torch_geometric.nn.conv.PANConv

class PANConv(in_channels: int, out_channels: int, filter_size: int, **kwargs)

Bases: MessagePassing

基于路径积分的卷积算子来自 “Path Integral Based Convolution and Pooling for Graph Neural Networks” 论文。

\[\mathbf{X}^{\prime} = \mathbf{M} \mathbf{X} \mathbf{W}\]

其中 \(\mathbf{M}\) 表示归一化并学习的最大熵转移（MET）矩阵，该矩阵包括最多 filter_size 跳的邻居：

\[\mathbf{M} = \mathbf{Z}^{-1/2} \sum_{n=0}^L e^{-\frac{E(n)}{T}} \mathbf{A}^n \mathbf{Z}^{-1/2}\]

Parameters:

• in_channels (int) – Size of each input sample, or -1 to derive the size from the first input(s) to the forward method.

• out_channels (int) – Size of each output sample.

• filter_size (int) – 过滤器大小 \(L\)。

• **kwargs (optional) – Additional arguments of torch_geometric.nn.conv.MessagePassing.

Shapes:

• 输入: 节点特征 \((|\mathcal{V}|, F_{in})\), 边索引 \((2, |\mathcal{E}|)\),

• output: node features \((|\mathcal{V}|, F_{out})\)

forward(x: Tensor, edge_index: Union[Tensor, SparseTensor]) → Tuple[Tensor, SparseTensor]

运行模块的前向传播。

Return type:

Tuple[Tensor, SparseTensor]

reset_parameters()

重置模块的所有可学习参数。