IvanIsCoding/GNN-for-Combinatorial-Optimization

JAX + Flax implementation of "Combinatorial Optimization with Physics-Inspired Graph Neural Networks" by Schuetz et al.

36
/ 100
Emerging

This project explores how well Graph Neural Networks (GNNs) can solve complex scheduling or resource allocation problems, known as combinatorial optimization. It takes problem definitions, like a network of connections, and outputs potential optimal solutions, comparing GNN performance against traditional methods like simulated annealing. This is for researchers or practitioners in operations research, logistics, or scientific computing who are evaluating modern AI techniques for challenging optimization tasks.

Use this if you are a researcher or advanced practitioner investigating the practical effectiveness of Graph Neural Networks for solving NP-hard combinatorial optimization problems like Max-Cut or Maximum Independent Set.

Not ideal if you need a production-ready, highly optimized solver for specific combinatorial optimization problems, as this project focuses on research and comparative analysis rather than turnkey solutions.

combinatorial-optimization operations-research algorithm-comparison graph-analysis resource-optimization
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

66

Forks

3

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IvanIsCoding/GNN-for-Combinatorial-Optimization"

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