torch_geometric_signed_directed.nn.signed.SiGAT

Classes

SiGAT

The signed graph attention network model (SiGAT) from the `"Signed Graph

Module Contents

class SiGAT(node_num: int, edge_index_s, in_dim: int = 20, out_dim: int = 20, init_emb: torch.FloatTensor = None, init_emb_grad: bool = True, **kwargs)

Bases: torch.nn.Module

The signed graph attention network model (SiGAT) from the “Signed Graph Attention Networks” paper.

Parameters:

node_num ([type]) – Number of node.
edge_index_s (list) – The edgelist with sign. (e.g., [[0, 1, -1]] )
in_dim (int, optional) – Size of each input sample features. Defaults to 20.
out_dim (int) – Size of each output embeddings. Defaults to 20.
init_emb – (FloatTensor, optional): The initial embeddings. Defaults to None, which will use TSVD as initial embeddings.
init_emb_grad (bool optional) – Whether to set the initial embeddings to be trainable. (default: False)

in_dim = 20

out_dim = 20

node_num

device

pos_edge_index

neg_edge_index

x

adj_lists

edge_lists

aggs = []

mlp_layer

lsp_loss

reset_parameters()

map_adj_to_edges(adj_list: List) → torch.LongTensor

get_tri_features(u: int, v: int, r_edgelist: List) → Tuple[int, int, int, int, int, int, int, int, int, int, int, int, int, int, int, int]

build_adj_lists(edge_index_s: torch.LongTensor) → List

forward() → torch.FloatTensor

loss() → torch.FloatTensor