Related papers: Heteroscedastic Temporal Variational Autoencoder F…

We propose a robust variational autoencoder with $\beta$ divergence for tabular data (RTVAE) with mixed categorical and continuous features. Variational autoencoders (VAE) and their variations are popular frameworks for anomaly detection…

Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and…

Purpose: Handling heterogeneous and mixed data types has become increasingly critical with the exponential growth in real-world databases. While deep generative models attempt to merge diverse data views into a common latent space, they…

Variational autoencoders (VAEs) rely on amortized variational inference to enable efficient posterior approximation, but this efficiency comes at the cost of a shared parametrization, giving rise to the amortization gap. We propose the…

Variational autoencoders (VAEs) are a powerful class of deep generative latent variable model for unsupervised representation learning on high-dimensional data. To ensure computational tractability, VAEs are often implemented with a…

This paper proposes a flexible framework for inferring large-scale time-varying and time-lagged correlation networks from multivariate or high-dimensional non-stationary time series with piecewise smooth trends. Built on a novel and unified…

Generating synthetic tabular data under severe class imbalance is essential for domains where rare but high-impact events drive decision-making. However, most generative models either overlook minority groups or fail to produce samples that…

Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost…

The ability to record activities from hundreds of neurons simultaneously in the brain has placed an increasing demand for developing appropriate statistical techniques to analyze such data. Recently, deep generative models have been…

Irregularly sampled time series data with missing values is observed in many fields like healthcare, astronomy, and climate science. Interpolation of these types of time series is crucial for tasks such as root cause analysis and medical…

This paper introduces a hybrid attention and autoencoder (AE) model for unsupervised online anomaly detection in time series. The autoencoder captures local structural patterns in short embeddings, while the attention model learns long-term…

Disentangled sequential autoencoders (DSAEs) represent a class of probabilistic graphical models that describes an observed sequence with dynamic latent variables and a static latent variable. The former encode information at a frame rate…

We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…

In this study, a deep learning based conditional density estimation technique known as conditional variational auto-encoder (CVAE) is used to fill gaps typically observed in particle image velocimetry (PIV) measurements in combustion…

Self-supervised learning has become a central strategy for representation learning, but the majority of architectures used for encoding data have only been validated on regularly-sampled inputs such as images, audios. and videos. In many…

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or…

Time series forecasting represents a significant and challenging task across various fields. Recently, methods based on mode decomposition have dominated the forecasting of complex time series because of the advantages of capturing local…

In this technical report, we present our solutions to the Traffic4cast 2022 core challenge and extended challenge. In this competition, the participants are required to predict the traffic states for the future 15-minute based on the…

Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transformations based on a mixture of two overlapping…

Humans are able to create rich representations of their external reality. Their internal representations allow for cross-modality inference, where available perceptions can induce the perceptual experience of missing input modalities. In…