Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization

Hongzong Li; Jun Wang

doi:10.1109/ICICIP64458.2025.10898111

Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Bi-clustering, also known as co-clustering, is a powerful data analysis technique that simultaneously clusters rows and columns of a data matrix, revealing hidden patterns. In this paper, we propose a neurodynamics-driven binary matrix factorization approach for bi-clustering binary data. The proposed method utilizes multiple discrete Hopfield networks operating concurrently to explore local optimal solutions. Furthermore, a particle swarm optimization rule is iteratively applied to reinitialize the neuronal states for directing the search toward better solutions. Comparative evaluations across six benchmark datasets reveal that the proposed method outperforms five existing methods in terms of five internal and external indices. © 2025 IEEE.

Original language	English
Title of host publication	2025 13th International Conference on Intelligent Control and Information Processing (ICICIP)
Publisher	IEEE
Pages	90-97
ISBN (Electronic)	979-8-3315-1614-7
ISBN (Print)	79-8-3315-1615-4
DOIs	https://doi.org/10.1109/ICICIP64458.2025.10898111
Publication status	Published - 2025
Event	13th International Conference on Intelligent Control and Information Processing (ICICIP 2025) - Hybrid, Muscat, Oman Duration: 6 Feb 2025 → 11 Feb 2025 https://conference.cs.cityu.edu.hk/icicip/ICICIP2025/index.html

Publication series

Name	International Conference on Intelligent Control and Information Processing, ICICIP
ISSN (Print)	2835-9569
ISSN (Electronic)	2835-9577

Conference

Conference	13th International Conference on Intelligent Control and Information Processing (ICICIP 2025)
Abbreviated title	ICICIP2025
Country/Territory	Oman
City	Muscat
Period	6/02/25 → 11/02/25
Internet address	https://conference.cs.cityu.edu.hk/icicip/ICICIP2025/index.html

Funding

This work was supported in part by the Research Grants Council of the Hong Kong Special Administrative Region of China under Grants 11202019, and 11203721; and in part by the InnoHK initiative, the Government of the Hong Kong Special Administrative Region, and the Laboratory for AI-Powered Financial Technologies.

Research Keywords

Bi-clustering
binary matrix factorization
Boltzmann machine
co-clustering
collaborative neurodynamic optimization
quadratic unconstrained binary optimization (QUBO)

Access Output

10.1109/ICICIP64458.2025.10898111

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{dc9c58e2d1584735a51d24d4efe6a0f6,

title = "Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization",

abstract = "Bi-clustering, also known as co-clustering, is a powerful data analysis technique that simultaneously clusters rows and columns of a data matrix, revealing hidden patterns. In this paper, we propose a neurodynamics-driven binary matrix factorization approach for bi-clustering binary data. The proposed method utilizes multiple discrete Hopfield networks operating concurrently to explore local optimal solutions. Furthermore, a particle swarm optimization rule is iteratively applied to reinitialize the neuronal states for directing the search toward better solutions. Comparative evaluations across six benchmark datasets reveal that the proposed method outperforms five existing methods in terms of five internal and external indices. {\textcopyright} 2025 IEEE.",

keywords = "Bi-clustering, binary matrix factorization, Boltzmann machine, co-clustering, collaborative neurodynamic optimization, quadratic unconstrained binary optimization (QUBO)",

author = "Hongzong Li and Jun Wang",

year = "2025",

doi = "10.1109/ICICIP64458.2025.10898111",

language = "English",

isbn = "79-8-3315-1615-4",

series = "International Conference on Intelligent Control and Information Processing, ICICIP",

publisher = "IEEE",

pages = "90--97",

booktitle = "2025 13th International Conference on Intelligent Control and Information Processing (ICICIP)",

address = "United States",

note = "13th International Conference on Intelligent Control and Information Processing (ICICIP 2025), ICICIP2025 ; Conference date: 06-02-2025 Through 11-02-2025",

url = "https://conference.cs.cityu.edu.hk/icicip/ICICIP2025/index.html",

}

Li, H & Wang, J 2025, Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization. in 2025 13th International Conference on Intelligent Control and Information Processing (ICICIP). International Conference on Intelligent Control and Information Processing, ICICIP, IEEE, pp. 90-97, 13th International Conference on Intelligent Control and Information Processing (ICICIP 2025), Muscat, Oman, 6/02/25. https://doi.org/10.1109/ICICIP64458.2025.10898111

Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization. / Li, Hongzong ; Wang, Jun.
2025 13th International Conference on Intelligent Control and Information Processing (ICICIP). IEEE, 2025. p. 90-97 (International Conference on Intelligent Control and Information Processing, ICICIP).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization

AU - Li, Hongzong

AU - Wang, Jun

PY - 2025

Y1 - 2025

N2 - Bi-clustering, also known as co-clustering, is a powerful data analysis technique that simultaneously clusters rows and columns of a data matrix, revealing hidden patterns. In this paper, we propose a neurodynamics-driven binary matrix factorization approach for bi-clustering binary data. The proposed method utilizes multiple discrete Hopfield networks operating concurrently to explore local optimal solutions. Furthermore, a particle swarm optimization rule is iteratively applied to reinitialize the neuronal states for directing the search toward better solutions. Comparative evaluations across six benchmark datasets reveal that the proposed method outperforms five existing methods in terms of five internal and external indices. © 2025 IEEE.

AB - Bi-clustering, also known as co-clustering, is a powerful data analysis technique that simultaneously clusters rows and columns of a data matrix, revealing hidden patterns. In this paper, we propose a neurodynamics-driven binary matrix factorization approach for bi-clustering binary data. The proposed method utilizes multiple discrete Hopfield networks operating concurrently to explore local optimal solutions. Furthermore, a particle swarm optimization rule is iteratively applied to reinitialize the neuronal states for directing the search toward better solutions. Comparative evaluations across six benchmark datasets reveal that the proposed method outperforms five existing methods in terms of five internal and external indices. © 2025 IEEE.

KW - Bi-clustering

KW - binary matrix factorization

KW - Boltzmann machine

KW - co-clustering

KW - collaborative neurodynamic optimization

KW - quadratic unconstrained binary optimization (QUBO)

UR - http://www.scopus.com/inward/record.url?scp=105001125399&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105001125399&origin=recordpage

U2 - 10.1109/ICICIP64458.2025.10898111

DO - 10.1109/ICICIP64458.2025.10898111

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 79-8-3315-1615-4

T3 - International Conference on Intelligent Control and Information Processing, ICICIP

SP - 90

EP - 97

BT - 2025 13th International Conference on Intelligent Control and Information Processing (ICICIP)

PB - IEEE

T2 - 13th International Conference on Intelligent Control and Information Processing (ICICIP 2025)

Y2 - 6 February 2025 through 11 February 2025

ER -

Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Neurodynamics-driven Optimization and Control of Intelligent Heating, Ventilation and Air Conditioning Systems

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

Cite this

Bi-clustering of Binary Data via Neurodynamics-driven Binary Matrix Factorization

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Neurodynamics-driven Optimization and Control of Intelligent Heating, Ventilation and Air Conditioning Systems

GRF: Collaborative Neurodynamic Approaches to Portfolio Optimization

Cite this