Siamese_Gconv¶
- class src.gconv.Siamese_Gconv(in_features, num_features)[source]¶
Siamese Gconv neural network for processing arbitrary number of graphs.
- Parameters
in_features – the dimension of input node features
num_features – the dimension of output node features
- forward(g1: Tuple[torch.Tensor, torch.Tensor, torch.Tensor, int], *args) Union[torch.Tensor, List[torch.Tensor]] [source]¶
Forward computation of Siamese Gconv.
- Parameters
g1 – The first graph, which is a tuple of (\((b\times n\times n)\) {0,1} adjacency matrix, \((b\times n\times d)\) input node embedding, normalize connectivity matrix or not)
args – Other graphs
- Returns
A list of tensors composed of new node embeddings \((b\times n\times d^\prime)\)
- training: bool¶