GATConv

class dhg.nn.GATConv(*args, **kwargs)[source]

Bases: torch.nn.Module

The GAT convolution layer proposed in Graph Attention Networks paper (ICLR 2018).

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.
atten_neg_slope (float) – Hyper-parameter of the LeakyReLU activation of edge attention. Defaults to 0.2.
is_last (bool) – If set to True, the layer will not apply the final activation and dropout functions. Defaults to False.

forward(X, g)[source]

The forward function.

Parameters