From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder

Abstract

Conditional Generative Models are now acknowledged an essential tool in Machine Learning. This paper focuses on their control. While many approaches aim at disentangling the data through the coordinate-wise control of their latent representations, another direction is explored in this paper. The proposed CompVAE handles data with a natural multi-ensemblist structure (i.e. that can naturally be decomposed into elements). Derived from Bayesian variational principles, CompVAE learns a latent representation leveraging both observational and symbolic information. A first contribution of the approach is that this latent representation supports a compositional generative model, amenable to multi-ensemblist operations (addition or subtraction of elements in the composition). This compositional ability is enabled by the invariance and generality of the whole framework w.r.t. respectively, the order and number of the elements. The second contribution of the paper is a proof of concept on synthetic 1D and 2D problems, demonstrating the efficiency of the proposed approach.

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Neural Message Passing for Quantum Chemistry
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• The information bottleneck method
• Conditional Image Generation with PixelCNN Decoders
• Semi-Supervised Learning with Deep Generative Models
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Opening the Black Box of Deep Neural Networks via Information
• Deep Convolutional Inverse Graphics Network
• A Recurrent Latent Variable Model for Sequential Data
• Adversarially Learned Inference
• Auxiliary Deep Generative Models
• Ladder Variational Autoencoders
• Deep Learning for Generic Object Detection: A Survey
• The Variational Fair Autoencoder
• Invariant Representations without Adversarial Training
• PixelVAE: A Latent Variable Model for Natural Images
• Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings