Anomaly scores for generative models

TL;DR

This paper introduces a theoretically grounded anomaly score for generative models like auto-encoders and GANs, addressing limitations of the traditional reconstruction error in anomaly detection.

Contribution

It proposes a new anomaly score compatible with generative models, providing a better theoretical foundation and practical utility for hyper-parameter selection.

Findings

The new score aligns with the theoretical properties of generative models.

It can be used effectively for hyper-parameter tuning.

Reconstruction error performs well empirically despite theoretical limitations.

Abstract

Reconstruction error is a prevalent score used to identify anomalous samples when data are modeled by generative models, such as (variational) auto-encoders or generative adversarial networks. This score relies on the assumption that normal samples are located on a manifold and all anomalous samples are located outside. Since the manifold can be learned only where the training data lie, there are no guarantees how the reconstruction error behaves elsewhere and the score, therefore, seems to be ill-defined. This work defines an anomaly score that is theoretically compatible with generative models, and very natural for (variational) auto-encoders as they seem to be prevalent. The new score can be also used to select hyper-parameters and models. Finally, we explain why reconstruction error delivers good experimental results despite weak theoretical justification.