chennnM / GCNII

PyTorch implementation of "Simple and Deep Graph Convolutional Networks"
325 stars 72 forks source link

Question above OGB implementation #9

Closed CongWeilin closed 3 years ago

CongWeilin commented 3 years ago

Hey,

I found the OBG implementation only has ``initial connection'' but without identity mapping.

Furthermore, in the paper, you propose to use an APPNP like propagation method, i.e.,

(1-alpha)LH^{(\ell-1)} + \alpha X,

but in the implementation you are using

LH^{(\ell-1)} + alpha X.

Do I miss something? Or there is a specific reason you do this?