torch_geometric.nn.conv.HypergraphConv
- class HypergraphConv(in_channels: int, out_channels: int, use_attention: bool = False, attention_mode: str = 'node', heads: int = 1, concat: bool = True, negative_slope: float = 0.2, dropout: float = 0, bias: bool = True, **kwargs)[source]
Bases:
MessagePassing来自“超图卷积和超图注意力”论文的超图卷积算子。
\[\mathbf{X}^{\prime} = \mathbf{D}^{-1} \mathbf{H} \mathbf{W} \mathbf{B}^{-1} \mathbf{H}^{\top} \mathbf{X} \mathbf{\Theta}\]其中 \(\mathbf{H} \in {\{ 0, 1 \}}^{N \times M}\) 是关联矩阵，\(\mathbf{W} \in \mathbb{R}^M\) 是对角超边权重矩阵，而 \(\mathbf{D}\) 和 \(\mathbf{B}\) 是对应的度矩阵。
例如，在超图场景中 \(\mathcal{G} = (\mathcal{V}, \mathcal{E})\) 其中 \(\mathcal{V} = \{ 0, 1, 2, 3 \}\) 和 \(\mathcal{E} = \{ \{ 0, 1, 2 \}, \{ 1, 2, 3 \} \}\)，
hyperedge_index表示为：hyperedge_index = torch.tensor([ [0, 1, 2, 1, 2, 3], [0, 0, 0, 1, 1, 1], ])
- Parameters:
in_channels (int) – Size of each input sample, or
-1to derive the size from the first input(s) to the forward method.out_channels (int) – Size of each output sample.
use_attention (bool, 可选) – 如果设置为
True，将会在这一层添加注意力机制。（默认值：False）attention_mode (str, optional) – 计算注意力的模式。 如果设置为
"node"，将计算属于同一超边的所有节点之间的注意力分数。 如果设置为"edge"，将计算包含该节点的所有边之间的注意力分数。 (默认:"node")heads (int, optional) – Number of multi-head-attentions. (default:
1)concat (bool, optional) – If set to
False, the multi-head attentions are averaged instead of concatenated. (default:True)negative_slope (float, optional) – LeakyReLU angle of the negative slope. (default:
0.2)dropout (float, optional) – Dropout probability of the normalized attention coefficients which exposes each node to a stochastically sampled neighborhood during training. (default:
0)bias (bool, optional) – If set to
False, the layer will not learn an additive bias. (default:True)**kwargs (optional) – Additional arguments of
torch_geometric.nn.conv.MessagePassing.
- Shapes:
输入: 节点特征 \((|\mathcal{V}|, F_{in})\), 超边索引 \((|\mathcal{V}|, |\mathcal{E}|)\), 超边权重 \((|\mathcal{E}|)\) (可选) 超边特征 \((|\mathcal{E}|, D)\) (可选)
output: node features \((|\mathcal{V}|, F_{out})\)
- forward(x: Tensor, hyperedge_index: Tensor, hyperedge_weight: Optional[Tensor] = None, hyperedge_attr: Optional[Tensor] = None, num_edges: Optional[int] = None) Tensor[source]
运行模块的前向传播。
- Parameters:
x (torch.Tensor) – Node feature matrix \(\mathbf{X} \in \mathbb{R}^{N \times F}\).
hyperedge_index (torch.Tensor) – 超边索引，即 稀疏关联矩阵 \(\mathbf{H} \in {\{ 0, 1 \}}^{N \times M}\) 从 节点映射到边。
hyperedge_weight (torch.Tensor, optional) – 超边权重 \(\mathbf{W} \in \mathbb{R}^M\). (默认:
None)hyperedge_attr (torch.Tensor, optional) – 超边特征矩阵 在 \(\mathbb{R}^{M \times F}\) 中。 这些特征仅在
use_attention=True时需要传入。（默认值：None）
- Return type: