多标记学习研究综述

doi:10.3969/j.issn.1006-2475.2015.08.010

摘要/Abstract

摘要： 多标记学习不同于传统的监督学习，它是为了解决客观世界中多义性对象的建模问题而提出的一种学习框架。在该框架下，一个示例可以同时隶属于多个标记。经过十多年的发展，机器学习界已经出现了大量关于多标记学习的研究成果，并得到了广泛的应用。本文对多标记学习问题进行系统而详细的阐述，给出多标记学习的问题定义和评价指标，重点介绍多标记学习算法，并提出多标记学习进一步的研究方向。


关键词: 多标记学习, 评价指标, 问题转换, 算法适应, 机器学习, 数据挖掘

Abstract: Multi-label learning is different from the traditional supervised learning. It is a framework which is proposed to represent objects which might have multiple semantic meanings simultaneously in the external world. Under this framework, an instance might be associated with a set of labels. Over the past decades, a lot of research results of multi-label learning have been achieved and gotten extensive application. This paper provides a systematic and detailed review in this area. Firstly, fundamentals on multi-label learning including formal definition and evaluation metrics are given. Secondly, some important and classic multi-label learning algorithms are presented. Finally, some valuable research directions in this area are discussed.


Key words: multi-label learning, evaluation metrics, problem transformation, algorithm adaptation, machine learning, data mining

中图分类号:

TP181

梁伟超,宋斌. 多标记学习研究综述[J]. 计算机与现代化, 2015, 0(8): 48-56.

LIANG Wei-chao， SONG Bin. A Review on Multi-Label Learning[J]. Computer and Modernization, 2015, 0(8): 48-56.

参考文献

［1］ Schapire R E, Singer Y. Boostexter: A boosting-based system for text categorization［J］. Machine Learning, 2000,39(2/3):135-168.
［2］ Ueda N, Saito K. Parametric mixture models for multi-labeled text［C］// Proceedings of the 10th International Conference on Neural Information Processing. 2003:721-728.
［3］ Gao Sheng, Wu Wen, Lee C H, et al. An MFoM learning approach to robust multiclass multi-label text categorization［C］// Proceedings of the 21st International Conference on Machine Learning. 2004:329-336.
［4］ Boutell M R, Luo Jiebo, Shen Xipeng, et al. Learning multi-label scene classification［J］. Pattern Recognition, 2004,37(9):1757-1771.
［5］ Sanden C, Zhang J Z. Enhancing multi-label music genre classification through ensemble techniques［C］// Proceeding of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2011:705-714.
［6］ Wieczorkowska A, Synak P, Ra〖KG-*4〗〖JX-+0.5mm〗〖XCs.tif〗〖JX+0.5mm〗 Z W. Multi-label classification of emotions in music［C］// Proceedings of the 16th International Conference on Intelligent Information Processing and Web Mining. 2006:307-315.
［7］ Wang Mei, Zhou Xiangdong, Chua Tat-Seng. Automatic image annotation via local multi-label classification［C］// Proceedings of the 2008 International Conference on Content-based Image and Video Retrieval. 2008:17-26.
［8］ Kazawa H, Izumitani T, Taira H, et al. Maximal margin labeling for multi-topic text categorization［C］// Proceedings of the Advances in Neural Information Processing Systems 17. 2004:649-656.
［9］ Tang Lei, Rajan S, Narayanan V K. Large scale multi-label classification via metalabeler［C］// Proceedings of the 18th International Conference on World Wide Web. 2009:211-220.
［10］Rak R, Kurgan L, Reformat M. Multi-label associative classification of medical documents from MEDLINE［C］// Proceedings of the 4th International Conference on Machine Learning and Applications. 2005:177-186.
［11］Thabtah F A, Cowling P, Peng Yonghong. MMAC: A new multi-class, multi-label associative classification approach［C］// Proceedings of the 4th IEEE International Conference on Data Mining. 2004:217-224.
［12］Sangsuriyun S, Marukatat S, Waiyamai K. Hierarchical multi-label associative classification(HMAC) using negative rules ［C］// Proceedings of the 9th IEEE International Conference on Cognitive Informatics. 2010:919-924.
［13］Gopal S, Yang Yi-ming. Multilabel classification with meta-level features［C］// Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2010:315-322.
［14］Read J, Puurula A, Bifet A. Multi-label classification with meta-labels［C］// Proceedings of the 14th IEEE International Conference on Data Mining. 2014:941-946.
［15］Zhu Sheng-huo, Ji Xiang, Xu Wei, et al. Multi-labelled classification using maximum entropy method［C］// Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2005:274-281.
［16］Clare A, King R. Knowledge discovery in multi-label phenotype data［C］// Proceedings of the 5th European Conference on Principles of Data Mining and Knowledge Discovery. 2001:42-53.
［17］Zhang Min-ling, Zhou Zhi-hua. Multilabel neural networks with applications to functional genomics and text categorization［J］. IEEE Transactions on Knowledge and Data Engineering, 2006,18(10):1338-1351.
［18］Kordmahalleh M M, Homaifar A, Dukka B K C. Hierarchical multi-label gene function prediction using adaptive mutation in crowding niching ［C］// Proceedings of the 13th International Conference on Bioinformatics and Bioengineering. 2013:1-6.
［19］Fabris F, Freitas A A. Dependency network methods for hierarchical multi-label classification of gene functions［C］// Proceedings of the 2014 IEEE Symposium on Computational Intelligence and Data Mining. 2014:241-248.
［20］Song Yang, Zhang Lu, Giles L C. A sparse Gaussian processes classification framework for fast tag suggestions［C］// Proceedings of the 17th ACM Conference on Information and Knowledge Management. 2008:93-102.
［21］Xia Xin, Lo David, Wang Xin-yu, et al. Tag recommendation in software information sites［C］// Proceedings of the 10th IEEE Working Conference on Mining Software Repositories. 2013:287-296.
［22］Maimon O, Rokach L. Data Mining and Knowledge Discovery Handbook［M］. 2nd ed. Berlin: Springer, 2010:667-685.
［23］Zhang Min-ling, Zhang Kun. Multi-label learning by exploiting label dependency［C］// Proceedings of 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2010:999-1008.
［24］Tsoumakas G, Vlahavas I. Random k-labelsets: An ensemble method for multilabel classification［C］// Proceedings of the 18th European Conference on Machine Learning. 2007:406-417.
［25］Ghamrawi I N, McCallum A. Collective multi-label classification［C］// Proceedings of the 14th ACM International Conference on Information and Knowledge Management. 2005:195-200.
［26］Godbole S, Sarawagi S. Discriminative methods for multi-labelled classification［C］// Proceedings of the 8th Pacific-Asia Conference on Knowledge Discovery and Data Mining. 2004:22-30.
［27］Hüllermeier E, Fürnkranz J, Cheng Wei-wei， et al. Label ranking by learning pairwise preferences［J］. Artificial Intelligence, 2008,172(16-17):1897-1916.
［28］Fürnkranz J, Hüllermeier E, Mencía L E, et al. Multilabel classification via calibrated label ranking［J］. Machine Learning, 2008,73(2):133-153.
［29］Read J, Pfahringer B, Holmes G, et al. Classifier chains for multi-label classification［C］// Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part II. 2009,5782:254-269.
［30］Read J. A pruned problem transformation method for multi-label classification［C］// Proceedings of the New Zealand Computer Science Research Student Conference. 2008:143-150.
［31］Zhang Min-ling, Zhou Zhi-hua. ML-KNN: A lazy learning approach to multi-label learning ［J］. Pattern Recognition, 2007,40(7):2038-2048.〖HJ1.6mm〗
［32］Simoudis E, Aha D W. Special AI review issue on lazy learning［J］. Artificial Intelligence Review, 1997,11(1-5):7-10.
［33］Luo Xiao, Zincir-Heywood A N. Evaluation of two systems on multi-class multi-label document classification［C］// Proceedings of 15th International Symposium on Methodologies for Intelligent System. 2005:161-169.
［34］Xu Jian-hua. Multi-label weighted k-nearest neighbor classifier with adaptive weight estimation［C］// Proceedings of the 18th International Conference on Neural Information Processing. 2011:79-88.
［35］张敏灵. 一种新型多标记懒惰学习算法［J］. 计算机研究与发展, 2012,49(11):2271-2282.
［36］程圣军,黄庆成,刘家锋,等. 一种改进的ML-KNN多标记文档分类方法［J］. 哈尔滨工业大学学报, 2013,45(11):45-49.
［37］De Comité F, Gilleron R, Tommasi M. Learning multi-label alternating decision tree from texts and data［C］// Proceedings of the 3rd International Conference on Machine Learning and Data Mining in Pattern Recognition. 2003:35-49.
［38］Borges H B, Nievola J C. Multi-label hierarchical classification using a competitive neural network for protein function prediction ［C］// Proceedings of the 2012 International Joint Conference on Neural Networks. 2012:1-8.
［39］Kongsorot Y, Horata P. Multi-label classification with extreme learning machine［C］// Proceedings of the 6th International Joint Conference on Knowledge and Smart Technology. 2014:81-86.
［40］Chen Ben-hui, Duan Li-hua, Hu Jing-lu. Composite kernel based SVM for hierarchical multi-label gene function classification［C］// Proceedings of the 2012 International Joint Conference on Neural Networks. 2012:1-6.
［41］Wan Shi-biao, Mak Man-wai, Kung Sun-yuan. Adaptive thresholding for multi-label SVM classification with application to protein subcellular localization prediction［C］// Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013:3457-3551.
［42］孔祥南,黎铭,姜远,等. 一种针对弱标记的直推式多标记分类方法［J］. 计算机研究与发展, 2010,47(8):1392-1399.
［43］田枫,沈旭昆. 弱标签环境下基于语义邻域学习的图像标注［J］. 计算机研究与发展, 2014,51(8):1821-1832.
［44］Sun Yu-yin, Zhang Yin, Zhou Zhi-hua. Multi-label learning with weak label［C］// Proceedings of the 24th AAAI Conference on Artificial Intelligence. 2010:593-598.
［45］Chen Gang, Song Yangqiu, Wang Fei, et al. Semi-supervised multi-label learning by solving a Sylvester equation［C］// Proceedings of the 8th SIAM International Conference on Data Mining. 2008:410-419.
［46］〖JP2〗Zhang Chen-guang, Zhang Xia-huan. Graph-based semi-supervised multi-label learning method［C］// Proceedings of the 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer. 2013:1021-1025.
［47］Wang Hua, Huang Heng, Ding C. Image annotation using multi-label correlated Green’s function［C］// Proceedings of the 12th IEEE International Conference on Computer Vision. 2009:2029-2034.
［48］Kong Xiang-nan, Michael K N, Zhou Zhi-hua. Transductive multilabel learning via label set propagation［J］. IEEE Transactions on Knowledge and Data Engineering, 2013,25(3):704-719.
［49］Liu Yi, Jin Rong, Yang Liu. Semi-supervised multi-label learning by constrained non-negative matrix factorization［C］// Proceedings of the 21st AAAI Conference on Artificial Intelligence. 2006:421-426.
［50］Esuli A, Sebastiani F. Active learning strategies for multi-label text classification［C］// Proceedings of the 31st European Conference on IR Research on Advances in Information Retrieval. 2007:102-113.
［51］Wu Jian, Sheng V S, Zhang Jing, et al. Multi-label active learning for image classification［C］// Proceedings of the 2014 IEEE International Conference on Image Processing. 2014:5227-5231.
［52］Yu Kai, Yu Shi-peng, Tresp V. Multi-label informed latent semantic indexing［C］// Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 2005:258-265.
［53］Wang Hua, Ding C, Huang Heng. Multi-label linear discriminant analysis［C］// Proceedings of the 11th European Conference on Computer Vision: Part VI. 2010:126-139.
［54］Park C H, Lee M. On applying linear discriminant analysis for multi-labeled problems［J］. Pattern Recognition Letters, 2008,29(7):878-887.
［55］Doquire G, Verleysen M. Feature selection for multi-label classification problems［C］// Proceedings of the 11th International Work-Conference on Artificial Neural Networks. 2011:9-16.
［56］Jungjit S, Freitas A A, Michaelis M, et al. Two extensions to multi-label correlation-based feature selection: A case study in bioinformatics［C］// Proceedings of the 2013 IEEE International Conference on Systems, Man, and Cybernetics. 2013:1519-1524.
［57］Zhang Yin, Zhou Zhi-hua. Multilabel dimensionality reduction via dependence maximization［J］. ACM Transactions on Knowledge Discovery from Data, 2010,4(3):Article No.14.
［58］〖JP2〗Gu Quan-quan, Li Zhen-hui, Han Jia-wei. Correlated multi-label feature selection［C］// Proceedings of the 20th ACM International Conference on Information and Knowledge Management. 2011:1087-1096.
［59］Ji Shui-wang, Ye Jie-ping. Linear dimensionality reduction for multi-label classification［C］// Proceedings of the 21st International Joint Conference on Artificial Intelligence. 2010:1077-1082.

[1]	王梦溪, 李峻. 老年人跌倒检测技术研究综述[J]. 计算机与现代化, 2024, 0(08): 30-36.
[2]	袁红伟1, 常利军1, 郝家欢2, 樊娜2, 王超2, 罗闯2, 张泽辉2. 基于标签传播的轨迹兴趣点挖掘及隐私保护[J]. 计算机与现代化, 2024, 0(05): 46-54.
[3]	贾潇瑶, . 融合CatBoost和SHAP的乳腺癌预测及特征分析[J]. 计算机与现代化, 2023, 0(10): 32-38.
[4]	谢仕斌, 刘梦赤, 唐诗琪, 周瑞平, . 基于多特征提取的时间卷积知识追踪模型[J]. 计算机与现代化, 2023, 0(07): 25-29.
[5]	刘佩. 基于数据挖掘的医保控费系统[J]. 计算机与现代化, 2023, 0(06): 89-94.
[6]	张芸, 白开峰, 王星, 仓甜, 周通, 段锦文, 苏晗. 智能电网环境下窃电行为检测[J]. 计算机与现代化, 2023, 0(03): 60-65.
[7]	王劭华, 欧阳会丹, 孙丹, 王康, 吴鸿萍, 钟询, 褚兴平, 杨松涛. 基于Apriori算法的大学生体测项目关联规则挖掘[J]. 计算机与现代化, 2023, 0(03): 66-70.
[8]	石志伟, 武志峰, 张哲. 纠正学习策略下LightGBM-GRU模型的股票波动率预测[J]. 计算机与现代化, 2023, 0(01): 95-102.
[9]	宋晓丽, 张勇波, 张培颖. 基于半监督学习的学生消费数据异常检测[J]. 计算机与现代化, 2022, 0(12): 13-17.
[10]	关云鹏, 刘玉龙. 基于从共现矩阵提取关联的类别型数据聚类[J]. 计算机与现代化, 2022, 0(11): 1-8.
[11]	孙丹, 施炜利, 饶兰香, 孟莎莎, 郭晓明, 李逸伦. 基于改进混合采样和XGBoost算法的信用卡欺诈检测方法[J]. 计算机与现代化, 2022, 0(09): 111-118.
[12]	孙丹, 饶兰香, 施炜利, 孟莎莎, 胡少文, 胡必伟, 应嵩. 基于混合N-Gram模型和XGBoost算法的内部威胁检测方法[J]. 计算机与现代化, 2022, 0(08): 99-105.
[13]	段桂芹, 邹臣嵩. 基于近邻传播聚类的职业能力评价模型[J]. 计算机与现代化, 2022, 0(05): 21-27.
[14]	冷涛, . 基于深度学习的加密流量分类研究综述[J]. 计算机与现代化, 2021, 0(08): 112-120.
[15]	邓子云, . 一种为辅助诊断筛选机器学习模型的方法[J]. 计算机与现代化, 2021, 0(03): 88-93.