AI Article Synopsis

  • Unsupervised feature selection (UFS) removes redundant information and picks the most representative features from high-dimensional data, which is crucial for effective data preprocessing.
  • Many existing methods explore data correlations and labeling but haven't integrated these approaches into a unified model for optimal feature selection.
  • This article introduces a new UFS method, CNAFS, that combines convex non-negative matrix factorization with adaptive graph constraints to enhance feature selection by simultaneously optimizing pseudo labeling and self-expression, validated through extensive experiments.

Article Abstract

Unsupervised feature selection (UFS) aims to remove the redundant information and select the most representative feature subset from the original data, so it occupies a core position for high-dimensional data preprocessing. Many proposed approaches use self-expression to explore the correlation between the data samples or use pseudolabel matrix learning to learn the mapping between the data and labels. Furthermore, the existing methods have tried to add constraints to either of these two modules to reduce the redundancy, but no prior literature embeds them into a joint model to select the most representative features by the computed top ranking scores. To address the aforementioned issue, this article presents a novel UFS method via a convex non-negative matrix factorization with an adaptive graph constraint (CNAFS). Through convex matrix factorization with adaptive graph constraint, it can dig up the correlation between the data and keep the local manifold structure of the data. To our knowledge, it is the first work that integrates pseudo label matrix learning into the self-expression module and optimizes them simultaneously for the UFS solution. Besides, two different manifold regularizations are constructed for the pseudolabel matrix and the encoding matrix to keep the local geometrical structure. Eventually, extensive experiments on the benchmark datasets are conducted to prove the effectiveness of our method. The source code is available at: https://github.com/misteru/CNAFS.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCYB.2020.3034462DOI Listing

Publication Analysis

Top Keywords

matrix factorization
12
factorization adaptive
12
adaptive graph
12
convex non-negative
8
non-negative matrix
8
unsupervised feature
8
feature selection
8
select representative
8
correlation data
8
pseudolabel matrix
8

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!