Classifier Chain Algorithm Based on Multi-label Importance Rank
LI Na1, PAN Zhisong1, ZHOU Xingyu2
1.College of Command Information System, PLA University of Science and Technology, Nanjing 210007 2.College of Communication Engineering, PLA University of Science and Technology, Nanjing 210010
Abstract The learning performance of the classifier chain algorithm often decreases due to the random prediction order of multiple labels in the classifier chains. Moreover, the error information is disseminated. With the consideration of the order of labels in a chain, a classifier chain algorithm based on multi-label importance rank is proposed. The information of interaction between the markers is used as a prerequisite to measure the label importance. On the basis of correlation, the labels are sorted according to their importance, and the ranking results are regarded as the classifier order in classifier chain algorithm. Thus, the problem of multi-label prediction sequence is solved. Experiments show that the proposed algorithm is more stable and efficient for multi-label classification compared with some state-of-the-art methods.
Corresponding Authors:
PAN Zhisong(Corresponding author), born in 1973, Ph.D., professor. His research interests include pattern recognition and machine learning.
About author:: LI Na, born in 1990, master student. Her research interests include pattern recognition and machine learning.ZHOU Xingyu, born in 1985, Ph.D., lecturer. His research interests include pattern recognition and machine learning.
[1] 李志欣,卓亚琦,张灿龙,等.多标记学习研究综述.计算机应用研究, 2014, 31(6): 1601-1605. (LI Z X, ZHUO Y Q, ZHANG C L, et al. Survey on Multi-label Learning. Application Research of Computers, 2014, 31(6): 1601-1605.) [2] ZHOU Z H. Exploitation of Label Relationship in Multi-label Learning // Proc of the IEEE International Conference on Granular Computing. Hangzhou, China: IEEE, 2012: 19. [3] BOUTELL M R, LUO J B, SHEN X P, et al. Learning Multi-label Scene Classification. Pattern Recognition, 2004, 37(9):1757-1771. [4] ZHANG M L, ZHOU Z H. ML-KNN: A Lazy Learning Approach to Multi-label Learning. Pattern Recognition, 2007, 40(7):2038-2048. [5] 邱继钊,计 华,张化祥.用于多标记学习的局部顺序分类器链算法.计算机应用研究, 2013, 30(9): 2606-2609. (QIU J Z, JI H, ZHANG H X. Locally Ordinal Classifier Chains for Multi-label Learning. Application Research of Computers, 2013, 30(9): 2606-2609.) [6] TSOUMAKAS G, KATAKIS I. Multi-label Classification: An Overview. International Journal of Data Warehousing and Mining, 2007, 3(3): 1-13. [7] HUANG S J, GAO W, ZHOU Z H. Fast Multi-instance Multi-label Learning [J/OL]. [2013-10-08]. http://arxiv.org/abs/1310.2049. [8] READ J, PFAHRINGER B, HOLMES G, et al. Classifier Chains for Multi-label Classification. Machine Learning, 2011, 85(3): 333-359. [9] ZHANG M L, ZHANG K. Multi-label Learning by Exploiting Label Dependency // Proc of the 16th ACM SIGKDD International Confe-rence on Knowledge Discovery and Data Mining. New York, USA: ACM, 2010: 999-1008. [10] HUANG S J, ZHOU Z H. Multi-label Learning by Exploiting Label Correlations Locally // Proc of the 26th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI, 2012: 949-959. [11] HUANG S J, YU Y, ZHOU Z H. Multi-label Hypothesis Reuse // Proc of the 18th ACM SIGKDD International Conference on Know-ledge Discovery and Data Mining. New York, USA: ACM, 2012: 525-533. [12] LEE D D, SEUNG H S. Learning the Parts of Objects with Non-ne-gative Matrix Factorization. Nature, 1999, 401(6755): 788-791. [13] LI G P, PAN Z S, XIAO B, et al. Community Discovery and Importance Analysis in Social Network. Intelligent Data Analysis, 2014, 18(3): 495-510. [14] 何志芬,杨 明,刘会东.多标记分类和标记相关性的联合学习.软件学报, 2014, 25(9): 1967-1981. (HE Z F, YANG M, LIU H D. Joint Learning of Multi-label Classification and Label Correlations. Journal of Software, 2014, 25(9):1967-1981.) [15] ELISSEEFF A, WESTON J. A Kernel Method for Multi-labelled Classification // DIETTERICH T G, BECKER S, GHAHRAMANI Z, eds. Advances in Neural Information Processing Systems 14. Cambridge, USA: MIT Press, 2001: 681-687. [16] DIPLARIS S, TSOUMAKAS G, MITKAS P A, et al. Protein Classification with Multiple Algorithms // Proc of the 10th Panhellenic Conference on Advances in Informatics. Berlin, Germany: Springer-Verlag, 2005: 448-456. [17] KLIMT B, YANG Y M. The Enron Corpus: A New Dataset for Email Classification Research // Proc of the 15th European Confe-rence on Machine Learning. Berlin, Germany: Springer-Verlag, 2004: 217-226. [18] KLIMT B, YANG Y M. Introducing the Enron Corpus [EB/OL]. [2015-08-15]. http://www.bklimt.com/papers/2004_klimt_ceas.pdf. [19] KATAKIS I, TSOUMAKAS G, VLAHAVAS I. Multilabel Text Cla-ssification for Automated Tag Suggestion [EB/OL]. [2015-08-06]. http://www.kde.cs.uni-kassel.de/ws/rsdc08/pdf/9.pdf. [20] UEDA N, SAITO K. Parametric Mixture Models for Multi-labeled Text // BECKER S, THRUV S, OBERMAYER K, eds. Advances in Neural Information Processing Systems 15. Cambridge, USA: MIT Press, 2002: 721-728. [21] ZHOU Z H, ZHANG M L, HUANG S J, et al. Multi-instance Multi-label Learning. Artificial Intelligence, 2012, 176(1): 2291-2320. [22] ZHANG M L, ZHOU Z H. A Review on Multi-label Learning Algorithms. IEEE Trans on Knowledge and Data Engineering, 2014, 26(8): 1819-1837. [23] SCHAPIRE R E, SINGER Y. BoosTexter: A Boosting-Based System for Text Categorization. Machine Learning, 2000, 39(2/3): 135-168. [24] DE CARVALHO A C P L F, FREITAS A A. A Tutorial on Multi-label Classification Techniques // ABRAHAM A, HASSANIEN A E, SNEL V, eds. Foundations of Computational Intelligence. Berlin, Germany: Springer-Verlag, 2009: 177-195. [25] SCHAPIRE R E, SINGER Y. Improved Boosting Algorithms Using Confidence-Rated Predictions. Machine Learning, 1999, 37(3):297-336. [26] TSOUMAKAS G, VLAHAVAS I. Random k-Labelsets: An Ensemble Method for Multilabel Classification // Proc of the 18th Euro-pean Conference on Machine Learning. Berlin, Germany: Springer-Verlag, 2007: 406-417.
2016, Vol. 29 
