PyTorch Geometric provides graph neural network tools and libraries for PyTorch projects.
Open source
24 alternativesSpektral
Spektral provides a Python framework for creating graph neural networks with Keras and TensorFlow.
About Spektral
Spektral is an open-source Python framework for building graph neural networks (GNNs) using the Keras API and TensorFlow 2. It is designed for tasks such as social network user classification, molecular property prediction, graph generation, node clustering, and link prediction.
The library includes a wide range of pre-implemented GNN layers (including GCN, GAT, GraphSAGE, GIN, and others) and pooling layers, plus utilities for graph representation, manipulation, and transformation. It is compatible with Python 3.6 and above, and is tested on the latest versions of Ubuntu, macOS, and Windows, with other Linux distributions expected to work.
Key features
- Implements common GNN layers: GCN, GAT, GraphSAGE, GIN, ECC, APPNP
- Provides pooling layers: MinCut, DiffPool, Top-K, SAG, SortPool, global pooling
- Includes utilities for graph representation, manipulation, and transformation
- Offers GeneralConv and GeneralGNN classes for simplified model building
- Supports Keras model.fit training via built-in Loader class
- Compatible with Python 3.6+ and tested on Ubuntu, macOS, Windows
Best for: Developers and researchers working on graph deep learning tasks who prefer Keras and TensorFlow workflows.
Good for
- Open-source and available for free under the MIT license
- Built on the familiar Keras API for TensorFlow 2 users
- Includes a wide range of pre-built GNN layers and utilities
Watch out for
- Version 1.0 introduced a breaking change to the datasets API for existing users
- Only supports Python 3.6 and higher, with no support for older versions
- Official testing is limited to latest Ubuntu, macOS, and Windows; other Linux distros are not officially supported
Spektral 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 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Spektral alternatives
Tools and sites you could use instead, ranked by how closely they match.
This repository provides segmentation models with pretrained backbones for Keras and TensorFlow Keras.
Open source
24 alternatives
modAL provides a modular active learning framework for Python built on top of scikit-learn.
Open source
24 alternatives
Little Ball of Fur provides graph sampling extensions for NetworKit and NetworkX.
Open source
24 alternatives
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Open source
24 alternatives
Adala automates data labeling through an autonomous agent framework for organizing labeled datasets.
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
Spektral FAQ
What graph deep learning tasks can Spektral be used for?
It supports tasks including social network user classification, molecular property prediction, graph generation, node clustering, and link prediction.
What graph neural network layers are included in Spektral?
It includes layers such as GCN, GAT, GraphSAGE, GIN, ECC, APPNP, and pooling layers including MinCut, DiffPool, and SortPool.
How can Spektral be installed?
It can be installed via pip with 'pip install spektral', or from source by cloning the GitHub repository and running the setup command.
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.