Poster
Variational Autoencoder with Arbitrary Conditioning
Oleg Ivanov · Mikhail Figurnov · Dmitry P. Vetrov
Great Hall BC #74
Keywords: [ unsupervised learning ] [ generative models ] [ variational autoencoder ] [ conditional variational autoencoder ] [ missing features multiple imputation ] [ inpainting ]
We propose a single neural probabilistic model based on variational autoencoder that can be conditioned on an arbitrary subset of observed features and then sample the remaining features in "one shot". The features may be both real-valued and categorical. Training of the model is performed by stochastic variational Bayes. The experimental evaluation on synthetic data, as well as feature imputation and image inpainting problems, shows the effectiveness of the proposed approach and diversity of the generated samples.
Live content is unavailable. Log in and register to view live content