scglue.models.nn.GraphConv.forward

GraphConv.forward(input, eidx, enorm, esgn)[source]

Forward propagation

Parameters:

  • input (torch.Tensor) – Input data (\(n_{vertices} \times n_{features}\))

  • eidx (torch.Tensor) – Vertex indices of edges (\(2 \times n_{edges}\))

  • enorm (torch.Tensor) – Normalized weight of edges (\(n_{edges}\))

  • esgn (torch.Tensor) – Sign of edges (\(n_{edges}\))

Return type:

torch.Tensor

Returns:

result – Graph convolution result (\(n_{vertices} \times n_{features}\))