Robust Variational Autoencoder for Tabular Data with Beta Divergence

TL;DR

This paper introduces RTVAE, a robust variational autoencoder using beta divergence designed for tabular data with mixed features, improving anomaly detection by handling outliers in training data.

Contribution

The paper presents a novel robust VAE model tailored for tabular data with mixed features, incorporating beta divergence to mitigate outlier effects during training.

Findings

RTVAE outperforms standard VAEs in anomaly detection accuracy.

The approach effectively reduces the influence of outliers in training data.

Results on network traffic datasets demonstrate improved robustness and detection performance.

Abstract

We propose a robust variational autoencoder with $\beta$ divergence for tabular data (RTVAE) with mixed categorical and continuous features. Variational autoencoders (VAE) and their variations are popular frameworks for anomaly detection problems. The primary assumption is that we can learn representations for normal patterns via VAEs and any deviation from that can indicate anomalies. However, the training data itself can contain outliers. The source of outliers in training data include the data collection process itself (random noise) or a malicious attacker (data poisoning) who may target to degrade the performance of the machine learning model. In either case, these outliers can disproportionately affect the training process of VAEs and may lead to wrong conclusions about what the normal behavior is. In this work, we derive a novel form of a variational autoencoder for tabular data sets with categorical and continuous features that is robust to outliers in training data. Our results on the anomaly detection application for network traffic datasets demonstrate the effectiveness of our approach.