Abstract
In reality, like single-label data, multi-label data sets have the problem that only some have labels. This is an excellent challenge for multi-label feature selection. This paper combines the logistic regression model with graph regularization and sparse regularization to form a joint framework (SMLFS) for semi-supervised multi-label feature selection. First of all, the regularization of the feature graph is used to explore the geometry structure of the feature, to obtain a better regression coefficient matrix, which reflects the importance of the feature. Second, the label graph regularization is used to extract the available label information, and constrain the regression coefficient matrix, so that the regression coefficient matrix can better fit the label information. Third, the \(L_{2,p}\)-norm \(0<p\le 1\) constraint is used to ensure the sparsity of the regression coefficient matrix so that it is more convenient to distinguish the importance of features. In addition, an iterative updating algorithm with convergence is designed and proved to solve the above problems. Finally, the proposed method is validated on eight classic multi-label data sets, and the experimental results show the effectiveness of the proposed algorithm.
Similar content being viewed by others
References
Alalga A, Benabdeslem K, Taleb N (2016) Soft-constrained Laplacian score for semi-supervised multi-label feature selection. Knowl Inf Syst 47(1):75–98
Bermingham ML, Pong-Wong R, Spiliopoulou A, Hayward C, Rudan I, Campbell H, Wright AF, Wilson JF, Agakov F, Navarro P, Haley CS (2015) Application of high-dimensional feature selection: evaluation for genomic prediction in man. Sci Rep 5:10312
Cai ZL, Zhu W (2018) Multi-label feature selection via feature manifold learning and sparsity regularization. Int J Mach Learn Cybern 9(8):1321–1334
Cai J, Luo J, Wang S (2018) Feature selection in machine learning: a new perspective. Neurocomputing 300:70–79
Chang X, Shen H, Wang S, Liu J, Xue L (2014) Semi-supervised feature analysis for multimedia annotation by mining label correlation. Adv Knowl Discov Data Min 8444:74–85
Chang XJ, Nie FP, Yang Y, Zhang CQ, Huang H (2016) Convex sparse PCA for unsupervised feature learning. ACM Trans Knowl Discov Data 11(1):1–16
Chen SB, Zhang YM (2019) Extended adaptive Lasso for multi-class and multi-label feature selection. Knowl Based Syst 173:28–36
Deliparaschos KM, Nenedakis FI, Tzafestas SG (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(1):1–30
Duda J (1995) Supervised and unsupervised discretization of continuous features. In: Twelfth International Conference on Machine Learning. Sydney, Australia: ICML 1995:194–202
Elguebaly T, Bouguila N (2015) Simultaneous high-dimensional clustering and feature selection using asymmetric gaussian mixture models. Image Vis Comput 34:27–41
Gu Q, Zhou J (2009) Co-clustering on manifolds. In: Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, ACM 2009:359–368
Hu JC, Li YH, Gao WF, Zhang P (2020) Robust multi-label feature selection with dual-graph regularization. Knowl Based Syst 203:106126
Kawano S (2013) Semi-supervised logistic discrimination via labeled data and unlabeled data from different sampling distributions. Stat Anal Data Min 6(6):472–481
Kawano S, Misumi T, Konishi S (2012) Semi-Supervised Logistic Discrimination Via Graph-Based Regularization. Neural Process Lett 36(3):203–216
Lee J, Kim DW (2015) Fast multi-label feature selection based on information-theoretic feature ranking. Pattern Recogn 48(9):2761–2771
Lee J, Kim DW (2017) SCLS: multi-label feature selection based on scalable criterion for large label set. Pattern Recogn 66:342–352
Lee J, Lim H, Kim DW (2012) Approximating mutual information for multi-label feature selection. Electron Lett 48(15):929–930
Li T, Meng ZJ, Ni BB, Shen JB, Wang M (2016) Robust geometric p-norm feature pooling for image classification and action recognition. Image Vis Comput 55(2):64–76
Lin YJ, Hu QH, Liu JH, Duan J (2015) Multi-label feature selection based on max-dependency and min-redundancy. Neurocomputing 168(30):92–103
Liu H, Zhang S, Wu X (2014) MLSLR: multi-label learning via sparse logistic regression. Inf Sci 281:310–320
Nie FP, Huang H, Cai X et al (2010) Efficient and robust feature selection via joint \(L_{21}\)-norms minimization. Adv Neural Inf Process Syst NIPS 2010:1813–1821
Ren YZ, Zhang GJ, Yu GX, Li X (2012) Local and global structure preserving based feature selection. Neurocomputing 89:147–157
Shi CJ, Duan CY, Gu ZB, Tian Q, An GY, Zhao RZ (2018) Semi-supervised feature selection analysis with structured multi-view sparse regularization. Neurocomputing 330:412–424
Sun X, Liu YH, Li J, Zhu JQ, Liu XJ, Chen HL (2012) Using cooperative game theory to optimize the feature selection problem. Neurocomputing 97:86–93
Sun L, Kudo M, Kimura K (2017) READER: robust semi-supervised multi-label dimension reduction. IEICE Trans Inf Syst e100.d(10):2597–2604
Taher KA, Jisan BMY, Rahman MM (2019) Network intrusion detection using supervised machine learning technique with feature selection. 2019 International Conference on Robotics, Electrical and Signal Processing Techniques. Bangladesh: IEEE Press 2019:643–646
Tang BG, Zhang L (2020) Local preserving logistic I-relief for semi-supervised feature selection. Neurocomputing 399:48–64
Wang SP, Wang H (2017) Unsupervised feature selection via low-rank approximation and structure learning. Knowl Based Syst 124:70–79
Yan Y, Nie FP, Li W, Gao CQ, Yang Y, Xu D (2016) Image classification by cross-media active learning with privileged information. IEEE Trans Multimed 18(12):2494–2502
Yang Y, Xu D, Nie FP, Yan SC, Zhuang YT (2010) Image clustering using local discriminant models and global integration. IEEE Trans Image Process 19(10):2761–2773
Yang Y, Wu F, Nie FP (2012) Web and personal image annotation by mining label correlation with relaxed visual graph embedding. IEEE Trans Image Process 21(3):1339–1351
Yang Y, Yang Y, Shen HT, Zhang YC, Du XY, Zhou XF (2013) Discriminative nonnegative spectral clustering with out-of-sample extension. IEEE Trans Knowl Data Eng 25(8):1760–1771
Yang Y, Song JK, Huang Z, Ma ZG, Sebe N, Hauptmann Alexander G (2013) Multi-feature fusion via hierarchical regression for multimedia analysis. IEEE Trans Multimed 15(3):572–581
Zhang ML, Zhou ZH (2007) ML-KNN: a lazy learning approach to multi-label learning. Pattern Recogn 40(7):2038–2048
Zhang R, Nie FP, Li XL, Wei X (2018) Feature selection with multi-view data: a survey. Inf Fusion 50:158–167
Zhang P, Liu GX, Gao WF (2019) Distinguishing two types of labels for multi-label feature selection. Pattern Recogn 95:72–82
Zhang M, Ding C, Zhang Y (2014) Feature selection at the discrete limit. Twenty-Eighth AAAI conference on artificial intelligence
Zhu PF, Hu QH, Zhang CQ (2016) Coupled dictionary learning for unsupervised feature selection. In: The 30th AAAI conference on artificial intelligence 2016
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, Y., Ma, Y., Yang, X. et al. Semi-supervised multi-label feature selection with local logic information preserved. Adv. in Comp. Int. 1, 7 (2021). https://doi.org/10.1007/s43674-021-00008-6
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s43674-021-00008-6