IvanIsCoding/GNN-for-Combinatorial-Optimization
JAX + Flax implementation of "Combinatorial Optimization with Physics-Inspired Graph Neural Networks" by Schuetz et al.
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.
Stars
66
Forks
3
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/