Variational Selective Autoencoder

Despite promising progress on unimodal data imputation (e.g. image inpainting), models for multimodal data imputation are far from satisfactory. In this work, we propose variational selective autoencoder (VSAE) for this task. Learning only from partially-observed data, VSAE can model the joint distribution of observed/unobserved modalities and the imputation mask, resulting in a unified model for various down-stream tasks including data generation and imputation. Evaluation on synthetic high-dimensional and challenging low-dimensional multimodal datasets shows improvement over the state-of-the-art imputation models.