Table 1 The overall test MAE of the VAR and DCRNN model, in dependence of different forecasting horizons.

From: A graph neural network framework for causal inference in brain networks

Model

Forcasting horizon (TRs)

5

10

15

20

25

30

VAR

0.0321

0.0589

0.0751

0.1099

0.1449

0.1786

DCRNN

0.0018

0.0028

0.0065

0.0115

0.0163

0.0279

Back to article page