GCN-GRU icon indicating copy to clipboard operation
GCN-GRU copied to clipboard

Published 20 hours ago • verified publisher icon zxj32

n graphs，how to train

Open maybewh opened this issue 5 years ago • 1 comments

If I have n graphs which every node has a label， how I can get spatial feature and train in time series？

maybewh avatar Nov 21 '19 14:11 maybewh

So you don't have the physical feature for each node, right? Then we can use the identity matrix as the spatial feature for input (line 49 in "GCN_GRU_run.py")

zxj32 avatar Nov 21 '19 15:11 zxj32