mlsanityData to 7 Oct 2026

Graph Neural Networks in TensorFlow and Keras with Spektral

arXiv 2006.12138 ↗First posted 22 Jun 2020cs.LG stat.MLcited by 59

Not on the map. Why?

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.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 19; 2022: 19; 2023: 8; 2024: 11; 2025: 1; 2026: 1.

59 papers.

Sort:

  1. 2021PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Modelscited by 118
  2. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  3. 2021Understanding Pooling in Graph Neural Networkscited by 69
  4. 2021A Survey on Embedding Dynamic Graphscited by 60
  5. 2022TorchDrug: A Powerful and Flexible Machine Learning Platform for Drug Discoverycited by 45
  6. 2021Automated Machine Learning on Graphs: A Surveycited by 38
  7. 2022Distributed Graph Neural Network Training: A Surveycited by 32
  8. 2021The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphscited by 19
  9. 2022PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphscited by 18
  10. 2021Efficient Graph Deep Learning in TensorFlow with tf_geometriccited by 17
  11. 2021Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structurecited by 15
  12. 2022Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Surveycited by 14
38 more
  1. 2021PyTorch-Direct: Enabling GPU Centric Data Access for Very Large Graph Neural Network Training with Irregular Accessescited by 12
  2. 2021CogDL: A Comprehensive Library for Graph Deep Learningcited by 12
  3. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  4. 2022ChemicalX: A Deep Learning Library for Drug Pair Scoringcited by 11
  5. 2022Reduced Optimal Power Flow Using Graph Neural Networkcited by 11
  6. 2021GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Softwarecited by 8
  7. 2021Graph Neural Network Training with Data Tieringcited by 8
  8. 2022Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directionscited by 8
  9. 2023Deep graphical regression for jointly moderate and extreme Australian wildfirescited by 8
  10. 2021GRAPE for Fast and Scalable Graph Processing and random walk-based Embeddingcited by 7
  11. 2022Total Variation Graph Neural Networkscited by 7
  12. 2021IGNNITION: Bridging the Gap Between Graph Neural Networks and Networking Systemscited by 6
  13. 2022GCNET: graph-based prediction of stock price movement using graph convolutional networkcited by 6
  14. 2022Graph Neural Networks to Predict Sports Outcomescited by 6
  15. 2022Deep learning methods for drug response prediction in cancer: predominant and emerging trendscited by 6
  16. 2023Spatio-Temporal Deep Learning-Assisted Reduced Security-Constrained Unit Commitmentcited by 6
  17. 2023Graph Kalman Filterscited by 5
  18. 2025Geometry-Aware Edge Pooling for Graph Neural Networkscited by 5
  19. 2023PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Networkcited by 4
  20. 2021Implementing graph neural networks with TensorFlow-Kerascited by 3
  21. 2021Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagerycited by 3
  22. 2024N-1 Reduced Optimal Power Flow Using Augmented Hierarchical Graph Neural Networkcited by 3
  23. 2024Time Series Foundation Models and Deep Learning Architectures for Earthquake Temporal and Spatial Nowcastingcited by 3
  24. 2022Scalable Deep Gaussian Markov Random Fields for General Graphscited by 2
  25. 2024SST-GCN: The Sequential based Spatio-Temporal Graph Convolutional networks for Minute-level and Road-level Traffic Accident Risk Predictioncited by 2
  26. 2021Graph Attention Networks for Channel Estimation in RIS-assisted Satellite IoT Communicationscited by 1
  27. 2022MolGraph: a Python package for the implementation of molecular graphs and graph neural networks with TensorFlow and Kerascited by 1
  28. 2022Improving Operational Efficiency In EV Ridepooling Fleets By Predictive Exploitation of Idle Timescited by 1
  29. 2022NETpred: Network-based modeling and prediction of multiple connected market indicescited by 1
  30. 2023Classification of vertices on social networks by multiple approachescited by 1
  31. 2024Uncertainty Quantification of Graph Convolution Neural Network Models of Evolving Processescited by 1
  32. 2024Image2Flow: A hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI datacited by 1
  33. 2024VLSI Hypergraph Partitioning with Deep Learningcited by 1
  34. 2024Graph Neural Network-Accelerated Network-Reconfigured Optimal Power Flowcited by 1
  35. 2021Predicting Mergers and Acquisitions using Graph-based Deep Learningcited by 0
  36. 2021pygrank: A Python Package for Graph Node Rankingcited by 0
  37. 2022A Method to Predict Semantic Relations on Artificial Intelligence Paperscited by 0
  38. 2022Partition Pooling for Convolutional Graph Network Applications in Particle Physicscited by 0

50 most cited of 59 All 59 (JSON)