gammagl.layers.conv.GINConv

class GINConv(nn, eps=0.0, train_eps: bool = False, **kwargs)

The graph isomorphism operator from the “How Powerful are Graph Neural Networks?” paper

\[\mathbf{x}^{\prime}_i = h_{\mathbf{\Theta}} \left( (1 + \epsilon) \cdot \mathbf{x}_i + \sum_{j \in \mathcal{N}(i)} \mathbf{x}_j \right)\]

or

\[\mathbf{X}^{\prime} = h_{\mathbf{\Theta}} \left( \left( \mathbf{A} + (1 + \epsilon) \cdot \mathbf{I} \right) \cdot \mathbf{X} \right),\]

here \(h_{\mathbf{\Theta}}\) denotes a neural network, .i.e. an MLP.

Parameters:

• nn (tlx.nn.Module) – A neural network \(h_{\mathbf{\Theta}}\) that maps node features x of shape [-1, in_channels] to shape [-1, out_channels], e.g., defined by torch.nn.Sequential.

• eps (float, optional) – (Initial) \(\epsilon\)-value. (default: 0.)

• train_eps (bool, optional) – If set to True, \(\epsilon\) will be a trainable parameter. (default: False)

• **kwargs (optional) – Additional arguments of gammagl.layers.conv.MessagePassing.

forward(x, edge_index, size=None)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

message(x, edge_index)

Function that construct message from source nodes to destination nodes.

Parameters:

• x (tensor) – input node feature.

• edge_index (tensor) – edges from src to dst.

• edge_weight (tensor, optional) – weight of each edge.

Returns:

• tensor – output message

• Returns – the message matrix, and the shape is [num_edges, message_dim]