torch_geometric.nn.conv.FeaStConv

class FeaStConv(in_channels: int, out_channels: int, heads: int = 1, add_self_loops: bool = True, bias: bool = True, **kwargs)[source]

Bases: MessagePassing

The (translation-invariant) feature-steered convolutional operator from the “FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis” paper.

\[\mathbf{x}^{\prime}_i = \frac{1}{|\mathcal{N}(i)|} \sum_{j \in \mathcal{N}(i)} \sum_{h=1}^H q_h(\mathbf{x}_i, \mathbf{x}_j) \mathbf{W}_h \mathbf{x}_j\]

with \(q_h(\mathbf{x}_i, \mathbf{x}_j) = \mathrm{softmax}_j (\mathbf{u}_h^{\top} (\mathbf{x}_j - \mathbf{x}_i) + c_h)\), where \(H\) denotes the number of attention heads, and \(\mathbf{W}_h\), \(\mathbf{u}_h\) and \(c_h\) are trainable parameters.

Parameters:

• in_channels (int) – Size of each input sample, or -1 to derive the size from the first input(s) to the forward method.

• out_channels (int) – Size of each output sample.

• heads (int, optional) – Number of attention heads \(H\). (default: 1)

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

• bias (bool, optional) – If set to False, the layer will not learn an additive bias. (default: True)

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

Shapes:

• input: node features \((|\mathcal{V}|, F_{in})\) or \(((|\mathcal{V_s}|, F_{in}), (|\mathcal{V_t}|, F_{in}))\) if bipartite, edge indices \((2, |\mathcal{E}|)\)

• output: node features \((|\mathcal{V}|, F_{out})\) or \((|\mathcal{V_t}|, F_{out})\) if bipartite

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

Runs the forward pass of the module.

Return type:

Tensor

reset_parameters()[source]

Resets all learnable parameters of the module.