spamosaic.architectures.hg_lgcn.HG_LGCN_Conv

class spamosaic.architectures.hg_lgcn.HG_LGCN_Conv(*args: Any, **kwargs: Any)[source]

Heterogeneous Graph LightGCN convolution layer.

This layer handles intra-group and inter-group message passing separately, applying degree-normalized edge weights and combining both feature streams.

Inherits from:

torch_geometric.nn.conv.MessagePassing

forward(x, edge_index, edge_weight, edge_type)[source]

Executes the forward pass using intra- and inter-group edge types.

message(x_j, norm)[source]

Computes messages for each edge using normalized weights.