torch_geometric.nn.models.ARGA

class ARGA(encoder: Module, discriminator: Module, decoder: Optional[Module] = None)[source]

Bases: GAE

The Adversarially Regularized Graph Auto-Encoder model from the “Adversarially Regularized Graph Autoencoder for Graph Embedding” paper.

Parameters:
forward(*args, **kwargs) Tensor

Alias for encode().

reset_parameters()[source]

Resets all learnable parameters of the module.

reg_loss(z: Tensor) Tensor[source]

Computes the regularization loss of the encoder.

Parameters:

z (torch.Tensor) – The latent space \(\mathbf{Z}\).

discriminator_loss(z: Tensor) Tensor[source]

Computes the loss of the discriminator.

Parameters:

z (torch.Tensor) – The latent space \(\mathbf{Z}\).