Sparse Matrix Multiplication

Is there an equivalent of pytorch’s torch.spmm method? Which is essentially multiplication of two sparse matrices?

I see that there is an elementwise multiplication operation for sparse matrices

Hi @codewithsk,

You can use mxnet.ndarray.sparse.dot for this.

dot‘s behavior depends on the input array dimensions:

  • 1-D arrays: inner product of vectors
  • 2-D arrays: matrix multiplication
  • N-D arrays: a sum product over the last axis of the first input and the first axis of the second input

dot's output storage type depends on the inputs storage type, transpose option and forward_stype option for output storage type.