.png){kind=icon}
返回
AsynFormer: Transformer Capturing Asynchronous Cross-Variate Dependencies for Efficient Multivariate Time Series Forecasting
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2026.115557.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
• 提出一种双分支架构用于跨变量和序列内建模。
• 引入代理标记模块以高效捕捉跨变量交互。
• 采用分块式分支建模精细化的时序动态。
• 在预测任务中达到最先进性能并具有出色的效率。
Keyword:
Dual-branch architecture
Proxy-token module
Patch-wise branch
Multivariate time series forecasting
Asynchronous cross-variate dependencies
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Blood Glucose Level Time Series Forecasting: Nested Deep Ensemble Learning Lag Fusion血糖水平时间序列预测: 嵌套深度集成学习滞后融合.png)
BIOENGINEERING-BASEL
OAAI
BIOENGINEERING-BASELIF3.7
OAAI分享收藏LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series ForecastersLLM4TS：将预训练的大语言模型对齐为数据高效的时间序列预测器
OAAI
OAAI分享收藏A parallel and multi-scale probabilistic temporal convolutional neural networks for forecasting the key monitoring parameters of gas turbine一种用于预测燃气轮机关键监测参数的并行和多尺度概率时序卷积神经网络
PREAI
分享收藏Future energy insights: Time-series and deep learning models for city load forecastingAPPLIED ENERGYOAAI
APPLIED ENERGYIF11
OAAI分享收藏MA-EMD: Aligned empirical decomposition for multivariate time-series forecastingMA-EMD：用于多变量时间序列预测的对齐经验分解
PREAI
分享收藏MRLCD-A: Lag-aware alignment for multivariate time series forecasting in multiple scenariosMRLCD-A：多场景下考虑时滞的多变量时间序列预测对齐
PREAI
分享收藏
查看更多内容