Implementation of E(n)-Transformer, which incorporates attention mechanisms into Welling's E(n)-Equivariant Graph Neural Network
208
stars
28
forks
source link
generalizing to greater inter-coordinate distances #6
Closed
lucidrains closed 2 years ago
use the NERF-like technique from https://arxiv.org/abs/2111.09883
attn_bias = mlp(log(dist + 1))