Graph neural networks in TensorFlow-Keras with RaggedTensor representation (kgcnn)
Patrick Reiser, André Eberhard, Pascal Friederich · Software Impacts · 2021
Graph neural networks are a versatile machine learning architecture that received a lot of attention recently due to its wide range of applications. In this technical report, we present an implementation of graph convolution and graph 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. We developed the Keras Graph Convolutional Neural Network Python package kgcnn based on TensorFlow-Keras which focus on a transparent tensor structure passed between layers and an ease-of-use mindset.