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
  • [21] A novel classification method for class-imbalanced data and its application in microRNA recognition
    Geng X.
    Zhu Y.-Q.
    Yang Z.
    International Journal Bioautomation, 2018, 22 (02) : 133 - 146
  • [22] Parameter-Free Loss for Class-Imbalanced Deep Learning in Image Classification
    Du, Jie
    Zhou, Yanhong
    Liu, Peng
    Vong, Chi-Man
    Wang, Tianfu
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (06) : 3234 - 3240
  • [23] Polarimetry-Inspired Contrastive Learning for Class-Imbalanced PolSAR Image Classification
    Kuang, Zuzheng
    Bi, Haixia
    Li, Fan
    Xu, Chen
    Sun, Jian
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 19
  • [24] An Empirical Study on Preprocessing High-dimensional Class-imbalanced Data for Classification
    Yin, Hua
    Gai, Keke
    2015 IEEE 17TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS, 2015 IEEE 7TH INTERNATIONAL SYMPOSIUM ON CYBERSPACE SAFETY AND SECURITY, AND 2015 IEEE 12TH INTERNATIONAL CONFERENCE ON EMBEDDED SOFTWARE AND SYSTEMS (ICESS), 2015, : 1314 - 1319
  • [25] Classification method for failure modes of RC columns based on class-imbalanced datasets
    Yu, Bo
    Xie, Longlong
    Yu, Zecheng
    Cheng, Hao
    STRUCTURES, 2023, 48 : 694 - 705
  • [26] CardioCaps: Attention-based Capsule Network for Class-Imbalanced Echocardiogram Classification
    Han, Hyunkyung
    Seong, Jihyeon
    Choi, Jaesik
    2024 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING, IEEE BIGCOMP 2024, 2024, : 287 - 294
  • [27] Margin calibration in SVM class-imbalanced learning
    Yang, Chan-Yun
    Yang, Jr-Syu
    Wang, Jian-Jun
    NEUROCOMPUTING, 2009, 73 (1-3) : 397 - 411
  • [28] Prototypical Classifier for Robust Class-Imbalanced Learning
    Wei, Tong
    Shi, Jiang-Xin
    Li, Yu-Feng
    Zhang, Min-Ling
    ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2022, PT II, 2022, 13281 : 44 - 57
  • [29] Exploring of clustering algorithm on class-imbalanced data
    Li Xuan
    Chen Zhigang
    Yang Fan
    PROCEEDINGS OF THE 2013 8TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE & EDUCATION (ICCSE 2013), 2013, : 89 - 93
  • [30] Class-Imbalanced Voice Pathology Detection and Classification Using Fuzzy Cluster Oversampling Method
    Fan, Ziqi
    Wu, Yuanbo
    Zhou, Changwei
    Zhang, Xiaojun
    Tao, Zhi
    APPLIED SCIENCES-BASEL, 2021, 11 (08):