Anomaly detection with convolutional Graph Neural Networks

Atkinson, OliverOliverAtkinsonBhardwaj, AkankshaAkankshaBhardwajEnglert, ChristophChristophEnglertNgairangbam, Vishal S.Vishal S.NgairangbamSpannowsky, MichaelMichaelSpannowsky2025-08-312025-08-312021-08-0110.1007/JHEP08(2021)0802-s2.0-85112784886http://repository.iitgn.ac.in/handle/IITG2025/25358We 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.trueJetsAnomaly detection with convolutional Graph Neural NetworksArticlehttps://link.springer.com/content/pdf/10.1007/JHEP08(2021)080.pdf10298479August 20217280arJournal69