Graph Convolutional Network (GCN)

class hivegraph.nn.gcn.GCN(num_features: int, num_classes: int, num_layers: int, hidden: int, dropout: float = 0.5, use_jump: bool = False, conv_variant: str = 'GCN', jump_mode: str = 'cat', readout: str = 'mean', model_name: str = 'GCN')

Bases: Module

Implementation of Graph Convolutional Network

Parameters:

• num_features (int) – Number of input features.

• num_classes (int) – Number of output classes.

• num_layers (int) – Number of GINConv layers.

• hidden (int) – Number of hidden units.

• dropout (float, optional) – Dropout probability. Defaults to 0.5.

• use_jump (bool, optional) – If True, use JumpingKnowledge to aggregate representations from all layers. Defaults to False.

• conv_variant (str, optional) – Convolutional Layer to be used. Must be one of ‘GCN’ or ‘ResGatedGraph’. Defaults to ‘GCN’.

• jump_mode (str, optional) – JumpingKnowledge aggregation mode. Must be one of ‘cat’, ‘max’, or ‘lstm’. Defaults to ‘cat’.

• readout (str, optional) – Readout function. Must be one of ‘mean’, ‘max’, or ‘sum’. Defaults to ‘mean’.

Supported convolutional layers:

• GCNConv

• GraphSAGEConv

• ResGatedGraphConv

Supported readout functions:

• mean

• max

• sum

Supported JumpingKnowledge aggregation modes:

• cat: Concatenate representations from all layers.

• max: Take the maximum representation across all layers.

• lstm: Use a LSTM to aggregate representations from all layers.

References

• https://github.com/pyg-team/pytorch_geometric/blob/master/benchmark/kernel/gcn.py

Raises:

AssertionError – If conv_variant, readout, or jump_mode is not supported.

reset_parameters() → None

Reset the parameters of the model.

forward(data: Data) → Tensor

Compute a forward pass through the model.

Parameters:

data (Data) – Data object.

Returns:

Output of the model.

Return type:

torch.Tensor