kepsail/SHGP
NeurIPS 2022 - SHGP
This project helps machine learning researchers and data scientists working with complex, interconnected datasets. It takes a heterogeneous graph (a network with different types of nodes and relationships) and automatically learns meaningful representations of its structure. The output is a pre-trained model that can improve the performance of downstream tasks like node classification or link prediction.
No commits in the last 6 months.
Use this if you are a machine learning researcher or data scientist developing models for heterogeneous graph data and want to leverage self-supervised pre-training to improve model performance.
Not ideal if you are looking for a simple, out-of-the-box solution for basic graph analysis or do not have experience with deep learning frameworks like PyTorch.
Stars
32
Forks
2
Language
Python
License
—
Category
Last pushed
Jul 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kepsail/SHGP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE