Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

SEGAN: semi-supervised learning approach for missing data imputation

Xiaohua Pan, Weifeng Wu, Peiran Liu, Zhen Li, Peng Lu, Peijian Cao, Jianfeng Zhang, Xianfei Qiu, YangYang Wu

TL;DR

This paper theoretically proves that the SEGAN model that introduces a classifier and a missing hint matrix can learn the real known data distribution characteristics when reaching Nash equilibrium.

Abstract

In many practical real-world applications, data missing is a very common phenomenon, making the development of data-driven artificial intelligence theory and technology increasingly difficult. Data completion is an important method for missing data preprocessing. Most existing miss-ing data completion models directly use the known information in the missing data set but ignore the impact of the data label information contained in the data set on the missing data completion model. To this end, this paper proposes a missing data completion model SEGAN based on semi-supervised learning, which mainly includes three important modules: generator, discriminator and classifier. In the SEGAN model, the classifier enables the generator to make more full use of known data and its label information when predicting missing data values. In addition, the SE-GAN model introduces a missing hint matrix to allow the discriminator to more effectively distinguish between known data and data filled by the generator. This paper theoretically proves that the SEGAN model that introduces a classifier and a missing hint matrix can learn the real known data distribution characteristics when reaching Nash equilibrium. Finally, a large number of experiments were conducted in this article, and the experimental results show that com-pared with the current state-of-the-art multivariate data completion method, the performance of the SEGAN model is improved by more than 3%.

SEGAN: semi-supervised learning approach for missing data imputation

TL;DR

This paper theoretically proves that the SEGAN model that introduces a classifier and a missing hint matrix can learn the real known data distribution characteristics when reaching Nash equilibrium.

Abstract

In many practical real-world applications, data missing is a very common phenomenon, making the development of data-driven artificial intelligence theory and technology increasingly difficult. Data completion is an important method for missing data preprocessing. Most existing miss-ing data completion models directly use the known information in the missing data set but ignore the impact of the data label information contained in the data set on the missing data completion model. To this end, this paper proposes a missing data completion model SEGAN based on semi-supervised learning, which mainly includes three important modules: generator, discriminator and classifier. In the SEGAN model, the classifier enables the generator to make more full use of known data and its label information when predicting missing data values. In addition, the SE-GAN model introduces a missing hint matrix to allow the discriminator to more effectively distinguish between known data and data filled by the generator. This paper theoretically proves that the SEGAN model that introduces a classifier and a missing hint matrix can learn the real known data distribution characteristics when reaching Nash equilibrium. Finally, a large number of experiments were conducted in this article, and the experimental results show that com-pared with the current state-of-the-art multivariate data completion method, the performance of the SEGAN model is improved by more than 3%.
Paper Structure (19 sections, 2 theorems, 23 equations, 2 figures, 3 tables)

This paper contains 19 sections, 2 theorems, 23 equations, 2 figures, 3 tables.

Table of Contents

  1. Abstract
  2. Introduction
  3. Related Work
  4. Methods
  5. Experiment
  6. Result
  7. Discussion and Conclusions
  8. Acknowledgments

Key Result

Theorem 1

For a given missingness hint matrix $\mathbf{R}$, the equilibrium state of the USEGAN model $V(G, D)$ can be uniquely determined. At this equilibrium, the data distribution $p$ generated by the USEGAN model and the true data distribution $\hat{p}$ are the same under the given conditions, that is, $p

Figures (2)

  • Figure 1: The architecture of SEGAN.
  • Figure 2: The prediction performance vs. missing rate $R_m$.

Theorems & Definitions (2)

  • Theorem 1
  • Theorem 2