arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.03522cs.LGcs.NEcs.SIphysics.soc-phstat.ML
收藏

TF-GNN:TensorFlow 中的图神经网络

TF-GNN: Graph Neural Networks in TensorFlow

Google Core ML(谷歌核心机器学习部);Google Research(谷歌研究院);DeepMind(深度思维);EPFL(洛桑联邦理工学院)
Oleksandr Ferludin, Arno Eigenwillig, Martin Blais, Dustin Zelle, Jan Pfeifer, Alvaro Sanchez-Gonzalez, Wai Lok Sibon Li, Sami Abu-El-Haija, Peter Battaglia, Ne… 展开作者

Oleksandr Ferludin, Arno Eigenwillig, Martin Blais, Dustin Zelle, Jan Pfeifer, Alvaro Sanchez-Gonzalez, Wai Lok Sibon Li, Sami Abu-El-Haija, Peter Battaglia, Neslihan Bulut, Jonathan Halcrow, Filipe Miguel Gonçalves de Almeida, Pedro Gonnet, Liangze Jiang, Parth Kothari, Silvio Lattanzi, André Linhares, Brandon Mayer, Vahab Mirrokni, John Palowitch, Mihir Paradkar, Jennifer She, Anton Tsitsulin, Kevin Villela, Lisa Wang, David Wong, Bryan Perozzi

AI总结:

论文介绍开源可扩展库 TF-GNN,说明其异构图数据模型、Keras 消息传递 API、图采样与分布式训练能力,以支持 TensorFlow 图学习研究和生产应用。

摘要:

TensorFlow-GNN(TF-GNN)是一个面向 TensorFlow 的可扩展图神经网络库。它从底层开始设计,以支持当今信息生态系统中出现的各类丰富异构图数据。除了为机器学习研究人员和高级开发者提供支持外,TF-GNN 还提供低代码解决方案,以帮助更广泛的开发者群体进行图学习。Google 的许多生产模型都在使用 TF-GNN,该库最近已作为开源项目发布。本文介绍了 TF-GNN 的数据模型、其 Keras 消息传递 API,以及图采样和分布式训练等相关能力。

英文摘要:

TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that occurs in today's information ecosystems. In addition to enabling machine learning researchers and advanced developers, TF-GNN offers low-code solutions to empower the broader developer community in graph learning. Many production models at Google use TF-GNN, and it has been recently released as an open source project. In this paper we describe the TF-GNN data model, its Keras message passing API, and relevant capabilities such as graph sampling and distributed training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑