gammagl.models.FAGCNModel

class FAGCNModel(feature_dim, hidden_dim, num_class, drop_rate, eps, num_layers, name=None)[source]

The Frequency Adaptive Graph Convolution operator from the “Beyond Low-Frequency Information in Graph Convolutional Networks” paper.

Parameters:

  • feature_dim (int) – Dimension of feature vector in original input.

  • hidden_dim (int) – Dimension of feature vector in FAGCN.

  • num_class (int) – Dimension of feature vector in forward output.

  • drop_rate (float) – Dropout rate.

  • eps (float) – Epsilon parameter in paper.

  • num_layers (int) – Number of Frequency Adaptation Graph Convolutional Layers.

  • name (str, optional) – Name of the model.

forward(x, edge_index, edge_weight, num_nodes)[source]

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.