mindspore_gl.graph.add_self_loop

mindspore_gl.graph.add_self_loop(edge_index, edge_weight, node, fill_value, mode='dense')[source]

ADD the self loop from the input coo matrix. you can choose to operate on a dense matrix or a matrix in COO format.

Parameters

  • edge_index (Tensor) – Edge index. The shape is \((2, N\_e)\) where \(N\_e\) is the number of edges.

  • edge_weight (Tensor) – Edge weights. The shape is \((N\_e)\) where \(N\_e\) is the number of edges.

  • node (int) – Number of nodes.

  • fill_value (Tensor) – self-loop value.

  • mode (str, optional) – type of operation matrix. Support type is ‘dense’ and ‘coo’. Default: ‘dense’.

Returns

if mode is ‘dense’,

  • new_adj (Tensor) - dense matrix.

if mode is ‘coo’,

  • edge_index (Tensor) - new edge_index.

  • edge_weight (Tensor) - new edge_weight

Raises

  • ValueError – if mode not is ‘coo’ or ‘dense’.

  • ValueError – if fill_value length not equal to node.

  • TypeError – If node is not a positive int.

Supported Platforms:

Ascend GPU

Examples

>>> from mindspore import Tensor
>>> from mindspore_gl.graph import add_self_loop
>>> edge_index = [[1, 1, 2, 2], [0, 2, 0, 1]]
>>> edge_index = ms.Tensor(edge_index, ms.int32)
>>> edge_weight = Tensor([1, 1, 1, 1], ms.float32)
>>> node = 3
>>> fill_value = Tensor([2, 2, 2], ms.float32)
>>> new_adj = add_self_loop(edge_index, edge_weight, node, fill_value, mode='dense')
>>> print(new_adj)
[[2. 0. 0.]
 [1. 2. 1.]
 [1. 1. 2.]]
>>> edge_index, edge_weight = add_self_loop(edge_index, edge_weight, node, fill_value, mode='coo')
>>> print(edge_index)
[[1 1 2 2 0 1 2]
 [0 2 0 1 0 1 2]]
>>> print(edge_weight)
[1. 1. 1. 1. 2. 2. 2.]