- class GRUAggregation(in_channels: int, out_channels: int, **kwargs)
Performs GRU aggregation in which the elements to aggregate are interpreted as a sequence, as described in the “Graph Neural Networks with Adaptive Readouts” paper.
GRUAggregationis not a permutation-invariant operator.
Resets all learnable parameters of the module.
- forward(x: Tensor, index: Optional[Tensor] = None, ptr: Optional[Tensor] = None, dim_size: Optional[int] = None, dim: int = -2) Tensor
x (torch.Tensor) – The source tensor.
dim (int, optional) – The dimension in which to aggregate. (default: