torch_geometric_signed_directed.nn.directed.DiGCL

Classes

DiGCL_Encoder

An implementation of the DiGCL encoder model from the

DiGCL

An implementation of the DiGCL model from the

Module Contents

class DiGCL_Encoder(in_channels: int, out_channels: int, activation: str, num_layers: int = 2)

Bases: torch.nn.Module

An implementation of the DiGCL encoder model from the Directed Graph Contrastive Learning paper.

Parameters:

  • in_channels (int) – Dimension of input features.

  • out_channels (int) – Dimension of output representations.

  • activation (str) – Activation funciton to use.

  • num_layers (int, Optional) – Number of layers for encoder. (Default: 2)

conv
activation
reset_parameters()
forward(x: torch.Tensor, edge_index: torch.Tensor, edge_weight: torch.Tensor = None)

Making a forward pass of the DiGCL encoder model.

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:

  • x (PyTorch FloatTensor) - Embeddings for all nodes, with shape (num_nodes, out_channels).

class DiGCL(in_channels: int, activation: str, num_hidden: int, num_proj_hidden: int, tau: float, num_layers: int)

Bases: torch.nn.Module

An implementation of the DiGCL model from the Directed Graph Contrastive Learning paper.

Parameters:

  • in_channels (int) – Dimension of input features.

  • activation (str) – Activation funciton to use.

  • num_hidden (int) – Hidden dimension.

  • num_proj_hidden (int) – Hidden dimension for projection.

  • tau (float) – Tau value in the loss.

  • num_layers (int) – Number of layers for encoder.

encoder
tau: float
fc1
fc2
reset_parameters()
forward(x: torch.Tensor, edge_index: torch.Tensor, edge_weight: torch.Tensor = None) → torch.Tensor

Making a forward pass of the DiGCL model.

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:

  • x (PyTorch FloatTensor) - Embeddings for all nodes, with shape (num_nodes, out_channels).

projection(z: torch.Tensor) → torch.Tensor

Nonlinear transformation of the input hidden feature.

Args types::

  • z (PyTorch FloatTensor) - Node features.

Return types:

  • z (PyTorch FloatTensor) - Projected node features.

sim(z1: torch.Tensor, z2: torch.Tensor)

Normalized similarity calculation.

Args types::

  • z1 (PyTorch FloatTensor) - Node features.

  • z2 (PyTorch FloatTensor) - Node features.

Return types:

  • z (PyTorch FloatTensor) - Node-wise similarity.

semi_loss(z1: torch.Tensor, z2: torch.Tensor)

Semi-supervised loss function.

Arg types:

  • z1 (PyTorch FloatTensor) - Node features.

  • z2 (PyTorch FloatTensor) - Node features.

Return types:

  • loss (PyTorch FloatTensor) - Loss.

batched_semi_loss(z1: torch.Tensor, z2: torch.Tensor, batch_size: int)

Semi-supervised loss function. Space complexity: O(BN) (semi_loss: O(N^2))

Args types::

  • z1 (PyTorch FloatTensor) - Node features.

  • z2 (PyTorch FloatTensor) - Node features.

Return types:

  • loss (PyTorch FloatTensor) - Loss.

loss(z1: torch.Tensor, z2: torch.Tensor, mean: bool = True, batch_size: int = 0)

The DiGCL contrastive loss.

Arg types:

  • z1, z2 (PyTorch FloatTensor) - Node hidden representations.

  • mean (bool, optional) - Whether to return the mean of loss values, default True, otherwise return sum.

  • batch_size (int, optional) - Batch size, if 0 this means full-batch. Default 0.

Return types:

  • ret (PyTorch FloatTensor) - Loss.