torch_geometric.nn.conv.WLConvContinuous
- class WLConvContinuous(**kwargs)[source]
Bases:
MessagePassing来自“Wasserstein Weisfeiler-Lehman Graph Kernels”论文的Weisfeiler Lehman算子。
细化是通过度缩放的平均聚合完成的,并适用于具有连续属性的节点:
\[\mathbf{x}^{\prime}_i = \frac{1}{2}\big(\mathbf{x}_i + \frac{1}{\textrm{deg}(i)} \sum_{j \in \mathcal{N}(i)} e_{j,i} \cdot \mathbf{x}_j \big)\]where \(e_{j,i}\) denotes the edge weight from source node
jto target nodei(default:1)- Parameters:
**kwargs (optional) – Additional arguments of
torch_geometric.nn.conv.MessagePassing.
- Shapes:
输入: 节点特征 \((|\mathcal{V}|, F)\) 或 \(((|\mathcal{V_s}|, F), (|\mathcal{V_t}|, F))\) 如果是二分图, 边索引 \((2, |\mathcal{E}|)\), 边权重 \((|\mathcal{E}|)\) (可选)
输出: 节点特征 \((|\mathcal{V}|, F)\) 或 \((|\mathcal{V}_t|, F)\) 如果是二分图