GCNConv

class dhg.nn.GCNConv(*args, **kwargs)

Bases: torch.nn.Module

The GCN convolution layer proposed in Semi-Supervised Classification with Graph Convolutional Networks paper (ICLR 2017).

Matrix Format:

\[\mathbf{X}^{\prime} = \sigma \left( \mathbf{\hat{D}}^{-\frac{1}{2}} \mathbf{\hat{A}} \mathbf{\hat{D}}^{-\frac{1}{2}} \mathbf{X} \mathbf{\Theta} \right),\]

where \(\mathbf{\hat{A}} = \mathbf{A} + \mathbf{I}\) and \(\mathbf{\hat{D}}_{ii} = \sum_j \mathbf{\hat{A}}_{ij}\).

Parameters

• in_channels (int) – \(C_{in}\) is the number of input channels.

• out_channels (int) – \(C_{out}\) is the number of output channels.

• bias (bool) – If set to False, the layer will not learn the bias parameter. Defaults to True.

• use_bn (bool) – If set to True, the layer will use batch normalization. Defaults to False.

• drop_rate (float) – The dropout probability. If dropout <= 0, the layer will not drop values. Defaults to 0.5.

• is_last (bool) – If set to True, the layer will not apply the final activation and dropout functions. Defaults to False.

forward(X, g)

The forward function.

Parameters

• X (torch.Tensor) – Input vertex feature matrix. Size \((N, C_{in})\).

• g (dhg.Graph) – The graph structure that contains \(N\) vertices.