mindspore_gl.nn.GCNConv2

class mindspore_gl.nn.GCNConv2(in_feat_size: int, out_size: int)[source]

Graph Convolution Network Layer. from the paper Semi-Supervised Classification with Graph Convolutional Networks .

\[h_i^{(l+1)} = (\sum_{j\in\mathcal{N}(i)}h_j^{(l)}W_1^{(l)}+b^{(l)} )+h_i^{(l)}W_2^{(l)}\]

\(\mathcal{N}(i)\) represents the neighbour node of \(i\). \(W_1\) and \(W_2\) correspond to fc layers for neighbor nodes and root node.

Parameters

  • in_feat_size (int) – Input node feature size.

  • out_size (int) – Output node feature size.

Inputs:

  • x (Tensor) - The input node features. The shape is \((N, D_{in})\) where \(N\) is the number of nodes, and \(D_{in}\) should be equal to in_feat_size in Args.

  • g (Graph) - The input graph.

Outputs:

  • Tensor, output node features with shape of \((N, D_{out})\), where \((D_{out})\) should be the same as out_size in Args.

Raises

TypeError – If in_feat_size or out_size is not an int.

Supported Platforms:

Ascend GPU

Examples

>>> import mindspore as ms
>>> from mindspore_gl.nn import GCNConv2
>>> 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)
>>> gcnconv2 = GCNConv2(in_feat_size=4, out_size=2)
>>> res = gcnconv2(feat, *graph_field.get_graph())
>>> print(res.shape)
(4, 2)