Dist2Cycle: A Simplicial Neural Network for Homology Localization

Author name not available (Why is that?)

Publication date: 28 October 2021

Abstract: Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations between vertices at different resolutions, all at once. This concept is central towards detection of higher dimensional topological features of data, features to which graphs, encoding only pairwise relationships, remain oblivious. While attempts have been made to extend Graph Neural Networks (GNNs) to a simplicial complex setting, the methods do not inherently exploit, or reason about, the underlying topological structure of the network. We propose a graph convolutional model for learning functions parametrized by the

k

-homological features of simplicial complexes. By spectrally manipulating their combinatorial

k

-dimensional Hodge Laplacians, the proposed model enables learning topological features of the underlying simplicial complexes, specifically, the distance of each

k

-simplex from the nearest "optimal"

k

-th homology generator, effectively providing an alternative to homology localization.

Has companion code repository: https://github.com/alexdkeros/Dist2Cycle

Mathematics Subject Classification ID

No records found.

This page was built for publication: Dist2Cycle: A Simplicial Neural Network for Homology Localization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6381563)