# Variational Autoencoders for Sparse and Overdispersed Discrete Data

arXiv: https://arxiv.org/abs/1905.00616 · HTML: https://mlsanity.com/paper/1905.00616/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2019.

## Built on by (most cited first, 1 of 1)

- [ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts](https://mlsanity.com/paper/2205.06982/) (2022)

## Abstract (arXiv)

Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data. Although probabilistic matrix factorisation and linear/nonlinear latent factor models have enjoyed great success in modelling such data, many existing models may have inferior modelling performance due to the insufficient capability of modelling overdispersion in count-valued data and model misspecification in general. In this paper, we comprehensively study these issues and propose a variational autoencoder based framework that generates discrete data via negative-binomial distribution. We also examine the model's ability to capture properties, such as self- and cross-excitations in discrete data, which is critical for modelling overdispersion. We conduct extensive experiments on three important problems from discrete data analysis: text analysis, collaborative filtering, and multi-label learning. Compared with several state-of-the-art baselines, the proposed models achieve significantly better performance on the above problems.