Imbalanced graph learning via mixed entropy minimization

Abstract Imbalanced datasets, where the minority class is underrepresented, pose significant challenges for node classification in graph learning. Traditional methods often address this issue through synthetic oversampling techniques for the minority class, which can complicate the training process....

Full description

Bibliographic Details

Published in:	Scientific Reports
Main Authors:	Liwen Xu, Huaguang Zhu, Jiali Chen
Format:	Article
Language:	English
Published:	Nature Portfolio 2024-10-01
Subjects:	Imbalanced node classification Mixed entropy minimization (ME) Graph learning
Online Access:	https://doi.org/10.1038/s41598-024-75999-6