Loading [MathJax]/extensions/MathMenu.js
Graphusion: Latent Diffusion for Graph Generation | IEEE Journals & Magazine | IEEE Xplore

Graphusion: Latent Diffusion for Graph Generation


Abstract:

Graph generation is a fundamental task in machine learning with broad impacts on numerous real-world applications such as biomedical discovery and social science. Most re...Show More

Abstract:

Graph generation is a fundamental task in machine learning with broad impacts on numerous real-world applications such as biomedical discovery and social science. Most recently, generative models, especially diffusion models (DMs), have shown great promise in synthesizing realistic graphs. However, existing DMs methods typically conduct diffusion processes directly in complex graph space (i.e., node feature, adjacency matrix, or both), resulting in high modeling complexity and poor multimodal distribution coverage. In this paper, we propose Graphusion, a novel and unified latent-based graph generative framework to address the problems. Specifically, Graphusion is composed of a variational graph autoencoder mapping raw graphs with high-dimensional discrete space to low-dimensional topology-injected latent space, and latent DMs running there, producing a smoother, faster, and more expressive graph generation procedure. Thanks to the latest space modeling, we further develop principled latent self-guidance to sufficiently cover the whole semantical distribution of the unlabeled graph set. Experiments show that our Graphusion framework can consistently outperform previous graph generation baselines on both generic and molecular graph datasets, demonstrating the generality and extensibility along with further analytical justifications.
Published in: IEEE Transactions on Knowledge and Data Engineering ( Volume: 36, Issue: 11, November 2024)
Page(s): 6358 - 6369
Date of Publication: 25 April 2024

ISSN Information:

Funding Agency:


References

References is not available for this document.