Overview Statistic: PDF-Downloads (blue) and Frontdoor-Views (gray)

Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs

under review
  • We propose two graph neural network layers for graphs with features in a Riemannian manifold. First, based on a manifold-valued graph diffusion equation, we construct a diffusion layer that can be applied to an arbitrary number of nodes and graph connectivity patterns. Second, we model a tangent multilayer perceptron by transferring ideas from the vector neuron framework to our general setting. Both layers are equivariant with respect to node permutations and isometries of the feature manifold. These properties have been shown to lead to a beneficial inductive bias in many deep learning tasks. Numerical examples on synthetic data as well as on triangle meshes of the right hippocampus to classify Alzheimer's disease demonstrate the very good performance of our layers.
Author:Martin HanikORCiD, Gabriele SteidlORCiD, Christoph von TycowiczORCiD
Document Type:Article
Year of first publication:2024
ArXiv Id:http://arxiv.org/abs/2401.14381
Accept ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.