virne.solver.learning.gae_clustering.auto_encoder#

Classes

ARGA(encoder, discriminator[, decoder])

The Adversarially Regularized Graph Auto-Encoder model from the "Adversarially Regularized Graph Autoencoder for Graph Embedding" paper. paper. :param encoder: The encoder module. :type encoder: Module :param discriminator: The discriminator module. :type discriminator: Module :param decoder: The decoder module. If set to None, will default to the torch_geometric.nn.models.InnerProductDecoder. (default: None) :type decoder: Module, optional.

ARGVA(encoder, discriminator[, decoder])

The Adversarially Regularized Variational Graph Auto-Encoder model from the "Adversarially Regularized Graph Autoencoder for Graph Embedding" paper. paper. :param encoder: The encoder module to compute \(\mu\) and \(\log\sigma^2\). :type encoder: Module :param discriminator: The discriminator module. :type discriminator: Module :param decoder: The decoder module. If set to None, will default to the torch_geometric.nn.models.InnerProductDecoder. (default: None) :type decoder: Module, optional.

GAE(encoder[, decoder])

The Graph Auto-Encoder model from the "Variational Graph Auto-Encoders" paper based on user-defined encoder and decoder models. :param encoder: The encoder module. :type encoder: Module :param decoder: The decoder module. If set to None, will default to the torch_geometric.nn.models.InnerProductDecoder. (default: None) :type decoder: Module, optional.

InnerProductDecoder(*args, **kwargs)

The inner product decoder from the "Variational Graph Auto-Encoders" paper .. math:: sigma(mathbf{Z}mathbf{Z}^{ op}) where \(\mathbf{Z} \in \mathbb{R}^{N imes d}\) denotes the latent space produced by the encoder.

VGAE(encoder[, decoder])

The Variational Graph Auto-Encoder model from the "Variational Graph Auto-Encoders" paper. :param encoder: The encoder module to compute \(\mu\) and \(\log\sigma^2\). :type encoder: Module :param decoder: The decoder module. If set to None, will default to the torch_geometric.nn.models.InnerProductDecoder. (default: None) :type decoder: Module, optional.