Related papers: ACTIVA: Amortized Causal Effect Estimation via Tra…

Mobile data technologies use ``actigraphs'' to furnish information on health variables as a function of a subject's movement. The advent of wearable devices and related technologies has propelled the creation of health databases consisting…

In this work, we propose a novel generative method to identify the causal impact and apply it to prediction tasks. We conduct causal impact analysis using interventional and counterfactual perspectives. First, applying interventions, we…

Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target…

Estimating causal effects from observational data (at either an individual -- or a population -- level) is critical for making many types of decisions. One approach to address this task is to learn decomposed representations of the…

Variational autoencoder (VAE) estimates the posterior parameters (mean and variance) of latent variables corresponding to each input data. While it is used for many tasks, the transparency of the model is still an underlying issue. This…

Human perception is inherently multimodal. We integrate, for instance, visual, proprioceptive and tactile information into one experience. Hence, multimodal learning is of importance for building robotic systems that aim at robustly…

Disentangled representation learning aims to learn low-dimensional representations where each dimension corresponds to an underlying generative factor. While the Variational Auto-Encoder (VAE) is widely used for this purpose, most existing…

Variational autoencoders (VAEs) are a popular class of deep generative models with many variants and a wide range of applications. Improvements upon the standard VAE mostly focus on the modelling of the posterior distribution over the…

We present a conditional variational auto-encoder (VAE) which, to avoid the substantial cost of training from scratch, uses an architecture and training objective capable of leveraging a foundation model in the form of a pretrained…

The next decade will usher in a profound transformation of wireless communication, driven by the ever-increasing demand for data-intensive applications and the rapid adoption of emerging technologies. To fully unlock the potential of 5G and…

Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect…

Learning interpretable latent representations from tabular data remains a challenge in deep generative modeling. We introduce SE-VAE (Structural Equation-Variational Autoencoder), a novel architecture that embeds measurement structure…

Variational Autoencoders (VAEs) have recently shown promising performance in collaborative filtering with implicit feedback. These existing recommendation models learn user representations to reconstruct or predict user preferences. We…

Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missingness in real-world applications due to heterogeneity and…

Causal inference is to estimate the causal effect in a causal relationship when intervention is applied. Precisely, in a causal model with binary interventions, i.e., control and treatment, the causal effect is simply the difference between…

We present a Bayesian procedure for estimation of pairwise intervention effects in a high-dimensional system of categorical variables. We assume that we have observational data generated from an unknown causal Bayesian network for which…

Pedestrian trajectory prediction is the key technology in many applications for providing insights into human behavior and anticipating human future motions. Most existing empirical models are explicitly formulated by observed human…

Causal effect estimation from observational data is fundamental across various applications. However, selecting an appropriate estimator from dozens of specialized methods demands substantial manual effort and domain expertise. We present…

The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the latent variable given the data point is regularized by the prior…

Vector Quantized-Variational AutoEncoders (VQ-VAE) are generative models based on discrete latent representations of the data, where inputs are mapped to a finite set of learned embeddings.To generate new samples, an autoregressive prior…