A general soft-balanced clustering framework based on a novel balance regularizer

被引:9
作者
Chen, Huimin [1 ,2 ]
Zhang, Qianrong [1 ,2 ]
Wang, Rong [1 ]
Nie, Feiping [1 ]
Li, Xuelong [1 ]
机构
[1] Northwestern Polytech Univ, Sch Aitificial Intelligence Opt & Elect iOPEN, Xian 710072, Shaanxi, Peoples R China
[2] Northwestern Polytech Univ, Sch Comp Sci, Xian 710072, Shaanxi, Peoples R China
基金
中国国家自然科学基金;
关键词
Clustering; Balanced clustering; Soft-balanced clustering; Balance regularizer; ALGORITHM;
D O I
10.1016/j.sigpro.2022.108572
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In the past few decades, clustering algorithms have been extensively explored. Conventional clustering methods such as k-means and spectral clustering have achieved excellent clustering performance, however they pay less attention on the balanced distribution of many real-world data, which is significant to some practical applications. In this paper, we present a soft-balanced clustering framework, and the degree of balance can be flexibly adjusted by setting the parameter. The core of the framework is a novel regularizer, by optimizing which the clustering becomes more balanced. The framework can be combined with many clustering methods in a concise way. Taking k-means as an example, we extend k-means to a Balanced k-means with a Novel Constraint (BKNC) model with the help of this framework. Then an alternative iterative optimization algorithm is proposed to solve it. Comprehensive experiments on several benchmark datasets demonstrate the superior balance and clustering performance of the BKNC method than other k-means based hard- and soft-balanced methods. (C) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页数:10
相关论文
共 38 条
[1]   Clustering in sensor networks: A literature survey [J].
Afsar, M. Mehdi ;
Tayarani-N, Mohammad-H. .
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS, 2014, 46 :198-226
[2]  
Althoff T., 2011, Ser. Gesellschaft Inf., V1, P27
[3]  
Bertsekas D.P., 2019, Reinforcement Learning and Optimal Control
[4]  
Bühlmann P, 2011, SPRINGER SER STAT, P1, DOI 10.1007/978-3-642-20192-9
[5]  
Cai D, 2007, PROC CVPR IEEE, P650
[6]   Enhanced Balanced Min Cut [J].
Chen, Xiaojun ;
Hong, Weijun ;
Nie, Feiping ;
Huang, Joshua Zhexue ;
Shen, Li .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2020, 128 (07) :1982-1995
[7]   LABIN: Balanced Min Cut for Large-Scale Data [J].
Chen, Xiaojun ;
Chen, Renjie ;
Wu, Qingyao ;
Fang, Yixiang ;
Nie, Feiping ;
Huang, Joshua Zhexue .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (03) :725-736
[8]   Spectral Clustering of Large-scale Data by Directly Solving Normalized Cut [J].
Chen, Xiaojun ;
Hong, Weijun ;
Nie, Feiping ;
He, Dan ;
Yang, Min ;
Huang, Joshua Zhexue .
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, :1206-1215
[9]   A Self-Balanced Min-Cut Algorithm for Image Clustering [J].
Chen, Xiaojun ;
Haung, Joshua Zhexue ;
Nie, Feiping ;
Chen, Renjie ;
Wu, Qingyao .
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :2080-2088
[10]   Multi-label learning for concept-oriented labels of product image data [J].
Dai, Yong ;
Li, Yi ;
Li, Shu-Tao .
IMAGE AND VISION COMPUTING, 2020, 93