Graphcode: Learning from multiparameter persistent homology using graph neural networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kerber, Michael, Russold, Florian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929354816094208
author Kerber, Michael
Russold, Florian
author_facet Kerber, Michael
Russold, Florian
contents We introduce graphcodes, a novel multi-scale summary of the topological properties of a dataset that is based on the well-established theory of persistent homology. Graphcodes handle datasets that are filtered along two real-valued scale parameters. Such multi-parameter topological summaries are usually based on complicated theoretical foundations and difficult to compute; in contrast, graphcodes yield an informative and interpretable summary and can be computed as efficient as one-parameter summaries. Moreover, a graphcode is simply an embedded graph and can therefore be readily integrated in machine learning pipelines using graph neural networks. We describe such a pipeline and demonstrate that graphcodes achieve better classification accuracy than state-of-the-art approaches on various datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14302
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graphcode: Learning from multiparameter persistent homology using graph neural networks
Kerber, Michael
Russold, Florian
Algebraic Topology
Machine Learning
We introduce graphcodes, a novel multi-scale summary of the topological properties of a dataset that is based on the well-established theory of persistent homology. Graphcodes handle datasets that are filtered along two real-valued scale parameters. Such multi-parameter topological summaries are usually based on complicated theoretical foundations and difficult to compute; in contrast, graphcodes yield an informative and interpretable summary and can be computed as efficient as one-parameter summaries. Moreover, a graphcode is simply an embedded graph and can therefore be readily integrated in machine learning pipelines using graph neural networks. We describe such a pipeline and demonstrate that graphcodes achieve better classification accuracy than state-of-the-art approaches on various datasets.
title Graphcode: Learning from multiparameter persistent homology using graph neural networks
topic Algebraic Topology
Machine Learning
url https://arxiv.org/abs/2405.14302