[1]查思明,鲍庆森,骆健,等.自适应标记关联与实例关联诱导的缺失多视图弱标记学习[J].智能系统学报,2022,17(4):670-679.[doi:10.11992/tis.202106017]
ZHA Siming,BAO Qingsen,LUO Jian,et al.Adaptive label correlation and instance correlation guided incomplete multiview weak label learning[J].CAAI Transactions on Intelligent Systems,2022,17(4):670-679.[doi:10.11992/tis.202106017]
点击复制
ZHA Siming,BAO Qingsen,LUO Jian,et al.Adaptive label correlation and instance correlation guided incomplete multiview weak label learning[J].CAAI Transactions on Intelligent Systems,2022,17(4):670-679.[doi:10.11992/tis.202106017]
自适应标记关联与实例关联诱导的缺失多视图弱标记学习
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
17
期数:
2022年第4期
页码:
670-679
栏目:
学术论文—机器学习
出版日期:
2022-07-05
- Title:
- Adaptive label correlation and instance correlation guided incomplete multiview weak label learning
- Keywords:
- multi-view learning; multi-label learning; graph learning; manifold regularization; weakly supervised learning; matrix factorization; missing labels; missing views
- 分类号:
- TP181
- 摘要:
- 针对多视图多标记学习中视图不完整和标记不完整问题，提出一种自适应标记关联与实例关联诱导的缺失多视图弱标记学习模型。模型假设样本各视图特征基于一个共享表示，通过不同映射得到。首先通过嵌入指示矩阵进行矩阵分解，充分利用已有的不完整多视图弱标记数据，然后引入图论中学习标准拉普拉斯矩阵的技术来刻画标记关联关系、实例关联关系，从而在模型里嵌入流形正则化思想，使学到的潜在共享表示以及分类器更加合理，最后在4个多视图多标记数据集上实验。实验结果表明，所提方法能够有效解决不完整多视图弱标记学习问题。
- Abstract:
- Focusing on the problem of incomplete view and label in multiview multilabel learning, the paper proposes a model called adaptive label correlation and instance correlation guided incomplete multiview weak label learning. The model assumes each view of the instance is obtained from a common representation through different mappings. Firstly, matrix factorization is used by embedding the indicator matrix to make full use of the existing incomplete multiview weak label data and then introduces the technology of learning the standard Laplacian matrix in graph theory to describe the label correlation and instance correlation. Therefore, embedding manifold regularization in the model to make the learned common representation and classifier more reasonable. Finally, four multiview multilabel datasets were conducted in a series of experiments. The experimental results show that the proposed model can solve the task of incomplete multiview weak label learning effectively.
- 参考文献/References:
-
[1] ZHOU Tianyi, TAO Dacheng, WU Xindong. Compressed labeling on distilled labelsets for multi-label learning[J]. Machine learning, 2012, 88(1/2): 69–126.
[2] XU Linli, WANG Zhen, SHEN Zefan, et al. Learning low-rank label correlations for multi-label classification with missing labels[C]//2014 IEEE International Conference on Data Mining. Shenzhen: IEEE, 2014: 1067?1072.
[3] ZHU Yue, KWOK J T, ZHOU Zhihua. Multi-label learning with global and local label correlation[J]. IEEE transactions on knowledge and data engineering, 2018, 30(6): 1081–1094.
[4] ZHANG Minling, ZHOU Zhihua. A review on multi-label learning algorithms[J]. IEEE transactions on knowledge and data engineering, 2014, 26(8): 1819–1837.
[5] BOUTELL M R, LUO Jiebo, SHEN Xipeng, et al. Learning multi-label scene classification[J]. Pattern recognition, 2004, 37(9): 1757–1771.
[6] FüRNKRANZ J, HüLLERMEIER E, LOZA MENCíA E, et al. Multilabel classification via calibrated label ranking[J]. Machine learning, 2008, 73(2): 133–153.
[7] TSOUMAKAS G, VLAHAVAS I. Random k-labelsets: an ensemble method for multilabel classification[M]//Machine Learning: ECML 2007. Heidelberg: Springer Berlin Heidelberg, 2007: 406?417.
[8] ZHANG Jia, LUO Zhiming, LI Candong, et al. Manifold regularized discriminative feature selection for multi-label learning[J]. Pattern recognition, 2019, 95: 136–150.
[9] ZHANG Changqing, YU Ziwei, FU Huazhu, et al. Hybrid noise-oriented multilabel learning[J]. IEEE transactions on cybernetics, 2020, 50(6): 2837–2850.
[10] SUN Yuyin, ZHANG Yin, ZHI Zhihua. Multi-label learning with weak label[C]//Proceedings of the 24th AAAI Conference on Artificial Intelligence. Georgia: AAAI Press, 2010: 593?598.
[11] LI Junbing, ZHANG Changqing, ZHU Pengfei, et al. SPL-MLL: selecting predictable landmarks for multi-label learning[C]//European Conference on Computer Vision. Cham: Springer, 2020: 783?799.
[12] ZHANG Minling, ZHOU Zhihua. ML-KNN: a lazy learning approach to multi-label learning[J]. Pattern recognition, 2007, 40(7): 2038–2048.
[13] CLARE A, KING R D. Knowledge discovery in multi-label phenotype data[M]//Principles of Data Mining and Knowledge Discovery. Heidelberg: Springer Berlin Heidelberg, 2001: 42?53.
[14] GHAMRAWI N, MCCALLUM A. Collective multi-label classification[C]//CIKM ’05: Proceedings of the 14th ACM international conference on Information and knowledge management. New York: ACM, 2005: 195?200.
[15] ZHANG Changqing, YU Ziwei, HU Qinghua, et al. Latent semantic aware multi-view multi-label Classification[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Louisiana: AAAI Press, 2018: 2703?2709.
[16] LIU Meng, LUO Yong, TAO Dacheng, et al. Low-rank multi-view learning in matrix completion for multi-label image classification[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence. Texas: AAAI Press, 2015: 2278?2284.
[17] ZHANG Yongshan, WU Jia, CAI Zhihua, et al. Multi-view multi-label learning with sparse feature selection for image annotation[J]. IEEE transactions on multimedia, 2020, 22(11): 2844–2857.
[18] TAN Qiaoyu, YU Guoxian, DOMENICONI C, et al. Incomplete multi-view weak-label learning[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden. California: International Joint Conferences on Artificial Intelligence Organization, 2018: 2703?2709.
[19] ZHANG Changqing, CUI Yajie, HAN Zongbo, et al. Deep partial multi-view learning[J]. IEEE transactions on pattern analysis and machine intelligence, 2022, 44(5): 2402–2415.
[20] 张祎, 孔祥维, 王振帆, 等. 基于多视图矩阵分解的聚类分析[J]. 自动化学报, 2018, 44(12): 2160–2169
ZHANG Yi, KONG Xiangwei, WANG Zhenfan, et al. Matrix factorization for multi-view clustering[J]. Acta automatica sinica, 2018, 44(12): 2160–2169
[21] 孙亮, 韩毓璇, 康文婧, 等. 基于生成对抗网络的多视图学习与重构算法[J]. 自动化学报, 2018, 44(5): 819–828
SUN Liang, HAN Yuxuan, KANG Wenjing, et al. Multi-view learning and reconstruction algorithm via generative adversarial networks[J]. Acta automatica sinica, 2018, 44(5): 819–828
[22] XU Chang, TAO Dacheng, XU Chao. Multi-view learning with incomplete views[J]. IEEE transactions on image processing:a publication of the IEEE signal processing society, 2015, 24(12): 5812–5825.
[23] DATTA R, JOSHI D, LI Jia, et al. Image retrieval: ideas, influences, and trends of the new age[J]. ACM computing surveys, 2008, 40(2): 5.
[24] DONG Haochen, LI Yufeng, ZHOU Zhihua. Learning from semi-supervised weak-label data[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Stockholm: International Joint Conferences on Artificial Intelligence Organization, 2018, 32(1).
[25] LUO Dijun, DING C, HUANG Heng, et al. Non-negative Laplacian embedding[C]//2009 Ninth IEEE International Conference on Data Mining. Miami Beach: IEEE, 2009: 337?346.
[26] WANG Hua, HUANG Heng, DING C. Image annotation using multi-label correlated Green’s function[C]//2009 IEEE 12th International Conference on Computer Vision. Kyoto: IEEE, 2009: 2029?2034.
[27] CHUNG F R K, GRAHAM F C. Spectral graph theory [M]//Rhode Island: American Mathematic Society, 1997.
[28] 杨明, 刘先忠. 矩阵论[M]. 武汉: 华中工学院出版社, 2003.
[29] BOUMAL N, MISHRA B, ABSIL P A, et al. Manopt, a Matlab toolbox for optimization on manifolds[J]. Journal of machine learning research, 2014, 15: 1455–1459.
- 相似文献/References:
-
[1]刘杨磊,梁吉业,高嘉伟,等.基于Tri-training的半监督多标记学习算法[J].智能系统学报,2013,8(5):439.[doi:10.3969/j.issn.1673-4785.201305033]
LIU Yanglei,LIANG Jiye,GAO Jiawei,et al.Semi-supervised multi-label learning algorithm based on Tri-training[J].CAAI Transactions on Intelligent Systems,2013,8():439.[doi:10.3969/j.issn.1673-4785.201305033]
[2]杨文元.多标记学习自编码网络无监督维数约简[J].智能系统学报,2018,13(5):808.[doi:10.11992/tis.201804051]
YANG Wenyuan.Unsupervised dimensionality reduction of multi-label learning via autoencoder networks[J].CAAI Transactions on Intelligent Systems,2018,13():808.[doi:10.11992/tis.201804051]
[3]余鹰,王乐为,吴新念,等.基于改进卷积神经网络的多标记分类算法[J].智能系统学报,2019,14(3):566.[doi:10.11992/tis.201804056]
YU Ying,WANG Lewei,WU Xinnian,et al.A multi-label classification algorithm based on an improved convolutional neural network[J].CAAI Transactions on Intelligent Systems,2019,14():566.[doi:10.11992/tis.201804056]
[4]王一宾,裴根生,程玉胜.弹性网络核极限学习机的多标记学习算法[J].智能系统学报,2019,14(4):831.[doi:10.11992/tis.201806005]
WANG Yibin,PEI Gensheng,CHENG Yusheng.Multi-label learning algorithm of an elastic net kernel extreme learning machine[J].CAAI Transactions on Intelligent Systems,2019,14():831.[doi:10.11992/tis.201806005]
[5]黄琴,钱文彬,王映龙,等.代价敏感数据的多标记特征选择算法[J].智能系统学报,2019,14(5):929.[doi:10.11992/tis.201807027]
HUANG Qin,QIAN Wenbin,WANG Yinglong,et al.Multi-label feature selection algorithm for cost-sensitive data[J].CAAI Transactions on Intelligent Systems,2019,14():929.[doi:10.11992/tis.201807027]
[6]秦天,滕齐发,贾修一.结合局部标记序关系的弱监督标记分布学习[J].智能系统学报,2023,18(1):47.[doi:10.11992/tis.202204018]
QIN Tian,TENG Qifa,JIA Xiuyi.Weakly supervised label distribution learning by maintaining local label ranking[J].CAAI Transactions on Intelligent Systems,2023,18():47.[doi:10.11992/tis.202204018]
[7]胡军,王海峰.基于加权信息粒化的多标记数据特征选择算法[J].智能系统学报,2023,18(3):619.[doi:10.11992/tis.202111058]
HU Jun,WANG Haifeng.Feature selection algorithm of multi-labeled data based on weighted information granulation[J].CAAI Transactions on Intelligent Systems,2023,18():619.[doi:10.11992/tis.202111058]
备注/Memo
收稿日期:2021-06-15。
基金项目:国家自然科学基金项目（61872190）.
作者简介:查思明，硕士研究生，主要研究方向为机器学习;鲍庆森，硕士研究生，主要研究方向为机器学习;陈蕾，教授，博士生导师，中国计算机学会高级会员，主要研究方向为机器学习、模式识别、医学图像分析。申请发明专利20余项，授权8项，发表学术论文40余篇
通讯作者:陈蕾. E-mail：chenlei@njupt.edu.cn
更新日期/Last Update:
1900-01-01