Nonnegative Matrix Factorization in Dimensionality Reduction: A Survey
- URL: http://arxiv.org/abs/2405.03615v1
- Date: Mon, 6 May 2024 16:32:01 GMT
- Title: Nonnegative Matrix Factorization in Dimensionality Reduction: A Survey
- Authors: Farid Saberi-Movahed, Kamal Berahman, Razieh Sheikhpour, Yuefeng Li, Shirui Pan,
- Abstract summary: Dimensionality Reduction plays a pivotal role in improving feature learning accuracy and reducing training time.
Nonnegative Matrix Factorization (NMF) has emerged as a popular and powerful method for dimensionality reduction.
This paper presents a comprehensive survey of NMF, focusing on its applications in both feature extraction and feature selection.
- Score: 45.06188379747932
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Dimensionality Reduction plays a pivotal role in improving feature learning accuracy and reducing training time by eliminating redundant features, noise, and irrelevant data. Nonnegative Matrix Factorization (NMF) has emerged as a popular and powerful method for dimensionality reduction. Despite its extensive use, there remains a need for a comprehensive analysis of NMF in the context of dimensionality reduction. To address this gap, this paper presents a comprehensive survey of NMF, focusing on its applications in both feature extraction and feature selection. We introduce a classification of dimensionality reduction, enhancing understanding of the underlying concepts. Subsequently, we delve into a thorough summary of diverse NMF approaches used for feature extraction and selection. Furthermore, we discuss the latest research trends and potential future directions of NMF in dimensionality reduction, aiming to highlight areas that need further exploration and development.
Related papers
- Large-Scale OD Matrix Estimation with A Deep Learning Method [70.78575952309023]
The proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization.
We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset.
arXiv Detail & Related papers (2023-10-09T14:30:06Z) - RecFNO: a resolution-invariant flow and heat field reconstruction method
from sparse observations via Fourier neural operator [8.986743262828009]
We propose an end-to-end physical field reconstruction method with both excellent performance and mesh transferability named RecFNO.
The proposed method aims to learn the mapping from sparse observations to flow and heat field in infinite-dimensional space.
The experiments conducted on fluid mechanics and thermology problems show that the proposed method outperforms existing POD-based and CNN-based methods in most cases.
arXiv Detail & Related papers (2023-02-20T07:20:22Z) - DimenFix: A novel meta-dimensionality reduction method for feature
preservation [64.0476282000118]
We propose a novel meta-method, DimenFix, which can be operated upon any base dimensionality reduction method that involves a gradient-descent-like process.
By allowing users to define the importance of different features, which is considered in dimensionality reduction, DimenFix creates new possibilities to visualize and understand a given dataset.
arXiv Detail & Related papers (2022-11-30T05:35:22Z) - Adaptive Weighted Nonnegative Matrix Factorization for Robust Feature
Representation [9.844796520630522]
Nonnegative matrix factorization (NMF) has been widely used to dimensionality reduction in machine learning.
Traditional NMF does not properly handle outliers, so that it is sensitive to noise.
This paper proposes an adaptive weighted NMF, which introduces weights to emphasize the different importance of each data point.
arXiv Detail & Related papers (2022-06-07T05:27:08Z) - Hyperspectral Unmixing Based on Nonnegative Matrix Factorization: A
Comprehensive Review [25.50091058791411]
Hyperspectral unmixing estimates a set of endmembers and their corresponding abundances from a hyperspectral image.
Nonnegative matrix factorization (NMF) plays an increasingly significant role in solving this problem.
We show how to improve NMF by utilizing the main properties of HSIs.
arXiv Detail & Related papers (2022-05-20T02:48:43Z) - Log-based Sparse Nonnegative Matrix Factorization for Data
Representation [55.72494900138061]
Nonnegative matrix factorization (NMF) has been widely studied in recent years due to its effectiveness in representing nonnegative data with parts-based representations.
We propose a new NMF method with log-norm imposed on the factor matrices to enhance the sparseness.
A novel column-wisely sparse norm, named $ell_2,log$-(pseudo) norm, is proposed to enhance the robustness of the proposed method.
arXiv Detail & Related papers (2022-04-22T11:38:10Z) - Feature Weighted Non-negative Matrix Factorization [92.45013716097753]
We propose the Feature weighted Non-negative Matrix Factorization (FNMF) in this paper.
FNMF learns the weights of features adaptively according to their importances.
It can be solved efficiently with the suggested optimization algorithm.
arXiv Detail & Related papers (2021-03-24T21:17:17Z) - Algorithms for Nonnegative Matrix Factorization with the
Kullback-Leibler Divergence [20.671178429005973]
Kullback-Leibler (KL) divergence is one of the most widely used objective function for nonnegative matrix factorization (NMF)
We propose three new algorithms that guarantee the non-increasingness of the objective function.
We conduct extensive numerical experiments to provide a comprehensive picture of the performances of the KL NMF algorithms.
arXiv Detail & Related papers (2020-10-05T11:51:39Z) - Semi-supervised deep learning for high-dimensional uncertainty
quantification [6.910275451003041]
This paper presents a semi-supervised learning framework for dimension reduction and reliability analysis.
An autoencoder is first adopted for mapping the high-dimensional space into a low-dimensional latent space.
A deep feedforward neural network is utilized to learn the mapping relationship and reconstruct the latent space.
arXiv Detail & Related papers (2020-06-01T15:15:42Z) - Two-Dimensional Semi-Nonnegative Matrix Factorization for Clustering [50.43424130281065]
We propose a new Semi-Nonnegative Matrix Factorization method for 2-dimensional (2D) data, named TS-NMF.
It overcomes the drawback of existing methods that seriously damage the spatial information of the data by converting 2D data to vectors in a preprocessing step.
arXiv Detail & Related papers (2020-05-19T05:54:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.