# Graph Neural Networks in TensorFlow and Keras with Spektral

arXiv: https://arxiv.org/abs/2006.12138 · HTML: https://mlsanity.com/paper/2006.12138/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 30 of 60)

- [PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models](https://mlsanity.com/paper/2104.07788/) (2021)
- [DIG: A Turnkey Library for Diving into Graph Deep Learning Research](https://mlsanity.com/paper/2103.12608/) (2021)
- [Understanding Pooling in Graph Neural Networks](https://mlsanity.com/paper/2110.05292/) (2021)
- [A Survey on Embedding Dynamic Graphs](https://mlsanity.com/paper/2101.01229/) (2021)
- [TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discovery](https://mlsanity.com/paper/2202.08320/) (2022)
- [Automated Machine Learning on Graphs: A Survey](https://mlsanity.com/paper/2103.00742/) (2021)
- [Distributed Graph Neural Network Training: A Survey](https://mlsanity.com/paper/2211.00216/) (2022)
- [The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs](https://mlsanity.com/paper/2105.05911/) (2021)
- [PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs](https://mlsanity.com/paper/2202.10793/) (2022)
- [Efficient Graph Deep Learning in TensorFlow with tf_geometric](https://mlsanity.com/paper/2101.11552/) (2021)
- [Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure](https://mlsanity.com/paper/2104.11667/) (2021)
- [Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey](https://mlsanity.com/paper/2203.10480/) (2022)
- [PyTorch-Direct: Enabling GPU Centric Data Access for Very Large Graph Neural Network Training with Irregular Accesses](https://mlsanity.com/paper/2101.07956/) (2021)
- [CogDL: A Comprehensive Library for Graph Deep Learning](https://mlsanity.com/paper/2103.00959/) (2021)
- [Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges](https://mlsanity.com/paper/2203.12852/) (2022)
- [ChemicalX: A Deep Learning Library for Drug Pair Scoring](https://mlsanity.com/paper/2202.05240/) (2022)
- [Reduced Optimal Power Flow Using Graph Neural Network](https://mlsanity.com/paper/2206.13591/) (2022)
- [Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions](https://mlsanity.com/paper/2201.01288/) (2022)
- [GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software](https://mlsanity.com/paper/2102.07933/) (2021)
- [Graph Neural Network Training with Data Tiering](https://mlsanity.com/paper/2111.05894/) (2021)
- [Deep graphical regression for jointly moderate and extreme Australian wildfires](https://mlsanity.com/paper/2308.14547/) (2023)
- [GRAPE for Fast and Scalable Graph Processing and random walk-based Embedding](https://mlsanity.com/paper/2110.06196/) (2021)
- [Graph Neural Networks to Predict Sports Outcomes](https://mlsanity.com/paper/2207.14124/) (2022)
- [Total Variation Graph Neural Networks](https://mlsanity.com/paper/2211.06218/) (2022)
- [IGNNITION: Bridging the Gap Between Graph Neural Networks and Networking Systems](https://mlsanity.com/paper/2109.06715/) (2021)
- [GCNET: graph-based prediction of stock price movement using graph convolutional network](https://mlsanity.com/paper/2203.11091/) (2022)
- [Deep learning methods for drug response prediction in cancer: predominant and emerging trends](https://mlsanity.com/paper/2211.10442/) (2022)
- [Spatio-Temporal Deep Learning-Assisted Reduced Security-Constrained Unit Commitment](https://mlsanity.com/paper/2306.01570/) (2023)
- [Graph Kalman Filters](https://mlsanity.com/paper/2303.12021/) (2023)
- [Geometry-Aware Edge Pooling for Graph Neural Networks](https://mlsanity.com/paper/2506.11700/) (2025)

## Abstract (arXiv)

In this paper we present Spektral, an open-source Python library for building graph neural networks with TensorFlow and the Keras application programming interface. Spektral implements a large set of methods for deep learning on graphs, including message-passing and pooling operators, as well as utilities for processing graphs and loading popular benchmark datasets. The purpose of this library is to provide the essential building blocks for creating graph neural networks, focusing on the guiding principles of user-friendliness and quick prototyping on which Keras is based. Spektral is, therefore, suitable for absolute beginners and expert deep learning practitioners alike. In this work, we present an overview of Spektral's features and report the performance of the methods implemented by the library in scenarios of node classification, graph classification, and graph regression.