Simplicial 2-Complex Convolutional Neural Nets
Algebraic Topology
2020-12-14 v1
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.
Cite
@article{arxiv.2012.06010,
title = {Simplicial 2-Complex Convolutional Neural Nets},
author = {Eric Bunch and Qian You and Glenn Fung and Vikas Singh},
journal= {arXiv preprint arXiv:2012.06010},
year = {2020}
}
Comments
5 pages, accepted to TDA and Beyond: Workshop at NeurIPS 2020