class AttentionalAggregation(gate_nn: Module, nn: Optional[Module] = None)[source]

Bases: Aggregation

The soft attention aggregation layer from the “Graph Matching Networks for Learning the Similarity of Graph Structured Objects” paper.

\[\mathbf{r}_i = \sum_{n=1}^{N_i} \mathrm{softmax} \left( h_{\mathrm{gate}} ( \mathbf{x}_n ) \right) \cdot h_{\mathbf{\Theta}} ( \mathbf{x}_n ),\]

where \(h_{\mathrm{gate}} \colon \mathbb{R}^F \to \mathbb{R}\) and \(h_{\mathbf{\Theta}}\) denote neural networks, i.e. MLPs.

  • gate_nn (torch.nn.Module) – A neural network \(h_{\mathrm{gate}}\) that computes attention scores by mapping node features x of shape [-1, in_channels] to shape [-1, 1] (for node-level gating) or [1, out_channels] (for feature-level gating), e.g., defined by torch.nn.Sequential.

  • nn (torch.nn.Module, optional) – A neural network \(h_{\mathbf{\Theta}}\) that maps node features x of shape [-1, in_channels] to shape [-1, out_channels] before combining them with the attention scores, e.g., defined by torch.nn.Sequential. (default: None)


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[source]

Forward pass.

  • 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)