<ul><li>Variational Autoencoders (VAE) are widely used for dimensionality reduction of large-scale tabular and image datasets.</li><li>The proposed model, LMMVAE, separates the VAE latent model into fixed and random parts to account for correlated data observations.</li><li>LMMVAE improves squared reconstruction error and negative likelihood loss on unseen data.</li><li>It also enhances performance in downstream tasks such as supervised classification.</li></ul>

Integrating Random Effects in Variational Autoencoders for Dimensionality Reduction of Correlated Data

Discover more