An Adaptive Active Learning Method for Multiclass Imbalanced Data Streams with Concept Drift

被引:0
|
作者
Han, Meng [1 ]
Li, Chunpeng [1 ]
Meng, Fanxing [1 ]
He, Feifei [1 ]
Zhang, Ruihua [1 ]
机构
[1] North Minzu Univ, Sch Comp Sci & Engn, Yinchuan 750021, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 16期
关键词
data stream classification; multiclass imbalance; concept drift; ensemble learning; active learning; CLASSIFICATION;
D O I
10.3390/app14167176
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Learning from multiclass imbalanced data streams with concept drift and variable class imbalance ratios under a limited label budget presents new challenges in the field of data mining. To address these challenges, this paper proposes an adaptive active learning method for multiclass imbalanced data streams with concept drift (AdaAL-MID). Firstly, a dynamic label budget strategy under concept drift scenarios is introduced, which allocates label budgets reasonably at different stages of the data stream to effectively handle concept drift. Secondly, an uncertainty-based label request strategy using a dual-margin dynamic threshold matrix is designed to enhance learning opportunities for minority class instances and those that are challenging to classify, and combined with a random strategy, it can estimate the current class imbalance distribution by accessing only a limited number of instance labels. Finally, an instance-adaptive sampling strategy is proposed, which comprehensively considers the imbalance ratio and classification difficulty of instances, and combined with a weighted ensemble strategy, improves the classification performance of the ensemble classifier in imbalanced data streams. Extensive experiments and analyses demonstrate that AdaAL-MID can handle various complex concept drifts and adapt to changes in class imbalance ratios, and it outperforms several state-of-the-art active learning algorithms.
引用
收藏
页数:32
相关论文
共 50 条
  • [31] Reinforcement Online Active Learning Ensemble for Drifting Imbalanced Data Streams
    Zhang, Hang
    Liu, Weike
    Liu, Qingbao
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2022, 34 (08) : 3971 - 3983
  • [32] A comprehensive ensemble classification techniques detecting and managing concept drift in dynamic imbalanced data streams
    Junaid, K. A. Mohamed
    Paulraj, D.
    Sethukarasi, T.
    WIRELESS NETWORKS, 2025, 31 (01) : 19 - 30
  • [33] Classification of concept drift data streams
    Padmalatha, E.
    Reddy, C. R. K.
    Rani, B. Padmaja
    2014 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND APPLICATIONS (ICISA), 2014,
  • [34] An Augmented Learning Approach for Multiple Data Streams Under Concept Drift
    Wang, Kun
    Lu, Jie
    Liu, Anjin
    Zhang, Guangquan
    ADVANCES IN ARTIFICIAL INTELLIGENCE, AI 2023, PT I, 2024, 14471 : 391 - 402
  • [35] Dynamic Classification Ensembles for Handling Imbalanced Multiclass Drifted Data Streams
    Madkour A.H.
    Abdelkader H.M.
    Mohammed A.M.
    Information Sciences, 2024, 670
  • [36] Concept-drift-adaptive anomaly detector for marine sensor data streams
    Nguyen, Ngoc-Thanh
    Heldal, Rogardt
    Pelliccione, Patrizio
    INTERNET OF THINGS, 2024, 28
  • [37] Fast Adaptive Real-Time Classification for Data Streams with Concept Drift
    Tennant, Mark
    Stahl, Frederic
    Gomes, Joao Bartolo
    INTERNET AND DISTRIBUTED COMPUTING SYSTEMS, IDCS 2015, 2015, 9258 : 265 - 272
  • [38] Online Adaptive Asymmetric Active Learning for Budgeted Imbalanced Data
    Zhang, Yifan
    Zhao, Peilin
    Cao, Jiezhang
    Ma, Wenye
    Huang, Junzhou
    Wu, Qingyao
    Tan, Mingkui
    KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 2768 - 2777
  • [39] An Ensemble Classifier Method for Classifying Data Streams with Recurrent Concept Drift
    Wei, Guiying
    Zhang, Tao
    Wu, Sen
    Zou, Lei
    4TH INTERNATIONAL CONFERENCE ON AWARENESS SCIENCE AND TECHNOLOGY (ICAST 2012), 2012, : 3 - 9
  • [40] SDDM: an interpretable statistical concept drift detection method for data streams
    Simona Micevska
    Ahmed Awad
    Sherif Sakr
    Journal of Intelligent Information Systems, 2021, 56 : 459 - 484