tensorflow/gnn
TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
This library helps machine learning engineers and researchers build and train Graph Neural Networks (GNNs) using TensorFlow. You can input complex graph data, including graphs with different types of nodes and edges, and output trained GNN models capable of tasks like molecular classification or shortest path prediction. It's designed for those working with structured data that can be represented as graphs.
1,516 stars. Actively maintained with 3 commits in the last 30 days.
Use this if you are a machine learning engineer or researcher building models that analyze relationships within complex, graph-structured data and want to leverage the TensorFlow ecosystem.
Not ideal if you are looking for a plug-and-play solution for simple machine learning tasks that don't involve graph data or if you prefer a different deep learning framework.
Stars
1,516
Forks
198
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 09, 2026
Commits (30d)
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tensorflow/gnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
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.