torch_geometric_signed_directed.nn.signed.SNEA

Classes

SNEA	The signed graph attentional layers operator from the `"Learning Signed

Module Contents

class SNEA(node_num: int, edge_index_s: torch.LongTensor, in_dim: int = 64, out_dim: int = 64, layer_num: int = 2, init_emb: torch.FloatTensor = None, init_emb_grad: bool = True, lamb: float = 4)

Bases: torch.nn.Module

The signed graph attentional layers operator from the “Learning Signed Network Embedding via Graph Attention” paper :Parameters: * node_num (int) – The number of nodes.

• edge_index_s (LongTensor) – The edgelist with sign. (e.g., torch.LongTensor([[0, 1, -1], [0, 2, 1]]) )

• in_dim (int, optional) – Size of each input sample features. Defaults to 64.

• out_dim (int, optional) – Size of each output embeddings. Defaults to 64.

• layer_num (int, optional) – Number of layers. Defaults to 2.

• init_emb – (FloatTensor, optional): The initial embeddings. Defaults to None, which will use TSVD as initial embeddings.

• init_emb_grad (bool, optional) – Optimize initial embeddings or not.

• lamb (float, optional) – Balances the contributions of the overall objective. (default: 4)

node_num

in_dim = 64

out_dim = 64

lamb = 4

device

pos_edge_index

neg_edge_index

x

conv1

convs

weight

lsp_loss

structure_loss

reset_parameters()

loss() → torch.FloatTensor

forward() → torch.Tensor