You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I want to know how to split dataset for training a VGAE model with multiple graphs. Continue the discussion at #5649 , why we should call RandomLinkSplit on each data object before training?
In my case, I have multiple graphs, each with the same number of nodes, but different node feature values (data.x). I wonder if I can randomly choose some graph for traning, while others for validation and test? I do this beacuse I want to perform a graph-level regression task based on the reconstructed graphs. Correct me if VGAE doesn't work in this case, thanks!!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
I want to know how to split dataset for training a VGAE model with multiple graphs. Continue the discussion at #5649 , why we should call
RandomLinkSpliton eachdataobject before training?In my case, I have multiple graphs, each with the same number of nodes, but different node feature values (
data.x). I wonder if I can randomly choose some graph for traning, while others for validation and test? I do this beacuse I want to perform a graph-level regression task based on the reconstructed graphs. Correct me if VGAE doesn't work in this case, thanks!!Beta Was this translation helpful? Give feedback.
All reactions