# DeepMatrixFactorization

**Repository Path**: jshncu/DeepMatrixFactorization

## Basic Information

- **Project Name**: DeepMatrixFactorization
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 1
- **Created**: 2024-01-23
- **Last Updated**: 2026-03-30

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# DeepMatrixFactorization

#### Introduction
This package includes the proposed multi-view data clustering methods. The code shared in this repository implements the algorithms for the models proposed in the following papers. Welcome to use our models as the comparison methods in your papers. If you have any questions, you are welcome to send an email to me (jianshengwu@ncu.edu.cn). The source code for most of our published works is publicly available on Gitee. Should you be unable to locate the code for a specific work there, you can alternatively search for it on our Github repository (https://github.com/jshncu) or contact us via email for assistance.

#### 软件架构
1、Method 1：DNMF-CSLT
 Running the matlab script "Yale_Demos.m" in the folder "DNMF-CSLT" will yield the clustering partition of the dataset Yale.

 **_DNMF-CSLT ( Cluster Structure Augmented Deep Nonnegative Matrix Factorization with Low-rank Tensor Learning:  https://doi.org/10.1016/j.ins.2024.120585)_** 

@article{DNMF_DNMFCSLT_Zhong_2024, title={ Cluster Structure Augmented Deep Nonnegative Matrix Factorization with Low-rank Tensor Learning}, author={Zhong, Bo and Wu, Jian-Sheng and Huang, Wei}, journal={Information Sciences}, volume={670}, pages={120585}, year={2024}, publisher={Elsevier}, doi={10.1016/j.ins.2024.120585}, }

2、Method 2: MDRNMF 
  Running the matlab script "demo.m" in the folder "MDRNMF" will yield the clustering partition of the dataset BBCSport.

 **_MDRNMF (Multi-view Deep Reciprocal Nonnegative Matrix Factorization: https://doi.org/10.1016/j.engappai.2024.109508 )_** 

@article{DNMF_MDRNMF_Zhong_2025, title={Multi-view Deep Reciprocal Nonnegative Matrix Factorization}, author={Zhong, Bo and Wu, Jun-Yun and Wu, Jian-Sheng and Min, Weidong}, journal={Engineering Applications of Artificial Intelligence}, volume={139}, pages={109508}, year={2025}, publisher={Elsevier}, doi={10.1016/j.engappai.2024.109508}, }

3、Method 3：ADA-NMF
 Running the matlab script "MSRC_Demos.m" in the folder "ADA-NMF" will yield the clustering partition of the dataset MSRC_v1.

 **_ADA-NMF ( Asymmetric Deep Autoencoder-like Non-negative Matrix Factorization for Multi-view Clustering: https://doi.org/10.1016/j.engappai.2026.114235)_** 

@article{DNMF_ADANMF_Zhao_2026, title={ Asymmetric Deep Autoencoder-like Non-negative Matrix Factorization for Multi-view Clustering}, author={Zhao, Sang-Qi and Zeng, Qing-Peng and Wu, Jian-Sheng}, journal={Engineering Applications of Artificial Intelligence}, volume={170}, pages={114235}, year={2026}, publisher={Elsevier}, doi={https://doi.org/10.1016/j.engappai.2026.114235}, }


4、Method 4: TNAGL
  Running the matlab script "UCI2_Demos.m" in the folder "TNAGL/Demos" will yield the clustering partition of the dataset BBCSport.

 **_TNAGL (Tensorized Noise-aware Anchor Graph Learning with Deep Complementary Information Propagation for Scalable Multi-view Clustering )_** 

@article{DNMF_TNAGL_Wu_2026, title={Tensorized Noise-aware Anchor Graph Learning with Deep Complementary Information Propagation for Scalable Multi-view Clustering}, author={*****}, journal={****}, volume={***}, pages={****}, year={****}, publisher={IEEE}, doi={****}, }