Label-Specific Feature Augmentation for Long-Tailed Multi-Label Text Classification

被引:0
|
作者
Xu, Pengyu [1 ]
Xiao, Lin [1 ]
Liu, Bing [1 ]
Lu, Sijin [1 ]
Jing, Liping [1 ]
Yu, Jian [1 ]
机构
[1] Beijing Jiaotong Univ, Beijing Key Lab Traff Data Anal & Min, Beijing, Peoples R China
来源
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 9 | 2023年
基金
北京市自然科学基金; 中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multi-label text classification (MLTC) involves tagging a document with its most relevant subset of labels from a label set. In real applications, labels usually follow a long-tailed distribution, where most labels (called as tail-label) only contain a small number of documents and limit the performance of MLTC. To facilitate this low-resource problem, researchers introduced a simple but effective strategy, data augmentation (DA). However, most existing DA approaches struggle in multi-label settings. The main reason is that the augmented documents for one label may inevitably influence the other co-occurring labels and further exaggerate the long-tailed problem. To mitigate this issue, we propose a new pair-level augmentation framework for MLTC, called Label-Specific Feature Augmentation (LSFA), which merely augments positive feature-label pairs for the tail-labels. LSFA contains two main parts. The first is for label-specific document representation learning in the high-level latent space, the second is for augmenting tail-label features in latent space by transferring the documents second-order statistics (intra-class semantic variations) from head-labels to tail-labels. At last, we design a new loss function for adjusting classifiers based on augmented datasets. The whole learning procedure can be effectively trained. Comprehensive experiments on benchmark datasets have shown that the proposed LSFA outperforms the state-of-the-art counterparts.
引用
收藏
页码:10602 / 10610
页数:9
相关论文
共 50 条
  • [11] Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution
    Huang, Yi
    Giledereli, Buse
    Koksal, Abdullatif
    Ozgur, Arzucan
    Ozkirimli, Elif
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 8153 - 8161
  • [12] Multi-label learning with label-specific feature reduction
    Xu, Suping
    Yang, Xibei
    Yu, Hualong
    Yu, Dong-Jun
    Yang, Jingyu
    Tsang, Eric C. C.
    KNOWLEDGE-BASED SYSTEMS, 2016, 104 : 52 - 61
  • [13] Multi-label Learning with Label-Specific Feature Selection
    Yan, Yan
    Li, Shining
    Yang, Zhe
    Zhang, Xiao
    Li, Jing
    Wang, Anyi
    Zhang, Jingyu
    NEURAL INFORMATION PROCESSING, ICONIP 2017, PT I, 2017, 10634 : 305 - 315
  • [14] Label-Specific Dual Graph Neural Network for Multi-Label Text Classification
    Ma, Qianwen
    Yuan, Chunyuan
    Zhou, Wei
    Hu, Songlin
    59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (ACL-IJCNLP 2021), VOL 1, 2021, : 3855 - 3864
  • [15] Triple Alliance Prototype Orthotist Network for Long-Tailed Multi-Label Text Classification
    Xiao, Lin
    Xu, Pengyu
    Song, Mingyang
    Liu, Huafeng
    Jing, Liping
    Zhang, Xiangliang
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2023, 31 : 2616 - 2628
  • [16] Multi-label Learning Based On Label-specific Feature Extraction
    Nie, Ting
    2018 9TH IEEE INTERNATIONAL CONFERENCE ON BIG KNOWLEDGE (ICBK), 2018, : 298 - 305
  • [17] LSPCL: Label-specific supervised prototype contrastive learning for multi-label text classification
    Wang, Gang
    Du, Yajun
    Jiang, Yurui
    KNOWLEDGE-BASED SYSTEMS, 2025, 309
  • [18] End-to-End Probabilistic Label-Specific Feature Learning for Multi-Label Classification
    Hang, Jun-Yi
    Zhang, Min-Ling
    Feng, Yanghe
    Song, Xiaocheng
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 6847 - 6855
  • [19] A Multi-Label Classification Algorithm Based on Label-Specific Features
    QU Huaqiao1
    2.Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education
    WuhanUniversityJournalofNaturalSciences, 2011, 16 (06) : 520 - 524
  • [20] Partial multi-label learning via label-specific feature corrections
    JunYi HANG
    MinLing ZHANG
    Science China(Information Sciences), 2025, 68 (03) : 95 - 109