IRC-safe Graph Autoencoder for unsupervised anomaly detection

TL;DR

This paper introduces an infrared and collinear safe graph neural network autoencoder designed for anomaly detection, emphasizing theoretical consistency and sensitivity to non-QCD structures in physics data.

Contribution

It presents a novel IR and collinear safe autoencoder architecture based on graph neural networks with energy-weighted message passing, enhancing anomaly detection in physics.

Findings

The autoencoder is IR and collinear safe, ensuring theoretical consistency.

It demonstrates high sensitivity to non-QCD structures.

The approach combines physics principles with advanced neural network techniques.

Abstract

Anomaly detection through employing machine learning techniques has emerged as a novel powerful tool in the search for new physics beyond the Standard Model. Historically similar to the development of jet observables, theoretical consistency has not always assumed a central role in the fast development of algorithms and neural network architectures. In this work, we construct an infrared and collinear safe autoencoder based on graph neural networks by employing energy-weighted message passing. We demonstrate that whilst this approach has theoretically favourable properties, it also exhibits formidable sensitivity to non-QCD structures.