Curvature Filtrations for Graph Generative Model Evaluation
Abstract
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 of graphs, and has recently started to prove useful 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.
Cite
Text
Southern et al. "Curvature Filtrations for Graph Generative Model Evaluation." Neural Information Processing Systems, 2023.Markdown
[Southern et al. "Curvature Filtrations for Graph Generative Model Evaluation." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/southern2023neurips-curvature/)BibTeX
@inproceedings{southern2023neurips-curvature,
title = {{Curvature Filtrations for Graph Generative Model Evaluation}},
author = {Southern, Joshua and Wayland, Jeremy and Bronstein, Michael and Rieck, Bastian},
booktitle = {Neural Information Processing Systems},
year = {2023},
url = {https://mlanthology.org/neurips/2023/southern2023neurips-curvature/}
}