Anomaly detection with Convolutional Graph Neural Networks

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.

arXiv commentAdded two appendices, minor modifications in text, no changes in result, matches accepted version in JHEP

References in corpus (29)

• A Comprehensive Survey on Graph Neural Networks
• PYTHIA 6.4 Physics and Manual
• PYTHIA 6.2 Physics and Manual
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The anti-k_t jet clustering algorithm
• FastJet user manual
• Successive Combination Jet Algorithm For Hadron Collisions
• The Standard Model as an Effective Field Theory
• ParticleNet: Jet Tagging via Particle Clouds
• Anomaly Detection with Density Estimation
• Jet-Images -- Deep Learning Edition
• Searching for New Physics with Deep Autoencoders
• Anomaly Detection for Resonant New Physics with Machine Learning
• Jet-Images: Computer Vision Inspired Techniques for Jet Tagging
• QCD or What?
• Novelty Detection Meets Collider Physics
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• Finding physics signals with shower deconstruction
• Guiding New Physics Searches with Unsupervised Learning
• Autoencoders for unsupervised anomaly detection in high energy physics
• ABCNet: An attention-based method for particle tagging
• Finding physics signals with event deconstruction
• Probing stop pair production at the LHC with graph neural networks
• Learning the latent structure of collider events
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• Unsupervised clustering for collider physics
• Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics
• Calculating the primary Lund Jet Plane density
• Learning to Make Predictions on Graphs with Autoencoders

Cited by in corpus (39)

• Anomaly detection in high-energy physics using a quantum autoencoder
• Classifying Anomalies THrough Outer Density Estimation (CATHODE)
• Bump Hunting in Latent Space
• Challenges for Unsupervised Anomaly Detection in Particle Physics
• Online-compatible Unsupervised Non-resonant Anomaly Detection
• Deep Set Auto Encoders for Anomaly Detection in Particle Physics
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Lorentz group equivariant autoencoders
• What's Anomalous in LHC Jets?
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Anomaly Detection under Coordinate Transformations
• Anomaly detection from mass unspecific jet tagging
• High-dimensional and Permutation Invariant Anomaly Detection
• Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
• Constraints on the trilinear and quartic Higgs couplings from triple Higgs production at the LHC and beyond
• Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
• Boosting mono-jet searches with model-agnostic machine learning
• Jet tagging algorithm of graph network with HaarPooling message passing
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• Neural Embedding: Learning the Embedding of the Manifold of Physics Data
• Anomalies, Representations, and Self-Supervision
• Deep Learning Jet Image as a Probe of Light Higgsino Dark Matter at the LHC
• On the BSM reach of four top production at the LHC
• Taming modeling uncertainties with Mass Unspecific Supervised Tagging
• Does Lorentz-symmetric design boost network performance in jet physics?
• Semi-visible jets, energy-based models, and self-supervision
• Hypergraphs in LHC Phenomenology -- The Next Frontier of IRC-Safe Feature Extraction
• Non-resonant Anomaly Detection with Background Extrapolation
• High-dimensional Anomaly Detection with Radiative Return in $e^{+}{e}^{-}$ Collisions
• Simulation-based Anomaly Detection for Multileptons at the LHC
• Unsupervised and lightly supervised learning in particle physics
• Multiboson signals in the UN2HDM
• Top-philic Machine Learning
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Detecting New Physics as Novelty -- Complementarity Matters
• Graph theory inspired anomaly detection at the LHC
• First results of the NEXT-100 detector using ${}^{83m}$Kr decays
• Creating Simple, Interpretable Anomaly Detectors for New Physics in Jet Substructure