Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility.

ABSTRACT: Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires that the learned model provides an accurate representation of the input data and yields a latent space that effectively predicts outcomes relevant to the scientific question. Supervised Variational Autoencoders (SVAEs) have previously been used for this purpose, as a carefully designed decoder can be used as an interpretable generative model of the data, while the supervised objective ensures a predictive latent representation. Unfortunately, the supervised objective forces the encoder to learn a biased approximation to the generative posterior distribution, which renders the generative parameters unreliable when u

SUBMITTER: Tu L 

PROVIDER: S-EPMC9910304 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature