PKU-DAIR/SGL
A scalable graph learning toolkit for extremely large graph datasets. (WWW'22, 🏆 Best Student Paper Award)
This toolkit helps data scientists and researchers analyze extremely large graph datasets efficiently. It takes in massive graph data, automatically selects optimized graph neural network architectures, and outputs classifications, clusters, or predictions for nodes and links. It's designed for machine learning practitioners working with interconnected data at scale.
157 stars. No commits in the last 6 months.
Use this if you need to perform machine learning tasks like node classification or link prediction on graphs with billions of nodes and edges.
Not ideal if your graph datasets are small or if you prefer to manually design and tune every aspect of your graph neural network architecture.
Stars
157
Forks
24
Language
Python
License
MIT
Category
Last pushed
May 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PKU-DAIR/SGL"
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.