Zehong-Wang/G2PM
[NeurIPS 25] Generative Graph Pattern Machine (G2PM)
This project helps researchers and data scientists working with complex network data, such as social networks, biological interactions, or citation graphs. It takes large, intricate graphs as input and generates versatile representations that capture underlying patterns, even from massive datasets that overwhelm traditional methods. The primary users are researchers in fields like bioinformatics, social science, or academic knowledge management who need to analyze or classify graph-structured information.
Use this if you are working with extremely large graph datasets (up to 60 million nodes/edges) and need to learn high-quality, transferable representations for tasks like node classification, graph classification, or transfer learning, where traditional graph neural networks struggle with scalability or expressive power.
Not ideal if your datasets are small, or if you lack a high-end GPU with at least 24GB of memory, as this project is designed for large-scale graph analysis and requires significant computational resources.
Stars
9
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Zehong-Wang/G2PM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sdv-dev/Copulas
A library to model multivariate data using copulas.
jmtomczak/intro_dgm
"Deep Generative Modeling": Introductory Examples
Mohamedelrefaie/DrivAerNet
A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep...
RichardObi/medigan
medigan - A Python Library of Pretrained Generative Models for Medical Image Synthesis
RiqiangGao/GDP-HMM_AAPMChallenge
The code base for Generalizable Dose Prediction for Heterogenous Multi-Cohort and Multi-Site...