Spektral is a Python library for graph deep learning, based on the Keras API and TensorFlow 2. The main goal of this project is to provide a simple but flexible framework for creating graph neural networks (GNNs).
You can use Spektral for classifying the nodes of a network, predicting molecular properties, generating new graphs with GANs, clustering nodes, predicting links, and any other task where data is described by graphs.
Spektral implements some of the most popular layers for graph deep learning, including:
and many others (see convolutional layers).
You can also find pooling layers, including:
Spektral also includes lots of utilities for your graph deep learning projects.
The source code of the project is available on Github.
Read the documentation here.
You can also cite the paper introducing Spektral: Graph Neural Networks in TensorFlow and Keras with Spektral (ICML 2020 - GRL+ Workshop).
Spektral is compatible with Python 3.5+, and is tested on Ubuntu 16.04+ and MacOS. Other Linux distros should work as well, but Windows is not supported for now.
Some optional features of Spektral depend on RDKit, a library for cheminformatics and molecule manipulation (available through Anaconda).
The simplest way to install Spektral is from PyPi:
pip install spektral
To install Spektral from source, run this in a terminal:
git clone https://github.com/danielegrattarola/spektral.git cd spektral python setup.py install # Or 'pip install .'
To install Spektral on Google Colab:
! pip install spektral
Starting from version 0.3, Spektral only supports TensorFlow 2 and
The old version of Spektral, which is based on TensorFlow 1 and the stand-alone Keras library, is still available on the
tf1 branch on GitHub and can be installed from source:
git clone https://github.com/danielegrattarola/spektral.git cd spektral git checkout tf1 python setup.py install # Or 'pip install .'
In the future, the TF1-compatible version of Spektral (<0.2) will receive bug fixes, but all new features will only support TensorFlow 2.
Spektral is an open source project available on Github, and contributions of all types are welcome. Feel free to open a pull request if you have something interesting that you want to add to the framework.