torch_geometric.nn.aggr.DeepSetsAggregation

class DeepSetsAggregation(local_nn: Optional[Module] = None, global_nn: Optional[Module] = None)

Bases: Aggregation

Performs Deep Sets aggregation in which the elements to aggregate are first transformed by a Multi-Layer Perceptron (MLP) \(\phi_{\mathbf{\Theta}}\), summed, and then transformed by another MLP \(\rho_{\mathbf{\Theta}}\), as suggested in the “Graph Neural Networks with Adaptive Readouts” paper.

Parameters:

• local_nn (torch.nn.Module, optional) – The neural network \(\phi_{\mathbf{\Theta}}\), e.g., defined by torch.nn.Sequential or torch_geometric.nn.models.MLP. (default: None)

• global_nn (torch.nn.Module, optional) – The neural network \(\rho_{\mathbf{\Theta}}\), e.g., defined by torch.nn.Sequential or torch_geometric.nn.models.MLP. (default: None)

reset_parameters()

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

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