Anomalies, Representations, and Self-Supervision
This addresses anomaly detection for high-energy physics experiments, but it is incremental as it builds on existing contrastive learning and autoencoder techniques.
The paper tackles anomaly detection in collider event data by developing a self-supervised method using contrastive learning, resulting in significant improvements in performance metrics for all signals compared to the raw data baseline.
We develop a self-supervised method for density-based anomaly detection using contrastive learning, and test it using event-level anomaly data from CMS ADC2021. The AnomalyCLR technique is data-driven and uses augmentations of the background data to mimic non-Standard-Model events in a model-agnostic way. It uses a permutation-invariant Transformer Encoder architecture to map the objects measured in a collider event to the representation space, where the data augmentations define a representation space which is sensitive to potential anomalous features. An AutoEncoder trained on background representations then computes anomaly scores for a variety of signals in the representation space. With AnomalyCLR we find significant improvements on performance metrics for all signals when compared to the raw data baseline.