torch_geometric.nn.conv.LEConv
- class LEConv(in_channels: Union[int, Tuple[int, int]], out_channels: int, bias: bool = True, **kwargs)[source]
Bases:
MessagePassing来自“ASAP: 自适应结构感知池化用于学习层次图表示”论文的局部极值图神经网络算子。
LEConv使用差分算子找到节点相对于其邻居的重要性：\[\mathbf{x}^{\prime}_i = \mathbf{x}_i \cdot \mathbf{\Theta}_1 + \sum_{j \in \mathcal{N}(i)} e_{j,i} \cdot (\mathbf{\Theta}_2 \mathbf{x}_i - \mathbf{\Theta}_3 \mathbf{x}_j)\]其中 \(e_{j,i}\) 表示从源节点
j到目标节点i的边权重（默认值：1）- Parameters:
in_channels (int or tuple) – Size of each input sample, or
-1to 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.
**kwargs (optional) – Additional arguments of
torch_geometric.nn.conv.MessagePassing.
- Shapes:
输入: 节点特征 \((|\mathcal{V}|, F_{in})\) 或 \(((|\mathcal{V_s}|, F_{s}), (|\mathcal{V_t}|, F_{t}))\) 如果是二分图, 边索引 \((2, |\mathcal{E}|)\), 边特征 \((|\mathcal{E}|, D)\) (可选)
output: node features \((|\mathcal{V}|, F_{out})\) or \((|\mathcal{V}_t|, F_{out})\) if bipartite