caio-freitas/GraphARM

An implementation of the Autoregressive Diffusion Model for Graph Generation from [Kong et al. 2023]

46
/ 100
Emerging

Implements node-by-node autoregressive diffusion where a diffusion ordering network learns absorption probabilities during forward corruption, then reverses this process to generate graphs sequentially. The approach masks node features and edges during diffusion, enabling controlled graph generation through learned orderings. Built on PyTorch with standard graph neural network components for modeling node dependencies and feature reconstruction.

No License No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

44

Forks

11

Language

Python

License

Last pushed

Mar 16, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/caio-freitas/GraphARM"

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