Contents:
GraphConv.
forward
Forward propagation
input (Tensor) – Input data (\(n_{vertices} \times n_{features}\))
Tensor
eidx (Tensor) – Vertex indices of edges (\(2 \times n_{edges}\))
enorm (Tensor) – Normalized weight of edges (\(n_{edges}\))
esgn (Tensor) – Sign of edges (\(n_{edges}\))
result – Graph convolution result (\(n_{vertices} \times n_{features}\))