南京大学学报（自然科学版）2024，Vol.60Issue(5)：785-792,8.DOI:10.13232/j.cnki.jnju.2024.05.009
基于对抗数据增强的非平衡节点分类算法
Adversarial data augmentation algorithm for imbalanced node classification
摘要
Abstract
Graph Neural Networks(GNNs)have achieved notable success in node classification tasks.However,current GNN models tend to focus on majority classes with a large amount of labeled data,paying little attention to minority classes with fewer labels.Traditional methods often address this issue through oversampling,which may lead to overfitting.Some recent studies suggest synthesizing additional nodes for minority classes from labeled nodes,yet there's no clear guarantee that these generated nodes truly represent the corresponding minority classes.In fact,incorrect synthetic nodes may undermine the generalization ability of the algorithm.To address this issue,this paper introduces a simple,self-supervised data augmentation method based on adversarial training,Graph A 2,which enhances the data by adding perturbations at the farthest gradient space around minority classes while using contrastive learning to ensure consistency after augmentation.This approach not only increases the diversity of data but also ensures smoothness and coherence across the entire space,thereby enhancing generalization capability.The experiments show that this method outperforms the current state-of-the-art baseline models on various imbalanced datasets.关键词
图神经网络/节点分类/非平衡数据/过采样/对抗数据增强Key words
graph neural networks/node classification/imbalance data/oversampling/adversarial data augmentation分类
信息技术与安全科学引用本文复制引用
程凤伟,王文剑,史颖,张珍珍..基于对抗数据增强的非平衡节点分类算法[J].南京大学学报（自然科学版）,2024,60(5):785-792,8.基金项目
国家自然科学基金(U21A20513,62076154),山西省重点研发计划(202202020101003),山西省高等学校科技创新项目(2024L382) （U21A20513,62076154）
