torch_geometric.nn.aggr.LSTMAggregation
- class LSTMAggregation(in_channels: int, out_channels: int, **kwargs)[source]
Bases:
Aggregation
Performs LSTM-style aggregation in which the elements to aggregate are interpreted as a sequence, as described in the “Inductive Representation Learning on Large Graphs” paper.
Warning
LSTMAggregation
is not a permutation-invariant operator.- Parameters
in_channels (int) – Size of each input sample.
out_channels (int) – Size of each output sample.
**kwargs (optional) – Additional arguments of
torch.nn.LSTM
.
- forward(x: Tensor, index: Optional[Tensor] = None, ptr: Optional[Tensor] = None, dim_size: Optional[int] = None, dim: int = -2) Tensor [source]
- Parameters
x (torch.Tensor) – The source tensor.
index (torch.Tensor, optional) – The indices of elements for applying the aggregation. One of
index
orptr
must be defined. (default:None
)ptr (torch.Tensor, optional) – If given, computes the aggregation based on sorted inputs in CSR representation. One of
index
orptr
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
)