Related papers: Nonparametric Topic Modeling with Neural Inference

In real world machine learning applications, testing data may contain some meaningful new categories that have not been seen in labeled training data. To simultaneously recognize new data categories and assign most appropriate category…

Traditional Relational Topic Models provide a way to discover the hidden topics from a document network. Many theoretical and practical tasks, such as dimensional reduction, document clustering, link prediction, benefit from this revealed…

Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy. However, it is unclear how to incorporate prior…

Though word embeddings and topics are complementary representations, several past works have only used pre-trained word embeddings in (neural) topic modeling to address data sparsity problem in short text or small collection of documents.…

Recently, there has been considerable progress on designing algorithms with provable guarantees -- typically using linear algebraic methods -- for parameter learning in latent variable models. But designing provable algorithms for inference…

Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the…

Data augmentation effectively addresses the imbalanced-small sample data (ISSD) problem in hyperspectral image classification (HSIC). While most methodologies extend features in the latent space, few leverage text-driven generation to…

Hierarchical models with gamma hyperpriors provide a flexible, sparse-promoting framework to bridge $L^1$ and $L^2$ regularizations in Bayesian formulations to inverse problems. Despite the Bayesian motivation for these models, existing…

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the…

We propose SAHMM-VAE, a source-wise adaptive Hidden Markov prior variational autoencoder for unsupervised blind source separation. Instead of treating the latent prior as a single generic regularizer, the proposed framework assigns each…

Variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant…

The embedded topic model (ETM) is a widely used approach that assumes the sampled document-topic distribution conforms to the logistic normal distribution for easier optimization. However, this assumption oversimplifies the real…

In this paper, we present a novel approach for training a Variational Autoencoder (VAE) on a highly imbalanced data set. The proposed training of a high-resolution VAE model begins with the training of a low-resolution core model, which can…

Word embedding models such as the skip-gram learn vector representations of words' semantic relationships, and document embedding models learn similar representations for documents. On the other hand, topic models provide latent…

Topic models are frequently used in machine learning owing to their high interpretability and modular structure. However, extending a topic model to include a supervisory signal, to incorporate pre-trained word embedding vectors and to…

As an important problem in causal inference, we discuss the estimation of treatment effects (TEs). Representing the confounder as a latent variable, we propose Intact-VAE, a new variant of variational autoencoder (VAE), motivated by the…

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling,…

By illuminating latent structures in a corpus of text, topic models are an essential tool for categorizing, summarizing, and exploring large collections of documents. Probabilistic topic models, such as latent Dirichlet allocation (LDA),…

Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian distribution. Recent works demonstrated that choice of prior distribution affects learning capacity of VAE models. We propose a general technique…

Understanding relationships across multiple imaging modalities is central to neuroimaging research. We introduce the Integrative Variational Autoencoder (InVA), the first hierarchical VAE framework for image-on-image regression in…