arXiv · 2012.06010
Simplicial 2-Complex Convolutional Neural Nets
Abstract
Recently, neural network architectures have been developed to accommodate when the data has the structure of a graph or, more generally, a hypergraph. While useful, graph structures can be potentially limiting. Hypergraph structures in general do not account for higher order relations between their hyperedges. Simplicial complexes offer a middle ground, with a rich theory to draw on. We develop a convolutional neural network layer on simplicial 2-complexes.
Explore related subjects
Keep this discovery
Eric Bunch, Qian You, Glenn Fung, Vikas Singh. 2020-12-10. Simplicial 2-Complex Convolutional Neural Nets. https://arxiv.org/abs/2012.06010
Cite the original work for its findings. Save a collection to share your selection of sources.