scSLAT.model.graphconv.combnet.CombUnweighted
- class scSLAT.model.graphconv.combnet.CombUnweighted(K=1, cached=False, bias=True, **kwargs)[source]
Bases:
MessagePassingLGCN (GCN without learnable and concat)
- Parameters:
K (
typing.Optional[int]) – K-hop neighbor to propagate
Methods
Runs the forward pass of the module.
Constructs messages from node \(j\) to node \(i\) in analogy to \(\phi_{\mathbf{\Theta}}\) for each edge in
edge_index.Attributes