Anomaly detection with convolutional Graph Neural Networks

Atkinson, Oliver; Bhardwaj, Akanksha; Englert, Christoph; Ngairangbam, Vishal S.; Spannowsky, Michael

Abstract

We devise an autoencoder based strategy to facilitate anomaly detection for boosted jets, employing Graph Neural Networks (GNNs) to do so. To overcome known limitations of GNN autoencoders, we design a symmetric decoder capable of simultaneously reconstructing edge features and node features. Focusing on latent space based discriminators, we find that such setups provide a promising avenue to isolate new physics and competing SM signatures from sensitivity-limiting QCD jet contributions. We demonstrate the flexibility and broad applicability of this approach using examples of W bosons, top quarks, and exotic hadronically-decaying exotic scalar bosons.

Citation

Atkinson, O., Bhardwaj, A., Englert, C., Ngairangbam, V. S., & Spannowsky, M. (2021). Anomaly detection with convolutional Graph Neural Networks. Journal of High Energy Physics, 2021(8), https://doi.org/10.1007/jhep08%282021%29080

• Journal Article Type: Article
• Acceptance Date: Aug 1, 2021
• Online Publication Date: Aug 17, 2021
• Publication Date: 2021
• Deposit Date: Nov 9, 2021
• Publicly Available Date: Nov 9, 2021
• Journal: Journal of High Energy Physics
• Print ISSN: 1126-6708
• Electronic ISSN: 1029-8479
• Publisher: Scuola Internazionale Superiore di Studi Avanzati (SISSA)
• Peer Reviewed: Peer Reviewed
• Volume: 2021
• Issue: 8
• DOI: https://doi.org/10.1007/jhep08%282021%29080
• Public URL: https://durham-repository.worktribe.com/output/1225819