torch_geometric.nn.models.LINKX
- class LINKX(num_nodes: int, in_channels: int, hidden_channels: int, out_channels: int, num_layers: int, num_edge_layers: int = 1, num_node_layers: int = 1, dropout: float = 0.0)[source]
Bases:
Module来自“大规模非同质图学习：新基准和强大的简单方法”论文的LINKX模型。
\[ \begin{align}\begin{aligned}\mathbf{H}_{\mathbf{A}} &= \textrm{MLP}_{\mathbf{A}}(\mathbf{A})\\\mathbf{H}_{\mathbf{X}} &= \textrm{MLP}_{\mathbf{X}}(\mathbf{X})\\\mathbf{Y} &= \textrm{MLP}_{f} \left( \sigma \left( \mathbf{W} [\mathbf{H}_{\mathbf{A}}, \mathbf{H}_{\mathbf{X}}] + \mathbf{H}_{\mathbf{A}} + \mathbf{H}_{\mathbf{X}} \right) \right)\end{aligned}\end{align} \]注意
有关使用LINKX的示例，请参见examples/linkx.py。
- Parameters:
num_nodes (int) – The number of nodes in the graph.
in_channels (int) – Size of each input sample, or
-1to derive the size from the first input(s) to the forward method.hidden_channels (int) – Size of each hidden sample.
out_channels (int) – Size of each output sample.
num_layers (int) – \(\textrm{MLP}_{f}\) 的层数。
num_edge_layers (int, optional) – \(\textrm{MLP}_{\mathbf{A}}\) 的层数。 (默认:
1)num_node_layers (int, optional) – 层数 \(\textrm{MLP}_{\mathbf{X}}\). (默认:
1)dropout (float, optional) – 每个隐藏嵌入的丢弃概率。（默认值：
0.0）