YichengDWu/NeuralGraphPDE.jl

Integrating Neural Ordinary Differential Equations, the Method of Lines, and Graph Neural Networks

27
/ 100
Experimental

This is a framework for researchers and scientists interested in advanced computational methods for modeling complex systems. It helps you design and test new neural network architectures that can learn from and predict changes in graph-structured data over time, especially when described by partial differential equations. You input your scientific data and a definition of your system's dynamics, and it outputs a trained model capable of simulating or forecasting those dynamics.

No commits in the last 6 months.

Use this if you are a researcher developing novel deep learning methods for modeling dynamic systems on networks, such as protein interactions, social networks, or fluid dynamics, and need a flexible framework to explore Neural Graph PDE concepts.

Not ideal if you need an actively maintained library for production-ready applications or if you are looking for out-of-the-box solutions for standard graph neural network tasks without deep customization.

scientific-modeling computational-physics dynamic-systems graph-analysis numerical-simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Julia

License

MIT

Last pushed

Oct 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YichengDWu/NeuralGraphPDE.jl"

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