Abstract
In multi-label learning, instances with multiple semantic labels suffer from the impact of high feature dimensionality. The goal of multi-label feature selection is to process multi-dimensional and multi-label data and keep relevant information in the original data. However, varieties of existing feature ranking-based multi-label feature selection methods do not take into account the relationship between features. Methods based on feature graph can present and utilize the association between features but still have imperfections. Among them, the exploration of the correlation between features and labels is not sufficient, and there is no efficient use of the association between features to evaluate features. In this paper, a multi-label feature selection method based on feature graph with ridge regression and eigenvector centrality is proposed. Ridge regression is used to learn a valid representation of feature label correlation. The learned correlation representation is mapped to a graph to efficiently display and use feature relationships. Eigenvector centrality is used to evaluate nodes in the graph to obtain scores for features. The effectiveness of the proposed method is testified according to three evaluation metrics (Ranking loss, Average precision, and Micro-F1) on four datasets by comparison with seven state-of-the-art multi-label feature selection methods.
This work is supported by the National Natural Science Foundation of China under grant NO. 61502155, National Natural Science Foundation of China under grant NO. 61772180 and Fujian Provincial Key Laboratory of Data Intensive Computing and Key Laboratory of Intelligent Computing and Information Processing, Fujian: BD201801.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chauhan, V., Tiwari, A., Joshi, N., Khandelwal, S.: Multi-label classifier for protein sequence using heuristic-based deep convolution neural network. Appl. Intell. 52(3), 2820–2837 (2022). https://doi.org/10.1007/s10489-021-02529-6
Tirupattur, P., Duarte, K., Rawat, Y.S., Shah, M.: Modeling multi-label action dependencies for temporal action localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1460–1470 (2021)
Gao, B.B., Zhou, H.Y.: Learning to discover multi-class attentional regions for multi-label image recognition. IEEE Trans. Image Process. 30, 5920–5932 (2021)
Cai, J., Luo, J., Wang, S., Yang, S.: Feature selection in machine learning: a new perspective. Neurocomputing 300, 70–79 (2018)
Kashef, S., Nezamabadipour, H., Nipour, B.: Multilabel feature selection: a comprehensive review and guide experiments. WIREs Data Min. Knowl. Discov. 8(2), e1240 (2018)
Hu, L., Gao, L., Li, Y., Zhang, P., Gao, W.: Feature-specific mutual information variation for multi-label feature selection. Inf. Sci. 593, 449–471 (2022)
Paniri, M., Dowlatshahi, M.B., Nezamabadi-Pour, H.: MLACO: a multi-label feature selection algorithm based on ant colony optimization. Knowl.-Based Syst. 192, 105285 (2020)
Hashemi, A., Dowlatshahi, M.B., Nezamabadi-Pour, H.: MGFS: a multi-label graph-based feature selection algorithm via PageRank centrality. Expert Syst. Appl. 142, 113024 (2020)
Chen, W., Yan, J., Zhang, B., Chen, Z., Yang, Q.: Document transformation for multi-label feature selection text categorization. In: 7th IEEE International Conference on Data Mining (ICDM 2007), New York, pp. 451–456. IEEE Press (2007)
Read, J.: A pruned problem transformation method for multi-label classification. In: Proceedings of 2008 New Zealand Computer Science Research Student Conference (NZCSRS 2008), Christchurch, pp. 143–150 (2008)
Doquire, G., Verleysen, M.: Feature selection for multi-label classification problems. In: Cabestany, J., Rojas, I., Joya, G. (eds.) IWANN 2011. LNCS, vol. 6691, pp. 9–16. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21501-8_2
Lee, J., Kim, D.W.: Fast multi-label feature selection based on information-theoretic feature ranking. Pattern Recogn. 48(9), 2761–2771 (2015)
Zhang, P., Liu, G., Gao, W.: Distinguishing two types of labels for multi-label feature selection. Pattern Recogn. 95, 72–82 (2019)
Hatami, M., Mahmood, S.R., Moradi, P.: A graph-based multi-label feature selection using ant colony optimization. In: 2020 10th International Symposium on Telecommunications (IST), Tehran, pp. 175–180. IEEE Press (2020)
Paniri, M., Dowlatshahi, M.B., Nezamabadi-pour, H.: Ant-TD: Ant colony optimization plus temporal difference reinforcement learning for multi-label feature selection. Swarm Evol. Comput. 64, 100892 (2021)
McDonald, G.C.: Tracing ridge regression coefficients. WIREs Comput. Stat. 2(6), 695–703 (2010)
Bonacich, P.: Some unique properties of eigenvector centrality. Soc. Netw. 29(4), 555–564 (2007)
Roffo, G., Melzi, S.: Ranking to learn: feature ranking and selection via eigenvector centrality. In: Appice, A., Ceci, M., Loglisci, C., Masciari, E., Raś, Z.W. (eds.) NFMCP 2016. LNCS (LNAI), vol. 10312, pp. 19–35. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-61461-8_2
Huang, R., Jiang, W., Sun, G.: Manifold-based constraint Laplacian score for multi-label feature selection. Pattern Recogn. Lett. 112, 346–352 (2018)
Jian, L., Li, J., Shu, K., Liu, H.: Multi-label informed feature selection. In: 25th International Joint Conference on Artificial Intelligence (IJCAI), New York, pp. 1627–1633 (2016)
Zhang, M.L., Zhou, Z.H.: ML-KNN: a lazy learning approach to multi-label learning. Pattern Recogn. 40(7), 2038–2048 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ye, Z., Zhang, H., Wang, M., He, Q. (2023). A Multi-label Feature Selection Method Based on Feature Graph with Ridge Regression and Eigenvector Centrality. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1791. Springer, Singapore. https://doi.org/10.1007/978-981-99-1639-9_10
Download citation
DOI: https://doi.org/10.1007/978-981-99-1639-9_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1638-2
Online ISBN: 978-981-99-1639-9
eBook Packages: Computer ScienceComputer Science (R0)