CodeJeNN auto-generates self-contained C++ code from trained Keras models, delivering 2–38× faster inference than Keras backends and enabling neural-network surrogates inside CFD solvers.
Graph Neural Networks in TensorFlow and Keras with Spektral
1 Pith paper cite this work, alongside 62 external citations. Polarity classification is still indexing.
1
Pith paper citing it
62
external citations · Pith
abstract
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.
fields
physics.comp-ph 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CodeJeNN: A simple C++ neural network generator for physics applications
CodeJeNN auto-generates self-contained C++ code from trained Keras models, delivering 2–38× faster inference than Keras backends and enabling neural-network surrogates inside CFD solvers.