Scalable Graph Neural Networks with Deep Graph Library

Da Zheng, Minjie Wang, Quan Gan, Zheng Zhang, Geroge Karypis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Learning from graph and relational data plays a major role in many applications including social network analysis, marketing, e-commerce, information retrieval, knowledge modeling, medical and biological sciences, engineering, and others. In the last few years, Graph Neural Networks (GNNs) have emerged as a promising new supervised learning framework capable of bringing the power of deep representation learning to graph and relational data. This ever-growing body of research has shown that GNNs achieve state-of-the-art performance for problems such as link prediction, fraud detection, target-ligand binding activity prediction, knowledge-graph completion, and product recommendations. In practice, many of the real-world graphs are very large. It is urgent to have scalable solutions to train GNN on large graphs efficiently. The objective of this tutorial is twofold. First, it will provide an overview of the theory behind GNNs, discuss the types of problems that GNNs are well suited for, and introduce some of the most widely used GNN model architectures and problems/applications that are designed to solve. Second, it will introduce the Deep Graph Library (DGL), a scalable GNN framework that simplifies the development of efficient GNN-based training and inference programs at a large scale. To make things concrete, the tutorial will cover state-of-the-art training methods to scale GNN to large graphs and provide hands-on sessions to show how to use DGL to perform scalable training in different settings (multi-GPU training and distributed training). This hands-on part will start with basic graph applications (e.g., node classification and link prediction) to set up the context and move on to train GNNs on large graphs. It will provide tutorials to demonstrate how to apply the techniques in DGL to train GNNs for real-world applications.

Original languageEnglish (US)
Title of host publicationKDD 2020 - Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages3521-3522
Number of pages2
ISBN (Electronic)9781450379984
DOIs
StatePublished - Aug 23 2020
Externally publishedYes
Event26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020 - Virtual, Online, United States
Duration: Aug 23 2020Aug 27 2020

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2020
Country/TerritoryUnited States
CityVirtual, Online
Period8/23/208/27/20

Bibliographical note

Publisher Copyright:
© 2020 Owner/Author.

Keywords

  • deep graph library
  • graph neural networks
  • scalability

Fingerprint

Dive into the research topics of 'Scalable Graph Neural Networks with Deep Graph Library'. Together they form a unique fingerprint.

Cite this