torch_geometric.nn.aggr.LCMAggregation

class LCMAggregation(in_channels: int, out_channels: int, project: bool = True)[source]

Bases: Aggregation

The Learnable Commutative Monoid aggregation from the “Learnable Commutative Monoids for Graph Neural Networks” paper, in which the elements are aggregated using a binary tree reduction with \(\mathcal{O}(\log |\mathcal{V}|)\) depth.

Note

LCMAggregation requires sorted indices index as input. Specifically, if you use this aggregation as part of MessagePassing, ensure that edge_index is sorted by destination nodes, either by manually sorting edge indices via sort_edge_index() or by calling torch_geometric.data.Data.sort().

Warning

LCMAggregation is not a permutation-invariant operator.

Parameters:

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

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

  • project (bool, optional) – If set to True, the layer will apply a linear transformation followed by an activation function before aggregation. (default: True)

reset_parameters()[source]

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, max_num_elements: Optional[int] = None) → Tensor[source]

Forward pass.

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