Graph Filtration Learning
Machine Learning
2021-05-18 v3 Algebraic Topology
Machine Learning
Abstract
We propose an approach to learning with graph-structured data in the problem domain of graph classification. In particular, we present a novel type of readout operation to aggregate node features into a graph-level representation. To this end, we leverage persistent homology computed via a real-valued, learnable, filter function. We establish the theoretical foundation for differentiating through the persistent homology computation. Empirically, we show that this type of readout operation compares favorably to previous techniques, especially when the graph connectivity structure is informative for the learning problem.
Cite
@article{arxiv.1905.10996,
title = {Graph Filtration Learning},
author = {Christoph D. Hofer and Florian Graf and Bastian Rieck and Marc Niethammer and Roland Kwitt},
journal= {arXiv preprint arXiv:1905.10996},
year = {2021}
}