Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Generative Diffusion Models on Graphs: Methods and Applications

Chengyi Liu, Wenqi Fan, Yunqing Liu, Jiatong Li, Hang Li, Hui Liu, Jiliang Tang, Qing Li

TL;DR

<3-5 sentence high-level summary>

Abstract

Diffusion models, as a novel generative paradigm, have achieved remarkable success in various image generation tasks such as image inpainting, image-to-text translation, and video generation. Graph generation is a crucial computational task on graphs with numerous real-world applications. It aims to learn the distribution of given graphs and then generate new graphs. Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years. In this paper, we first provide a comprehensive overview of generative diffusion models on graphs, In particular, we review representative algorithms for three variants of graph diffusion models, i.e., Score Matching with Langevin Dynamics (SMLD), Denoising Diffusion Probabilistic Model (DDPM), and Score-based Generative Model (SGM). Then, we summarize the major applications of generative diffusion models on graphs with a specific focus on molecule and protein modeling. Finally, we discuss promising directions in generative diffusion models on graph-structured data. For this survey, we also created a GitHub project website by collecting the supporting resources for generative diffusion models on graphs, at the link: https://github.com/ChengyiLIU-cs/Generative-Diffusion-Models-on-Graphs

Generative Diffusion Models on Graphs: Methods and Applications

TL;DR

<3-5 sentence high-level summary>

Abstract

Diffusion models, as a novel generative paradigm, have achieved remarkable success in various image generation tasks such as image inpainting, image-to-text translation, and video generation. Graph generation is a crucial computational task on graphs with numerous real-world applications. It aims to learn the distribution of given graphs and then generate new graphs. Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years. In this paper, we first provide a comprehensive overview of generative diffusion models on graphs, In particular, we review representative algorithms for three variants of graph diffusion models, i.e., Score Matching with Langevin Dynamics (SMLD), Denoising Diffusion Probabilistic Model (DDPM), and Score-based Generative Model (SGM). Then, we summarize the major applications of generative diffusion models on graphs with a specific focus on molecule and protein modeling. Finally, we discuss promising directions in generative diffusion models on graph-structured data. For this survey, we also created a GitHub project website by collecting the supporting resources for generative diffusion models on graphs, at the link: https://github.com/ChengyiLIU-cs/Generative-Diffusion-Models-on-Graphs
Paper Structure (19 sections, 10 equations, 2 figures, 1 table)

This paper contains 19 sections, 10 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Deep Generative Models on Graphs
  4. Diffusion Models
  5. Score Matching with Langevin Dynamics (SMLD)
  6. Denoising Diffusion Probabilistic Model (DDPM)
  7. Score-based Generative Model (SGM)
  8. Generative Diffusion Models on Graphs
  9. SMLD on Graphs
  10. DDPM on Graphs
  11. SGM on Graphs
  12. Applications
  13. Molecule Modeling
  14. Molecule Conformation Generation
  15. Molecular Docking
  16. ...and 4 more sections

Figures (2)

  • Figure 1: Deep Generative Models on Graphs.
  • Figure 2: An illustration of diffusion models on molecular and protein generations. The forward diffusion process involves the gradual addition of noise from the fixed posterior distribution $q(\textbf{G}_t|\textbf{G}_{t-1})$ to the input graph $\textbf{G}_0$ (representing a molecule or protein) over a period of time $T$ steps, ultimately resulting in the destruction of the molecule or protein structure. In contrast, the reverse diffusion process samples an initial graph $\textbf{G}_T$ from a standard Gaussian distribution and gradually refines the graph's structure by using Markov kernels $p_{\theta}(\textbf{G}_{t-1}|\textbf{G}_T)$.