THUDM/GraphMAE
GraphMAE: Self-Supervised Masked Graph Autoencoders in KDD'22
This project helps data scientists and machine learning engineers analyze complex network-structured data, like social networks or molecular structures, to classify nodes, entire graphs, or predict molecular properties. You provide your graph datasets, and the tool outputs enhanced data representations that lead to more accurate predictions for tasks like identifying communities in a social network, categorizing different types of chemical compounds, or forecasting how a drug might interact with the body.
579 stars. No commits in the last 6 months.
Use this if you need to extract meaningful insights and improve prediction accuracy from your graph-structured data for classification or property prediction tasks.
Not ideal if you are looking for a simple, off-the-shelf solution without any programming or machine learning experience, as it requires familiarity with Python and deep learning frameworks.
Stars
579
Forks
80
Language
Python
License
—
Category
Last pushed
Apr 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/THUDM/GraphMAE"
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.