# Including Sparse Production Knowledge into Variational Autoencoders to Increase Anomaly Detection Reliability

arXiv: https://arxiv.org/abs/2103.12998 · HTML: https://mlsanity.com/paper/2103.12998/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 23 references that are in the map.
- First posted on arXiv 24 Mar 2021.

## Builds on (most cited first, 3 of 3)

- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Toward Supervised Anomaly Detection](https://mlsanity.com/paper/1401.6424/) (2014)
- [Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning](https://mlsanity.com/paper/1908.03015/) (2019)

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

- [Physics-Informed Diffusion Models for Unsupervised Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2508.11528/) (2025)
- [Interpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders](https://mlsanity.com/paper/2306.15938/) (2023)
- [Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme](https://mlsanity.com/paper/2505.05020/) (2025)

## Abstract (arXiv)

Digitalization leads to data transparency for production systems that we can benefit from with data-driven analysis methods like neural networks. For example, automated anomaly detection enables saving resources and optimizing the production. We study using rarely occurring information about labeled anomalies into Variational Autoencoder neural network structures to overcome information deficits of supervised and unsupervised approaches. This method outperforms all other models in terms of accuracy, precision, and recall. We evaluate the following methods: Principal Component Analysis, Isolation Forest, Classifying Neural Networks, and Variational Autoencoders on seven time series datasets to find the best performing detection methods. We extend this idea to include more infrequently occurring meta information about production processes. This use of sparse labels, both of anomalies or production data, allows to harness any additional information available for increasing anomaly detection performance.