基于特征选择与鲁棒图学习的多视图聚类

doi:10.19678/j.issn.1000-3428.0063279

摘要/Abstract

摘要： 现有的多视图聚类方法大多直接在原始数据样本上构建各视图的相似图，而原始数据中的冗余特征和噪声会导致聚类精度下降。针对该问题，基于特征选择和鲁棒图学习提出多视图聚类算法FRMC。在自适应选择不同视图特征时降低数据维度，减少冗余特征，同时利用自表示学习获取数据的表示系数，滤除噪声影响并得到数据样本的全局结构，从而去除样本中的噪声和离群点。在此基础上，通过自适应近邻学习构造样本鲁棒图，利用鲁棒图矩阵的加权和构建最终的亲和图矩阵，提出一种基于增广拉格朗日乘子的交替迭代算法对目标函数进行优化。在6个不同类型的标准数据集上进行实验，与SC、RGC、AWP等算法的对比结果表明，FRMC算法能够有效提升聚类精度且具有较好的收敛性与鲁棒性。

关键词: 多视图聚类, 特征选择, 自表示学习, 自适应近邻学习, 亲和图矩阵

Abstract: Most existing multi-view clustering methods directly construct the similarity graph of each view on the original data samples, and redundant features and noise in the original data often cause clustering accuracy to decline. Therefore, a multi-view clustering algorithm based on feature selection and robust graph learning is proposed, named FRMC.When different view features are adaptively selected, data dimensions are reduced to reduce redundant features. Meanwhile, self-representation learning is used to obtain the data representation coefficients, and the global structure of the data samples can be obtained while filtering out the influence of noise.On this basis, adaptive nearest neighbor learning is used to generate the sample robust graphs, and the weighted sum of the robust graphs is used to generate the final affinity graph matrix.Finally, to optimize the objective function, an alternating iterative algorithm based on an augmented Lagrange multiplier is proposed.Four evaluation indicators are used, and experiments on six different types of standard data sets are performed.The experimental results on six different types of standard datasets show that, compared with SC, RGC, AMP etc., FRMC can significantly improve clustering accuracy.Meanwhile, this algorithm has better convergence and robustness.

Key words: multi-view clustering, feature selection, self-representation learning, adaptive nearest neighbor learning, affinity graph matrix

中图分类号:

TP391.4

黄奕轩, 杜世强, 余瑶, 肖庆江, 宋金梅. 基于特征选择与鲁棒图学习的多视图聚类[J]. 计算机工程, 2022, 48(12): 95-103.

HUANG Yixuan, DU Shiqiang, YU Yao, XIAO Qingjiang, SONG Jinmei. Multi-View Clustering Based on Feature Selection and Robust Graph Learning[J]. Computer Engineering, 2022, 48(12): 95-103.

https://www.ecice06.com/CN/Y2022/V48/I12/95

图/表 12

20230112183001

20230112183004

20230112183007

20230112183011

20230112183015

20230112183019

20230112183022

20230112183027

20230112183031

20230112183035

20230112183038

20230112183042

参考文献

[1] PENG C, KANG Z, CHENG Q.Subspace clustering via variance regularized ridge regression[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2017:682-691.
[2] 钱雪忠, 姚琳燕.面向稀疏高维大数据的扩展增量模糊聚类算法[J].计算机工程, 2019, 45(6):75-81, 88. QIAN X Z, YAO L Y.Extended incremental fuzzy clustering algorithm for sparse high-dimensional big data[J].Computer Engineering, 2019, 45(6):75-81, 88.(in Chinese)
[3] FENG L, CAI L, LIU Y, et al.Multi-view spectral clustering via robust local subspace learning[J].Soft Computing, 2017, 21(8):1937-1948.
[4] HU Z X, NIE F P, CHANG W, et al.Multi-view spectral clustering via sparse graph learning[J].Neurocomputing, 2020, 384:1-10.
[5] HUANG S D, REN Y Z, XU Z L.Robust multi-view data clustering with multi-view capped-norm K-means[J].Neurocomputing, 2018, 311:197-208.
[6] DU L, ZHOU P, SHI L, et al.Robust multiple kernel k-means using l₂₁-norm[C]//Proceedings of the 24th International Joint Conference on Artificial Intelligence.Washington D.C., USA:IEEE Press, 2015:3476-3482.
[7] 沈俊鑫, 郭晓军, 王文浩, 等.基于协议组降低策略的二次并行k均值聚类算法[J].计算机工程, 2015, 41(8):150-155. SHEN J X, GUO X J, WANG W H, et al.Secondary parallel k-means clustering algorithm based on protocol group-reduced strategy[J].Computer Engineering, 2015, 41(8):150-155.(in Chinese)
[8] KANG Z, PAN H Q, HOI S C H, et al.Robust graph learning from noisy data[J].IEEE Transactions on Cybernetics, 2020, 50(5):1833-1843.
[9] LIU G C, LIN Z C, YAN S C, et al.Robust recovery of subspace structures by low-rank representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1):171-184.
[10] CHEN M S, HUANG L, WANG C D, et al.Multi-view clustering in latent embedding space[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence.Palo Alto, USA:AAAI Press, 2020:3513-3520.
[11] DU H S, WANG Y X, ZHANG F, et al.Low-rank discriminative adaptive graph preserving subspace learning[J].Neural Processing Letters, 2020, 52(3):2127-2149.
[12] BRBIĆ M, KOPRIVA I.Multi-view low-rank sparse subspace clustering[J].Pattern Recognition, 2018, 73:247-258.
[13] LUO S R, ZHANG C Q, ZHANG W, et al.Consistent and specific multi-view subspace clustering[C]//Proceedings of the 32th AAAI Conference on Artificial Intelligence.Palo Alto, USA:AAAI Press, 2018:3730-3737.
[14] ZHANG G Y, ZHOU Y R, HE X Y, et al.One-step kernel multi-view subspace clustering[J].Knowledge-Based Systems, 2020, 189:105-126.
[15] 陶洋, 鲍灵浪, 胡昊.结构约束的对称低秩表示子空间聚类算法[J].计算机工程, 2021, 47(4):56-61, 67. TAO Y, BAO L L, HU H.Structure-constrained symmetric low-rank representation algorithm for subspace clustering[J].Computer Engineering, 2021, 47(4):56-61, 67.(in Chinese)
[16] NIE F P, WANG X Q, JORDAN M I, et al.The constrained Laplacian rank algorithm for graph-based clustering[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.Palo Alto, USA:AAAI Press, 2016:1969-1976.
[17] WANG H, YANG Y, LIU B, et al.A study of graph-based system for multi-view clustering[J].Knowledge-Based Systems, 2019, 163:1009-1019.
[18] WANG H, YANG Y, LIU B.GMC:graph-based multi-view clustering[J].IEEE Transactions on Knowledge and Data Engineering, 2020, 32(6):1116-1129.
[19] 葛君伟, 杨广欣.基于共享最近邻的密度自适应邻域谱聚类算法[J].计算机工程, 2021, 47(8):116-123. GE J W, YANG G X.Spectral clustering algorithm for density adaptive neighborhood based on shared nearest neighbors[J].Computer Engineering, 2021, 47(8):116-123.(in Chinese)
[20] NIE F P, LI J, LI X L, et.al.Parameter-free auto-weighted multiple graph learning:a framework for multi-view clustering and semi-supervised classification[C]//Proceedings of International Joint Conference on Artificial Intelligence.Washington D.C., USA:IEEE Press, 2016:1881-1887.
[21] NIE F P, TIAN L, LI X L.Multiview clustering via adaptively weighted Procrustes[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York, USA:ACM Press, 2018:2022-2030.
[22] NIE F P, LI J, LI X L.Self-weighted multiview clustering with multiple graphs[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.Melbourne, Australia:International Joint Conferences on Artificial Intelligence Organization, 2017:2564-2570.
[23] LIN S X, ZHONG G, SHU T.Simultaneously learning feature-wise weights and local structures for multi-view subspace clustering[J].Knowledge-Based Systems, 2020, 205:106280.
[24] LIU X W, WANG L, ZHANG J, et al.Global and local structure preservation for feature selection[J].IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(6):1083-1095.
[25] BOYD S, PARIKH N, CHU E.Distributed optimization and statistical learning via the alternating direction method of multipliers[M].[S.l.]:Now Publishers Inc., 2011.
[26] DU S Q, MA Y D, MA Y R.Graph regularized compact low rank representation for subspace clustering[J].Knowledge-Based Systems, 2017, 118:56-69.
[27] BOYD S.Convex optimization:from embedded real-time to large-scale distributed[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2011:21-24.
[28] XIA R, PAN Y, DU L, et al.Robust multi-view spectral clustering via low-rank and sparse decomposition[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.Palo Alto, USA:AAAI Press, 2014:2149-2155.
[29] RIEDEL K S.A Sherman-Morrison-Woodbury identity for rank augmenting matrices with application to centering[J].SIAM Journal on Matrix Analysis and Applications, 1992, 13(2):659-662.

选择文件类型/文献管理软件名称

选择包含的内容