Graph Filtration 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
Text
Hofer et al. "Graph Filtration Learning." International Conference on Machine Learning, 2020.Markdown
[Hofer et al. "Graph Filtration Learning." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/hofer2020icml-graph/)BibTeX
@inproceedings{hofer2020icml-graph,
title = {{Graph Filtration Learning}},
author = {Hofer, Christoph and Graf, Florian and Rieck, Bastian and Niethammer, Marc and Kwitt, Roland},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {4314-4323},
volume = {119},
url = {https://mlanthology.org/icml/2020/hofer2020icml-graph/}
}