Robust Variational Autoencoder for Tabular Data with Beta Divergence
This work addresses the issue of outlier sensitivity in VAEs for anomaly detection, which is crucial for applications like network security, but it is incremental as it builds on existing VAE frameworks with a specific robustness enhancement.
The authors tackled the problem of training variational autoencoders (VAEs) for anomaly detection on tabular data when the training data contains outliers, which can degrade model performance. They proposed a robust VAE using beta divergence, demonstrating its effectiveness on network traffic datasets.
We propose a robust variational autoencoder with $β$ 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.