Spektral provides a Python framework for creating graph neural networks with Keras and TensorFlow.
Open source
24 alternativesPyTorch Geometric
PyTorch Geometric provides graph neural network tools and libraries for PyTorch projects.
About PyTorch Geometric
PyTorch Geometric is an open-source library built on PyTorch for writing and training Graph Neural Networks for structured data. It provides methods for deep learning on graphs and other irregular structures based on published papers.
It includes mini-batch loaders for many small graphs or a single large graph, multi-GPU, torch.compile and DataPipe support, benchmark datasets with interfaces to create custom datasets, and transforms for graphs, 3D meshes and point clouds. It also supports scalable graphs with millions of nodes, dynamic graphs for node prediction over time, and heterogeneous graphs with multiple node and edge types.
Key features
- Build and train GNNs on graphs and irregular structured data with PyTorch
- Pre-implemented GNN layers such as GCNConv based on published papers
- Message passing API with operators for custom models and extensions
- Mini-batch loaders for many small graphs or single large graphs
- Multi-GPU, torch.compile and DataPipe support for training workflows
- Transforms for arbitrary graphs, 3D meshes and point clouds
Best for: PyTorch users who need to build graph neural networks for structured data research or applications.
Good for
- Tensor-centric API that follows vanilla PyTorch design principles
- Includes implementations of many published GNN methods and models
- Supports scalable, dynamic and heterogeneous graph use cases
PyTorch Geometric at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
PyTorch Geometric alternatives
Tools and sites you could use instead, ranked by how closely they match.
pytorch tabular provides a unified framework for deep learning models on tabular data.
Open source
24 alternatives
This repository implements YOLOv3 variants in PyTorch for real time object detection, training, validation, inference, and export.
Open source
24 alternatives
Captum explains model behavior and supports interpretability analysis for PyTorch systems.
Open source
24 alternatives
PyTorch Frame provides a library for applying deep learning models to tabular data.
Open source
24 alternatives
GPyTorch provides an efficient implementation of Gaussian processes using PyTorch.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
PyTorch Geometric FAQ
What types of graphs and structures does PyG support?
Arbitrary graphs, 3D meshes and point clouds, including scalable graphs with millions of nodes, dynamic graphs for node prediction over time, and heterogeneous graphs with multiple node and edge types.
Can I use standard PyTorch workflows with PyG?
Yes. PyG uses a tensor-centric API close to vanilla PyTorch and models can be optimized in a standard PyTorch training loop.
What data utilities are included?
Mini-batch loaders for small and single giant graphs, benchmark datasets with interfaces to create custom datasets, and transforms for graphs, meshes and point clouds.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.