GraphGUIDE: interpretable and controllable conditional graph generation with discrete Bernoulli diffusion

Alex M Tseng, Nathaniel Lee Diamant, Tommaso Biancalani, Gabriele Scalia

Keywords: diffusion model, generative model, conditional generation, graphs, molecules, interpretability

TL;DR: A framework for graph diffusion models via discrete diffusion on edges, which allows for interpretable and controllable conditional generation of structural properties

Abstract: Diffusion models achieve state-of-the-art performance in generating realistic objects and have been successfully applied to images, text, and videos. Recent work has shown that diffusion can also be defined on graphs, including graph representations of drug-like molecules. Unfortunately, it remains difficult to perform conditional generation on graphs in a way which is interpretable and controllable. In this work, we propose GraphGUIDE, a novel framework for graph generation using diffusion models, where edges in the graph are flipped or set at each discrete time step. We demonstrate GraphGUIDE on several graph datasets, and show that it enables full control over the conditional generation of arbitrary structural properties without relying on predefined labels. Our framework for graph diffusion can have a large impact on the interpretable conditional generation of graphs, including the generation of drug-like molecules with desired properties in a way which is informed by experimental evidence.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2302.03790/code)