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 was wondering if it would make sense to allow models.DeepGraphInfomax to have a rectangular weight matrix. For example, if my summary function uses concatenation (JumpingKnowledge style) and produces a summary vector with more dimensions than my node embeddings. My understanding from the paper is that this should be possible as long the function remains injective, but I might be wrong.
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
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
I was wondering if it would make sense to allow models.DeepGraphInfomax to have a rectangular weight matrix. For example, if my summary function uses concatenation (JumpingKnowledge style) and produces a summary vector with more dimensions than my node embeddings. My understanding from the paper is that this should be possible as long the function remains injective, but I might be wrong.
Beta Was this translation helpful? Give feedback.
All reactions