alexOarga/haiku-geometric
A collection of graph neural networks implementations in JAX
This project provides pre-built modules for various graph neural networks, allowing machine learning researchers and practitioners to easily experiment with and apply these models. It takes graph-structured data as input and produces outputs like node embeddings or graph-level predictions, which can be used for tasks such as classifying molecules or recommending connections. Data scientists, machine learning engineers, and AI researchers working with connected data will find this useful.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning practitioner experimenting with or implementing graph neural networks in JAX and Haiku.
Not ideal if you are looking for a production-ready solution, as this project is still under active development.
Stars
35
Forks
1
Language
Python
License
—
Category
Last pushed
Nov 28, 2023
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alexOarga/haiku-geometric"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/