EDNN {mnda}

Encoder decoder neural network (EDNN) function

Description

Encoder decoder neural network (EDNN) function

Usage

EDNN(
  X,
  Y,
  Xtest,
  embedding_size = 2,
  epochs = 10,
  batch_size = 5,
  l2reg = 0,
  demo = TRUE,
  verbose = TRUE
)

Arguments

X

concatenated adjacency matrices for different layers containing the nodes in training phase

Y

concatenated random walk probability matrices for different layers containing the nodes in training phase

Xtest

concatenated adjacency matrices for different layers containing the nodes in test phase. Can be = X for transductive inference.

embedding_size

the dimension of embedding space, equal to the number of the bottleneck hidden nodes.

epochs

maximum number of pocks. An early stopping callback with a patience of 5 has been set inside the function (default = 10).

batch_size

batch size for learning (default = 5).

l2reg

the coefficient of L2 regularization for the input layer (default = 0).

demo

a boolean vector to indicate this is a demo example or not

verbose

if TRUE a progress bar is shown.

Value

The embedding space for Xtest.

Examples

myNet = network_gen(N_nodes = 50)
graphData = myNet[["data_graph"]]
edge.list = graphData[,1:2]
edge.weight = graphData[,3:4]
XY = ednn_IOprepare(edge.list, edge.weight)
X = XY[["X"]]
Y = XY[["Y"]]
embeddingSpace = EDNN(X = X, Y = Y, Xtest = X)