torch_geometric.nn.conv.GINConv
- class GINConv(nn: Callable, eps: float = 0.0, train_eps: bool = False, **kwargs)[source]
Bases:
MessagePassing来自“图神经网络有多强大？”论文的图同构算子。
\[\mathbf{x}^{\prime}_i = h_{\mathbf{\Theta}} \left( (1 + \epsilon) \cdot \mathbf{x}_i + \sum_{j \in \mathcal{N}(i)} \mathbf{x}_j \right)\]或
\[\mathbf{X}^{\prime} = h_{\mathbf{\Theta}} \left( \left( \mathbf{A} + (1 + \epsilon) \cdot \mathbf{I} \right) \cdot \mathbf{X} \right),\]这里 \(h_{\mathbf{\Theta}}\) 表示一个神经网络，即 一个多层感知器（MLP）。
- Parameters:
nn (torch.nn.Module) – A neural network \(h_{\mathbf{\Theta}}\) that maps node features
xof shape[-1, in_channels]to shape[-1, out_channels], e.g., defined bytorch.nn.Sequential.eps (float, optional) – (Initial) \(\epsilon\)-value. (default:
0.)train_eps (bool, optional) – If set to
True, \(\epsilon\) will be a trainable parameter. (default:False)**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 \((2, |\mathcal{E}|)\)
output: node features \((|\mathcal{V}|, F_{out})\) or \((|\mathcal{V}_t|, F_{out})\) if bipartite