TF-GNN: Graph Neural Networks in TensorFlow

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 develop...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Ferludin, Oleksandr, Eigenwillig, Arno, Blais, Martin, Zelle, Dustin, Pfeifer, Jan, Sanchez-Gonzalez, Alvaro, Wai Lok Sibon Li, Abu-El-Haija, Sami, Battaglia, Peter, Bulut, Neslihan, Halcrow, Jonathan, Filipe Miguel Gonçalves de Almeida, Gonnet, Pedro, Jiang, Liangze, Kothari, Parth, Lattanzi, Silvio, Linhares, André, Mayer, Brandon, Mirrokni, Vahab, Palowitch, John, Paradkar, Mihir, She, Jennifer, Tsitsulin, Anton, Villela, Kevin, Wang, Lisa, Wong, David, Perozzi, Bryan
Format: Article
Language:English
Subjects:
Environment models
Graph neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422