easygraph.nn package

Subpackages

• easygraph.nn.convs package
  • Subpackages
    • easygraph.nn.convs.hypergraphs package
      • Submodules
      • easygraph.nn.convs.hypergraphs.dhcf_conv module
      • easygraph.nn.convs.hypergraphs.halfnlh_conv module
      • easygraph.nn.convs.hypergraphs.hgnn_conv module
      • easygraph.nn.convs.hypergraphs.hgnnp_conv module
      • easygraph.nn.convs.hypergraphs.hnhn_conv module
      • easygraph.nn.convs.hypergraphs.hypergcn_conv module
      • easygraph.nn.convs.hypergraphs.unignn_conv module
      • Module contents
  • Submodules
  • easygraph.nn.convs.common module
    • MultiHeadWrapper
      • MultiHeadWrapper.forward()
      • MultiHeadWrapper.training
  • easygraph.nn.convs.pma module
  • Module contents

Submodules

easygraph.nn.loss module

class easygraph.nn.loss.BPRLoss(alpha: float = 1.0, beta: float = 1.0, activation: str = 'sigmoid_then_log')

Bases: Module

This criterion computes the Bayesian Personalized Ranking (BPR) loss between the positive scores and the negative scores.

Parameters:

• alpha (float, optional) – The weight for the positive scores in the BPR loss. Defaults to 1.0.

• beta (float, optional) – The weight for the negative scores in the BPR loss. Defaults to 1.0.

• activation (str, optional) – The activation function to use can be one of "sigmoid_then_log", "softplus". Defaults to "sigmoid_then_log".

forward(pos_scores: Tensor, neg_scores: Tensor)

The forward function of BPRLoss.

Parameters:

• pos_scores (torch.Tensor) – The positive scores.

• neg_scores (torch.Tensor) – The negative scores.

training: bool

easygraph.nn.regularization module

class easygraph.nn.regularization.EmbeddingRegularization(p: int = 2, weight_decay: float = 0.0001)

Bases: Module

Regularization function for embeddings.

Parameters:

• p (int) – The power to use in the regularization. Defaults to 2.

• weight_decay (float) – The weight of the regularization. Defaults to 1e-4.

forward(*embs: List[Tensor])

The forward function.

Parameters:

embs (List[torch.Tensor]) – The input embeddings.

training: bool

Module contents