Unsupervised feature selection via low-rank graph embedding

Articles in Press

Document Type : Research Paper

Author

Department of Electrical Engineering, Lorestan University, Khoramabad, Iran

Abstract

In unsupervised feature selection, the absence of class labels makes it necessary to rely on statistical measures like variance to assess feature importance. However, the presence of noise, outliers, and feature redundancy can significantly reduce the accuracy of this process, negatively affecting the performance of machine learning models. To address these issues, this paper proposes the UFSLRAGE algorithm, which begins by applying the LRAGE feature extraction method to minimize reconstruction error, adaptively updating the similarity between samples to remove noise and outliers while generating orthogonal and uncorrelated features. This paper then constructs a weighted bipartite graph that represents both original and extracted features, with cosine similarity determining the edge weights. The LAPJV algorithm is used to identify a maximum matching in this graph, where the vertices corresponding to the original features are selected as the most informative ones. This paper evaluates UFSLRAGE on five widely-used image datasets: Jaffe, Yale, ORL, COIL-20, and pixraw10P, using metrics such as accuracy, normalized mutual information (NMI), precision, recall, and F-measure. Experimental results demonstrate that UFSLRAGE consistently outperforms other state-of-the-art unsupervised feature selection methods, achieving an average NMI of 0.9358 and an average accuracy of 0.9333 on the pixraw10P face image dataset with 10,000 features.

Keywords

Main Subjects

References

[1] Miao, J., Zhao, J., Yang, T., Fan, C., Tian, Y., Shi, Y., & Xu, M. (2024). Explicit unsupervised feature selection based on structured graph and locally linear embedding. Expert Systems with Applications, 255(June). https://doi.org/10.1016/j.eswa.2024.124568.
[2] Rossi, R., Murari, A., & Gelfusa, M. (2025). A Deep Learning Framework for Feature Selection and Dimensional Analysis: Variational Explainable Neural Networks. Knowledge-Based Systems. Published online 6 June 2025. https://doi.org/10.1016/j.knosys.2025.113940.
[3] Liang, S., Zhang, Y., Zheng, K., & Bai, Y. (2025). FeatureX: An explainable feature selection for deep learning. Expert Systems with Applications. Published online 21 April 2025. https://doi.org/10.1016/j.eswa.2025.127675.
[4] Moslemi, A., Bidar, M., & Ahmadian, A. (2023). Subspace learning using structure learning and non-convex regularization: Hybrid technique with mushroom reproduction optimization in gene selection. Computers in Biology and Medicine, 164, 107309. https://doi.org/10.1016/j.compbiomed.2023.107309.
[5] Yan, J., Hu, G., & Wei, G. (2025). Unsupervised feature selection via latent feature representation and modi ed graph embedding. Engineering Applications of Arti cial Intelligence, 161, 112121. Published online 1 December 2025. https://doi.org/10.1016/j.engappai.2025.112121.
[6] Qin, Z., Chen, H., Mi, Y., Luo, C., Horng, S., & Li, T. (2024). Multi-label Feature selection with adaptive graph learning and label information enhancement. Knowledge-Based Systems, 285, 111363. https://doi.org/10.1016/j.knosys.2023.111363.
[7] Zuo, X., Zhang, W., Wang, X., Dang, L., Qiao, B., & Wang, Y. (2025). Unsupervised feature selection via maximum relevance and minimum global redundancy. Pattern Recognition, 164, 111483. Published online 1 August 2025. https://doi.org/10.1016/j.patrec.2025.111483.
[8] Han, K., Wang, Y., Zhang, C., Li, C., & Xu, C. (2018). Autoencoder Inspired Unsupervised Feature Selection. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 2941{2945). https://doi.org/10.1109/ICASSP.2018.8462261.
[9] Guo, J., & Zhu, W. (2018). Dependence guided unsupervised feature selection. In 32nd AAAI Conference on Arti cial Intelligence, AAAI 2018 (pp. 2232{2239).
[10] Zhu, P., Zuo, W., Zhang, L., Hu, Q., & Shiu, S. C. K. (2015). Unsupervised feature selection by regularized self-representation. Pattern Recognition, 48(2), 438{446. https://doi.org/10.1016/j.patcog.2014.08.006.
[11] Huang, D., Cai, X., & Wang, C. D. (2019). Unsupervised feature selection with multisubspace randomization and collaboration. Knowledge-Based Systems, 182, 1{?. https://doi.org/10.1016/j.knosys.2019.07.027.
[12] Li, X., Zhang, H., Zhang, R., Liu, Y., & Nie, F. (2019). Generalized Uncorrelated Regression with Adaptive Graph for Unsupervised Feature Selection. IEEE Transactions on Neural Networks and Learning Systems, 30(5), 1587{1595. https://doi.org/10.1109/TNNLS.2018.2868847.
[13] Xie, J., Wang, M., Xu, S., Huang, Z., & Grant, P. W. (2021). The Unsupervised Feature Selection Algorithms Based on Standard Deviation and Cosine Similarity for Genomic Data Analysis. Frontiers in Genetics, 12, 1{17. https://doi.org/10.3389/fgene.2021.684100.
[14] Paniri, M., Dowlatshahi, M. B., & Nezamabadi-pour, H. (2020). MLACO: A multi-label feature selection algorithm based on ant colony optimization. Knowledge-Based Systems, 192, 105285. https://doi.org/10.1016/j.knosys.2019.105285.
[15] Beiranvand, F., & Mehrdad, V. (2026). Unsupervised feature selection based on the two-dimensional principal component analysis and bipartite graph for face image classi cation. Journal of Mahani Mathematical Research, 15(1), 1{37.
[16] Beiranvand, F. (2026). Unsupervised feature selection using orthogonal locality preserving projections and bipartite graph matching for face image classi cation. Journal of Mahani Mathematical Research, 15(2), 65{104.
[17] Hashemi, A., Dowlatshahi, M. B., & Nezamabadi-Pour, H. (2021). A bipartite matching-based feature selection for multi-label learning. International Journal of Machine Learning and Cybernetics, 12(2), 459{475. https://doi.org/10.1007/s13042-020-01180-w.
[18] Beiranvand, F., Mehrdad, V., & Dowlatshahi, M. B. (2022). Unsupervised feature selection for image classi cation: A bipartite matching-based principal component analysis approach. Knowledge-Based Systems, 250, 109085. https://doi.org/10.1016/j.knosys.2022.109085.
[19] Wahid, A., Khan, D. M., Hussain, I., Khan, S. A., & Khan, Z. (2022). Unsupervised feature selection with robust data reconstruction (UFS-RDR) and outlier detection. Expert Systems with Applications, 201, 117008. https://doi.org/10.1016/j.eswa.2022.117008.
[20] Hu, Q. (2020). Low-Rank Adaptive Graph Embedding for Unsupervised Feature Extraction. https://doi.org/10.1016/j.patcog.2020.107758.
[21] Goyal, P., & Ferrara, E. (2017). Graph Embedding Techniques, Applications, and Performance: A Survey.
[22] Jones, W., Chawdhary, A., & King, A. (2016). Optimising the Volgenant{Jonker algorithm for approximating graph edit distance. R, 0, 1{8. https://doi.org/10.1016/j.patrec.2016.07.024.
[23] Xia, P., Zhang, L., & Li, F. (2015). Learning similarity with cosine similarity ensemble. Information Sciences, 307, 39{52. https://doi.org/10.1016/j.ins.2015.02.024.
[24] Zhang, N., Xu, Y., Zhu, Q., & He, Y. (2022). Improved Locality Preserving Projections Based on Heat-Kernel and Cosine Weights for Fault Classi cation in Complex Industrial Processes. IEEE Transactions on Reliability, PP, 1{10. https://doi.org/10.1109/TR.2021.3139539.
[25] Goyal, P., & Ferrara, E. (2017). Graph Embedding Techniques, Applications, and Per-formance: A Survey.
[26] Armiti, A., & Gertz, M. (n.d.). Geometric Graph Matching and Similarity: A Probabilistic Approach. Categories and Subject Descriptors.
[27] Toroslu, I. H., & Arslanoglu, Y. (2007). Genetic algorithm for the personnel assignment problem with multiple objectives. Information Sciences, 177, 787{803. https://doi.org/10.1016/j.ins.2006.07.032.
[28] Erciyes, K., & Erciyes, K. (2018). Matching. In Guide to Graph Algorithms: Sequential, Parallel and Distributed (pp. 263{303).
[29] Wang, A., An, N., Chen, G., Li, L., & Alterovitz, G. (2015). Accelerating wrapper-based feature selection with K-nearest-neighbor. Knowledge-Based Systems, 83(1), 81{91. https://doi.org/10.1016/j.knosys.2015.03.009.
[30] Terven, J., Cordova-Esparza, D. M., Ramirez-Pedraza, A., & Chavez-Urbiola, E. A. (2023). Loss functions and metrics in deep learning: A review. arXiv preprint arXiv:2307.02694. 
Journal of Mahani Mathematical Research

Articles in Press, Accepted Manuscript
Available Online from 20 April 2026

Files

History

  • Receive Date: 02 October 2025
  • Revise Date: 19 February 2026
  • Accept Date: 20 April 2026

Share

How to cite

Statistics