MIWAE: Deep Generative Modelling and Imputation of Incomplete Data
This addresses the challenge of handling missing data in machine learning, particularly for deep generative models, offering a practical solution for imputation tasks.
The authors tackled the problem of training deep latent variable models on incomplete data and performing imputation, introducing MIWAE which trains without extra computational cost and achieves test performance similar to models trained on complete data, with competitive accuracy on various datasets.
We consider the problem of handling missing data with deep latent variable models (DLVMs). First, we present a simple technique to train DLVMs when the training set contains missing-at-random data. Our approach, called MIWAE, is based on the importance-weighted autoencoder (IWAE), and maximises a potentially tight lower bound of the log-likelihood of the observed data. Compared to the original IWAE, our algorithm does not induce any additional computational overhead due to the missing data. We also develop Monte Carlo techniques for single and multiple imputation using a DLVM trained on an incomplete data set. We illustrate our approach by training a convolutional DLVM on a static binarisation of MNIST that contains 50% of missing pixels. Leveraging multiple imputation, a convolutional network trained on these incomplete digits has a test performance similar to one trained on complete data. On various continuous and binary data sets, we also show that MIWAE provides accurate single imputations, and is highly competitive with state-of-the-art methods.