Feature Selection for Latent Factor Models

2024/12/13 by Rittwika Kansabanik, Kansabanik, Rittwika, Adrian Barbu +1
Computer Science · #Applications (stat.AP) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Technology and Data Analysis

paper · pdf · doi:10.48550/arxiv.2412.10128

openalex publication_date 2024/12/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Feature selection is crucial for pinpointing relevant features in high-dimensional datasets, mitigating the 'curse of dimensionality,' and enhancing machine learning performance. Traditional feature selection methods for classification use data from all classes to select features for each class. This paper explores feature selection methods that select features for each class separately, using class models based on low-rank generative methods and introducing a signal-to-noise ratio (SNR) feature selection criterion. This novel approach has theoretical true feature recovery guarantees under certain assumptions and is shown to outperform some existing feature selection methods on standard classification datasets.

Related

• Feature and Variable Selection in Classification
• Deep Feature Selection Using a Novel Complementary Feature Mask
• Embedded methods for feature selection in neural networks
• Feature Selection as Deep Sequential Generative Learning
• Feature Selection Using Classifier in High Dimensional Data