DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting

1 code implementation • CIKM ’19, November 3–7, 2019, Beijing, China 2019 • Siteng Huang Donglin Wang∗

The difficulty of the task lies in that traditional methods fail to capture complicated nonlinear dependencies between time steps and between multiple time series.

Multivariate Time Series Forecasting Time Series