Abstract
Multi-metric learning is important for improving performance of learners. For complex data, multi metric learning algorithms need intensive research. Moreover, the existing multi-metric learning methods may lead to the distance not being comparable. To solve these shortcomings and characterize better complexity data, we propose a novel multi-metric learning framework, where each class is divided into several clusters, and then a local metric and two concentric hypers-pheres are trained jointly in a cluster, such that the samples of the same cluster distribute within one hypersphere, and the classification margin are as large as possible simultaneously. This will leads to intra-class compactness and inter-class dispersion. During the test phase, the relative distance in learned metric space is designed to make classification decisions. A new example is classified to the class of its closest hyper-sphere center. This ensures that the comparison of distances is meaningful and avoids effectively the limitation of k-nearest neighbors (kNN) classifiers. Moreover,some important properties the proposed algorithm are analyzed theoretically. Further, an alternating iterative algorithm is developed to solve the problem. Numerical experiments are carried out on different scales and types datasets. Experiment results confirm the feasibility and effectiveness of the proposed method.
Similar content being viewed by others
Data availability
The data that support the findings of this study will available on reasonable request from the corresponding author.
Notes
References
Cover TM, Hart PE (2003) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27
Likas A, Vlassis N, Verbeek JJ (2002) The global K-means clustering algorithm. Pattern Recognit 36(2):451–461
Wang CS (2011) Theoretical analysis for solution of support vector data description. Neural Netw 24:360–369
Jian Yu, Yujian Feng (2019) Quadruplet-center loss for face verification. In 2019 Chinese Automation Congress (CAC), 5034–5039
Yin F, Liu CL (2009) Handwritten Chinese text line segmentation by clustering with distance metric learning. Pattern Recognit 42(12):3146–3157
Tang J, Li D, Tian Y (2022) Image classification with multi-view multi-instance metric learning. Expert Syst Appl 189:116117
Chang X, Ma Z, Wei X, Hong X, Gong Y (2020) Transductive semi-supervised metric learning for person re-identification. Pattern Recognit 108:107569
Ysc A, Myw A, Lang HB et al (2020) Joint deep semantic embedding and metric learning for person re-identification. Pattern Recognit Lett 130:306–311
Xiang S, Nie F, Zhang C (2008) Learning a Mahalanobis distance metric for data clustering and classification. Pattern Recognit 41(12):3600–3612
Weinberger Kilian Q, Saul Lawrence K (2009) Distance metric learning for large margin nearest neighbor classification. J Mach Learn Res 10(9):207–244
Ye H, Zhan D, Li N, Jiang Y (2020) Learning multiple local metrics: global consideration helps. IEEE Trans Pattern Anal Mach Intell 42(7):1698–1712
Ye H, Zhan D, Jiang Y, Zhou Z (2019) What makes objects similar: a unified multi-metric learning approach. IEEE Trans Pattern Anal Mach Intell 41(5):1257–1270
Yuan Y, Xiao Y, Hao Z, Liu B (2021) A nearest-neighbor search model for distance metric learning. Inf Sci 552:261–277
Yuan Y, Xiao Y, Hao Z, Liu B (2021) A convex model for support vector distance metric learning. IEEE Trans Neural Netw Learn Syst 2021:1–14
Schultz M , Joachims T. Learning a distance metric from relative comparisons. Advances in Neural Information Processing Systems, NIPS 2003, MIT Press
Xu Y, Miao C, Liu Y et al (2020) Kernel-target alignment based non-linear metric learning. Neurocomputing 411:54–66
Bac N, Ferri FJ, Carlos M, de Baets B (2019) An efficient method for clustered multi-metric learning. Inf. Sci. 471:149–163
Frome A,Singer Y, Sha F, Malik J. Learning globally-consistent local distance functions for shape-based image retrieval and classification. in: 2007 IEEE 11th international conference on computer vision, 2007,pp 1–8
Wang J, Woznica A, Kalousis A (2012) Parametric local metric learning for nearest neighbor classification. Adv Neural Inf Process Syst 2:1601–1609
Amand J S , Huan J . Sparse compositional local metric learning. in: Acm Sigkdd international conference on knowledge discovery and data mining, ACM, 2017: 1097–1104
Wu M, Ye J (2009) A small sphere and large margin approach for novelty detection using training data with outliers. IEEE Trans Pattern Anal Mach Intell 31(11):2088–2092
Le T , Tran D , Ma W , Sharma D. An optimal sphere and two large margins approach for novelty detection. in: The 2010 international joint conference on neural networks (IJCNN), 2010, pp 18-23
Khemchandani R, Chandra S (2007) Twin support vector machines for pattern classification. IEEE Trans Pattern Anal Mach Intell 29(5):905–910
Vapnik VN (1995) The nature of statistical learning theory. Springer
Peng X, Xu D (2013) A twin-hypersphere support vector machine classifier and the fast learning algorithm. Inf Sci 221:12–27
Zhao Y, Yang L (2023) Distance metric learning based on the class center and nearest neighbor relationship. Inpress, Neural Networks
Tseng P (2001) Convergence of a block coordinate descent method for nondifferentiable minimization. J Optim Theory Appl 109(3):475–494
Gass Saul I (2003) Linear programming: methods and applications. Courier Corporation
Yang L, Qian Y (2016) A sparse logistic regression framework by difference of convex functions programming. Appl Intell 45(2):1–14
Bac N, De BB (2018) An approach to supervised distance metric learning based on difference of convex functions programming. Pattern Recognit 81:562–574
Sardarmehni T, Heydari A (2018) Sub-optimal scheduling in switched systems with continuous-time dynamics: a gradient descent approach. Neurocomputing 285:10–22
Zadeh PH, Hosseini R, and Sra S Geometric mean metric learning. In: Proceedings of the 33rd international conference on machine learning, 2016,48: pp 2464–2471
Bamakan S, Wang H, Shi Y (2017) Ramp loss K-support vector classification-Regression; a robust and sparse multi-class approach to the intrusion detection problem. Knowled-based Syst 2017:126
Bac N, Carlos M, De BB (2017) Supervised distance metric learning through maximization of the Jeffrey divergence. Pattern Recognit 64:215–225
Demiar J, Schuurmans D (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no conflicts of interest in this study.
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
Zhao, Y., Yang, L. A multi-metric small sphere large margin method for classification. Pattern Anal Applic 26, 1615–1629 (2023). https://doi.org/10.1007/s10044-023-01188-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-023-01188-2