logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Generalizable federated graph contrastive learning

delete2026-03-14
delete0
PRE
AI
Q
Qingyong Wang
DOI：10.1016/j.eswa.2026.131910delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A generalizable federated graph contrastive learning for unlabeled and noisy graphs is proposed. • Clients transmit only embedding clusters for secure collaboration. • A pretrained model denoises and sharpens class centroids to enhance alignment. • Extensive experiments demonstrate consistent gains over strong baselines.

Journal

Expert Systems with Applications cover
Expert Systems with Applications
IF:
7.5
Papers:
3.0W
Citations:
10.2W

Organization

A
Anhui Agricultural University
Scholars:
1.2W
Papers: 5.7K
Citations: 1.0W
H
Henan University of Science and Technology
Scholars:
2.9K
Papers: 814
Citations: 1.0K
Cited Papers

Cited Papers

No cited papers available