Log In Sign Up

Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations

by   Jaehyeong Jo, et al.

Generating graph-structured data requires learning the underlying distribution of graphs. Yet, this is a challenging problem, and the previous graph generative methods either fail to capture the permutation-invariance property of graphs or cannot sufficiently model the complex dependency between nodes and edges, which is crucial for generating real-world graphs such as molecules. To overcome such limitations, we propose a novel score-based generative model for graphs with a continuous-time framework. Specifically, we propose a new graph diffusion process that models the joint distribution of the nodes and edges through a system of stochastic differential equations (SDEs). Then, we derive novel score matching objectives tailored for the proposed diffusion process to estimate the gradient of the joint log-density with respect to each component, and introduce a new solver for the system of SDEs to efficiently sample from the reverse diffusion process. We validate our graph generation method on diverse datasets, on which it either achieves significantly superior or competitive performance to the baselines. Further analysis shows that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule, demonstrating the effectiveness of the system of SDEs in modeling the node-edge relationships.


GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph Generation

Graph generative models have broad applications in biology, chemistry an...

NVDiff: Graph Generation through the Diffusion of Node Vectors

Learning to generate graphs is challenging as a graph is a set of pairwi...

Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generation

Learning the underlying distribution of molecular graphs and generating ...

Score-based Continuous-time Discrete Diffusion Models

Score-based modeling through stochastic differential equations (SDEs) ha...

How Much is Enough? A Study on Diffusion Times in Score-based Generative Models

Score-based diffusion models are a class of generative models whose dyna...

GraphRNN: A Deep Generative Model for Graphs

Modeling and generating graphs is fundamental for studying networks in b...

Improving Graph Generation by Restricting Graph Bandwidth

Deep graph generative modeling has proven capable of learning the distri...