iMoonLab/HGNN
Hypergraph Neural Networks (AAAI 2019)
This project helps researchers and data scientists analyze complex, multi-modal data by modeling high-order relationships. It takes feature representations of objects (like 3D models or images) as input and outputs improved data representations and classifications. This is ideal for those working with datasets where items have intricate, non-simple connections.
829 stars. No commits in the last 6 months.
Use this if you need to classify complex data objects like 3D shapes or images and believe that understanding the high-order relationships between these objects can improve your model's performance.
Not ideal if your data has simple, pairwise relationships or if you are not working with multi-modal data where hypergraphs would be beneficial.
Stars
829
Forks
155
Language
Python
License
MIT
Category
Last pushed
Aug 31, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/iMoonLab/HGNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.