Variational Autoencoder with Arbitrary Conditioning
This addresses the problem of flexible conditional generation for researchers and practitioners in machine learning, though it appears incremental as it builds on existing variational autoencoder frameworks.
The authors tackled the problem of generating missing features when conditioning on arbitrary subsets of observed features, proposing a variational autoencoder model that handles both real-valued and categorical data and achieves effective performance in experiments on synthetic data, feature imputation, and image 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.