torch_geometric.nn.conv.AGNNConv

class AGNNConv(requires_grad: bool = True, add_self_loops: bool = True, **kwargs)

Bases: MessagePassing

The graph attentional propagation layer from the “Attention-based Graph Neural Network for Semi-Supervised Learning” paper.

\[\mathbf{X}^{\prime} = \mathbf{P} \mathbf{X},\]

where the propagation matrix \(\mathbf{P}\) is computed as

\[P_{i,j} = \frac{\exp( \beta \cdot \cos(\mathbf{x}_i, \mathbf{x}_j))} {\sum_{k \in \mathcal{N}(i)\cup \{ i \}} \exp( \beta \cdot \cos(\mathbf{x}_i, \mathbf{x}_k))}\]

with trainable parameter \(\beta\).

Parameters:

• requires_grad (bool, optional) – If set to False, \(\beta\) will not be trainable. (default: True)

• add_self_loops (bool, optional) – If set to False, will not add self-loops to the input graph. (default: True)

• **kwargs (optional) – Additional arguments of torch_geometric.nn.conv.MessagePassing.

Shapes:

• input: node features \((|\mathcal{V}|, F)\), edge indices \((2, |\mathcal{E}|)\)

• output: node features \((|\mathcal{V}|, F)\)

forward(x: Tensor, edge_index: Union[Tensor, SparseTensor]) → Tensor

Runs the forward pass of the module.

reset_parameters()

Resets all learnable parameters of the module.