torch_geometric.nn.conv.TransformerConv
- class TransformerConv(in_channels: Union[int, Tuple[int, int]], out_channels: int, heads: int = 1, concat: bool = True, beta: bool = False, dropout: float = 0.0, edge_dim: Optional[int] = None, bias: bool = True, root_weight: bool = True, **kwargs)[source]
Bases:
MessagePassing来自“Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification”论文的图变换器操作符。
\[\mathbf{x}^{\prime}_i = \mathbf{W}_1 \mathbf{x}_i + \sum_{j \in \mathcal{N}(i)} \alpha_{i,j} \mathbf{W}_2 \mathbf{x}_{j},\]其中注意力系数 \(\alpha_{i,j}\) 是通过多头点积注意力计算的：
\[\alpha_{i,j} = \textrm{softmax} \left( \frac{(\mathbf{W}_3\mathbf{x}_i)^{\top} (\mathbf{W}_4\mathbf{x}_j)} {\sqrt{d}} \right)\]- Parameters:
in_channels (int or tuple) – Size of each input sample, or
-1to derive the size from the first input(s) to the forward method. A tuple corresponds to the sizes of source and target dimensionalities.out_channels (int) – Size of each output sample.
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)beta (bool, 可选) –
如果设置，将通过以下方式结合聚合和跳过信息
\[\mathbf{x}^{\prime}_i = \beta_i \mathbf{W}_1 \mathbf{x}_i + (1 - \beta_i) \underbrace{\left(\sum_{j \in \mathcal{N}(i)} \alpha_{i,j} \mathbf{W}_2 \vec{x}_j \right)}_{=\mathbf{m}_i}\]其中 \(\beta_i = \textrm{sigmoid}(\mathbf{w}_5^{\top} [ \mathbf{W}_1 \mathbf{x}_i, \mathbf{m}_i, \mathbf{W}_1 \mathbf{x}_i - \mathbf{m}_i ])\) (默认:
False)dropout (float, optional) – Dropout probability of the normalized attention coefficients which exposes each node to a stochastically sampled neighborhood during training. (default:
0)edge_dim (int, optional) –
边特征维度（如果有的话）。边特征在线性变换后添加到键中，即在计算注意力点积之前。它们也在相同的线性变换后添加到最终值中。模型为：
\[\mathbf{x}^{\prime}_i = \mathbf{W}_1 \mathbf{x}_i + \sum_{j \in \mathcal{N}(i)} \alpha_{i,j} \left( \mathbf{W}_2 \mathbf{x}_{j} + \mathbf{W}_6 \mathbf{e}_{ij} \right),\]其中注意力系数 \(\alpha_{i,j}\) 现在通过以下方式计算：
\[\alpha_{i,j} = \textrm{softmax} \left( \frac{(\mathbf{W}_3\mathbf{x}_i)^{\top} (\mathbf{W}_4\mathbf{x}_j + \mathbf{W}_6 \mathbf{e}_{ij})} {\sqrt{d}} \right)\]（默认
None）bias (bool, optional) – If set to
False, the layer will not learn an additive bias. (default:True)root_weight (bool, 可选) – 如果设置为
False，该层将不会将转换后的根节点特征添加到输出中，并且选项beta将被设置为False。（默认值：True）**kwargs (optional) – Additional arguments of
torch_geometric.nn.conv.MessagePassing.
- forward(x: Union[Tensor, Tuple[Tensor, Tensor]], edge_index: Union[Tensor, SparseTensor], edge_attr: Optional[Tensor] = None, return_attention_weights: Optional[Tensor] = None) Tensor[source]
- forward(x: Union[Tensor, Tuple[Tensor, Tensor]], edge_index: Tensor, edge_attr: Optional[Tensor] = None, return_attention_weights: bool = None) Tuple[Tensor, Tuple[Tensor, Tensor]]
- forward(x: Union[Tensor, Tuple[Tensor, Tensor]], edge_index: SparseTensor, edge_attr: Optional[Tensor] = None, return_attention_weights: bool = None) Tuple[Tensor, SparseTensor]
运行模块的前向传播。
- Parameters:
x (torch.Tensor 或 (torch.Tensor, torch.Tensor)) – 输入的节点特征。
edge_index (torch.Tensor or SparseTensor) – The edge indices.
edge_attr (torch.Tensor, optional) – The edge features. (default:
None)return_attention_weights (bool, optional) – If set to
True, will additionally return the tuple(edge_index, attention_weights), holding the computed attention weights for each edge. (default:None)
- Return type:
Union[Tensor,Tuple[Tensor,Tuple[Tensor,Tensor]],Tuple[Tensor,SparseTensor]]