dgn.toy_dgn

class pydgn.model.dgn.toy_dgn.ToyDGN(*args: Any, **kwargs: Any)

A toy Deep Graph Network used to test the library

forward(data: torch_geometric.data.Batch) → Tuple[torch.Tensor, Optional[torch.Tensor], Optional[List[object]]]

Implements an Toy DGN with some SAGE graph convolutional layers.

dgn.toy_mlp

class pydgn.model.dgn.toy_mlp.ToyMLP(*args: Any, **kwargs: Any)

A toy MLP model used to test the library. Technically, a DGN that ignores the adjacency matrix.

forward(data: torch_geometric.data.Batch) → Tuple[torch.Tensor, Optional[torch.Tensor], Optional[List[object]]]

Implements an MLP (structure agnostic baseline)