• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
Advanced Search
Zhang Yong, Chen Rongrong, Zhang Jing. Safe Tri-training Algorithm Based on Cross Entropy[J]. Journal of Computer Research and Development, 2021, 58(1): 60-69. DOI: 10.7544/issn1000-1239.2021.20190838
Citation: Zhang Yong, Chen Rongrong, Zhang Jing. Safe Tri-training Algorithm Based on Cross Entropy[J]. Journal of Computer Research and Development, 2021, 58(1): 60-69. DOI: 10.7544/issn1000-1239.2021.20190838

Safe Tri-training Algorithm Based on Cross Entropy

Funds: This work was supported by the National Natural Science Foundation of China (61772252, 61902165), the Program for Liaoning Innovative Talents in Universities (LR2017044), and the Natural Science Foundation of Liaoning Province (2019-MS-216).
More Information
  • Published Date: December 31, 2020
  • Semi-supervised learning methods improve learning performance with a small amount of labeled data and a large amount of unlabeled data. Tri-training algorithm is a classic semi-supervised learning method based on divergence, which does not need redundant views of datasets and has no specific requirements for basic classifiers. Therefore, it has become the most commonly used technology in semi-supervised learning methods based on divergence. However, Tri-training algorithm may produce the problem of label noise in the learning process, which leads to a bad impact on the final model. In order to reduce the prediction bias of the noise in Tri-training algorithm on the unlabeled data and learn a better semi-supervised classification model, cross entropy is used to replace the error rate to better reflect the gap between the predicted results and the real distribution of the model, and the convex optimization method is combined to reduce the label noise and ensure the effect of the model. On this basis, we propose a Tri-training algorithm based on cross entropy, a safe Tri-training algorithm and a safe Tri-training learning algorithm based on cross entropy, respectively. The validity of the proposed method is verified on the benchmark dataset such as UCI (University of California Irvine) machine learning repository and the performance of the method is further verified from a statistical point of view using a significance test. The experimental results show that the proposed semi-supervised learning method is superior to the traditional Tri-training algorithm in classification performance, and the safe Tri-training algorithm based on cross entropy has higher classification performance and generalization ability.
  • Related Articles

    [1]Zhang Liping, Liu Lei, Hao Xiaohong, Li Song, Hao Zhongxiao. Voronoi-Based Group Reverse k Nearest Neighbor Query in Obstructed Space[J]. Journal of Computer Research and Development, 2017, 54(4): 861-871. DOI: 10.7544/issn1000-1239.2017.20151111
    [2]Zhu Huaijie, Wang Jiaying, Wang Bin, and Yang Xiaochun. Location Privacy Preserving Obstructed Nearest Neighbor Queries[J]. Journal of Computer Research and Development, 2014, 51(1): 115-125.
    [3]Yang Zexue, Hao Zhongxiao. Group Obstacle Nearest Neighbor Query in Spatial Database[J]. Journal of Computer Research and Development, 2013, 50(11): 2455-2462.
    [4]Liu Runtao, Hao Zhongxiao. Fast Algorithm of Nearest Neighbor Query for Line Segments of Spatial Database[J]. Journal of Computer Research and Development, 2011, 48(12): 2379-2384.
    [5]Zhang Xu, He Xiangnan, Jin Cheqing, and Zhou Aoying. Processing k-Nearest Neighbors Query over Uncertain Graphs[J]. Journal of Computer Research and Development, 2011, 48(10): 1871-1878.
    [6]Liao Haojun, Han Jizhong, Fang Jinyun. All-Nearest-Neighbor Queries Processing in Spatial Databases[J]. Journal of Computer Research and Development, 2011, 48(1): 86-93.
    [7]Sun Dongpu, Hao Zhongxiao. Group Nearest Neighbor Queries Based on Voronoi Diagrams[J]. Journal of Computer Research and Development, 2010, 47(7): 1244-1251.
    [8]Sun Dongpu, Hao Zhongxiao. Multi-Type Nearest Neighbor Queries with Partial Range Constrained[J]. Journal of Computer Research and Development, 2009, 46(6): 1036-1042.
    [9]Hao Zhongxiao, Wang Yudong, He Yunbin. Line Segment Nearest Neighbor Query of Spatial Database[J]. Journal of Computer Research and Development, 2008, 45(9): 1539-1545.
    [10]Dong Daoguo, Liu Zhenzhong, and Xue Xiangyang. VA-Trie: A New and Efficient High Dimensional Index Structure for Approximate k Nearest Neighbor Query[J]. Journal of Computer Research and Development, 2005, 42(12): 2213-2218.
  • Cited by

    Periodical cited type(6)

    1. 赵迪,赵祖高,何克勤,聂磊. 混杂条件下的三维点云目标识别. 组合机床与自动化加工技术. 2023(06): 58-62 .
    2. 赵迪,赵祖高,程煜林,聂磊. 多特征关键点的自适应尺度融合特征点云配准. 电子测量技术. 2023(10): 68-75 .
    3. 孙昊. 基于改进随机森林的海量高维数据最近邻检索. 自动化技术与应用. 2022(11): 73-76 .
    4. 孟祥福,王丹丹,张霄雁,贾江浩. Top-k集合空间关键字近似查询方法. 计算机工程与应用. 2022(23): 104-116 .
    5. 宋涛,曹利波,赵明富,刘帅,罗宇航,杨鑫. 三维点云中关键点的配准与优化算法. 激光与光电子学进展. 2021(04): 375-383 .
    6. 孟祥福,王丹丹,张峰. 空间关键字查询综述. 计算机工程与应用. 2021(20): 13-24 .

    Other cited types(10)

Catalog

    Article views (1368) PDF downloads (262) Cited by(16)

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return