product iamge

Robust Latent Feature Learning for Incomplete Big Data

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Download
Search on Amazon

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

Incomplete big data are frequently encountered in many industrial applications, such as recommender systems, the Internet of Things, intelligent transportation, cloud computing, and so on. It is of great significance to analyze them for mining rich and valuable knowledge and patterns. Latent feature analysis (LFA) is one of the most popular representation learning methods tailored for incomplete big data due to its high accuracy, computational efficiency, and ease of scalability. The crux of analyzing incomplete big data lies in addressing the uncertainty problem caused by their incomplete characteristics. However, existing LFA methods do not fully consider such uncertainty.

In this book, the author introduces several robust latent feature learning methods to address such uncertainty for effectively and efficiently analyzing incomplete big data, including robust latent feature learning based on smooth L1-norm, improving robustness of latent feature learning using L1-norm, improving robustness of latent feature learning using double-space, data-characteristic-aware latent feature learning, posterior-neighborhood-regularized latent feature learning, and generalized deep latent feature learning. Readers can obtain an overview of the challenges of analyzing incomplete big data and how to employ latent feature learning to build a robust model to analyze incomplete big data. In addition, this book provides several algorithms and real application cases, which can help students, researchers, and professionals easily build their models to analyze incomplete big data.

Author(s): Di Wu
Series: SpringerBriefs in Computer Science
Publisher: Springer
Year: 2023

Language: English
Pages: 118
City: Singapore

Preface
Acknowledgments
Contents
About the Author
Chapter 1: Introduction
1.1 Background
1.2 Symbols and Notations (Table 1.1)
1.3 Book Organization
References
Chapter 2: Basis of Latent Feature Learning
2.1 Overview
2.2 Preliminaries
2.3 Latent Feature Learning
2.3.1 A Basic LFL Model
2.3.2 A Biased LFL Model
2.3.3 Algorithms Design
2.4 Performance Analysis
2.4.1 Evaluation Protocol
2.4.2 Discussion
2.5 Summary
References
Chapter 3: Robust Latent Feature Learning based on Smooth L1-norm
3.1 Overview
3.2 Related Work
3.3 A Smooth L1-Norm Based Latent Feature Model
3.3.1 Objective Formulation
3.3.2 Model Optimization
3.3.3 Incorporating Linear Biases into SL-LF
3.4 Performance Analysis
3.4.1 General Settings
3.4.2 Performance Comparison
3.4.2.1 Comparison of Prediction Accuracy
3.4.2.2 Comparison of Computational Efficiency
3.4.3 Outlier Data Sensitivity Tests
3.4.4 The Impact of Hyper-Parameter
3.5 Summary
References
Chapter 4: Improving Robustness of Latent Feature Learning Using L1-Norm
4.1 Overview
4.2 Related Work
4.3 An L1-and-L2-Norm-Oriented Latent Feature Model
4.3.1 Objective Formulation
4.3.2 Model Optimization
4.3.3 Self-Adaptive Aggregation
4.4 Performance Analysis
4.4.1 General Settings
4.4.2 L3F´s Aggregation Effects
4.4.3 Comparison Between L3F and Baselines
4.4.3.1 Comparison of Rating Prediction Accuracy
4.4.3.2 Comparison of Computational Efficiency
4.4.4 L3F´s Robustness to Outlier Data
4.5 Summary
References
Chapter 5: Improve Robustness of Latent Feature Learning Using Double-Space
5.1 Overview
5.2 Related Work
5.3 A Double-Space and Double-Norm Ensembled Latent Feature Model
5.3.1 Predictor Based on Inner Product Space (D2E-LF-1)
5.3.2 Predictor on Euclidean Distance Space (D2E-LF-2)
5.3.3 Ensemble of D2E-LF-1 and D2E-LF-2
5.3.4 Algorithm Design and Analysis
5.4 Performance Analysis
5.4.1 General Settings
5.4.2 Performance Comparison
5.5 Summary
References
Chapter 6: Data-characteristic-aware Latent Feature Learning
6.1 Overview
6.2 Related Work
6.2.1 Related LFL-Based Models
6.2.2 DPClust Algorithm
6.3 A Data-Characteristic-Aware Latent Feature Model
6.3.1 Model Structure
6.3.2 Step 1: Latent Feature Extraction
6.3.3 Step 2: Neighborhood and Outlier Detection
6.3.4 Step 3: Prediction
6.4 Performance Analysis
6.4.1 Prediction Rule Selection
6.4.2 Performance Comparison
6.5 Summary
References
Chapter 7: Posterior-neighborhood-regularized Latent Feature Learning
7.1 Overview
7.2 Related Work
7.3 A Posterior-Neighborhood-Regularized Latent Feature Model
7.3.1 Primal Latent Feature Extraction
7.3.2 Posterior-Neighborhood Construction
7.3.3 Posterior-Neighborhood-Regularized LFL
7.4 Performance Analysis
7.4.1 General Settings
7.4.2 Comparisons Between PLF and State-of-the-Art Models
7.5 Summary
References
Chapter 8: Generalized Deep Latent Feature Learning
8.1 Overview
8.2 Related Work
8.3 A Deep Latent Feature Model
8.4 Performance Analysis
8.4.1 General Settings
8.4.2 Effects of Layer Count in DLF
8.4.3 Comparison Between DLF and Related Models
8.5 Summary
References
Chapter 9: Conclusion and Outlook
9.1 Conclusion
9.2 Outlook