lamp.nn.graph.GCN$
See theGCN companion class
object GCN
Attributes
Members list
Type members
Inherited types
The names of the product elements
The names of the product elements
Attributes
- Inherited from:
- Mirror
The name of the type
The name of the type
Attributes
- Inherited from:
- Mirror
Value members
Concrete methods
def computeSparseAdjacency[S : Sc](valueOpt: STenOptions, edgeI: STen, edgeJ: STen, numNodes: Long): (Constant, Constant)
Performs D^-0.5 (A+A'+I) D^-0.5 W where are node features (N x D) A is the asymmetric adjacency matrix without self loops, elements in {0,1} I is identity D is degree(A+I)
Performs D^-0.5 (A+A'+I) D^-0.5 W where are node features (N x D) A is the asymmetric adjacency matrix without self loops, elements in {0,1} I is identity D is degree(A+I)
Value parameters
- edgeList
-
N x 2 long tensor the edges in A (asymmetric, no diagonal)
- nodeFeatures
-
N x D node features
Attributes
- Returns
-
N x D aggregated features
Implicits
Implicits
In this article