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)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.