Implementing graph neural networks with TensorFlow-Keras

Abstract

Graph neural networks are a versatile machine learning architecture that received a lot of attention recently. In this technical report, we present an implementation of convolution and pooling layers for TensorFlow-Keras models, which allows a seamless and flexible integration into standard Keras layers to set up graph models in a functional way. This implies the usage of mini-batches as the first tensor dimension, which can be realized via the new RaggedTensor class of TensorFlow best suited for graphs. We developed the Keras Graph Convolutional Neural Network Python package kgcnn based on TensorFlow-Keras that provides a set of Keras layers for graph networks which focus on a transparent tensor structure passed between layers and an ease-of-use mindset.

References in corpus (29)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• TensorFlow: A system for large-scale machine learning
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Spectral Networks and Locally Connected Networks on Graphs
• SchNet - a deep learning architecture for molecules and materials
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Fast Graph Representation Learning with PyTorch Geometric
• Variational Graph Auto-Encoders
• Hierarchical Graph Representation Learning with Differentiable Pooling
• Learning Convolutional Neural Networks for Graphs
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Learning Deep Generative Models of Graphs
• Self-Attention Graph Pooling
• Representation Learning on Graphs: Methods and Applications
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules
• Blocks and Fuel: Frameworks for deep learning
• Edge Contraction Pooling for Graph Neural Networks
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Graph Neural Networks in TensorFlow and Keras with Spektral
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
• Analyzing dynamical disorder for charge transport in organic semiconductors via machine learning
• iPool -- Information-based Pooling in Hierarchical Graph Neural Networks
• Stochastic Graph Recurrent Neural Network

Cited by in corpus (4)

• JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
• DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
• MEGAN: Multi-Explanation Graph Attention Network
• Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies