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.
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.