Abstract
In multi-label classification, each sample can be associated with a set of class labels. When the number of labels grows to the hundreds or even thousands, existing multi-label classification methods often become computationally inefficient. To this end, dimensionality reduction strategy is applied to label space via exploiting label correlation information, resulting in label embedding and label selection techniques. Compared with a lot of label embedding work, less attention has been paid to label selection techniques due to its difficulty. Therefore, it is a challenging task to design more effective label selection techniques for multi-label classification. Column subset selection is the problem of selecting a small portion of columns from a large data matrix as one form of interpretable data summarization. So, the column subset selection problem translates naturally to this purpose, as it provides simple linear models for low-rank data reconstruction. Iterative column subset selection is one of the methods to solve the problem of column subset selection, and this method can achieve a good result in the problem. In this paper, we first execute iterative column subset selection to select a small portion of columns from a large label matrix, in the prediction stage, we do some processing on the recovery matrix. So, a new method of multi-label classifier based on iterative column subset selection is proposed. The new method is tested on six publicly available datasets with varying numbers of labels. The experimental evaluation shows that the new method works particularly well on datasets with a large number of labels.
Supported by the Natural Science Foundation of China (NSFC) under grants 62076134 and 61703096.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bi, W., Kwok, J.: Efficient multi-label classification with many labels. In: ICML, pp. 405–413 (2013)
Boutell, M.R., Luo, J., Shen, X., Brown, C.M.: Learning multi-label scene classification. Pattern Recognit. 37(9), 1757–1771 (2004)
Boutsidis, C., Mahoney, M.W., Drineas, P.: Unsupervised feature selection for principal components analysis. In: SIGKDD, pp. 61–69 (2008)
Chen, Y.N., Lin, H.T.: Feature-aware label space dimension reduction for multi-label classification. In: NIPS, vol. 25, pp. 1538–1546 (2012)
Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: CVPR, pp. 5177–5186 (2019)
Civril, A., Magdon-Ismail, M.: Column subset selection via sparse approximation of SVD. Theor. Comput. Sci. 421, 1–14 (2012)
Demsar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006)
Deng, X., Li, Y., Weng, J., Zhang, J.: Feature selection for text classification: a review. Multimedia Tools Appl. 78(3), 3797–3816 (2018). https://doi.org/10.1007/s11042-018-6083-5
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley, New York (2001)
Farahat, A.K., Ghodsi, A., Kamel, M.S.: An efficient greedy method for unsupervised feature selection. In: ICDM, pp. 161–170 (2011)
Herrera, F., Charte, F., Rivera, A.J., del Jesus, M.J.: Multilabel Classification Problem Analysis, Metrics and Techniques. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-41111-8
Hsu, D.J., Kakade, S.M., Langford, J., Zhang, T.: Multi-label prediction via compressed sensing. In: NIPS, pp. 772–780 (2009)
Jain, H., Prabhu, Y., Varma, M.: Extreme multi-label loss functions for recommendation, tagging, ranking & other missing label applications. In: SIGKDD, pp. 935–944 (2016)
Ji, T., Li, J., Xu, J.: Label selection algorithm based on Boolean interpolative decomposition with sequential backward selection for multi-label classification. In: Lladós, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12822, pp. 130–144. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86331-9_9
Krömer, P., Platoš, J., Nowaková, J., Snášel, V.: Optimal column subset selection for image classification by genetic algorithms. Ann. Oper. Res. 265(2), 205–222 (2018)
Lee, J., Yu, I., Park, J., Kim, D.W.: Memetic feature selection for multilabel text categorization using label frequency difference. Inf. Sci. 485, 263–280 (2019)
Liu, L., Tang, L.: Boolean matrix decomposition for label space dimension reduction: method, framework and applications. In: CISAT, p. 052061 (2019)
Maltoudoglou, L., Paisios, A., Lenc, L., Martínek, J., Král, P., Papadopoulos, H.: Well-calibrated confidence measures for multi-label text classification with a large number of labels. Pattern Recognit. 122, 108271 (2022)
Nowaková, J., Krömer, P., Platoš, J., Snášel, V.: Preprocessing COVID-19 radiographic images by evolutionary column subset selection. In: Barolli, L., Li, K.F., Miwa, H. (eds.) INCoS 2020. AISC, vol. 1263, pp. 425–436. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-57796-4_41
Ordozgoiti, B., Canaval, S.G., Mozo, A.: Iterative column subset selection. Knowl. Inf. Syst. 54(1), 65–94 (2018)
Rastin, N., Taheri, M., Jahromi, M.Z.: A stacking weighted k-nearest neighbour with thresholding. Inf. Sci. 571, 605–622 (2021)
Shitov, Y.: Column subset selection is NP-complete. Linear Algebra Appl. 610, 52–58 (2021)
Sun, S., Zong, D.: LCBM: a multi-view probabilistic model for multi-label classification. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2682–2696 (2020)
Sun, Y., Ye, S., Sun, Y., Kameda, T.: Exact and approximate Boolean matrix decomposition with column-use condition. Int. J. Data Sci. Anal. 1(3–4), 199–214 (2016)
Tai, F., Lin, H.T.: Multilabel classification with principal label space transformation. Neural Comput. 24(9), 2508–2542 (2012)
Wicker, J., Pfahringer, B., Kramer, S.: Multi-label classification using Boolean matrix decomposition. In: SAC, pp. 179–186 (2012)
Zhang, D., Zhao, S., Duan, Z., Chen, J., Zhang, Y., Tang, J.: A multi-label classification method using a hierarchical and transparent representation for paper-reviewer recommendation. ACM Trans. Inf. Syst. 38(1), 1–20 (2020)
Zhang, M.L., Zhou, Z.H.: A review on multi-label learning algorithms. IEEE Trans. Knowl. Data Eng. 26(8), 1819–1837 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
The following is the detailed process of Iterative column subset selection algorithm.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Peng, T., Li, J., Xu, J. (2022). Label Selection Algorithm Based on Iteration Column Subset Selection for Multi-label Classification. In: Strauss, C., Cuzzocrea, A., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2022. Lecture Notes in Computer Science, vol 13426. Springer, Cham. https://doi.org/10.1007/978-3-031-12423-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-12423-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12422-8
Online ISBN: 978-3-031-12423-5
eBook Packages: Computer ScienceComputer Science (R0)