twitter-research/graph-neural-pde
Graph Neural PDEs
This project offers advanced methods for analyzing and making predictions on graph-structured data, like social networks, citation networks, or molecular structures. It takes your raw graph data (nodes and their connections) and helps identify patterns, classify nodes, or predict relationships with greater accuracy. This is designed for researchers or practitioners working with complex network data who need robust and stable graph learning models.
339 stars. No commits in the last 6 months.
Use this if you are working with graph data and need to overcome common challenges in graph neural networks such as depth limitations, oversmoothing, or bottlenecks to achieve more stable and accurate predictions.
Not ideal if you are looking for a simple, out-of-the-box solution for basic graph analysis without diving into advanced deep learning concepts or if your primary need is not prediction on graph data.
Stars
339
Forks
57
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Oct 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/twitter-research/graph-neural-pde"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.