广东工业大学学报

• •    

块对角引导的多视角一致性学习

滕少华1, 韦晓杰1, 滕璐瑶2, 张巍1   

  1. 1. 广东工业大学 计算机学院, 广东 广州 510006;
    2. 广州番禺职业技术学院 信息工程学院, 广东 广州 511483
  • 收稿日期:2023-11-13 出版日期:2025-01-14 发布日期:2025-01-14
  • 通信作者: 滕璐瑶(1990–)，女，讲师，博士，主要研究方向为协同计算、模式识别，E-mail：luna.teng@qq.com
  • 作者简介:滕少华(1962–)，男，教授，博士，主要研究方向为数据挖掘、协同计算、模式识别，E-mail：shteng@gdut.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(61972102)；广州市科技计划项目(2023A04J1729)

Multi-view Consistency Learning with Block Diagonal Guidance

Teng Shao-hua1, Wei Xiao-jie1, Teng Lu-yao2, Zhang Wei1   

  1. 1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China;
    2. School of Information Engineering, Guangzhou Panyu Polytechnic, Guangzhou 511483, China
  • Received:2023-11-13 Online:2025-01-14 Published:2025-01-14

HTML

0

PDF (PC)

50

摘要： 基于图的多视角聚类方法得到了广泛的研究。然而，现有方法仍然存在两个问题：(1) 有些方法虽然将相似矩阵划分为一致性矩阵和不一致性矩阵，但难以处理被错误划分到不一致性矩阵中的一致性信息，导致有效信息不能得到充分提取。(2) 有些方法虽然得到了具有块对角结构的统一相似矩阵，但没有去除统一相似矩阵中的冗余信息。为了解决这两个问题，本文提出了一种块对角引导的多视角一致性学习(Multi-view Consistency Learning with Block Diagonal Guidance, MCLBDG) 方法。首先，该方法通过低秩表示和自适应邻域的方式获得每个视角的相似矩阵；其次，将每个视角的相似矩阵划分为一致性矩阵和不一致性矩阵。其中，不同视角的不一致性部分通过哈达玛积来筛选。在迭代过程中，被错误划分的一致性部分可以从不一致性信息中逐步提取出来。此外，提出了块对角引导来尽可能去除统一相似矩阵中的冗余信息，减少了不同簇样本之间的干扰。最后，将谱聚类应用到模型当中，直接得到聚类结果。在几个常用数据集上的比较实验验证了该方法的优越性。

关键词: 块对角引导, 多视角聚类, 多视角图学习, 一致性, 无监督学习

Abstract: Graph-based multi-view clustering methods are widely explored. However, there are still two problems with existing methods: 1) Although some methods divide the similarity matrix into a consistency matrix and an inconsistency matrix, it is difficult to deal with the consistency information that has been misclassified in the inconsistency matrix, resulting in insufficient extraction of the valid information; and 2) Although some methods obtain a unified similarity matrix with a block diagonal structure, they do not remove redundancy information from the unified similarity matrix. To address these two issues, this paper proposes a Multi-view Consistency Learning with Block Diagonal Guidance (MCLBDG) method. First, we obtain a similarity matrix for each view via low rank representation and adaptive neighborhood. Second, we divide the similarity matrix of each view into a consistency matrix and an inconsistency matrix. The inconsistency part of different views is sieved via Hadamard product. During iterations, the misclassified consistency part can be gradually extracted from the inconsistency information. In addition, block diagonal guidance is proposed to remove the redundancy information in the unified similarity matrix as much as possible, which reduces the interference of extra-cluster samples. Finally, spectral clustering is incorporated into the model to obtain clustering results directly. Comparative experimental results on the commonly used datasets demonstrate the superiority of the method over the existing methods.

Key words: block diagonal guidance, multi-view clustering, multi-view graph learning, consistency, unsupervised learning

中图分类号: 

  • TP181
[1] DAFIR Z, LAMARI Y, SLAOUI S C. A survey on parallel clustering algorithms for big data[J]. Artificial Intelligence Review, 2021, 54(4): 2411-2443.
[2] BHATTACHARJEE P, MITRA P. A survey of density-based clustering algorithms[J]. Frontiers of Computer Science (print) , 2020, 15(1): 151308.
[3] CHEN M S, LIN J Q, LI X L, et al. Representation learning in multi-view clustering: a literature review[J]. Data Science and Engineering, 2022, 7(3): 225-241.
[4] XIE Y, ZHANG W S, QU Y Y, et al. Hyper-laplacian regularized multilinear multiview self-representations for clustering and semisupervised learning[J]. IEEE Transactions on Cybernetics, 2020, 50(2): 572-586.
[5] ZHANG C Q, FU H Z, HU Q H, et al. Generalized latent multi-view subspace clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(1): 86-99.
[6] FENG Y C, YUAN Y, LU X Q. Person reidentification via unsupervised cross-view metric learning[J]. IEEE Transactions on Cybernetics, 2021, 51(4): 1849-1859.
[7] FEI L K, ZHANG B, TENG S H, et al. Joint multiview feature learning for hand-print recognition[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(12): 9743-9755.
[8] KANG Z, SHI G X, HUANG S D, et al. Multi-graph fusion for multi-view spectral clustering[J]. Knowledge-Based Systems, 2020, 105102, ISSN 0950-7051.
[9] NIE F P, CAI G H, LI X L. Multi-view clustering and semi-supervised classification with adaptive neighbors[C]//Thirty-first AAAI conference on artificial intelligence. San Francisco: AAAI Press, 2017: 2408-2414.
[10] ZHAN K, ZHANG C Q, GUAN J P, et al. Graph learning for multiview clustering[J]. IEEE Transactions on Cybernetics, 2018, 48(10): 2887-2895.
[11] WANG H, YANG Y, LIU B. GMC: graph-based multi-view clustering[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 32: 1116-1129.
[12] SHI S J, NIE F P, WANG R, et al. Auto-weighted multi-view clustering via spectral embedding[J]. Neurocomputing, 2020, 399: 369-379.
[13] LIANG Y W, HUANG D, WANG C D, et al. Multi-view graph learning by joint modeling of consistency and inconsistency[J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35(2): 2848-2862.
[14] HAO W Y, PANG S M, YANG B, et al. Tensor-based multi-view clustering with consistency exploration and diversity regularization[J]. Knowledge based systems, 2022, 252: 109342.
[15] ZHANG G Y, CHEN X W, ZHOU Y R, et al. Consistency-and inconsistency-aware multi-view subspace clustering[C]//Database Systems for Advanced Applications: 26th International Conference, DASFAA 2021, Taipei: Springer International Publishing, 2021: 291-306.
[16] FANG X Z, HAN N, WONG W K, et al. Flexible affinity matrix learning for unsupervised and semi supervised classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 30(4): 1133-1149.
[17] ZHANG C Q, HU Q H, FU H Z, et al. Latent multi-view subspace clustering[C]//Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . USA: IEEE Computer Society, 2017: 4279-4287.
[18] XIE D Y, ZHANG X D, GAO Q X, et al. Multiview clustering by joint latent representation and similarity learning[J]. IEEE Transactions on Cybernetics, 2019, 50(11): 4848-4854.
[19] ZHOU T, ZHANG C Q, GONG C, et al. Multiview latent space learning with feature redundancy minimization[J]. IEEE Transactions on Cybernetics, 2020, 50(4): 1655-1668.
[20] MEI Y Y, REN Z W, WU B, et al. Robust graph-based multi-view clustering in latent embedding space[J]. International Journal of Machine Learning and Cybernetics, 2022, 13: 497-508.
[21] ZHENG Q H, ZHU J H, LI Z Y, et al. Feature concatenation multi-view subspace clustering[J]. Neurocomputing, 2020, 379: 89-102.
[22] LIANG N Y, YANG Z Y, LI Z N, et al. Multi-view clustering by non-negative matrix factorization with co-orthogonal constraints[J]. Knowledge-Based Systems, 2020, 194: 105582.
[23] TANG C, LIU X W, ZHU X Z, et al. Cgd: multi-view clustering via cross-view graph diffusion[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(4): 5924-5931.
[24] ZHONG G, SHU T, HUANG G H, et al. Multi-view spectral clustering by simultaneous consensus graph learning and discretization[J]. Knowledge-Based Systems, 2022, 235: 107632.
[25] 刘瑜童, 滕少华, 张巍. 图的多视角一致性稀疏聚类[J]. 计算机应用研究, 2021, 38(8): 2315-2320.
LIU Y T, TENG S H, ZHANG W. Multiview consistency sparse clustering for graph[J]. Application Research of Computers, 2021, 38(8): 2315-2320.
[26] YANG Y, WANG H. Multi-view clustering: a survey[J]. Big Data Mining and Analytics, 2018, 1(2): 83-107.
[27] 梁毅聪, 张巍, 滕少华. 块对角引导的多视角统一图聚类[J]. 小型微型计算机系统, 2023, 44(8): 1728-1734.
LIANG Y C, ZHANG W, TENG S H. Multi-view unified graph clustering guided by block diagonal[J]. Journal of Chinese Computer Systems, 2023, 44(8): 1728-1734.
[28] WANG Y, WU L, LIN X M, et al. Multi-view spectral clustering via structured low-rank matrix factorization[J]. 2018, 29(10): 4833-4843.
[29] LIANG Y W, HUANG D, WANG C D. Consistency meets inconsistency: a unified graph learning framework for multi-view clustering[C]//IEEE International Conference on Data Mining (ICDM) . Beijing: IEEE, 2019: 1204-1209.
[30] ZHAN K, NIE F P, WANG J, et al. Multiview consensus graph clustering[J]. IEEE Transactions on Image Processing, 2019, 28(3): 1261-1270.
[31] NIE F P, TIAN L, LI X L. Multiview clustering via adaptively weighted Procrustes[C]//Proceedings of the Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London: KDD, 2018: 2022-2030.
[32] WEN J, ZHANG Z, ZHANG Z, et al. Generalized Incomplete Multiview Clustering With Flexible Locality Structure Diffusion[J]. IEEE Transactions on Cybernetics, 2020, 51(1): 101-114.
[1] 谢光强, 万梓坤, 李杨. 基于分层邻域选择的切换拓扑多智能体系统一致性协议[J]. 广东工业大学学报, 2024, 41(04): 44-51.
[2] 陈应瑟, 彭世国, 王永华. 动态事件触发脉冲机制下多智能体系统的拟一致性[J]. 广东工业大学学报, 2024, 41(04): 52-60.
[3] 胡然, 彭世国. 基于脉冲观测器的多智能体系统的领导跟随一致性[J]. 广东工业大学学报, 2023, 40(05): 88-93.
[4] 谷志华, 彭世国, 黄昱嘉, 冯万典, 曾梓贤. 基于事件触发脉冲控制的具有ROUs和RONs的非线性多智能体系统的领导跟随一致性研究[J]. 广东工业大学学报, 2023, 40(01): 50-55.
[5] 谢光强, 许浩然, 李杨, 陈广福. 基于多智能体强化学习的社交网络舆情增强一致性方法[J]. 广东工业大学学报, 2022, 39(06): 36-43.
[6] 曾梓贤, 彭世国, 黄昱嘉, 谷志华, 冯万典. 两种不同脉冲欺骗攻击下随机多智能体系统的均方拟一致性[J]. 广东工业大学学报, 2022, 39(01): 71-77.
[7] 张巍, 张圳彬. 联合图嵌入与特征加权的无监督特征选择[J]. 广东工业大学学报, 2021, 38(05): 16-23.
[8] 岑仕杰, 何元烈, 陈小聪. 结合注意力与无监督深度学习的单目深度估计[J]. 广东工业大学学报, 2020, 37(04): 35-41.
[9] 滕少华, 冯镇业, 滕璐瑶, 房小兆. 联合低秩表示与图嵌入的无监督特征选择[J]. 广东工业大学学报, 2019, 36(05): 7-13.
[10] 张弘烨, 彭世国. 基于模型简化法的含有随机时延的多智能体系统一致性研究[J]. 广东工业大学学报, 2019, 36(02): 86-90,96.
[11] 张振华, 彭世国. 二阶多智能体系统拓扑切换下的领导跟随一致性[J]. 广东工业大学学报, 2018, 35(02): 75-80.
[12] 蒋盛益, 王连喜. 聚类分析研究的挑战性问题[J]. 广东工业大学学报, 2014, 31(3): 32-38.
[13] 朱婧丽1, 金朝永1, 郭红萍2. 具有参考时变状态的多智能体的H∞一致性[J]. 广东工业大学学报, 2011, 28(3): 83-86.
[14] 赵洁； 张鹏； 齐德昱； . 多数据库中间件中分布异构数据缓冲区系统的关键技术[J]. 广东工业大学学报, 2007, 24(03): 64-68.
Viewed
Full text
50
HTML PDF
Just accepted Online first Issue Just accepted Online first Issue
0 0 0 0 50 0

  From Others local
  Times 20 30
  Rate 40% 60%

Abstract
43
Just accepted Online first Issue
0 43 0
  From Others local
  Times 2 41
  Rate 5% 95%

Cited
Web of Science  Crossref   ScienceDirect  Search for Citations in Google Scholar >>
 
This page requires you have already subscribed to WoS.
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发