Thumbnail - No thumbnail

Deep Generative Missingness Pattern-Set Mixture Models

Ghalebikesabi, Sahra; Cornish, Rob; Holmes, Chris; Kelly, Luke Joseph (2021), Deep Generative Missingness Pattern-Set Mixture Models, in Arindam Banerjee, Kenji Fukumizu, Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR Vol. 130, Proceedings of Machine Learning Research (PMLR), p. 3727-3735

View/Open
Type
Communication / Conférence
Date
2021
Conference title
24th International Conference on Artificial Intelligence and Statistics
Conference date
2021-04
Conference city
Virtual
Conference country
France
Book title
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR Vol. 130
Book author
Arindam Banerjee, Kenji Fukumizu
Publisher
Proceedings of Machine Learning Research (PMLR)
Pages
3727-3735
Metadata
Show full item record
Author(s)
Ghalebikesabi, Sahra
UNIVERSITY OF OXFORD GBR
Cornish, Rob
Holmes, Chris
Department of Statistics [Oxford]
Kelly, Luke Joseph
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Abstract (EN)
We propose a variational autoencoder architecture to model both ignorable and nonignorable missing data using pattern-set mixtures as proposed by Little (1993). Our model explicitly learns to cluster the missing data into missingness pattern sets based on the observed data and missingness masks. Underpinning our approach is the assumption that the data distribution under missingness is probabilistically semi-supervised by samples from the observed data distribution. Our setup trades off the characteristics of ignorable and nonignorable missingness and can thus be applied to data of both types. We evaluate our method on a wide range of data sets with different types of missingness and achieve state-of-the-art imputation performance. Our model outperforms many common imputation algorithms, especially when the amount of missing data is high and the missingness mechanism is nonignorable.