dgl.ops.e_dot_uΒΆ

dgl.ops.e_dot_u(g, x, y)ΒΆ

Generalized SDDMM function. It computes edge features by dot edge features and source node features.

Parameters
  • g (DGLGraph) – The input graph

  • x (tensor) – The edge features.

  • y (tensor) – The source node features.

Returns

The result tensor.

Return type

tensor

Notes

This function supports autograd (computing input gradients given the output gradient). If the feature shape of two input operands do not match, we first broadcasts the features to a unified shape (note that the memory usage will not increase accordingly) and then performs the operation.

Broadcasting follows NumPy semantics. Please see https://docs.scipy.org/doc/numpy/user/basics.broadcasting.html for more details about the NumPy broadcasting semantics.