基于自表示学习更新的图非负矩阵分解聚类

陈勇亨; 王振友; 徐圣兵

doi:10.12052/gdutxb.250181

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于自表示学习更新的图非负矩阵分解聚类

计算机科学与技术 | 更新时间：2026-08-04

- 基于自表示学习更新的图非负矩阵分解聚类
- Graph Non-negative Matrix Factorization Based on Self-representation Learning Update for Clustering
- 广东工业大学学报 2026年43卷第4期页码：103-114
- 作者机构：
  
  广东工业大学数学与统计学院,广东,广州,510520
- 作者简介：
  
  陈勇亨(2001–) ，男，硕士研究生，主要研究方向为非负矩阵分解，E-mail：1666597702@qq.com
  徐圣兵(1974–)，男，讲师，博士，主要研究方向为机器学习、环境暴露与健康效应等，E-mail：xushengbing@gdut.edu.cn
- 基金信息：
  
  广东省自然科学基金资助项目(2023A1515012891)
- DOI：10.12052/gdutxb.250181
  中图分类号： TP391
- 纸质出版：2026
- 稿件说明：
移动端阅览
陈勇亨, 王振友, 徐圣兵. 基于自表示学习更新的图非负矩阵分解聚类[J]. 广东工业大学学报, 2026, 43(4): 103-114.
陈勇亨, 王振友, 徐圣兵. 基于自表示学习更新的图非负矩阵分解聚类[J]. 广东工业大学学报, 2026, 43(4): 103-114. DOI： 10.12052/gdutxb.250181.

DOI： 10.12052/gdutxb.250181

摘要

非负矩阵分解(Non-negative Matrix Factorization，NMF) 是一种基于矩阵分解的降维技术，用于寻找基于潜在特征的线性表示。针对NMF忽略数据局部几何结构的问题，本文提出的图非负矩阵分解(Graph non-negative Matrix Factorization，GNMF)虽然可以较好地改善高维空间中数据之间的几何关系，但其所遵循的图信息，即邻接矩阵是基于可观测空间中原始样本的相关性构建的，无法反映对象间的真实距离关系。针对这个问题，本文将基于自表示的图信息融入到NMF的算法框架中，提出了自表示更新下的图非负矩阵分解(Graph Non-negative Matrix Factorization based on Self-representation Learning Update，GNMFSLU)，该方法利用迭代的方式对图的邻接矩阵进行更新，使得图信息更加接近对象间的真实距离关系，增强了NMF的聚类性能。

Abstract

Non-negative Matrix Factorization (NMF) is a dimensionality reduction technique based on matrix factorization

used to find linear representations based on latent features. Although Graph Nonnegative Matrix Factorization (GNMF)

which is proposed to address the issue of NMF ignoring the local geometric structure of data

can improve the geometric relationship between data in high-dimensional spaces relatively well

the graph information it follows - that is

the adjacency matrix - is constructed based on the distance relationship of the observable space of the original samples and cannot reflect the true distance relationship between objects. To address this issue

we integrate the graph information based on self-representation into the algorithm framework of NMF and propose Graph Non-negative Matrix Factorization based on Self-representation Learning Update (GNMFSLU) . This method updates the adjacency matrix of the graph in each iteration

thereby making the graph information closer to the true distance relationship between objects and enhancing the clustering performance of NMF.

关键词

Keywords

references

CHEN S, ZHU Z D, YANG Z Y, et al . Co- consensus multi-view spectral clustering[J ] . Journal of Guangdong University of Technology, 2024, 41(4): 98-105.

JIANG S Y, WANG L X. Some challenges in clustering analysis[J]. Journal of Guangdong University of Technology, 2014, 31(3): 32-38.

CHEN L, FAN M, WANG J. A controlled data envelopment analysis clustering approach based on individual perspective[J]. Information Sciences, 2024, 677: 120932.

KANG Z, PENG C, CHENG Q. Kernel-driven similarity learning[J]. Neurocomputing, 2017, 267: 210-219.

CHEN Y, LI W, ZHAO J. A novel study of kernel graph regularized semi-non-negative matrix factorization with orthogonal subspace for clustering[J]. Big Data Research, 2025, 40: 100531.

SHEN X M, LI B J, SUN X, et al . Large scale face clustering based on convolutional neural network[J ] . Journal of Guangdong University of Technology, 2016, 33(6): 77-84.

DENG P, ZHANG F, LI T, et al . Biased unconstrained non-negative matrix factorization for clustering[J ] . Knowledge-Based Systems, 2022, 239: 108040.

LEE D, SEUNG, H. Learning the parts of objects by non-negative matrix factorization.[J]. Nature, 1999, 401: 788-791.

YAN J, LIU H, LEI Z, et al . Two-dimensional data partitioning for non-negative matrix tri-factorization[J ] . Big Data Research, 2024, 37: 100473.

CHALISE P, NI Y, FRIDLEY B L. Network-based integrative clustering of multiple types of genomic data using non-negative matrix factorization[J]. Computers in Biology and Medicine, 2020, 118: 103625.

LIU X, SONG P, SHENG C, et al . Robust multi-view non-negative matrix factorization for clustering[J ] . Digital Signal Processing, 2022, 123: 103447.

VESSELINOV V V, AHMMED B, MUDUNURU M K, et al . Discovering hidden geothermal signatures using non-negative matrix factorization with customized K-means clustering[J ] . Geothermics, 2022, 106: 102576.

LI T, DING C H Q. Nonnegative matrix factorizations for clustering: a survey[J]. Data Cluster, 2014, 28: 652.

JING W, LU L, OU W. Semi-supervised non-negative matrix factorization with structure preserving for image clustering[J]. Neural Networks, 2025, 187: 107340.

LIU X, SONG P. Virtual label guided multi-view non-negative matrix factorization for data clustering[J]. Digital Signal Processing, 2023, 133: 103888.

PENG S, SER W, CHEN B, et al . Robust orthogonal nonnegative matrix tri-factorization for data representation [J ] . Knowledge-Based Systems, 2020, 201-202: 106054.

XING Z, WEN M, PENG J, et al . Discriminative semi-supervised non-negative matrix factorization for data clustering[J ] . Engineering Applications of Artificial Intelligence, 2021, 103: 104289.

CHEN Y, HUANG T Z, ZHAO X L, et al . Hyperspectral image restoration using framelet-regularized low-rank nonnegative matrix factorization[J ] . Applied Mathematical Modelling, 2018, 63: 128-147.

LUO W, WU Z, ZHOU N. Hypergraph-based convex semi-supervised unconstraint symmetric matrix factorization for image clustering[J]. Information Sciences, 2024, 680: 121138.

ZENG K, YU J, LI C, et al . Image clu stering by hyper-graph regularized non-negative matrix factorization[J ] . Neurocomputing, 2014, 138: 209-217.

AGHDAM M H, ZANJANI M D. A novel regularized asymmetric non-negative matrix factorization for text clustering[J]. Information Processing Management, 2021, 58(6): 102694.

DENG P, LI T, WANG D, et al . Multi-view clustering guided by unconstrained non-negative matrix factorization[J ] . Knowledge-Based Systems, 2023, 266: 110425.

GUNAWARDENA S, LUONG K, BALASUBRAMANIAM T, et al . DCCNMF: deep complementary and consensus non-negative matrix factorization for multi-view clustering[J ] . Knowledge-Based Systems, 2024, 285: 111330.

LI J, KANG P, SUN W, et al . Local residual preserving non-negative matrix factorization for multi-view clustering[J ] . Neurocomputing, 2024, 600: 128054.

LI H, ZHOU Y, ZHAO P, et al . Class-driven nonnegative matrix factorization with manifold regularization for data clustering[J ] . Neurocomputing, 2024, 592: 127751.

HYEKYOUNG L, JIHO Y, SEUNGJIN C. Semi-supervised nonnegative matrix factorization[J]. IEEE Signal Processing Letters, 2010, 17(1): 4-7.

LIU H F, WU Z H, LI X L, et al . Constrained nonnegative matrix factorization for image representation[J ] . IEEE Transactions On Pattern Analysis And Machine Intelligence, 2012, 34(7): 1299-1311.

CHAVOSHINEJAD J, SEYEDI S A, AKHLAGHIAN T F, et al . Self-supervised semi-supervised nonnegative matrix factorization for data clustering[J ] . Pattern Recognition, 2023, 137: 109282.

LI J, SHEN X, LI C, et al . Elements discriminative non-negative matrix factorization for data clustering [J ] . Engineering Applications of Artificial Intelligence, 2025, 156(Part A): 111210.

GUNAWARDENA S D L, LUONG K, BALASUBRAMANIAM T, et al . LapSDNMF: label propagation assisted soft-constrained deep non-negative matrix factorisation for semi-supervised multi-view clustering[J ] . Machine Learning with Applications, 2025, 22: 100783.

LI S, WANG Q, LUO M, et al . Self-supervised star graph optimization embedding non-negative matrix factorization[J ] . Information Processing Management, 2025, 62(2): 103969.

WU W B, ZHOU W, TANG D M. Feature learning method based on improved graph regularized auto-encoder[J]. Application Research of Computers, 2022, 39(2): 485-490.

DENG C, XIAOFEI H, JIAWEI H, et al . Graph regularized nonnegative matrix factorization for data representation[J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1548-1560.

ZUO H, LI S, LIANG C, et al . Auto-adjustable hypergraph regularized non-negative matrix factorization for image clustering[J ] . Pattern Recognition, 2024, 145: 109963.

SHANG F, JIAO L C, WANG F. Graph dual regularization non-negative matrix factorization for co-clustering[J]. Pattern Recognition, 2012, 45(6): 2237-2250.

JING SUN X C, FUMING SUN, RICHANG HONG. Dual graph-regularized constrained nonnegative matrix factorization for Image clustering[J]. KSII Transactions on Internet and Information Systems, 2017, 11(5): 2607-2627.

CHEN Y, QU G, ZHAO J. Orthogonal graph regularized non-negative matrix factorization under sparse constraints for clustering[J]. Expert Systems with Applications, 2024, 249: 123797.

ELHAMIFAR E, VIDAL R. Sparse subspace clustering: algorithm, theory, and applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(11): 2765-2781.

CHEN M, WANG J, GUO A X, et al . Multi-source information reconstruction and self-representation forincomplete multi-view clustering[J ] . Control and Decision, 2025, 41(3): 765-776.

SAM T, ROWEIS L K S. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500): 2323.

YANG L D, ZHAO Y J, PAN Z H. Research on L21 incremental non-negative matrix factorizationwith sparsity constraints[J]. Science Technology Information, 2024, 22(12): 240-244.

LEE D, SEUNG H S. Algorithms for non-negative matrix factorization[C]//Advances in Neural Information Processing Systems. Denver, CO: MIT Press, 2000: 556-562.

MIROSLAV FIEDLER P. Miroslav fiedler algebraic connectivity of graphs[J]. Czechoslovak Mathematical Journal, 1973, 23: 298-305.

LLOYD S. Least squares quantization in PCM[J]. IEEE Transactions on Information Theory, 1982, 28(2): 129-137.

DING C, LI T, PENG W, et al . Orthogonal nonnegative matrix t-factorizations for clustering[C ] //Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining. New York: Association for Computing Machinery, 2006: 126-135.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于自适应图正则化低秩表示的scRNA-seq数据分析方法

基于方向控制的差分隐私轨迹数据发布方法

一种基于Fréchet距离的谱聚类算法

基于多阶段聚类的PM2.5质量浓度预测及对比研究

改进的聚类算法在恐怖袭击事件中的应用