caio-freitas/GraphARM
An implementation of the Autoregressive Diffusion Model for Graph Generation from [Kong et al. 2023]
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.
Stars
44
Forks
11
Language
Python
License
—
Category
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.
Higher-rated alternatives
MinkaiXu/GeoDiff
Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).
MinkaiXu/GeoLDM
Geometric Latent Diffusion Models for 3D Molecule Generation
microsoft/foldingdiff
Diffusion models of protein structure; trigonometry and attention are all you need!
aqlaboratory/genie
De Novo Protein Design by Equivariantly Diffusing Oriented Residue Clouds
pengxingang/MolDiff
MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation