Resilient VAE: Unsupervised Anomaly Detection at the SLAC Linac Coherent Light Source

TL;DR

ResVAE is an unsupervised deep generative model that detects anomalies in complex engineering systems like particle accelerators by being resilient to contaminated training data and providing feature-level anomaly attribution.

Contribution

The paper introduces ResVAE, a novel unsupervised variational autoencoder that effectively detects anomalies even with contaminated training data and offers detailed feature-level anomaly attribution.

Findings

ResVAE successfully detects various anomalies in accelerator data.

It learns anomaly probabilities for samples and features during training.

ResVAE outperforms traditional methods in anomaly detection accuracy.

Abstract

Significant advances in utilizing deep learning for anomaly detection have been made in recent years. However, these methods largely assume the existence of a normal training set (i.e., uncontaminated by anomalies) or even a completely labeled training set. In many complex engineering systems, such as particle accelerators, labels are sparse and expensive; in order to perform anomaly detection in these cases, we must drop these assumptions and utilize a completely unsupervised method. This paper introduces the Resilient Variational Autoencoder (ResVAE), a deep generative model specifically designed for anomaly detection. ResVAE exhibits resilience to anomalies present in the training data and provides feature-level anomaly attribution. During the training process, ResVAE learns the anomaly probability for each sample as well as each individual feature, utilizing these probabilities to effectively disregard anomalous examples in the training data. We apply our proposed method to detect anomalies in the accelerator status at the SLAC Linac Coherent Light Source (LCLS). By utilizing shot-to-shot data from the beam position monitoring system, we demonstrate the exceptional capability of ResVAE in identifying various types of anomalies that are visible in the accelerator.