YichengDWu/NeuralGraphPDE.jl
Integrating Neural Ordinary Differential Equations, the Method of Lines, and Graph Neural Networks
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.
Stars
18
Forks
1
Language
Julia
License
MIT
Category
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.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.