Curvature Filtrations for Graph Generative Model Evaluation

by   Joshua Southern, et al.

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 cutting-edge methods from topological data analysis to obtain robust, expressive descriptors for evaluating graph generative models.


Topology Based Scalable Graph Kernels

We propose a new graph kernel for graph classification and comparison us...

Generative modeling of the enteric nervous system employing point pattern analysis and graph construction

We describe a generative network model of the architecture of the enteri...

Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework

Bridging geometry and topology, curvature is a powerful and expressive i...

Network Model with Application to Allergy Diseases

We propose a new graphical model to describe the comorbidity of allergic...

Graph topological property recovery with heat and wave dynamics-based features on graphs

In this paper, we propose Graph Differential Equation Network (GDeNet), ...

On Explicit Curvature Regularization in Deep Generative Models

We propose a family of curvature-based regularization terms for deep gen...

Property Graph Exchange Format

Recently, a variety of database implementations adopting the property gr...

Please sign up or login with your details

Forgot password? Click here to reset