Yuma-Ichikawa/CRA4CO

A PyTorch implementation: Controlling Continuous Relaxation for Combinatorial Optimization

20
/ 100
Experimental

This project offers a PyTorch implementation for solving complex combinatorial optimization problems, which involve finding the best solution from a finite set of possibilities (like scheduling or resource allocation). It takes a problem definition, often represented as a graph, and outputs a refined solution that is more accurate and efficient than other unsupervised learning methods. This tool is designed for researchers and practitioners working on advanced optimization techniques.

No commits in the last 6 months.

Use this if you are a researcher or advanced practitioner developing unsupervised learning-based solvers for combinatorial optimization and need to improve solution quality and accelerate the training process.

Not ideal if you are looking for an off-the-shelf, easy-to-use solver for standard optimization problems without deep learning expertise.

combinatorial-optimization unsupervised-learning graph-optimization operations-research algorithm-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

7

Forks

Language

Jupyter Notebook

License

BSD-3-Clause-Clear

Last pushed

Mar 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Yuma-Ichikawa/CRA4CO"

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