dgl.sparse.spspmm¶

dgl.sparse.spspmm(A: Union[dgl.sparse.sparse_matrix.SparseMatrix, dgl.sparse.diag_matrix.DiagMatrix], B: Union[dgl.sparse.sparse_matrix.SparseMatrix, dgl.sparse.diag_matrix.DiagMatrix]) → Union[dgl.sparse.sparse_matrix.SparseMatrix, dgl.sparse.diag_matrix.DiagMatrix][source]¶

Multiplies a sparse matrix by a sparse matrix, equivalent to A @ B.

The non-zero values of the two sparse matrices must be 1D.

Parameters

A (SparseMatrix or DiagMatrix) – Sparse matrix of shape (L, M)
B (SparseMatrix or DiagMatrix) – Sparse matrix of shape (M, N)

Returns

Matrix of shape (L, N). It is a DiagMatrix object if both matrices are DiagMatrix objects, otherwise a SparseMatrix object.

Return type

SparseMatrix or DiagMatrix

Examples

>>> indices1 = torch.tensor([[0, 1, 1], [1, 0, 1]])
>>> val1 = torch.ones(len(row1))
>>> A = dglsp.spmatrix(indices1, val1)
>>> indices2 = torch.tensor([[0, 1, 1], [0, 2, 1]])
>>> val2 = torch.ones(len(row2))
>>> B = dglsp.spmatrix(indices2, val2)
>>> dglsp.spspmm(A, B)
SparseMatrix(indices=tensor([[0, 0, 1, 1, 1],
                             [1, 2, 0, 1, 2]]),
             values=tensor([1., 1., 1., 1., 1.]),
             shape=(2, 3), nnz=5)