Towards replacing detector simulation with heterogeneous GNNs in flavour physics analyses

2025/07/07 by Guillermo Hijano, Davide Lancierini, Hijano, Guillermo +19 · 1 citation
Physics and Astronomy · #FOS: Physical sciences #High Energy Physics - Experiment (hep-ex) #Instrumentation and Detectors (physics.ins-det) #Radiation Detection and Scintillator Technologies

paper · pdf · doi:10.48550/arxiv.2507.05069

openalex publication_date 2025/07/07 · openalex created_date 2025/10/20 · openalex updated_date 2026/07/31

Abstract

Driven by the increasing volume of recorded data, the demand for simulation from experiments based at the Large Hadron Collider will rise sharply in the coming years. Addressing this demand solely with existing computationally intensive workflows is not feasible. This paper introduces a new fast simulation tool designed to address this demand at the LHCb experiment. This tool emulates the detector response to arbitrary multibody decay topologies at LHCb. Rather than memorising specific decay channels, the model learns generalisable patterns within the response, allowing it to interpolate to channels not present in the training data. Novel heterogeneous graph neural network architectures are employed that are designed to embed the physical characteristics of the task directly into the network structure. We demonstrate the performance of the tool across a range of decay topologies, showing the networks can correctly model the relationships between complex variables. The architectures and methods presented are generic and could readily be adapted to emulate workflows at other simulation-intensive particle physics experiments.

Citations

• Measurement of the branching fraction ratio R_K at large dilepton invariant mass
• Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks
• Measurement of C !P violation observables in D⁺\→ K^-K⁺\π⁺ decays
• Systematic Evaluation of Generative Machine Learning Capability to Simulate Distributions of Observables at the Large Hadron Collider
• Lamarr: LHCb ultra-fast simulation based on machine learning models deployed within Gauss
• Simple and Efficient Heterogeneous Graph Neural Network
• Generative Adversarial Networks
• Test of lepton universality in beauty-quark decays
• Fast Graph Representation Learning with PyTorch Geometric

Cited by

• Leveraging Reinforcement Learning, Genetic Algorithms and Transformers for background determination in particle physics

Related

• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• Lamarr: LHCb ultra-fast simulation based on machine learning models deployed within Gauss
• GNN for Deep Full Event Interpretation and hierarchical reconstruction of heavy-hadron decays in proton-proton collisions
• Generative Networks for LHC events
• Data Augmentation at the LHC through Analysis-specific Fast Simulation with Deep Learning