Consensus and complementarity-based multi-view least square support vector machine

被引：0
|
作者：
Tang J. [1 ,2 ]
Li J. [1 ,2 ]
Tian Y. [3 ,4 ]
机构：
[1] School of Business Administration, Southwestern University of Finance and Economics, Chengdu
[2] Institute of Big Data, Southwestern University of Finance and Economics, Chengdu
[3] Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing
[4] School of Economics and Management, University of Chinese Academy of Sciences, Beijing
来源：
Xitong Gongcheng Lilun yu Shijian/System Engineering Theory and Practice | 2022年 / 42卷 / 09期
基金：
中国国家自然科学基金;
关键词：
complementarity principle; consensus principle; least square support vector machine; multi-view learning;
D O I：
10.12011/SETP2021-0170
中图分类号：
学科分类号：
摘要：
Multi-view learning (MVL) exploits the multi-view data to improve the performance of the learning tasks. However, most multi-view leaning models are built for only two-view setting, or mainly embed either the consensus principle or the complementarity principle. To overcome aforementioned drawbacks, we propose a consensus and complementarity-based multi-view least square support vector machine (MVLSSVM-2C), which leverages view-agreement on multi-view predictors and weight combination strategy. We then adopt an iterative two-step strategy to solve the optimization problem efficiently. Further more, the generalization capability is theoretically analyzed by using Rademacher complexity. The extensive experiments validate the effectiveness of the proposed model. © 2022 Systems Engineering Society of China. All rights reserved.
引用
收藏
页码：2461 / 2471
页数：10
相关论文
共 19 条
  • [1] Farquhar J, Hardoon D, Meng H, Et al., Two view learning: SVM-2K, theory and practice, Advances in Neural Information Processing Systems, pp. 355-362, (2005)
  • [2] Kumar A, Rai P, Daume H., Co-regularized multi-view spectral clustering, Advances in Neural Information Processing Systems, pp. 1413-1421, (2011)
  • [3] Zheng Y, Hu X P, Yin J., Health data fusion method based on multi-task support vector machine, Systems Engineering - Theory & Practice, 39, 2, pp. 418-428, (2019)
  • [4] Zhang Y S, Wu J, Cai Z H, Et al., Multi-view multi-label learning with sparse feature selection for image annotation[J], IEEE Transactions on Multimedia, 22, 11, pp. 2844-2857, (2020)
  • [5] Xu C, Tao D C, Xu C., A survey on multi-view learning[J], (2013)
  • [6] Rosales R, Yu S P, Krishnapuram B, Et al., Bayesian co-training, Journal of Machine Learning Research, 12, 3, pp. 2649-2680, (2012)
  • [7] Tang J J, Tian Y J., A multi-kernel framework with nonparallel support vector machine, Neurocomputing, 266, pp. 226-238, (2017)
  • [8] Han Y N, Yang Y X, Li X L, Et al., Matrix-regularized multiple kernel learning via (r, p) norms, IEEE Transactions on Neural Networks and Learning Systems, 29, 10, pp. 4997-5007, (2018)
  • [9] Hardoon D R, Shawe-Taylor J., Convergence analysis of kernel canonical correlation analysis: Theory and prac tice^], Machine Learning, 74, 1, pp. 23-38, (2009)
  • [10] Nie F P, Tian L, Wang R, Et al., Multiview semi-supervised learning model for image classification, IEEE Transactions on Knowledge and Data Engineering, 32, 12, pp. 2389-2400, (2020)
12