# Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning

arXiv: https://arxiv.org/abs/1908.03015 · HTML: https://mlsanity.com/paper/1908.03015/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2019.

## Built on by (most cited first, 3 of 3)

- [Assessing the Quality of the Datasets by Identifying Mislabeled Samples](https://mlsanity.com/paper/2109.05000/) (2021)
- [Including Sparse Production Knowledge into Variational Autoencoders to Increase Anomaly Detection Reliability](https://mlsanity.com/paper/2103.12998/) (2021)
- [Fairness in Machine Learning-based Hand Load Estimation: A Case Study on Load Carriage Tasks](https://mlsanity.com/paper/2504.05610/) (2025)

## Abstract (arXiv)

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unlabeled datapoints not only boost unsupervised tasks, but also the classification performance. Vice versa, every label not only improves classification, but also unsupervised tasks. The proposed architecture is simple: A classification layer is connected to the topmost encoder layer, and then combined with the resampled latent layer for the decoder. The usual evidence lower bound (ELBO) loss is supplemented with a supervised loss target on this classification layer that is only applied for labeled datapoints. This simplicity allows for extending any existing VAE model to our proposed semi-supervised framework with minimal effort. In the context of classification, we found that this approach even outperforms a direct supervised setup.