dgl.NodeFlow.block_incidence_matrix¶
-
NodeFlow.
block_incidence_matrix
(block_id, typestr, ctx)[source]¶ Return the incidence matrix representation of the block.
An incidence matrix is an n x m sparse matrix, where n is the number of nodes and m is the number of edges. Each nnz value indicating whether the edge is incident to the node or not.
There are two types of an incidence matrix I:
in
:I[v, e] = 1 if e is the in-edge of v (or v is the dst node of e);
I[v, e] = 0 otherwise.
out
:I[v, e] = 1 if e is the out-edge of v (or v is the src node of e);
I[v, e] = 0 otherwise.
“both” isn’t defined in the block of a NodeFlow.
- Parameters
- Returns
SparseTensor – The incidence matrix.
Tensor – A index for data shuffling due to sparse format change. Return None if shuffle is not required.