divelab/DIG
A library for graph deep learning research
This library provides a comprehensive platform for researchers working with graph deep learning. It helps you explore advanced tasks like generating new graphs, self-supervised learning on graph data, and explaining Graph Neural Network predictions. Researchers can input various graph datasets and implement or benchmark different algorithms within a unified framework, producing insights and comparisons for their studies. This is for machine learning researchers and scientists focusing on novel methods and evaluations in graph-structured data.
2,002 stars. No commits in the last 6 months.
Use this if you are a researcher developing new graph deep learning methods or comparing existing ones for tasks such as graph generation, self-supervised learning, or explainability.
Not ideal if you are a practitioner looking for an out-of-the-box solution to apply standard graph algorithms to business problems without engaging in research and development.
Stars
2,002
Forks
293
Language
Python
License
GPL-3.0
Category
Last pushed
Jul 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/divelab/DIG"
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.