Autobahn: Automorphism-based Graph Neural Nets

1 code implementation • NeurIPS 2021 • Erik Henning Thiede, Wenda Zhou, Risi Kondor

Our formalism also encompasses novel architectures: as an example, we introduce a graph neural network that decomposes the graph into paths and cycles.

The general theory of permutation equivarant neural networks and higher order graph variational encoders

1 code implementation • 8 Apr 2020 • Erik Henning Thiede, Truong Son Hy, Risi Kondor

Previous work on symmetric group equivariant neural networks generally only considered the case where the group acts by permuting the elements of a single vector.

Graph Generation Graph Learning +2