torch_geometric.nn.conv.AntiSymmetricConv
- class AntiSymmetricConv(in_channels: int, phi: Optional[MessagePassing] = None, num_iters: int = 1, epsilon: float = 0.1, gamma: float = 0.1, act: Optional[Union[str, Callable]] = 'tanh', act_kwargs: Optional[Dict[str, Any]] = None, bias: bool = True)[source]
Bases:
Module来自“Anti-Symmetric DGN: a stable architecture for Deep Graph Networks”论文的反对称图卷积算子。
\[\mathbf{x}^{\prime}_i = \mathbf{x}_i + \epsilon \cdot \sigma \left( (\mathbf{W}-\mathbf{W}^T-\gamma \mathbf{I}) \mathbf{x}_i + \Phi(\mathbf{X}, \mathcal{N}_i) + \mathbf{b}\right),\]其中 \(\Phi(\mathbf{X}, \mathcal{N}_i)\) 表示一个
MessagePassing层。- Parameters:
in_channels (int) – Size of each input sample.
phi (MessagePassing, optional) – 消息传递模块 \(\Phi\)。如果设置为
None，将使用GCNConv层作为默认值。 (默认值:None)num_iters (int, optional) – 反称深度图网络运算符被调用的次数。（默认值：
1）epsilon (float, optional) – 离散化步长 \(\epsilon\). (默认:
0.1)gamma (float, optional) – 扩散强度 \(\gamma\)。 它调节方法的稳定性。（默认值：
0.1）act (str, 可选) – 非线性激活函数 \(\sigma\), 例如,
"tanh"或"relu". (默认:"tanh")act_kwargs (Dict[str, Any], optional) – Arguments passed to the respective activation function defined by
act. (default:None)bias (bool, optional) – If set to
False, the layer will not learn an additive bias. (default:True)
- Shapes:
输入: 节点特征 \((|\mathcal{V}|, F_{in})\), 边索引 \((2, |\mathcal{E}|)\), 边权重 \((|\mathcal{E}|)\) (可选)
output: node features \((|\mathcal{V}|, F_{in})\)