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]