Coupling importance sampling neural network for imbalanced data classification with multi-level learning bias

被引:0
作者
Huang, Zhan ao [1 ]
Xiao, Wei [1 ]
Yang, Zhipeng [2 ]
Li, Xiaojie [1 ]
Wu, Xi [1 ]
机构
[1] Chengdu Univ Informat Technol, Sch Comp Sci, Chengdu 610225, Peoples R China
[2] Chengdu Univ Informat Technol, Coll Elect Engn, Chengdu 610225, Peoples R China
基金
中国国家自然科学基金;
关键词
Neural network; Imbalanced data classification; Multi-level learning bias; Coupling importance sampling;
D O I
10.1016/j.neucom.2025.129427
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Imbalanced data classification is a classic challenge in neural network learning. Current rebalancing methods for neural networks mainly rely on resampling and reweighting to alleviate the learning bias caused by imbalanced data learning. It is difficult to properly balance the learning and resampling and rarely dives into the problem of multi-level learning bias. In this paper, we propose a coupling importance sampling to couple the resampling and neural networks learning, while handling both class-level and cluster-level learning biases that occur between and within classes, respectively. Specifically, in the coupling of resampling and learning, as for the class-level learning bias, we extend the resampling from sample to cluster. A composite importance factor is developed to sample important clusters to balance samples between classes. Here, a distribution preservation strategy is additionally maintained to reduce the loss of important samples from resampled clusters. Regarding cluster-level learning bias, a learning regulatory factor is designed to highlight the importance of sampled clusters and avoid the recurrence of imbalance within classes. The proposed method is validated on 34 imbalanced datasets with imbalance ratios ranging from 16.90 to 100.14. The tested results show promising classification performance and prove the advantages of considering the multi-level learning bias in imbalanced data classification.
引用
收藏
页数:12
相关论文
共 32 条
  • [21] Integrating reference point, Kuhn–Tucker conditions and neural network approach for multi-objective and multi-level programming problems
    Rizk-Allah R.M.
    Abo-Sinna M.A.
    OPSEARCH, 2017, 54 (4) : 663 - 683
  • [22] Weighting class importance in agricultural crop classification from remotely sensed data with an artificial neural network
    Foody, GM
    BIOMETRICAL JOURNAL, 1996, 38 (02) : 181 - 193
  • [23] Learning label-specific features via neural network for multi-label classification
    Ling Jia
    Dong Sun
    Yu Shi
    Yi Tan
    Qingwei Gao
    Yixiang Lu
    International Journal of Machine Learning and Cybernetics, 2023, 14 : 1161 - 1177
  • [24] Learning label-specific features via neural network for multi-label classification
    Jia, Ling
    Sun, Dong
    Shi, Yu
    Tan, Yi
    Gao, Qingwei
    Lu, Yixiang
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2023, 14 (04) : 1161 - 1177
  • [25] Data Fusion for Heart Diseases Classification Using Multi-Layer Feed Forward Neural Network
    Obayya, Marwa
    Abou-Chadi, Fatma
    ICCES: 2008 INTERNATIONAL CONFERENCE ON COMPUTER ENGINEERING & SYSTEMS, 2007, : 67 - 70
  • [26] A novel model of estimating sea state bias based on multi-layer neural network and multi-source altimeter data
    Miao, Hongli
    Guo, Yingting
    Zhong, Guoqiang
    Liu, Benxiu
    Wang, Guizhong
    EUROPEAN JOURNAL OF REMOTE SENSING, 2018, 51 (01) : 616 - 626
  • [27] Multi-category Bangla News Classification using Machine Learning Classifiers and Multi-layer Dense Neural Network
    Yeasmin, Sharmin
    Kuri, Ratnadip
    Rana, A. R. M. Mahamudul Hasan
    Uddin, Ashraf
    Pathan, A. Q. M. Sala Uddin
    Riaz, Hasnat
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2021, 12 (05) : 757 - 767
  • [28] M2GDL: Multi-manifold guided dictionary learning based oversampling and data validation for highly imbalanced classification problems
    Feizi, Tayyebe
    Moattar, Mohammad Hossein
    Tabatabaee, Hamid
    INFORMATION SCIENCES, 2024, 682
  • [29] A novel unsupervised domain adaptation framework based on graph convolutional network and multi-level feature alignment for inter-subject ECG classification
    He, Ziyang
    Chen, Yufei
    Yuan, Shuaiying
    Zhao, Jianhui
    Yuan, Zhiyong
    Polat, Kemal
    Alhudhaif, Adi
    Alenezi, Fayadh
    Hamid, Arwa
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 221
  • [30] Intrusion detection system employing multi-level feed forward neural network along with firefly optimization (fmlf2n2)
    Sai Rama Krishna K.V.S.
    Prakash B.B.
    Ingenierie des Systemes d'Information, 2019, 24 (02): : 139 - 145