Related papers: Discovering Influential Factors in Variational Aut…

Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on the inference of…

Posterior collapse plagues VAEs for text, especially for conditional text generation with strong autoregressive decoders. In this work, we address this problem in variational neural machine translation by explicitly promoting mutual…

The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models. However, the main drawback of this approach is the blurriness of the generated…

Deep metric learning has been demonstrated to be highly effective in learning semantic representation and encoding information that can be used to measure data similarity, by relying on the embedding learned from metric learning. At the…

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of…

Neural Networks play a growing role in many science disciplines, including physics. Variational Autoencoders (VAEs) are neural networks that are able to represent the essential information of a high dimensional data set in a low dimensional…

As a general-purpose generative model architecture, VAE has been widely used in the field of image and natural language processing. VAE maps high dimensional sample data into continuous latent variables with unsupervised learning. Sampling…

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

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…

Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No'; a (nominally trained) VAE does not necessarily amortize…

Variational auto-encoders (VAEs) have proven to be a well suited tool for performing dimensionality reduction by extracting latent variables lying in a potentially much smaller dimensional space than the data. Their ability to capture…

The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a…

Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred…

User attributes, such as gender and education, face severe incompleteness in social networks. In order to make this kind of valuable data usable for downstream tasks like user profiling and personalized recommendation, attribute inference…

A new form of variational autoencoder (VAE) is developed, in which the joint distribution of data and codes is considered in two (symmetric) forms: ($i$) from observed data fed through the encoder to yield codes, and ($ii$) from latent…

The variational autoencoder (VAE) is a generative model with continuous latent variables where a pair of probabilistic encoder (bottom-up) and decoder (top-down) is jointly learned by stochastic gradient variational Bayes. We first…

Variational Autoencoders and their many variants have displayed impressive ability to perform dimensionality reduction, often achieving state-of-the-art performance. Many current methods however, struggle to learn good representations in…

Learning interpretable representations with variational autoencoders (VAEs) is a major goal of representation learning. The main challenge lies in obtaining disentangled representations, where each latent dimension corresponds to a distinct…

Adversarial learning is a widely used technique in fair representation learning to remove the biases on sensitive attributes from data representations. It usually requires to incorporate the sensitive attribute labels as prediction targets.…

Recommendation models are typically trained on observational user interaction data, but the interactions between latent factors in users' decision-making processes lead to complex and entangled data. Disentangling these latent factors to…