# Variational Deep Alliance: A Generative Auto-Encoding Approach to Longitudinal Data Analysis

## TL;DR

This paper introduces VaDA, a deep learning method for analyzing longitudinal data that can predict outcomes, cluster subjects, and learn representations simultaneously.

## Contribution

VaDA is a novel generative model that unifies outcome prediction, clustering, and representation learning in longitudinal data analysis.

## Key findings

- VaDA demonstrates high robustness and generalization across synthetic scenarios.
- The model successfully detects meaningful clusters and generates high-quality face images using the CelebFaces Attributes dataset.

## Abstract

Rapid advancements in the field of deep learning have had a profound impact on a wide range of scientific studies. This paper incorporates the power of deep neural networks to learn complex relationships in longitudinal data. The novel generative approach, Variational Deep Alliance (VaDA), is established, where an “alliance” is formed across repeated measurements via the strength of Variational Auto-Encoder. VaDA models the generating process of longitudinal data with a unified and well-structured latent space, allowing outcomes prediction, subjects clustering and representation learning simultaneously. The integrated model can be inferred efficiently within a stochastic Auto-Encoding Variational Bayes framework, which is scalable to large datasets and can accommodate variables of mixed type. Quantitative comparisons to those baseline methods are considered. VaDA shows high robustness and generalization capability across various synthetic scenarios. Moreover, a longitudinal study based on the well-known CelebFaces Attributes dataset is carried out, where we show its usefulness in detecting meaningful latent clusters and generating high-quality face images.