8 papers
Simple Graph Convolutional Networks
Luca Pasa, Nicolò Navarin, Wolfgang Erb +1
Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago. Since then, many alternative definitions have been proposed, that tend…
Partition of Unity Methods for Signal Processing on Graphs
Roberto Cavoretto, Alessandra De Rossi, Wolfgang Erb
Partition of unity methods (PUMs) on graphs are simple and highly adaptive auxiliary tools for graph signal processing. Based on a greedy-type metric clustering and augmentation sc…
A new 3D model for magnetic particle imaging using realistic magnetic field topologies for algebraic reconstruction
Gaël Bringout, Wolfgang Erb, Jürgen Frikel
We derive a new 3D model for magnetic particle imaging (MPI) that is able to incorporate realistic magnetic fields in the reconstruction process. In real MPI scanners, the generate…
Semi-Supervised Learning on Graphs with Feature-Augmented Graph Basis Functions
Wolfgang Erb
For semi-supervised learning on graphs, we study how initial kernels in a supervised learning regime can be augmented with additional information from known priors or from unsuperv…
Graph signal interpolation with Positive Definite Graph Basis Functions
Wolfgang Erb
For the interpolation of graph signals with generalized shifts of a graph basis function (GBF), we introduce the concept of positive definite functions on graphs. This concept merg…
Anisotropic Gaussian approximation in
Wolfgang Erb, Thomas Hangelbroek, Amos Ron
Let be the dictionary of Gaussian mixtures: the functions created by affine change of variables of a single Gaussian in dimensions. is used pervasiv…