Contents:
GraphAttent.
forward
Forward propagation
input (Tensor) – Input data (\(n_{vertices} \times n_{features}\))
Tensor
eidx (Tensor) – Vertex indices of edges (\(2 \times n_{edges}\))
ewt (Tensor) – Weight of edges (\(n_{edges}\))
esgn (Tensor) – Sign of edges (\(n_{edges}\))
result – Graph attention result (\(n_{vertices} \times n_{features}\))