MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets

By Pierre-Alexandre Mattei, Jes Frellsen. International Conference on Machine Learning, 2019

339 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Joint probabilistic modeling of single-cell multi-omic data with totalVI (2021, methodology): “mismatched dimensions in the encoder, we substitute zeros for missing proteins, and for the decoder, we only calculate the ELBO terms corresponding to observed data [66].”
A Brief Overview of Unsupervised Neural Speech Representation Learning (2022, methodology): “Previous work has largely focused on the ability of these models to yield high-quality imputations within the tabular and image data domains, without probing for the effects on the learned latent representation (Mattei and Frellsen 2019; Ipsen, Mattei, and Frellsen 2021).”