Machine learningTime-series forecasting
Crossformer:用于多元时间序列预测的跨维度依赖Transformer
Crossformer是由张云浩和阎峻驰在ICLR 2023上提出的一种基于Transformer的多元时间序列预测架构。与早期独立处理每个变量的Transformer变体不同,Crossformer在建模时间模式的同时,显式地建模了跨维度依赖。它通过两阶段的注意力设计——跨时间注意力和跨维度注意力——来实现这一点,这些注意力作用于分层编码器中组织好的分段级嵌入,使模型能够同时捕捉单变量内部动态和多变量之间相关性。
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
- Zhang, Y., & Yan, J. (2023). Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. ICLR. link ↗
如何引用本页
ScholarGate. (2026, June 2). Crossformer (Cross-Dimension Dependency Transformer). ScholarGate. https://scholargate.app/zh/deep-learning/crossformer
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 →