GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification

被引:9
|
作者
Li, Wen-Zhi [1 ]
Wang, Chang-Dong [1 ]
Xiong, Hui [2 ,3 ]
Lai, Jian-Huang [1 ]
机构
[1] Sun Yat Sen Univ, CSE, Guangzhou, Peoples R China
[2] HKUST GZ, AI Thrust, Guangzhou, Peoples R China
[3] HKUST, CSE, Hong Kong, Peoples R China
关键词
node classification; class imbalance; graph neural network; hard sample; data augmentation;
D O I
10.1145/3580305.3599374
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Class imbalance is the phenomenon that some classes have much fewer instances than others, which is ubiquitous in real-world graph-structured scenarios. Recent studies find that off-the-shelf Graph Neural Networks (GNNs) would under-represent minor class samples. We investigate this phenomenon and discover that the subspaces of minor classes being squeezed by those of the major ones in the latent space is the main cause of this failure. We are naturally inspired to enlarge the decision boundaries of minor classes and propose a general framework GraphSHA by Synthesizing HArder minor samples. Furthermore, to avoid the enlarged minor boundary violating the subspaces of neighbor classes, we also propose a module called SemiMixup to transmit enlarged boundary information to the interior of the minor classes while blocking information propagation from minor classes to neighbor classes. Empirically, GraphSHA shows its effectiveness in enlarging the decision boundaries of minor classes, as it outperforms various baseline methods in class-imbalanced node classification with different GNN backbone encoders over seven public benchmark datasets. Code is avilable at https://github.com/wenzhilics/GraphSHA.
引用
收藏
页码:1328 / 1340
页数:13
相关论文
共 50 条
  • [31] SGBGAN: minority class image generation for class-imbalanced datasets
    Wan, Qian
    Guo, Wenhui
    Wang, Yanjiang
    MACHINE VISION AND APPLICATIONS, 2024, 35 (02)
  • [32] Research on classification method of high-dimensional class-imbalanced datasets based on SVM
    Chunkai Zhang
    Ying Zhou
    Jianwei Guo
    Guoquan Wang
    Xuan Wang
    International Journal of Machine Learning and Cybernetics, 2019, 10 : 1765 - 1778
  • [33] Research on classification method of high-dimensional class-imbalanced datasets based on SVM
    Zhang, Chunkai
    Zhou, Ying
    Guo, Jianwei
    Wang, Guoquan
    Wang, Xuan
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2019, 10 (07) : 1765 - 1778
  • [34] Class prediction for high-dimensional class-imbalanced data
    Blagus, Rok
    Lusa, Lara
    BMC BIOINFORMATICS, 2010, 11 : 523
  • [35] Class prediction for high-dimensional class-imbalanced data
    Rok Blagus
    Lara Lusa
    BMC Bioinformatics, 11
  • [36] SGBGAN: minority class image generation for class-imbalanced datasets
    Qian Wan
    Wenhui Guo
    Yanjiang Wang
    Machine Vision and Applications, 2024, 35
  • [37] Auxiliary generative mutual adversarial networks for class-imbalanced fault diagnosis under small samples
    Ranran LI
    Shunming LI
    Kun XU
    Mengjie ZENG
    Xianglian LI
    Jianfeng GU
    Yong CHEN
    Chinese Journal of Aeronautics, 2023, 36 (09) : 464 - 478
  • [38] Regularized Discrete Optimal Transport for Class-Imbalanced Classifications
    Chen, Jiqiang
    Wan, Jie
    Ma, Litao
    MATHEMATICS, 2024, 12 (04)
  • [39] Oversampling adversarial network for class-imbalanced fault diagnosis
    Zareapoor, Masoumeh
    Shamsolmoali, Pourya
    Yang, Jie
    MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2021, 149
  • [40] Rethinking the Value of Labels for Improving Class-Imbalanced Learning
    Yang, Yuzhe
    Xu, Zhi
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33