ScholarGate
助手
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。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

Crossformer:用于多元时间序列预测的跨维度依赖Transformer
InformeriTransformer:用于多元时间序列预测的…PatchTST

来源

  1. 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

被引用于

ScholarGateCrossformer (Crossformer (Cross-Dimension Dependency Transformer)). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/crossformer · 数据集: https://doi.org/10.5281/zenodo.20539026