Multiple Imputation with Denoising Autoencoder using Metamorphic Truth and Imputation Feedback

02/19/2020
by   Haw-minn Lu, et al.
0

Although data may be abundant, complete data is less so, due to missing columns or rows. This missingness undermines the performance of downstream data products that either omit incomplete cases or create derived completed data for subsequent processing. Appropriately managing missing data is required in order to fully exploit and correctly use data. We propose a Multiple Imputation model using Denoising Autoencoders to learn the internal representation of data. Furthermore, we use the novel mechanisms of Metamorphic Truth and Imputation Feedback to maintain statistical integrity of attributes and eliminate bias in the learning process. Our approach explores the effects of imputation on various missingness mechanisms and patterns of missing data, outperforming other methods in many standard test cases.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/08/2017

Multiple Imputation Using Deep Denoising Autoencoders

Missing data is a well-recognized problem impacting all domains. State-o...
research
04/06/2020

Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problems

Dealing with missing data in data analysis is inevitable. Although power...
research
06/30/2021

DAEMA: Denoising Autoencoder with Mask Attention

Missing data is a recurrent and challenging problem, especially when usi...
research
12/04/2015

Proposition of a Theoretical Model for Missing Data Imputation using Deep Learning and Evolutionary Algorithms

In the last couple of decades, there has been major advancements in the ...
research
06/16/2021

Projective Resampling Imputation Mean Estimation Method for Missing Covariates Problem

Missing data is a common problem in clinical data collection, which caus...
research
03/15/2020

Unified Multi-Domain Learning and Data Imputation using Adversarial Autoencoder

We present a novel framework that can combine multi-domain learning (MDL...
research
02/08/2023

IRTCI: Item Response Theory for Categorical Imputation

Most datasets suffer from partial or complete missing values, which has ...

Please sign up or login with your details

Forgot password? Click here to reset