BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Qian, Liu, Zemin, Zhang, Zhen, He, Bingsheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929249132216320
author Wang, Qian
Liu, Zemin
Zhang, Zhen
He, Bingsheng
author_facet Wang, Qian
Liu, Zemin
Zhang, Zhen
He, Bingsheng
contents Class imbalance in graph-structured data, where minor classes are significantly underrepresented, poses a critical challenge for Graph Neural Networks (GNNs). To address this challenge, existing studies generally generate new minority nodes and edges connecting new nodes to the original graph to make classes balanced. However, they do not solve the problem that majority classes still propagate information to minority nodes by edges in the original graph which introduces bias towards majority classes. To address this, we introduce BuffGraph, which inserts buffer nodes into the graph, modulating the impact of majority classes to improve minor class representation. Our extensive experiments across diverse real-world datasets empirically demonstrate that BuffGraph outperforms existing baseline methods in class-imbalanced node classification in both natural settings and imbalanced settings. Code is available at https://anonymous.4open.science/r/BuffGraph-730A.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13114
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes
Wang, Qian
Liu, Zemin
Zhang, Zhen
He, Bingsheng
Machine Learning
Artificial Intelligence
Class imbalance in graph-structured data, where minor classes are significantly underrepresented, poses a critical challenge for Graph Neural Networks (GNNs). To address this challenge, existing studies generally generate new minority nodes and edges connecting new nodes to the original graph to make classes balanced. However, they do not solve the problem that majority classes still propagate information to minority nodes by edges in the original graph which introduces bias towards majority classes. To address this, we introduce BuffGraph, which inserts buffer nodes into the graph, modulating the impact of majority classes to improve minor class representation. Our extensive experiments across diverse real-world datasets empirically demonstrate that BuffGraph outperforms existing baseline methods in class-imbalanced node classification in both natural settings and imbalanced settings. Code is available at https://anonymous.4open.science/r/BuffGraph-730A.
title BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2402.13114