Machine learningTime-series forecasting
Autoformer：用于长期时间序列预测的分解Transformer
Autoformer是由清华大学的Wu等人于2021年在NeurIPS上提出的一个用于长期时间序列预测的深度学习架构。它用自动相关机制取代了标准的自注意力机制，该机制利用了频域中的周期性依赖关系，并在编码器和解码器中嵌入了渐进式序列分解模块，以分别建模趋势和季节性分量。
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., Xu, J., Wang, J., & Long, M. (2021). Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. NeurIPS, 34. link ↗
如何引用本页
ScholarGate. (2026, June 2). Autoformer (Auto-Correlation Decomposition Transformer). ScholarGate. https://scholargate.app/zh/deep-learning/autoformer
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
- FEDformer：频率增强分解Transformer深度学习↔ compare
- Informer深度学习↔ compare
- TimesNet：面向时间序列的二维时变建模深度学习↔ compare