torch_geometric.nn.aggr.LSTMAggregation

class LSTMAggregation(in_channels: int, out_channels: int, **kwargs)[source]

Bases: Aggregation

执行LSTM风格的聚合，其中要聚合的元素被解释为一个序列，如“Inductive Representation Learning on Large Graphs”论文中所述。

注意

LSTMAggregation 需要排序后的索引 index 作为输入。 具体来说，如果你将此聚合用作 MessagePassing 的一部分，请确保 edge_index 按目标节点排序，可以通过手动 使用 sort_edge_index() 排序边索引 或调用 torch_geometric.data.Data.sort() 来实现。

警告

LSTMAggregation 不是一个排列不变的运算符。

Parameters:

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

  • out_channels (int) – 每个输出样本的大小。

  • **kwargs (可选) – torch.nn.LSTM 的额外参数。

reset_parameters()[source]

重置模块的所有可学习参数。

forward(x: Tensor, index: Optional[Tensor] = None, ptr: Optional[Tensor] = None, dim_size: Optional[int] = None, dim: int = -2, max_num_elements: Optional[int] = None) → Tensor[source]

前向传播。

Parameters:

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

  • index (torch.Tensor, optional) – The indices of elements for applying the aggregation. One of index or ptr must be defined. (default: None)

  • ptr (torch.Tensor, optional) – If given, computes the aggregation based on sorted inputs in CSR representation. One of index or ptr must be defined. (default: None)

  • dim_size (int, optional) – The size of the output tensor at dimension dim after aggregation. (default: None)

  • dim (int, optional) – The dimension in which to aggregate. (default: -2)

  • max_num_elements (Optional[int], default: None) – (int, optional): The maximum number of elements within a single aggregation group. (default: None)

Return type:

Tensor