
ScholarGate. (2026, June 2). Pyraformer (Pyramidal Attention for Long-Range Forecasting). ScholarGate. https://scholargate.app/zh/deep-learning/pyraformer
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.
- Autoformer：用于长期时间序列预测的分解Transformer深度学习↔ compare
- Informer深度学习↔ compare
- Reformer：长序列的高效Transformer深度学习↔ compare