JuliaGraphs/GraphNeuralNetworks.jl
Graph Neural Networks in Julia
This project provides building blocks for creating machine learning models that understand relationships within connected data. It takes in structured graph data (like social networks or molecular structures) and outputs models capable of making predictions or classifications based on how entities are connected. Data scientists and machine learning engineers who use Julia will find this useful for complex graph-based analysis.
293 stars.
Use this if you are a Julia user looking to build deep learning models that process information structured as graphs, such as for node classification, link prediction, or whole-graph property prediction.
Not ideal if you are not working with graph-structured data or prefer to use other programming languages or deep learning frameworks outside of Julia, Flux, or Lux.
Stars
293
Forks
63
Language
Julia
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JuliaGraphs/GraphNeuralNetworks.jl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
lmcinnes/umap
Uniform Manifold Approximation and Projection
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE