Improving Imbalanced Text Classification with Dynamic Curriculum Learning

被引:2
|
作者
Zhang, Xulong [1 ]
Wang, Jianzong [1 ]
Cheng, Ning [1 ]
Xiao, Jing [1 ]
机构
[1] Ping Technol Shenzhen Co Ltd, Shenzhen, Peoples R China
关键词
efficient curriculum learning; imbalanced text classification; self-paced learning; data augmentation; nuclearnorm;
D O I
10.1109/MSN57253.2022.00167
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Recent advances in pre-trained language models have improved the performance for text classification tasks. However, little attention is paid to the priority scheduling strategy on the samples during training. Humans acquire knowledge gradually from easy to complex concepts, and the difficulty of the same material can also vary significantly in different learning stages. Inspired by this insights, we proposed a novel self-paced dynamic curriculum learning (SPDCL) method for imbalanced text classification, which evaluates the sample difficulty by both linguistic character and model capacity. Meanwhile, rather than using static curriculum learning as in the existing research, our SPDCL can reorder and resample training data by difficulty criterion with an adaptive from easy to hard pace. The extensive experiments on several classification tasks show the effectiveness of SPDCL strategy, especially for the imbalanced dataset.
引用
收藏
页码:1031 / 1036
页数:6
相关论文
共 50 条
  • [1] Dynamic Curriculum Learning for Imbalanced Data Classification
    Wang, Yiru
    Gan, Weihao
    Yang, Jie
    Wu, Wei
    Yan, Junjie
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 5016 - 5025
  • [2] Graph Neural Network with curriculum learning for imbalanced node classification
    Li, Xiaohe
    Fan, Zide
    Huang, Feilong
    Hu, Xuming
    Deng, Yawen
    Wang, Lei
    Zhao, Xinyu
    [J]. NEUROCOMPUTING, 2024, 574
  • [3] Text Generation for Imbalanced Text Classification
    Akkaradamrongrat, Suphamongkol
    Kachamas, Pornpimon
    Sinthupinyo, Sukree
    [J]. 2019 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER SCIENCE AND SOFTWARE ENGINEERING (JCSSE 2019), 2019, : 181 - 186
  • [4] Improving imbalanced scientific text classification using sampling strategies and dictionaries
    Borrajo, L.
    Romero, R.
    Iglesias, E. L.
    Redondo Marey, C. M.
    [J]. JOURNAL OF INTEGRATIVE BIOINFORMATICS, 2011, 8 (03)
  • [5] Imbalanced Classification Algorithm for Semi Supervised Text Learning (iCASSTLE)
    Banerjee, Debanjana
    Prabhat, Gyan
    Bhowal, Riyanka
    [J]. 2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2018, : 1012 - 1016
  • [6] Curriculum learning and evolutionary optimization into deep learning for text classification
    Alfredo Arturo Elías-Miranda
    Daniel Vallejo-Aldana
    Fernando Sánchez-Vega
    A. Pastor López-Monroy
    Alejandro Rosales-Pérez
    Victor Muñiz-Sanchez
    [J]. Neural Computing and Applications, 2023, 35 : 21129 - 21164
  • [7] Curriculum learning and evolutionary optimization into deep learning for text classification
    Elias-Miranda, Alfredo Arturo
    Vallejo-Aldana, Daniel
    Sanchez-Vega, Fernando
    Lopez-Monroy, A. Pastor
    Rosales-Perez, Alejandro
    Muniz-Sanchez, Victor
    [J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (28): : 21129 - 21164
  • [8] Improving the Performance of Sentiment Classification on Imbalanced Datasets With Transfer Learning
    Xiao, Z.
    Wang, L.
    Du, J. Y.
    [J]. IEEE ACCESS, 2019, 7 : 28281 - 28290
  • [9] Utilizing DTRS for Imbalanced Text Classification
    Zhou, Bing
    Yao, Yiyu
    Liu, Qingzhong
    [J]. ROUGH SETS, (IJCRS 2016), 2016, 9920 : 219 - 228
  • [10] Laplacian least learning machine with dynamic updating for imbalanced classification
    Zhou, Jie
    Jiang, Zhibin
    Wang, Shitong
    [J]. APPLIED SOFT COMPUTING, 2020, 88