Graph generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs in an efficient manner. Curvature constitutes one such property that has recently proved its utility in characterising graphs. Its expressive properties, stability, and practical utility in model evaluation remain largely unexplored, however. We combine graph curvature descriptors with emerging methods from topological data analysis to obtain robust, expressive descriptors for evaluating graph generative models.
@article{arxiv.2301.12906,
title = {Curvature Filtrations for Graph Generative Model Evaluation},
author = {Joshua Southern and Jeremy Wayland and Michael Bronstein and Bastian Rieck},
journal= {arXiv preprint arXiv:2301.12906},
year = {2023}
}
Comments
Accepted at the 37th Conference on Neural Information Processing Systems (NeurIPS) 2023