torch_geometric.nn.aggr.PatchTransformerAggregation

class PatchTransformerAggregation(in_channels: int, out_channels: int, patch_size: int, hidden_channels: int, num_transformer_blocks: int = 1, heads: int = 1, dropout: float = 0.0, aggr: Union[str, List[str]] = 'mean')

Bases: Aggregation

执行补丁变换器聚合，其中要聚合的元素通过跨补丁的多头注意力块进行处理，如“简化时间异质网络以进行连续时间链接预测”论文中所述。

Parameters:

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

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

• patch_size (int) – 一个补丁中的元素数量。

• hidden_channels (int) – 每个样本的中间大小。

• num_transformer_blocks (int, optional) – 变压器块的数量 (默认: 1).

• heads (int, optional) – Number of multi-head-attentions. (default: 1)

• dropout (float, optional) – 注意力权重的丢弃概率。 (默认值: 0.0)

• aggr (str 或 list[str], 可选) – 聚合模块，例如, "sum", "mean", "min", "max", "var", "std". (默认: "mean")

reset_parameters() → None

重置模块的所有可学习参数。

Return type:

None

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

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