A Serial Sample Selection Framework for Active Learning

被引:0
|
作者
Li, Chengchao [1 ]
Zhao, Pengpeng [1 ]
Wu, Jian [1 ]
Xu, Haihui [1 ]
Cui, Zhiming [1 ]
机构
[1] Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Peoples R China
关键词
Data Mining; Active Learning; Sampling Strategy; Uncertainty; Representativeness;
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
Active Learning is a machine learning and data mining technique that selects the most informative samples for labeling and uses them as training data. It aims to obtain a high performance classifier by labeling as little data as possible from large amount of unlabeled samples, which means sampling strategy is the core issue. Existing approaches either tend to ignore information in unlabeled data and are prone to querying outliers or noise samples, or calculate large amounts of non-informative samples leading to significant computation cost. In order to solve above problems, this paper proposed a serial active learning framework. It first measures uncertainty of unlabeled samples and selects the most uncertain sample set. From which, it further generates the most representative sample set based on the mutual information criterion. Finally, the framework selects the most informative sample from the most representative sample set based on expected error reduction strategy. Experimental results on multiple datasets show that our approach outperforms Random Sampling and the state of the art adaptive active learning method.
引用
收藏
页码:435 / 446
页数:12
相关论文
共 50 条
  • [21] ACTIVE LEARNING TO OVERCOME SAMPLE SELECTION BIAS: APPLICATION TO PHOTOMETRIC VARIABLE STAR CLASSIFICATION
    Richards, Joseph W.
    Starr, Dan L.
    Brink, Henrik
    Miller, Adam A.
    Bloom, Joshua S.
    Butler, Nathaniel R.
    James, J. Berian
    Long, James P.
    Rice, John
    ASTROPHYSICAL JOURNAL, 2012, 744 (02):
  • [22] Sample Selection Based on Active Learning for Short-Term Wind Speed Prediction
    Yang, Jian
    Zhao, Xin
    Wei, Haikun
    Zhang, Kanjian
    ENERGIES, 2019, 12 (03)
  • [23] Learning in serial mergers: Evidence from a global sample
    Pandey, Vivek K.
    Sutton, Ninon K.
    Steigner, Tanja
    JOURNAL OF BUSINESS FINANCE & ACCOUNTING, 2021, 48 (9-10) : 1747 - 1796
  • [24] Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision
    Kaushal, Vishal
    Iyer, Rishabh
    Kothawade, Suraj
    Mahadev, Rohan
    Doctor, Khoshrav
    Ramakrishnan, Ganesh
    2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 1289 - 1299
  • [25] Online Learning with Sample Selection Bias
    Singhvi, Divya
    Singhvi, Somya
    OPERATIONS RESEARCH, 2025,
  • [26] Training sample selection in learning control
    Cheng, J
    Xu, YS
    Chung, R
    IEEE ROBIO 2004: PROCEEDINGS OF THE IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS, 2004, : 368 - 373
  • [27] Efficient sample selection for safe learning
    Zagorowska, Marta
    Balta, Efe C.
    Behrunani, Varsha
    Rupenyan, Alisa
    Lygeros, John
    IFAC PAPERSONLINE, 2023, 56 (02): : 10107 - 10112
  • [28] MULTIBOX SAMPLE SELECTION FOR ACTIVE OBJECT DETECTION
    Dong, Jiaxiang
    Zhang, Li
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 2447 - 2452
  • [29] Active Learning with Model Selection
    Ali, Alnur
    Caruana, Rich
    Kapoor, Ashish
    PROCEEDINGS OF THE TWENTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2014, : 1673 - 1679
  • [30] Influence Selection for Active Learning
    Liu, Zhuoming
    Ding, Hao
    Zhong, Huaping
    Li, Weijia
    Dai, Jifeng
    He, Conghui
    2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 9254 - 9263