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

By Jaehyeong Jo, Seul Lee, Sung Ju Hwang. International Conference on Machine Learning, 2022

357 citations recorded by the source corpus.

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. Our code is available at https://github.com/harryjo97/GDSS.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/3312af738432a817e0d3d913dca87d7445a85696

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Clément Vignac
  2. Bin Cui
  3. Yue Zhao
  4. Volkan Cevher
  5. Pascal Frossard
  6. Ming-Hsuan Yang
  7. Wentao Zhang
  8. Shenda Hong

In Molecular Biology

  1. Clément Vignac
  2. Bin Cui
  3. Volkan Cevher
  4. Pascal Frossard
  5. Ming-Hsuan Yang

In Statistical and Nonlinear Physics

  1. Clément Vignac
  2. Bin Cui
  3. Yue Zhao
  4. Pascal Frossard
  5. Ming-Hsuan Yang
  6. Wentao Zhang
  7. Shenda Hong
  8. Ling Yang

Citations in the corpus