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
  • [1] A novel graph oversampling framework for node classification in class-imbalanced graphs
    Xia, Riting
    Zhang, Chunxu
    Zhang, Yan
    Liu, Xueyan
    Yang, Bo
    SCIENCE CHINA-INFORMATION SCIENCES, 2024, 67 (06)
  • [2] A novel graph oversampling framework for node classification in class-imbalanced graphs
    Riting XIA
    Chunxu ZHANG
    Yan ZHANG
    Xueyan LIU
    Bo YANG
    Science China(Information Sciences), 2024, 67 (06) : 214 - 229
  • [3] A Hybrid Framework for Class-Imbalanced Classification
    Chen, Rui
    Luo, Lailong
    Chen, Yingwen
    Xia, Junxu
    Guo, Deke
    WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS, WASA 2021, PT I, 2021, 12937 : 301 - 313
  • [4] TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification
    Song, Jaeyun
    Park, Joonhyung
    Yang, Eunho
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [5] A graph neural network-based node classification model on class-imbalanced graph data
    Huang, Zhenhua
    Tang, Yinhao
    Chen, Yunwen
    KNOWLEDGE-BASED SYSTEMS, 2022, 244
  • [6] Deeply-supervised pseudo learning with small class-imbalanced samples for hyperspectral image classification
    Luo, Weiran
    Zhang, Chengcai
    Li, Ying
    Yang, Feng
    Zhang, Dongying
    Hong, Zhiming
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2022, 112
  • [7] GraphMixup: Improving Class-Imbalanced Node Classification by Reinforcement Mixup and Self-supervised Context Prediction
    Wu, Lirong
    Xia, Jun
    Gao, Zhangyang
    Lin, Haitao
    Tan, Cheng
    Li, Stan Z.
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT IV, 2023, 13716 : 519 - 535
  • [8] Subclass-based Undersampling for Class-imbalanced Image Classification
    Lehmann, Daniel
    Ebner, Marc
    PROCEEDINGS OF THE 17TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISAPP), VOL 5, 2022, : 493 - 500
  • [9] Improving the Performance of an Associative Classifier in the Context of Class-Imbalanced Classification
    Rolon-Gonzalez, Carlos Alberto
    Castanon-Mendez, Rodrigo
    Alarcon-Paredes, Antonio
    Lopez-Yanez, Itzama
    Yanez-Marquez, Cornelio
    ELECTRONICS, 2021, 10 (09)
  • [10] Class-Imbalanced Graph Convolution Smoothing for Hyperspectral Image Classification
    Ding, Yun
    Chong, Yanwen
    Pan, Shaoming
    Zheng, Chun-Hou
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 18