gammagl.models.GMMModel

class GMMModel(feature_dim, hidden_dim, num_class, dim, n_kernels, drop_rate, num_layers, name=None)

The Gaussian Mixture Model or MoNet from the “Geometric deep learning on graphs and manifolds using mixture model CNNs” paper.

Parameters:

• feature_dim (int) – input feature dimension.

• hidden_dim (int) – hidden dimension.

• num_class (int) – number of classes.

• dim (int) – Dimensionality of pseudo-coordinte.

• n_kernels (int) – Number of kernels.

• drop_rate (float) – dropout rate.

• num_layers (int) – number of layers.

• name (str, optional) – model name.

forward(x, edge_index, pseudo)