Abstract
In the process of multi-label learning, feature selection methods are often adopted to solve the high-dimensionality problem in feature spaces. Most existing multi-label feature selection algorithms focus on exploring the correlation between features and labels and then obtain the target feature subset by importance ranking. These algorithms commonly use single-channel structure to obtain important features, which induces the excessive reliance on the ranking results and causes the loss of important features. However, the correlation between label-specific feature and label-instance is ignored. Therefore, this paper proposes Parallel Dual-channel Multi-label Feature Selection algorithm (PDMFS). We first introduce the concept of dual channel and design the algorithm model as two independent modules. The algorithm obtained different feature correlation sequences, thus avoided relevant feature loss. And then, the proposed algorithm uses the subspace model to select the feature subset with the maximum correlation and minimum redundancy for each sequence, thus obtaining feature subsets under respective correlations. Finally, the subsets are cross-merged to reduce the important feature loss caused by the serial structure processing single feature correlation. The experimental results on eight datasets and statistical hypothesis testing indicate that the proposed algorithm is effective.
Similar content being viewed by others
Data availability
All datasets are publicly downloadable from internet. The specific URLs are given in Sect. 5.
References
Aim H, Mohammad DB, Hossein N (2021) An efficient Pareto-based feature selection algorithm for multi-label classification. Inf Sci 581:428–447
Amin H, Mohammad BD, Hossein N (2020) MFS-MCDM: Multi-label feature selection using multi-criteria decision making. Knowl-Based Syst 206:106365
Cheng YS, Zhang C, Pang SF (2022) Multi-label space reshape for semantic-rich label-specific features learning. Int J Mach Learn Cybern 13(4):1005–1019
Cui X, Zou C, Wang Z (2021) Remote sensing image recognition based on dual-channel deep learning network. Multimedia Tools Appl 80(18):27683–27699
Estrela G, Gubitoso MD, Ferreira CE et al (2020) An efficient, parallelized algorithm for optimal conditional entropy-based feature selection. Entropy 22(4):492
Fan Y, Liu J, Weng W et al (2021a) Multi-label feature selection with constraint regression and adaptive spectral graph. Knowl-Based Syst 212:106621
Fan Y, Liu J, Weng W et al (2021b) Multi-label feature selection with local discriminant model and label correlations. Neurocomputing 442:98–115
Guo X, Yu K, Liu L et al (2022) Causal feature selection with dual correction. IEEE Trans Neural Networks Learn Syst. https://doi.org/10.1109/TNNLS.2022.3178075
Hu L, Li Y, Gao W et al (2020) Multi-label feature selection with shared common mode. Pattern Recogn 104:107344
Huang J, Li G, Huang Q, et al (2015) Learning label specific features for multi-label classification. In: Proceedings of the IEEE international conference on data mining. IEEE, Atlantic City, New Jersey, USA pp 181–190
Huang R, Wu Z (2021) Multi-label feature selection via manifold regularization and dependence maximization. Pattern Recogn 120:108149
Janez D, Dale S (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30
Jiang L, Yu G, Guo M et al (2020) Feature selection with missing labels based on label compression and local feature correlation. Neurocomputing 395:95–106
Lee J, Kim DW (2013) Feature selection for multi-label classification using multivariate mutual information. Pattern Recogn Lett 34(3):349–357
Lee J, Kim DW (2015a) Memetic feature selection algorithm for multi-label classification. Inf Sci 293:80–96
Lee J, Kim DW (2015b) Mutual information based multi-label feature selection using interaction information. Expert Syst Appl 42(4):2013–2025
Li Y, Cheng Y (2019) Streaming feature selection for multi-label data with dynamic sliding windows and feature repulsion loss. Entropy 21(12):1151
Li H, Zheng Y, Ren P (2019) Dual-channel attention model for text sentiment analysis. Int J Perform Eng 15(3):834–841
Lin Y, Hu X, Wu X (2014) Quality of information-based source assessment and selection. Neurocomputing 133:95–102
Lin Y, Hu Q, Liu J (2015) Multi-label feature selection based on max-dependency and min-redundancy. Neuro Comput 168:92–103
Lin Y, Hu Q, Liu J et al (2016) Multi-label feature selection based on neighborhood mutual information. Appl Soft Comput 38:244–256
Liu J, Lin M, Wang C et al (2016) Multi-label feature selection algorithm based on local subspace. Pattern Recognit Artif Intell 29(3):240–251
Schapire RE, Singer Y (2000) BoosTexter: a boosting-based system for text categorization. Mach Learn 39(2):135–168
Spolaôr N, Cherman EA, Monard MC et al (2013) A comparison of multi-label feature selection methods using the problem transformation approach. Electron Notes Theor Comput Sci 292:135–151
Wang Y, Zheng W, Cheng Y et al (2020) Joint label completion and label-specific features for multi-label learning algorithm. Soft Comput 24(9):6553–6569
Wang Y, Zheng W, Cheng Y et al (2021a) Two-level label recovery-based label embedding for multi-label classification with missing labels. Appl Soft Comput 99:106868
Wang X, Liu Y, Du Z et al (2021b) Prediction of protein solubility based on sequence feature fusion and DDcCNN. Interdiscip Sci Comput Life Sci 13(4):703–716
Wu X, Jiang B, Yu K, et al (2020) Multi-label causal feature selection. In: Proceedings of the AAAI conference on artificial intelligence 34(04): 6430–6437
Xu Y, Lu L, Xu Z et al (2019) Dual-channel CNN for efficient abnormal behavior identification through crowd feature engineering. Mach vis Appl 30(5):945–958
Yu K, Cai M, Wu X et al (2021) Multilabel feature selection: a local causal structure learning approach. IEEE Trans Neural Networks Learn Syst. https://doi.org/10.1109/TNNLS.2021.3111288
Zeng Z, Wang X, Chen Y (2017) Multimedia annotation via semi-supervised shared-subspace feature selection. J vis Commun Image Represent 48:386–395
Zhang ML, Zhou ZH (2007) ML-KNN: A lazy learning approach to multi-label learning. Pattern Recogn 40(7):2038–2048
Zhang Y, Zhou ZH (2010) Multilabel dimensionality reduction via dependence maximization. ACM Trans Knowl Discov Data 4(3):1–21
Zhang ML, Zhou ZH (2013) A review on multi-label learning algorithms. IEEE Trans Knowl Data Eng 26(8):1819–1837
Zhang P, Gao W, Hu J et al (2020) Multi-label feature selection based on high-order label correlation assumption. Entropy 22(7):797
Zhang P, Liu G, Gao W et al (2021a) Multi-label feature selection considering label supplementation. Pattern Recogn 120:108137
Zhang L, Cheng T, Wang Y et al (2021b) Feature-label dual-mapping for missing label-specific features learning. Soft Comput 25(14):9307–9323
Zhang J, Lin Y, Jiang M et al (2022) Fast multilabel feature selection via global relevance and redundancy optimization. IEEE Trans Neural Networks Learn Syst. https://doi.org/10.1109/TNNLS.2022.3208956
Zhang J, Wu H, Jiang M et al (2023) Group-preserving label-specific feature selection for multi-label learning. Expert Syst Appl 213:118861
Zhang L, Hu Q, Duan J, et al (2014) Multi-label feature selection with fuzzy rough sets. In: International conference on rough sets and knowledge technology; Springer International Publishing: Cham, Switzerland, pp 121–128
Zhou F, Ma Y, Wang B et al (2021) Dual-channel convolutional neural network for power edge image recognition. J Cloud Comput 10(1):1–9
Acknowledgements
This work was supported by the National Natural Science Foundation of Anhui under Grant 2108085MF216; the Key Laboratory of Data Science and Intelligence Application, Fujian Province University (NO. D202005); and the Graduate Academic Innovation Program of Anqing Normal University.
Funding
This work was supported by the National Natural Science Foundation of Anhui (2108085MF216) and the Key Laboratory of Data Science and Intelligence Application, Fujian Province University (D202005).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared that they have no conflicts of interest to this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Miao, J., Wang, Y., Cheng, Y. et al. Parallel dual-channel multi-label feature selection. Soft Comput 27, 7115–7130 (2023). https://doi.org/10.1007/s00500-023-07916-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-023-07916-4