dgl.ops.u_sub_v(g, x, y)

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

  • g (DGLHeteroGraph) – The input graph

  • x (tensor) – The source node features.

  • y (tensor) – The destination node features.


The result tensor.

Return type



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.