Work

GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia

Year: 2024

Type: preprint

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}.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2412.06354

Authors: Lucibello, Carlo, Rossi, Aurora

Institutions: Bocconi University, COATI: Combinatoire, Optimisation et Algorithmes pour les Télécommunications

Language: English

Topic: Advanced Graph Neural Networks

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: European Commission, Agence Nationale de la Recherche

Awards: G1190173965, G1622702131, G1788406657, G2659019386, UCA Systèmes Numériques pour l'Homme, G6803667113, G7047759782, G972786147

OpenAlex ID: W4405254102

Cites:

Cited by: 1

Related to: 10