harryjo97/GDSS

Official Code Repository for the paper "Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations" (ICML 2022)

35
/ 100
Emerging

This project helps researchers and scientists generate new graph structures, such as chemical molecules or social network configurations, for various experimental purposes. You provide existing graph datasets, and the system learns their underlying patterns to produce novel, similar graphs, complete with both node features and connections. It's designed for machine learning researchers or computational chemists working with graph data.

186 stars. No commits in the last 6 months.

Use this if you need to create realistic, synthetic graph data, like new molecular structures or small-scale network topologies, for research, simulation, or dataset augmentation.

Not ideal if you're looking for a user-friendly application for direct data analysis or visualization, or if you don't have experience with machine learning model training.

computational chemistry materials science drug discovery network science generative AI research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

186

Forks

27

Language

Python

License

Last pushed

Nov 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/harryjo97/GDSS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.