GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia

TL;DR

GraphNeuralNetworks.jl is an open-source Julia framework that enables flexible, GPU-accelerated deep learning on various types of graphs, supporting custom layers and complex architectures.

Contribution

It introduces a comprehensive Julia-based framework for deep graph learning with support for multiple graph types, custom layers, and GPU acceleration.

Findings

Supports heterogeneous and temporal graphs

Enables custom message-passing layers

Provides efficient GPU backends

Abstract

GraphNeuralNetworks.jl is an open-source framework for deep learning on graphs, written in the Julia programming language. It supports multiple GPU backends, generic sparse or dense graph representations, and offers convenient interfaces for manipulating standard, heterogeneous, and temporal graphs with attributes at the node, edge, and graph levels. The framework allows users to define custom graph convolutional layers using gather/scatter message-passing primitives or optimized fused operations. It also includes several popular layers, enabling efficient experimentation with complex deep architectures. The package is available on GitHub: \url{https://github.com/JuliaGraphs/GraphNeuralNetworks.jl}.