Missing data imputation via denoising autoencoders: The untold story

• Type: Article in International Conference Proceedings Book
• Date: 2018

Authors

Costa, AF (Author) Other; Santos, MS (Author) Other; Soares, JP (Author) Other; Pedro Henriques Abreu (Author) Other

Conference proceedings International

Title: Advances in Intelligent Data Analysis XVII - 17th International Symposium, IDA 2018, 's-Hertogenbosch, The Netherlands, October 24-26, 2018, Proceedings

Pages: 87-98

17th International Symposium on Intelligent Data Analysis, IDA 2018

24 October 2018 through 26 October 2018

Indexing

Scopus - 34 Citations

Other information

Authenticus ID: P-00P-TH4

DOI: 10.1007/978-3-030-01768-2_8

Abstract (EN): Missing data consists in the lack of information in a dataset and since it directly influences classification performance, neglecting it is not a valid option. Over the years, several studies presented alternative imputation strategies to deal with the three missing data mechanisms, Missing Completely At Random, Missing At Random and Missing Not At Random. However, there are no studies regarding the influence of all these three mechanisms on the latest high-performance Artificial Intelligence techniques, such as Deep Learning. The goal of this work is to perform a comparison study between state-of-the-art imputation techniques and a Stacked Denoising Autoencoders approach. To that end, the missing data mechanisms were synthetically generated in 6 different ways; 8 different imputation techniques were implemented; and finally, 33 complete datasets from different open source repositories were selected. The obtained results showed that Support Vector Machines imputation ensures the best classification performance while Multiple Imputation by Chained Equations performs better in terms of imputation quality. © Springer Nature Switzerland AG 2018.

Language: English

Type (Professor's evaluation): Scientific