torch_geometric.nn.norm.GraphNorm

class GraphNorm(in_channels: int, eps: float = 1e-05)

Bases: Module

对单个图应用图归一化，如“GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training”论文中所述。

\[\mathbf{x}^{\prime}_i = \frac{\mathbf{x} - \alpha \odot \textrm{E}[\mathbf{x}]} {\sqrt{\textrm{Var}[\mathbf{x} - \alpha \odot \textrm{E}[\mathbf{x}]] + \epsilon}} \odot \gamma + \beta\]

其中 \(\alpha\) 表示学习在平均值中保留多少信息的参数。

Parameters:

• in_channels (int) – Size of each input sample.

• eps (float, optional) – A value added to the denominator for numerical stability. (default: 1e-5)

reset_parameters()

重置模块的所有可学习参数。

forward(x: Tensor, batch: Optional[Tensor] = None, batch_size: Optional[int] = None) → Tensor

前向传播。

Parameters:

• x (torch.Tensor) – The source tensor.

• batch (torch.Tensor, optional) – The batch vector \(\mathbf{b} \in {\{ 0, \ldots, B-1\}}^N\), which assigns each element to a specific example. (default: None)

• batch_size (int, optional) – The number of examples \(B\). Automatically calculated if not given. (default: None)

Return type:

Tensor