torch_geometric.nn.conv.GeneralConv

class GeneralConv(in_channels: Union[int, Tuple[int, int]], out_channels: Optional[int], in_edge_channels: Optional[int] = None, aggr: str = 'add', skip_linear: str = False, directed_msg: bool = True, heads: int = 1, attention: bool = False, attention_type: str = 'additive', l2_normalize: bool = False, bias: bool = True, **kwargs)[source]

Bases: MessagePassing

A general GNN layer adapted from the “Design Space for Graph Neural Networks” paper.

Parameters:

  • in_channels (int or tuple) – Size of each input sample, or -1 to derive the size from the first input(s) to the forward method. A tuple corresponds to the sizes of source and target dimensionalities.

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

  • in_edge_channels (int, optional) – Size of each input edge. (default: None)

  • aggr (str, optional) – The aggregation scheme to use ("add", "mean", "max"). (default: "mean")

  • skip_linear (bool, optional) – Whether apply linear function in skip connection. (default: False)

  • directed_msg (bool, optional) – If message passing is directed; otherwise, message passing is bi-directed. (default: True)

  • heads (int, optional) – Number of message passing ensembles. If heads > 1, the GNN layer will output an ensemble of multiple messages. If attention is used (attention=True), this corresponds to multi-head attention. (default: 1)

  • attention (bool, optional) – Whether to add attention to message computation. (default: False)

  • attention_type (str, optional) – Type of attention: "additive", "dot_product". (default: "additive")

  • l2_normalize (bool, optional) – If set to True, output features will be \(\ell_2\)-normalized, i.e., \(\frac{\mathbf{x}^{\prime}_i} {\| \mathbf{x}^{\prime}_i \|_2}\). (default: False)

  • 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 \(((|\mathcal{V_s}|, F_{s}), (|\mathcal{V_t}|, F_{t}))\) if bipartite, edge indices \((2, |\mathcal{E}|)\), edge attributes \((|\mathcal{E}|, D)\) (optional)

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

forward(x: Union[Tensor, Tuple[Tensor, Optional[Tensor]]], edge_index: Union[Tensor, SparseTensor], edge_attr: Optional[Tensor] = None, size: Optional[Tuple[int, int]] = None) → Tensor[source]

Runs the forward pass of the module.

reset_parameters()[source]

Resets all learnable parameters of the module.