Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Liang, Wei, Gengchen, Yang, Chen, Zhang, Shengzhong, Huang, Zengfeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910842888388608
author Yan, Liang
Wei, Gengchen
Yang, Chen
Zhang, Shengzhong
Huang, Zengfeng
author_facet Yan, Liang
Wei, Gengchen
Yang, Chen
Zhang, Shengzhong
Huang, Zengfeng
contents This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our approach integrates imbalanced node classification and Bias-Variance Decomposition, establishing a theoretical framework that closely relates data imbalance to model variance. We also leverage graph augmentation technique to estimate the variance, and design a regularization term to alleviate the impact of imbalance. Exhaustive tests are conducted on multiple benchmarks, including naturally imbalanced datasets and public-split class-imbalanced datasets, demonstrating that our approach outperforms state-of-the-art methods in various imbalanced scenarios. This work provides a novel theoretical perspective for addressing the problem of imbalanced node classification in GNNs.
format Preprint
id arxiv_https___arxiv_org_abs_2310_18765
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
Yan, Liang
Wei, Gengchen
Yang, Chen
Zhang, Shengzhong
Huang, Zengfeng
Machine Learning
This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our approach integrates imbalanced node classification and Bias-Variance Decomposition, establishing a theoretical framework that closely relates data imbalance to model variance. We also leverage graph augmentation technique to estimate the variance, and design a regularization term to alleviate the impact of imbalance. Exhaustive tests are conducted on multiple benchmarks, including naturally imbalanced datasets and public-split class-imbalanced datasets, demonstrating that our approach outperforms state-of-the-art methods in various imbalanced scenarios. This work provides a novel theoretical perspective for addressing the problem of imbalanced node classification in GNNs.
title Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
topic Machine Learning
url https://arxiv.org/abs/2310.18765