AnoushkaVyas/GraphZoo
Facilitating learning, using, and designing graph processing pipelines/models systematically.
This tool helps machine learning researchers systematically design and evaluate graph processing models. You can input various graph datasets and model configurations, then benchmark new hyperbolic or Euclidean graph networks against existing methods. It's designed for researchers who want to reproduce state-of-the-art results or explore novel graph neural network architectures.
No commits in the last 6 months. Available on PyPI.
Use this if you are a researcher focused on developing and testing graph neural networks, particularly those interested in hyperbolic geometry, and need a structured way to compare models and datasets.
Not ideal if you are looking for a pre-built solution for a specific graph analysis task without needing to design or compare custom graph models.
Stars
27
Forks
7
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AnoushkaVyas/GraphZoo"
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.