IRC-safe Graph Autoencoder for unsupervised anomaly detection

Atkinson, O., Bhardwaj, A., Englert, C. , Konar, P., Ngairangbam, V. S. and Spannowsky, M. (2022) IRC-safe Graph Autoencoder for unsupervised anomaly detection. Frontiers in Artificial Intelligence, 5, 943135. (doi: 10.3389/frai.2022.943135) (PMID:35937137) (PMCID:PMC9352857)

[img] Text
273702.pdf - Published Version
Available under License Creative Commons Attribution.

1MB

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 favorable properties, it also exhibits formidable sensitivity to non-QCD structures.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Atkinson, Mr Oliver and Bhardwaj, Dr Akanksha and Englert, Professor Christoph
Authors: Atkinson, O., Bhardwaj, A., Englert, C., Konar, P., Ngairangbam, V. S., and Spannowsky, M.
College/School:College of Science and Engineering > School of Physics and Astronomy
Journal Name:Frontiers in Artificial Intelligence
Publisher:Frontiers Media
ISSN:2624-8212
ISSN (Online):2624-8212
Copyright Holders:Copyright © 2022 Atkinson, Bhardwaj, Englert, Konar, Ngairangbam and Spannowsky
First Published:First published in Frontiers in Artificial Intelligence 5: 943135
Publisher Policy:Reproduced under a Creative Commons License
Data DOI:10.5281/zenodo.2603256

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
313214STFC Glasgow Physics 2020 DTPDavid IrelandScience and Technology Facilities Council (STFC)ST/V506692/1P&S - Physics & Astronomy
306883Research in Particle Physics Theory - Phenomenology from lattice QCD and collider physicsChristine DaviesScience and Technology Facilities Council (STFC)ST/T000945/1P&S - Physics & Astronomy
311961BSM interference effects in Higgs and Top-associated final states.Christoph EnglertLeverhulme Trust (LEVERHUL)RPG-2021-031P&S - Physics & Astronomy