torch_geometric.nn.conv.SAGEConv

class SAGEConv(in_channels: Union[int, Tuple[int, int]], out_channels: int, aggr: Optional[Union[str, List[str], Aggregation]] = 'mean', normalize: bool = False, root_weight: bool = True, project: bool = False, bias: bool = True, **kwargs)[source]

\[\mathbf{x}^{\prime}_i = \mathbf{W}_1 \mathbf{x}_i + \mathbf{W}_2 \cdot \mathrm{mean}_{j \in \mathcal{N(i)}} \mathbf{x}_j\]

如果 project = True，那么 \(\mathbf{x}_j\) 将首先通过以下方式投影

\[\mathbf{x}_j \leftarrow \sigma ( \mathbf{W}_3 \mathbf{x}_j + \mathbf{b})\]

如论文中的公式(3)所述。

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.
aggr (str 或 Aggregation, 可选) – 使用的聚合方案。可以使用 torch_geometric.nn.aggr 中的任何聚合方式，例如, "mean", "max", 或 "lstm"。 (默认: "mean")
normalize (bool, 可选) – 如果设置为 True，输出特征将会被 \(\ell_2\)-归一化，即， \(\frac{\mathbf{x}^{\prime}_i} {\| \mathbf{x}^{\prime}_i \|_2}\)。 (默认: False)
root_weight (bool, optional) – If set to False, the layer will not add transformed root node features to the output. (default: True)
项目 (bool, 可选) – 如果设置为 True，该层将在聚合之前应用线性变换和激活函数（如论文中的公式 (3) 所述）。 (默认: 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:

inputs: node features \((|\mathcal{V}|, F_{in})\) or \(((|\mathcal{V_s}|, F_{s}), (|\mathcal{V_t}|, F_{t}))\) if bipartite, edge indices \((2, |\mathcal{E}|)\)
outputs: 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], size: Optional[Tuple[int, int]] = None) → Tensor[source]

运行模块的前向传播。