Nonparametric Variational Auto-encoders for Hierarchical Representation Learning

Abstract

The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the latent variables such as standard normal distribution, thereby restricting its applications to relatively simple phenomena. In this work, we propose hierarchical nonparametric variational autoencoders, which combines tree-structured Bayesian nonparametric priors with VAEs, to enable infinite flexibility of the latent representation space. Both the neural parameters and Bayesian priors are learned jointly using tailored variational inference. The resulting model induces a hierarchical structure of latent semantic concepts underlying the data corpus, and infers accurate representations of data instances. We apply our model in video representation learning. Our method is able to discover highly interpretable activity hierarchies, and obtain improved clustering accuracy and generalization capacity based on the learned rich representations.

Accepted in ICCV 2017

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DRAW: A Recurrent Neural Network For Image Generation
• Composing graphical models with neural networks for structured representations and fast inference

Cited by in corpus (24)

• DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
• Conditional Flow Variational Autoencoders for Structured Sequence Prediction
• VAE with a VampPrior
• Semi-Amortized Variational Autoencoders
• Deep Learning for Insider Threat Detection: Review, Challenges and Opportunities
• Every Smile is Unique: Landmark-Guided Diverse Smile Generation
• Dual Motion GAN for Future-Flow Embedded Video Prediction
• Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Method
• On the Necessity and Effectiveness of Learning the Prior of Variational Auto-Encoder
• InfoCatVAE: Representation Learning with Categorical Variational Autoencoders
• LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
• Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders
• The LORACs prior for VAEs: Letting the Trees Speak for the Data
• Discond-VAE: Disentangling Continuous Factors from the Discrete
• Time-Aware and View-Aware Video Rendering for Unsupervised Representation Learning
• Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space
• Document Hashing with Mixture-Prior Generative Models
• Hierarchically Clustered Representation Learning
• ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE
• LaDDer: Latent Data Distribution Modelling with a Generative Prior
• BooVAE: Boosting Approach for Continual Learning of VAE
• Learning Priors for Adversarial Autoencoders
• Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations
• Efficient Correlated Topic Modeling with Topic Embedding