danielegrattarola/GNCA

Code for "Learning Graph Cellular Automata" (NeurIPS 2021).

36
/ 100
Emerging

This project provides code to explore and experiment with Graph Cellular Automata (GCA), which are systems that can learn to evolve and adapt on complex network structures. It takes raw graph data or simulated environments (like 'Boids' flocking behavior or Voronoi patterns) as input and outputs trained GCA models and visualizations of their evolving states. Researchers and students working in computational intelligence, complex systems, or machine learning for graph-structured data would use this.

No commits in the last 6 months.

Use this if you are a researcher or student interested in understanding, training, and visualizing how Graph Cellular Automata can model dynamic processes on networks.

Not ideal if you are looking for a plug-and-play solution for real-world graph prediction tasks without a deep interest in the underlying GCA mechanics.

graph-modeling complex-systems computational-intelligence network-dynamics research-prototyping
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

75

Forks

18

Language

Python

License

Last pushed

Sep 16, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danielegrattarola/GNCA"

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