torch_geometric_signed_directed.nn.directed.DiGCN_link_prediction

Classes

DiGCN_link_prediction

An implementation of the DiGCN model without inception blocks for link prediction from the

Module Contents

class DiGCN_link_prediction(num_features: int, hidden: int, label_dim: int, dropout: float = 0.5)

Bases: torch.nn.Module

An implementation of the DiGCN model without inception blocks for link prediction from the Digraph Inception Convolutional Networks paper.

Parameters:

• num_features (int) – Dimension of input features.

• hidden (int) – Hidden dimension.

• label_dim (int) – The dimension of labels.

• dropout (float) – Dropout value. (Default: 0.5)

conv1

conv2

dropout = 0.5

linear

reset_parameters()

forward(x: torch.FloatTensor, edge_index: torch.LongTensor, query_edges: torch.LongTensor, edge_weight: torch.FloatTensor = None) → torch.FloatTensor

Making a forward pass of the DiGCN node classification model without inception blocks.

Arg types:

• x (PyTorch FloatTensor) - Node features.

• edge_index (PyTorch LongTensor) - Edge indices.

• edge_weight (PyTorch FloatTensor, optional) - Edge weights corresponding to edge indices.

Return types:

• query_edges (PyTorch Long Tensor) - Edge indices for querying labels.

• x (PyTorch FloatTensor) - Logarithmic class probabilities for all nodes, with shape (num_nodes, num_classes).