TristanBilot/mlx-GCN

MLX implementation of GCN, with benchmark on MPS, CUDA and CPU (M1 Pro, M2 Ultra, M3 Max).

33
/ 100
Emerging

This project provides an example implementation of a Graph Convolutional Network (GCN) using the MLX framework, primarily for those working with Apple Silicon. It allows you to train and test a GCN model on a standard dataset, with inputs being graph-structured data and outputs being classified nodes or predictions based on the graph's connections. Researchers and machine learning engineers developing or experimenting with graph neural networks on Apple hardware would find this useful.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher developing graph neural networks and want to see an efficient GCN implementation on Apple Silicon devices (M1 Pro, M2 Ultra, M3 Max) using the MLX framework.

Not ideal if you are looking for a production-ready GCN library for general use cases or if you are not interested in benchmarking performance across different hardware backends.

graph-neural-networks machine-learning-research model-benchmarking apple-silicon-optimization graph-data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

25

Forks

3

Language

Python

License

MIT

Last pushed

Dec 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TristanBilot/mlx-GCN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.