gammagl.models.ChebNetModel

class ChebNetModel(feature_dim, hidden_dim, out_dim, k, drop_rate, name=None)

Graph Convolutional Network proposed in “Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering” paper.

Parameters:

• feature_dim (int) – The dimensionality of input feature.

• hidden_dim (int) – The dimensionality of hidden layer.

• out_dim (int) – The number of classes for prediction.

• k (int) – Chebyshev filter size.

• drop_rate (float) – Dropout rate.

• name (str) – The name of the model.

forward(x, edge_index, edge_weight, num_nodes)