mindspore_gl.nn.MeanConv

View Source On Gitee
class mindspore_gl.nn.MeanConv(in_feat_size: int, out_feat_size: int, feat_drop=0.4, bias=False, norm=None, activation=None)[source]

GraphSAGE Layer. From the paper Inductive Representation Learning on Large Graphs .

\[ \begin{align}\begin{aligned}\begin{split}h_{\mathcal{N}(i)}^{(l+1)} = \mathrm{aggregate} \left(\{h_{j}^{l}, \forall j \in \mathcal{N}(i) \}\right) \\\end{split}\\\begin{split}h_{i}^{(l+1)} = \sigma \left(W \cdot \mathrm{concat} (h_{i}^{l}, h_{\mathcal{N}(i)}^{l+1}) \right)\\\end{split}\\h_{i}^{(l+1)} = \mathrm{norm}(h_{i}^{l})\end{aligned}\end{align} \]

If weights are provided on each edge, the weighted graph convolution is defined as:

\[h_{\mathcal{N}(i)}^{(l+1)} = \mathrm{aggregate} \left(\{e_{ji} h_{j}^{l}, \forall j \in \mathcal{N}(i) \}\right)\]
Parameters

  • in_feat_size (int) – Input node feature size.

  • out_feat_size (int) – Output node feature size.

  • feat_drop (float, optional) – The dropout rate, greater equal than 0 and less than 1. E.g. dropout=0.1, dropping out 10% of input units. Default: 0.4.

  • bias (bool, optional) – Whether to use bias. Default: False.

  • norm (Cell, optional) – Normalization function Cell. Default: None.

  • activation (Cell, optional) – Activation function Cell. Default: None.

Inputs:

  • x (Tensor) - The input node features. The shape is \((N,D\_in)\) where \(N\) is the number of nodes and \(D\_in\) could be of any shape.

  • self_idx (Tensor) - The node idx. The shape is \((N\_v,)\) where \(N\_v\) is the number of self nodes.

  • g (Graph) - The input graph.

Outputs:

  • Tensor, the output feature of shape \((N\_v,D\_out)\). where \(N\_v\) is the number of self nodes and \(D\_out\) could be of any shape

Raises

  • TypeError – If in_feat_size or out_feat_size is not an int.

  • TypeError – If bias is not a bool.

  • TypeError – If norm is not a mindspore.nn.Cell.

  • ValueError – If dropout is not in range (0.0, 1.0]

  • ValueError – If activation is not tanh or relu.

Supported Platforms:

Ascend GPU

Examples

>>> import mindspore as ms
>>> from mindspore_gl.nn import MeanConv
>>> from mindspore_gl import GraphField
>>> n_nodes = 4
>>> n_edges = 7
>>> feat_size = 4
>>> src_idx = ms.Tensor([0, 1, 1, 2, 2, 3, 3], ms.int32)
>>> dst_idx = ms.Tensor([0, 0, 2, 1, 3, 0, 1], ms.int32)
>>> ones = ms.ops.Ones()
>>> feat = ones((n_nodes, feat_size), ms.float32)
>>> graph_field = GraphField(src_idx, dst_idx, n_nodes, n_edges)
>>> gmmconv = MeanConv(in_feat_size=4, out_feat_size=2, activation='relu')
>>> self_idx = ms.Tensor([0, 1], ms.int32)
>>> res = gmmconv(feat, self_idx, *graph_field.get_graph())
>>> print(res.shape)
(2, 2)