用Julia打造的图神经网络框架，支持多GPU和复杂图结构。
GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia
- 基于Julia实现，支持稀疏/稠密图表示与多GPU加速。
- 提供标准、异构、时序图的便捷操作接口。
- 可自定义卷积层，适合研究复杂图模型的开发者。
GraphNeuralNetworks.jl 是一个用 Julia 编写的开源图深度学习框架，支持多种 GPU 后端，兼容通用的稀疏或稠密图表示，并提供对节点、边和图层级属性的标准、异构及时间图的便捷操作接口。用户可通过收集/散射消息传递原语或优化的融合操作自定义图卷积层，同时内置多个流行层，支持高效构建复杂深度架构。该包已开源，可在 GitHub 获取： https://github.com/JuliaGraphs/GraphNeuralNetworks.jl。
原文摘要 · Abstract (English)
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}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。