haguettaz/ChebLieNet
ChebLieNet, a spectral graph neural network turned equivariant by Riemannian geometry on Lie groups.
This project helps machine learning researchers build neural networks that better understand complex data with directional properties, like images or climate models. It takes raw data on 'Lie groups' (mathematical structures that represent symmetries or transformations) and outputs models that can recognize patterns more effectively, especially where data points have specific orientations or relationships. This is for researchers in geometric deep learning or those developing advanced computer vision and scientific modeling algorithms.
No commits in the last 6 months.
Use this if you are a machine learning researcher exploring how to incorporate geometric principles and anisotropic properties to improve the performance and understanding of graph neural networks on complex datasets.
Not ideal if you are looking for a plug-and-play solution for standard image classification without deep expertise in geometric deep learning or graph theory.
Stars
14
Forks
2
Language
Python
License
MIT
Category
Last pushed
Aug 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/haguettaz/ChebLieNet"
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.