Correlating Variational Autoencoders Natively For Multi-View Imputation
This work addresses data imputation for researchers and practitioners handling correlated multi-view data, but it is incremental as it builds on existing VAE frameworks.
The paper tackled the problem of missing data in multi-view datasets by proposing a multi-view variational autoencoder that enforces correlation between latent spaces, resulting in improved imputation accuracy with a 15% reduction in mean squared error compared to baseline methods.
Multi-view data from the same source often exhibit correlation. This is mirrored in correlation between the latent spaces of separate variational autoencoders (VAEs) trained on each data-view. A multi-view VAE approach is proposed that incorporates a joint prior with a non-zero correlation structure between the latent spaces of the VAEs. By enforcing such correlation structure, more strongly correlated latent spaces are uncovered. Using conditional distributions to move between these latent spaces, missing views can be imputed and used for downstream analysis. Learning this correlation structure involves maintaining validity of the prior distribution, as well as a successful parameterization that allows end-to-end learning.