Abstract
Multi-label algorithms often use an identical feature space to build classification models for all labels. However, labels generally express different semantic information and should have their own characteristics. A few algorithms have been proposed to find label-specific features to construct discriminative classification models. Some use global label correlation to make the reconstructed features more discriminative, but they usually neglect the local correlation between labels. To solve this problem, we propose a new algorithm, named learning Label-specific Features with Global and Local label Correlation (LFGLC). The algorithm integrates both global and local label correlation to extract label-specific features for each label. Specifically, global label correlation is calculated by the label co-occurrence frequency between label pairs, and local label correlation is learned from the neighborhood of each instance. Comprehensive experiments on 12 multi-label data sets clearly manifest that the proposed algorithm performs competitively in feature selection and multi-label classification.
Similar content being viewed by others
References
Lin J, Cai Q, Lin M (2021) Multi-label classification of Fundus images with graph convolutional network and self-supervised learning. IEEE Signal Process Lett 28:454–458
Huang X, Chen B, Xiao L, Yu J, Jing L (2021) Label-aware document representation via hybrid attention for extreme multi-label text classification. Neural Process Lett, pp 1–17
Wen J, Wei L, Zhou W, Han J, Guo T (2020) GCN-IA: user profile based on graph convolutional network with implicit association labels. In: Conference on computational science. pp 355–364
Sun Z, Zhang J, Dai L, Li C, Zhou C, Xin J, Li S (2019) Mutual information based multi-label feature selection via constrained convex optimization. Neurocomputing 329:447–456
Bayati H, Dowlatshahi M, Paniri M (2020) MLPSO: a filter multi-label feature selection based on particle swarm optimization. In: Conference on computer society of Iran pp 1–6
Zhang J, Luo Z, Li C, Zhou C, Li S (2019) Manifold regularized discriminative feature selection for multi-label learning. Pattern Recognit 95:136–150
Gonzalez-Lopez J, Ventura S, Cano A (2020) Distributed multi-label feature selection using individual mutual information measures. Knowl-Based Syst, p 188
Gonzalez-Lopez J, Ventura S, Cano A (2020) Distributed selection of continuous features in multilabel classification using mutual information. IEEE Trans on Neural Netw Learn Syst 31(7):2280–2293
Alalga A, Benabdeslem K, Taleb N (2015) Soft-constrained Laplacian score for semi-supervised multi-label feature selection. Knowl Inf Syst 47(1):75–98
Huang R, Jiang W, Sun G (2018) Manifold-based constraint Laplacian score for multi-label feature selection. Pattern Recognit Lett 112:346–352
Zhang ML, Wu L (2015) Lift: multi-label learning with label-specific features. IEEE Trans Pattern Anal Mach Intell 37(1):107–120
Guan Y, Li W, Zhang B, Han B, Ji M (2020) Multi-label classification by formulating label-specific features from simultaneous instance level and feature level. Applied Intell 9:1–16
Guo Y, Chung F, Li G, Wang J, Gee JC (2019) leveraging Label-specific discriminant mapping features for multi-label learning. ACM Trans Knowl Discovery Data 13(2):1–23
Weng W, Lin Y, Wu S, Li Y, Kang Y (2018) Multi-label learning based on label specific features and local pairwise label correlation. Neurocomputing 273:385–394
Huang J, Li GR, Wang SH, Xue Z, Huang QM (2017) Multi-Label Classification by exploiting local positive and negative pairwise label correlation. Neurocomputing 257:164–174
Huang R, Kang L (2021) Local positive and negative label correlation analysis with label awareness for multi-label classification. Int J Mach Learn Cybern, pp 1–14
Cheng Z, Zeng Z (2020) Joint label-specific features and label correlation for multi-label learning with missing label. Applied Intell 50(11):4029–4049
Bao J, Wang Y, Cheng Y (2021) Asymmetry label correlation for multi-label learning. Applied Intell, pp 1–13
Che X, Chen D, Mi J (2021) Feature distribution-based label correlation in multi-label classification. Int J Mach Learn Cybern, pp 1–15
Read J, Pfahringer B, Holmes G, Frank E (2011) Classifier chains for multi-label classification. Mach Learn 85:333–359
Che X, Chen D, Mi J (2020) A novel approach for learning label correlation with application to feature selection of multi-label data. Inf Sci 512:795–812
Li Q, Peng X, Qiao Y, Peng Q (2020) Learning label correlations for multi-label image recognition with graph networks. Pattern Recognit Lett 138:378–384
Ma J, Chiu B, Chow T (2020) Multilabel classification with group-based mapping: a framework with local feature selection and local label correlation. IEEE Trans Cybern
Nan G, Li Q, Dou R, Liu J (2018) Local positive and negative correlation-based k-labelsets for multi-label classification. Neurocomputing 318:90–101
Xiao J, Tang S (2020) Joint Learning of Binary Classifiers and Pairwise Label Correlations for Multi-label Image Classification. In: IEEE conference on multimedia information processing and retrieval. pp 25–30
Li YK, Zhang ML, Geng X (2015) Leveraging implicit relative labeling-importance information for effective multi-label learning. In: IEEE international conference on data mining. pp 251–260
Boutell MR, Luo J, Shen X, Brown CM (2014) Learning multi-label scene classification. Pattern Recognit 37:1757–1771
Zhang ML, Zhou ZH (2007) Ml-knn: a lazy learning approach to multi-label learning. Pattern Recognit 40:2038–2048
Wu G, Tian Y, Liu D (2018) Cost-sensitive multi-label learning with positive and negative label pairwise correlations. Neural Netw 108:411–423
Xu H, Xu L (2017) Multi-label feature selection algorithm based on label pairwise ranking comparison transformation. In: International joint conference on neural networks. pp 1210–1217
Zhang Y, Zhao T, Miao D, Pedrycz W (2021) Granular multilabel batch active learning with pairwise label correlation. IEEE Trans on Systems, Man, and Cybern
Wang R, Ye S, Li K, Kwong S (2021) Bayesian network based label correlation analysis for multi-label classifier chain. Inf Sci 554:256–275
He Z F, Yang M, Gao Y, Liu H D, Yin Y (2019) Joint multi-label classification and label correlations with missing labels and feature selection. Knowl-Based Syst 163:145–158
Zhu Y, Kwok J T, Zhou Z H (2018) Multi-Label Learning with global and local label correlation. IEEE Trans Knowl Data Eng 30(6):1081–1094
Yan Y, Li S, Xiao Z, Wang A, Li Z, Zhang J (2018) k-Labelsets for Multimedia Classification with Global and Local Label Correlation. In: International conference on multimedia Mmodeling. pp 177–188
Huang J, Li GR, Huang QM, Wu XD (2015) Learning label specific features for multi-label classification. In: IEEE international conference on data mining. pp 181–190
Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surveys 31(3):264–323
Wei XY, Yu ZW, Zhang CQ, Hu QH (2018) Ensemble of label specific features for multi-label classification. In: IEEE international conference on multimedia and expo. pp 1–6
Huang J, Xu L, Qian K, Wang J, Yamanishi K (2021) Multi-label learning with missing and completely unobserved labels. IEEE Trans Knowl Data Eng 35:1061–1086
Weng W, Chen YN, Chen CL, Wu SX, Liu JH (2020) Non-sparse label specific features selection for multi-label classification. Neurocomputing 377:85–94
Huang J, Li GR, Huang QM, Wu XD (2018) Joint feature selection and classification for multilabel learning. IEEE Trans Cybern 48(3):876–889
Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. Siam J Imaging Sci 2(1):183–202
Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc 58(1):267–288
Chang CC, Lin CJ (2011) LIBSVM: A library for support vectormachines. ACM Trans Intell Syst Technol 2(3):1–27
Demiar J, Schuurmans D (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(1):1–30
Acknowledgements
This research was supported by the natural Science Foundation of Fujian Province of China (No. 2021J011187).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Wei Weng and Bowen Wei contributed equally to this work.
Rights and permissions
About this article
Cite this article
Weng, W., Wei, B., Ke, W. et al. Learning label-specific features with global and local label correlation for multi-label classification. Appl Intell 53, 3017–3033 (2023). https://doi.org/10.1007/s10489-022-03386-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03386-7