山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (2): 80-88.doi: 10.6040/j.issn.1672-3961.0.2021.316
龚楷伦,翟婷婷*,唐鸿成
GONG Kailun, ZHAI Tingting*, TANG Hongcheng
摘要： 针对现有算法多标签分类器收敛效率低和标签查询策略未考虑特征辨别能力的弊端,提出一种基于判别采样和镜像梯度下降规则的多标签在线主动学习算法(multi-label active mirror descent by discrimination sampling,MLAMD_D)。MLAMD_D算法采用二元关联策略将包含C个标签的多标签分类问题分解成C个相互独立的二分类问题,算法使用镜像梯度下降规则更新其二分类器,并采用基于判别的采样策略。将MLAMD_D算法与现有算法以及基于随机采样和镜像梯度下降规则的多标签在线主动学习算法(multi-label active mirror descent by random sampling,MLAMD_R)在6个多标签分类数据集上进行对比试验。试验结果表明,MLAMD_D算法的多标签分类性能优于其他多标签在线主动学习算法。因此,MLAMD_D算法在处理多标签在线主动学习的任务中具有可行性和有效性。
中图分类号:
| [1] ZHANG M L, ZHOU Z H. A review on multi-label learning algorithms[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(8):1819-1837. [2] AL-SALEMI B, AYOB M, NOAH S. Feature ranking for enhancing boosting-based multi-label text categorization[J]. Expert Systems with Applications, 2018, 113:531-543. [3] LIU Y, WEN K, GAO Q, et al. SVM based multi-label learning with missing labels for image annotation[J]. Pattern Recognition, 2018, 78:307-317. [4] XU X S, JIANG Y, PENG L, et al. Ensemble approach based onconditional random field for multi-label image and video annotation[C] //Proceedings of the 19th International Conference on Multimedea 2011. Scottsdale, AZ, USA: ACM, 2011: 1377-1380. [5] SUN L, ZU C, SHAO W, et al. Reliability-based robust multi-atlas label fusion for brain MRI segmentation[J]. ArtificialIntelligence in Medicine, 2019, 96:12-24. [6] TSOUMAKAS G, KATAKIS I, VLAHAVAS I. Mining multi-label data[M] //Data mining and knowledge discovery handbook. Boston, USA: Springer, 2009: 667-685. [7] BOUTELL M R, LUO J, SHEN X, et al. Learning multi-label scene classification[J]. Pattern Recognition, 2004, 37(9): 1757-1771. [8] ZHANG M L, ZHOU ZH. ML-KNN: a lazy learning approach to multi-label learning[J]. Pattern Recognition, 2007, 40(7): 2038-2048. [9] AGGARWA L, CHARU C. A survey of stream classification algorithms[J]. Data Classification: Algorithms and Applications, 2014: 245-274. [10] KREMPL G, SPILIOPOULOU M, STEFANOWSKI J, et al. Open challenges for data stream mining research[J]. Acm Sigkdd Explorations Newsletter, 2014, 16(1):1-10. [11] 翟婷婷,高阳,朱俊武.面向流数据分类的在线学习综述[J].软件学报,2020,31(4):912-931. ZHAI Tingting, GAO Yang, ZHU Junwu. Survey of online learning algorithms for streaming data classification[J]. Journal of Software, 2020, 31(4):912-931. [12] ZHANG X, GRAEPEL T, HERBRICH R. Bayesianonline learning for multi-label and multi-variate performance measures[C] //Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, JMLR Workshop and Conference Proceedings.Sardinia, Italy: JMLR Workshop and Conference Proceedings, 2010: 956-963. [13] HIGUCHI D, OZAWA S. Aneural network model for online multi-task multi-label pattern recognition[C] //International Conference on Artificial Neural Networks and Machine Learning. Berlin, Heidelberg:Springer, 2013: 162-169. [14] PARK S, CHOI S. Online multi-label learning with acceleratednonsmooth stochastic gradient descent[C] //IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, Canada: IEEE International Conference on Acoustics, 2013: 3322-3326. [15] LUGHOFER, EDWIN. On-line active learning: a new paradigm to improve practical useability of data stream modeling methods[J]. Information Sciences, 2017, 415: 356-376. [16] HUANG S J, LI G X, HUANG W Y, et al. Incremental multi-label learning with active queries[J]. Journal of Computer Science and Technology, 2020, 35(2):234-246. [17] HUA X S, QI G J. Online multi-label active annotation: towards large-scale content-based video search[C] //Proceedings of the 16th ACM International Conference on Multimedia. New York, USA: Association for Computing Machinery, 2008: 141-150. [18] 徐美香,孙福明,李豪杰.主动学习的多标签图像在线分类[J].中国图象图形学报,2015,20(2):237-244. XU Meixiang, SUN Fuming, LI Haojie. Online multi-label image classification with active learning[J]. Journal of Image and Graphics, 2015, 20(2): 237-244. [19] CRAMMER K, SINGER Y. A family of additive online algorithms for category ranking[J]. Journal of Machine Learning Research, 2003, 3: 1025-1058. [20] GUO X, ZHANG Y, XU J. Online multi-label passive aggressive active learning algorithm based on binary relevance[C] // International Conference on Neural Information Processing. Cham, Germany: Springer, 2017: 256-266. [21] GIBAJA E L, VENTURA S. Atutorial on multi-label learning[J]. ACM Computing Surveys, 2015, 47(3):1-38. [22] CRAMMER K, DEKEL O, KESHET J, et al. Online passive-aggressive algorithms[J]. Journal of Machine Learning Research, 2006, 7:551-585. [23] DUCHI J C, SHALEV-SHWARTZ S, SINGER Y, et al. Composite objective mirror descent[J]. Learning/statistics & Optimisation Theory & Algorithms, 2010: 14-26. [24] CRAMMER K, DREDZE M, PEREIRA F. Confidence-weighted linear classification for text categorization[J]. Journal of Machine Learning Research, 2012, 13: 1891-1926. [25] LU J, ZHAO P, HOI S C H. Onlinepassive-aggressive active learning[J]. Machine Learning, 2016, 103(2): 141-183. |
| [1] | 尹旭,刘兆英,张婷,李玉鑑. 基于弱监督和半监督学习的红外舰船分割方法[J]. 山东大学学报 (工学版), 2022, 52(2): 99-106. |
|
