Multi-label active learning by model guided distribution matching

Abstract

Multi-label learning is an effective framework for learning with objects that have multiple semantic labels, and has been successfully applied into many real-world tasks. In contrast with traditional single-label learning, the cost of labeling a multi-label example is rather high, thus it becomes an important task to train an effective multi-label learning model with as few labeled examples as possible. Active learning, which actively selects the most valuable data to query their labels, is the most important approach to reduce labeling cost. In this paper, we propose a novel approach MADM for batch mode multi-label active learning. On one hand, MADM exploits representativeness and diversity in both the feature and label space by matching the distribution between labeled and unlabeled data. On the other hand, it tends to query predicted positive instances, which are expected to be more informative than negative ones. Experiments on benchmark datasets demonstrate that the proposed approach can reduce the labeling cost significantly.

Keywords

multi-label learning / batch mode active learning / distribution matching

References

[1] Zhang M L, Zhou Z H. A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(8): 1819–1837

[2] Yang Y, Wu F, Nie F, Fei Wu, Shen H T, Zhuang Y, Hauptmann A G. Web and personal image annotation by mining label correlation with relaxed visual graph embedding. IEEE Transactions on Image Processing, 2012, 21(3): 1339–1351

[3] Lin W Z, Fang J A, Xiao X, Chou K C. iLoc-Animal: a multi-label learning classifier for predicting subcellular localization of animal proteins. Molecular BioSystems, 2013, 9(4): 634–644

[4] Settles B. Active learning literature survey. Madison: University of Wisconsin. Technical Report. 2010

[5] Li X, Wang L, Sung E. Multilabel SVM active learning for image classification. In: Proceedings of the 21st IEEE International Conference on Image Processing. 2004, 2207–2210

[6] Brinker K. On active learning in multi-label classification. In: Bühlmann P, Tellner D, Havemann S, et al., eds. From Data and Information Analysis to Knowledge Engineering. Springer Berlin Heidelberg, 2006, 206–213

[7] Yang B, Sun J T, Wang T, Chen Z. Effective multi-label active learning for text classification. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009, 917–926

[8] Vasisht D, Damianou A, Varma M, Kapoor A. Active learning for sparse bayesian multilabel classification. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014, 472–481

[9] Wu J, Sheng V S, Zhang J, Zhao P, Cui Z. Multi-label active learning for image classification. In: Proceedings of IEEE International Conference on Image Processing. 2014, 5227–5231

[10] Zhao S, Wu J, Sheng V S, Ye C, Zhao P, Cui Z. Weak labeled multi-label active learning for image classification. In: Proceedings of the 23rd Annual ACM Conference on Multimedia Conference. 2015, 1127–1130

[11] Li X, Guo Y. Active learning with multi-label svm classification. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence. 2013, 1479–1485

[12] Huang S J, Zhou Z H. Active query driven by uncertainty and diversity for incremental multi-label learning. In: Proceeding of the 13th IEEE International Conference on Data Mining. 2013, 1079–1084

[13] Huang S J, Jin R, Zhou Z H. Active learning by querying informative and representative examples. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(10): 1936–1949

[14] Li S Y, Jiang Y, Zhou Z H. Multi-label active learning from crowds. arXiv preprint arXiv:1508.00722, 2015

[15] Guo Y, Schuurmans D. Discriminative batch mode active learning. In: Proceedings of Advances in Neural Information Processing Systems. 2008, 593–600

[16] Yang Y, Ma Z, Nie F, Chang X, Hauptmann A G. Multi-class active learning by uncertainty sampling with diversity maximization. International Journal of Computer Vision, 2014, 113(2): 113–127

[17] Long C, Hua G, Multi-class multi-annotator active learning with robust Gaussian Process for visual recognition, In: Proceedings of IEEE International Conference on Computer Vision. 2015

[18] Xin J, Cui Z, Zhao P, He T. Active transfer learning of matching query results across multiple sources. Frontiers of Computer Science, 2015, 1–13

[19] Hoi S C H, Jin R, Zhu J, Lyu M. Batch mode active learning and its application to medical image classification. In: Proceedings of the 23rd International Conference on Machine Learning. 2006, 417–424

[20] Chattopadhyay R, Wang Z, Fan W, Ian D, Sethuraman P, Jieping Y. Batch mode active sampling based on marginal probability distribution matching. ACMTransactions on Knowledge Discovery from Data, 2013, 7(3): 965–991

[21] Guo Y. Active instance sampling via matrix partition. In: Proceedings of Advances in Neural Information Processing Systems. 2010, 802–810

[22] Hung C W, Lin H T. Multi-label active learning with auxiliary learner. In: Proceedings of the 3rd Asian Conference on Machine Learning. 2011, 315–332

[23] Vapnik V N. The nature of statistical learning theory. In: Cowell R G, Dawid A P, Lauritzen S L, et al., eds. Statistics for Engineering and Information Science. New York: Springer-Verlag, 2000

[24] Borgwardt K M, Gretton A, Rasch M, Kriegel H, Schölkopf B, Smola A. Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics, 2006, 22(14): 49–57

[25] Gretton A, Borgwardt K M, Rasch M, Kriegel H, Schölkopf B, Smola A. A kernel method for the two-sample-problem. In: Proceedings of Advances in Neural Information Processing Systems. 2006, 513–520

[26] Huang J, Smola A, Gretton A, Borgwardt K M, Schölkopf B. Correcting sample selection bias by unlabeled data. In: Proceedings of Advances in Neural Information Processing Systems. 2006, 601–608

[27] Pan S J, Tsang I W, Kwok J T, Yang Q. Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks, 2011, 22(2): 199–210

[28] Sriperumbudur B K, Gretton A, Fukumizu K, Schölkopf B, Lanckriet G. Hilbert space embeddings and metrics on probability measures. The Journal of Machine Learning Research, 2010, 11: 1517–1561

[29] Trohidis K, Tsoumakas G, Kalliris G, Vlahavas I. Multi-label classification of music into emotions. In: Proceedings of the 9th International Conference On Music Information Retrieval. 2008, 325–330

[30] Sebastiani F. Machine learning in automated text categorization. ACM Computing Surveys, 2002, 34(2): 1–47

[31] Boutell M R, Luo J, Shen X, Brown C M. Learning multi-label scene classification. Pattern Recognition, 2004, 37(9): 1757–1771

[32] Zhang M L and Zhou Z H. ML-kNN: a lazy learning approach to multilabel learning. Pattern Recognition, 2007, 40(7): 2038–2048

[33] Xu J. Fast multi-label core vector machine. Pattern Recognition, 2013, 46(3): 885–898

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag Berlin Heidelberg