Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract)

Yao Cheng; Minjie Chen; Caihua Shan; Xiang Li

doi:10.1109/ICDE65448.2025.00396

Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract)

Yao Cheng
, Minjie Chen
, Caihua Shan
, Xiang Li

数据科学与工程学院

East China Normal University
Microsoft USA

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Graphs are ubiquitous in the real world, in graphs, nodes represent entities and edges capture their relationships. Recently, graph neural networks (GNNs) [3]-[6] have been proposed to integrate these two sources of information. In GNNs, a node's embedding is learned by aggregating messages from its neighbors.

源语言	英语
主期刊名	Proceedings - 2025 IEEE 41st International Conference on Data Engineering, ICDE 2025
出版商	IEEE Computer Society
页	4734-4735
页数	2
ISBN（电子版）	9798331536039
DOI	https://doi.org/10.1109/ICDE65448.2025.00396
出版状态	已出版 - 2025
活动	41st IEEE International Conference on Data Engineering, ICDE 2025 - Hong Kong, 中国期限: 19 5月 2025 → 23 5月 2025

丛书

姓名	Proceedings - International Conference on Data Engineering
ISSN（印刷版）	1084-4627
ISSN（电子版）	2375-0286

会议

会议	41st IEEE International Conference on Data Engineering, ICDE 2025
国家/地区	中国
市	Hong Kong
时期	19/05/25 → 23/05/25

访问文件

10.1109/ICDE65448.2025.00396

其它文件与链接

链接到 Scopus 的出版物

引用此

Cheng, Y., Chen, M., Shan, C., & Li, X. (2025). Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract). 在 Proceedings - 2025 IEEE 41st International Conference on Data Engineering, ICDE 2025 (页码 4734-4735). (Proceedings - International Conference on Data Engineering). IEEE Computer Society. https://doi.org/10.1109/ICDE65448.2025.00396

@inproceedings{04648782762742e997a6a432465c688d,

title = "Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract)",

abstract = "Graphs are ubiquitous in the real world, in graphs, nodes represent entities and edges capture their relationships. Recently, graph neural networks (GNNs) [3]-[6] have been proposed to integrate these two sources of information. In GNNs, a node's embedding is learned by aggregating messages from its neighbors.",

keywords = "classification, graph heterophily, graph neural networks, representation learning",

author = "Yao Cheng and Minjie Chen and Caihua Shan and Xiang Li",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 41st IEEE International Conference on Data Engineering, ICDE 2025 ; Conference date: 19-05-2025 Through 23-05-2025",

year = "2025",

doi = "10.1109/ICDE65448.2025.00396",

language = "英语",

series = "Proceedings - International Conference on Data Engineering",

publisher = "IEEE Computer Society",

pages = "4734--4735",

booktitle = "Proceedings - 2025 IEEE 41st International Conference on Data Engineering, ICDE 2025",

address = "美国",

}

Cheng, Y, Chen, M, Shan, C & Li, X 2025, Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract). 在 Proceedings - 2025 IEEE 41st International Conference on Data Engineering, ICDE 2025. Proceedings - International Conference on Data Engineering, IEEE Computer Society, 页码 4734-4735, 41st IEEE International Conference on Data Engineering, ICDE 2025, Hong Kong, 中国, 19/05/25. https://doi.org/10.1109/ICDE65448.2025.00396

Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract). / Cheng, Yao; Chen, Minjie; Shan, Caihua 等.
Proceedings - 2025 IEEE 41st International Conference on Data Engineering, ICDE 2025. IEEE Computer Society, 2025. 页码 4734-4735 (Proceedings - International Conference on Data Engineering).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract)

AU - Cheng, Yao

AU - Chen, Minjie

AU - Shan, Caihua

AU - Li, Xiang

PY - 2025

Y1 - 2025

N2 - Graphs are ubiquitous in the real world, in graphs, nodes represent entities and edges capture their relationships. Recently, graph neural networks (GNNs) [3]-[6] have been proposed to integrate these two sources of information. In GNNs, a node's embedding is learned by aggregating messages from its neighbors.

AB - Graphs are ubiquitous in the real world, in graphs, nodes represent entities and edges capture their relationships. Recently, graph neural networks (GNNs) [3]-[6] have been proposed to integrate these two sources of information. In GNNs, a node's embedding is learned by aggregating messages from its neighbors.

KW - classification

KW - graph heterophily

KW - graph neural networks

KW - representation learning

UR - https://www.scopus.com/pages/publications/105015424390

U2 - 10.1109/ICDE65448.2025.00396

DO - 10.1109/ICDE65448.2025.00396

M3 - 会议稿件

AN - SCOPUS:105015424390

T3 - Proceedings - International Conference on Data Engineering

SP - 4734

EP - 4735

BT - Proceedings - 2025 IEEE 41st International Conference on Data Engineering, ICDE 2025

PB - IEEE Computer Society

T2 - 41st IEEE International Conference on Data Engineering, ICDE 2025

Y2 - 19 May 2025 through 23 May 2025

ER -

Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract)

摘要

丛书

会议

访问文件

其它文件与链接

学术指纹

引用此