Incidence Networks for Geometric Deep Learning
Machine Learning
2020-08-13 v4 Machine Learning
Abstract
Sparse incidence tensors can represent a variety of structured data. For example, we may represent attributed graphs using their node-node, node-edge, or edge-edge incidence matrices. In higher dimensions, incidence tensors can represent simplicial complexes and polytopes. In this paper, we formalize incidence tensors, analyze their structure, and present the family of equivariant networks that operate on them. We show that any incidence tensor decomposes into invariant subsets. This decomposition, in turn, leads to a decomposition of the corresponding equivariant linear maps, for which we prove an efficient pooling-and-broadcasting implementation.
Cite
@article{arxiv.1905.11460,
title = {Incidence Networks for Geometric Deep Learning},
author = {Marjan Albooyeh and Daniele Bertolini and Siamak Ravanbakhsh},
journal= {arXiv preprint arXiv:1905.11460},
year = {2020}
}
Comments
Last revised August 10, 2020