Graph Neural Networks in Modern Recommender Systems

Yunfei Chu; Jiangchao Yao; Chang Zhou; Hongxia Yang

doi:10.1007/978-981-16-6054-2_19

Graph Neural Networks in Modern Recommender Systems

Yunfei Chu
, Jiangchao Yao
, Chang Zhou
, Hongxia Yang

Research output: Chapter in book / Conference proceeding › Chapter in an edited book (as author) › Academic research › peer-review

11 Citations (Scopus)

Abstract

Graph is an expressive and powerful data structure that is widely applicable, due to its flexibility and effectiveness in modeling and representing graph structure data. It has been more and more popular in various fields, including biology, finance, transportation, social network, among many others. Recommender system, one of the most successful commercial applications of the artificial intelligence, whose user-item interactions can naturally fit into graph structure data, also receives much attention in applying graph neural networks (GNNs). We first summarize the most recent advancements of GNNs, especially in the recommender systems. Then we share our two case studies, dynamic GNN learning and device-cloud collaborative Learning for GNNs.We finalize with discussions regarding the future directions of GNNs in practice.

Original language	English
Title of host publication	Graph Neural Networks
Subtitle of host publication	Foundations, Frontiers, and Applications
Publisher	Springer Nature
Pages	423-445
Number of pages	23
ISBN (Electronic)	9789811660542
ISBN (Print)	9789811660535
DOIs	https://doi.org/10.1007/978-981-16-6054-2_19
Publication status	Published - Jan 2022
Externally published	Yes

ASJC Scopus subject areas

General Computer Science

More information

10.1007/978-981-16-6054-2_19

Cite this

@inbook{a844f00698614d1fa4cbc4ec807cb9f5,

title = "Graph Neural Networks in Modern Recommender Systems",

abstract = "Graph is an expressive and powerful data structure that is widely applicable, due to its flexibility and effectiveness in modeling and representing graph structure data. It has been more and more popular in various fields, including biology, finance, transportation, social network, among many others. Recommender system, one of the most successful commercial applications of the artificial intelligence, whose user-item interactions can naturally fit into graph structure data, also receives much attention in applying graph neural networks (GNNs). We first summarize the most recent advancements of GNNs, especially in the recommender systems. Then we share our two case studies, dynamic GNN learning and device-cloud collaborative Learning for GNNs.We finalize with discussions regarding the future directions of GNNs in practice.",

author = "Yunfei Chu and Jiangchao Yao and Chang Zhou and Hongxia Yang",

note = "Publisher Copyright: {\textcopyright} The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2022.",

year = "2022",

month = jan,

doi = "10.1007/978-981-16-6054-2\_19",

language = "English",

isbn = "9789811660535",

pages = "423--445",

booktitle = "Graph Neural Networks",

publisher = "Springer Nature",

address = "Switzerland",

}

TY - CHAP

T1 - Graph Neural Networks in Modern Recommender Systems

AU - Chu, Yunfei

AU - Yao, Jiangchao

AU - Zhou, Chang

AU - Yang, Hongxia

N1 - Publisher Copyright: © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2022.

PY - 2022/1

Y1 - 2022/1

N2 - Graph is an expressive and powerful data structure that is widely applicable, due to its flexibility and effectiveness in modeling and representing graph structure data. It has been more and more popular in various fields, including biology, finance, transportation, social network, among many others. Recommender system, one of the most successful commercial applications of the artificial intelligence, whose user-item interactions can naturally fit into graph structure data, also receives much attention in applying graph neural networks (GNNs). We first summarize the most recent advancements of GNNs, especially in the recommender systems. Then we share our two case studies, dynamic GNN learning and device-cloud collaborative Learning for GNNs.We finalize with discussions regarding the future directions of GNNs in practice.

AB - Graph is an expressive and powerful data structure that is widely applicable, due to its flexibility and effectiveness in modeling and representing graph structure data. It has been more and more popular in various fields, including biology, finance, transportation, social network, among many others. Recommender system, one of the most successful commercial applications of the artificial intelligence, whose user-item interactions can naturally fit into graph structure data, also receives much attention in applying graph neural networks (GNNs). We first summarize the most recent advancements of GNNs, especially in the recommender systems. Then we share our two case studies, dynamic GNN learning and device-cloud collaborative Learning for GNNs.We finalize with discussions regarding the future directions of GNNs in practice.

UR - https://www.scopus.com/pages/publications/85136728394

U2 - 10.1007/978-981-16-6054-2_19

DO - 10.1007/978-981-16-6054-2_19

M3 - Chapter in an edited book (as author)

AN - SCOPUS:85136728394

SN - 9789811660535

SP - 423

EP - 445

BT - Graph Neural Networks

PB - Springer Nature

ER -

Graph Neural Networks in Modern Recommender Systems

Abstract

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this