graphkernels (version 1.6.1)

CalculateVertexVertexEdgeHistKernel: Linear kernel combination of vertex label histograms and vertex-edge label histograms

Description

This function calculates a kernel matrix of the linear kernel combination \(K_{H}\) of vertex label histograms \(K_{VH}\) and vertex-edge label histograms \(K_{VEH}\).

Usage

CalculateVertexVertexEdgeHistKernel(G, par)

Arguments

G

a list of igraph graphs

par

a coefficient \(\lambda\), with which the resulting kernel is given as \(K_{VH} + \lambda K_{VEH}\)

Value

a kernel matrix that is equivalent to \(K_{VH} + \lambda K_{VEH}\)

References

Sugiyama, M., Borgwardt, K. M.: Halting in Random Walk Kernels, Advances in Neural Information Processing Systems (NIPS 2015), 28, 1630-1638 (2015) https://papers.nips.cc/paper/5688-halting-in-random-walk-kernels.pdf.

Examples

# NOT RUN {
data(mutag)
K <- CalculateVertexVertexEdgeHistKernel(mutag, .1)
# }