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
Hi, I noticed that the coefficient of the K-th order term is initialized in a way that is different from others. In one of my experiments, the learned coefficient of the K-th order term thus is much larger than others (alpha=0.1). Could you tell me why this is needed? Thanks!
This follows the original PPR formulation when truncated at step K. This makes the coefficient sum equal to 1. Note that in APPNA they also use this rule. More specifically:
Hi, I noticed that the coefficient of the K-th order term is initialized in a way that is different from others. In one of my experiments, the learned coefficient of the K-th order term thus is much larger than others (alpha=0.1). Could you tell me why this is needed? Thanks!
GPRGNN/src/GNN_models.py
Line 36 in dc24683
The text was updated successfully, but these errors were encountered: