- Physical Review Journals
All JournalsPhysics Magazine

Physical Review D

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Towards replacing detector simulations with heterogeneous graph neural networks in flavor physics analyses

G. Hijano3, D. Lancierini2, A. Marshall1,*, A. Mauri2, P. Owen3, M. Patel2, K. Petridis1, S. R. Qasim3, N. Serra3 et al.

W. Sutcliffe3 and H. Tilquin2

  • *Contact author: alex.marshall@cern.ch
PDF

Phys. Rev. D 113, 012005 – Published 13 January, 2026

DOI: https://doi.org/10.1103/k9ls-9pwc

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 the LHCb. Rather than memorizing specific decay channels, the model learns generalizable 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 that 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.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (55)

  1. L. Evans and P. Bryant, eds., LHC Machine, J. Instrum. 3, S08001 (2008).
  2. LHCb Collaboration, Framework TDR for the LHCb Upgrade II: Opportunities in flavour physics, and beyond, in the HL-LHC era, Technical Report No. CERN-LHCC-2021-012, LHCB-TDR-023, CERN, Geneva, 2021, https://cds.cern.ch/record/2776420.
  3. C. Bozzi, LHCb computing resource usage in 2023, Report No. LHCb-PUB-2024-003, CERN-LHCb-PUB-2024-003, CERN, Geneva, 2024, https://cds.cern.ch/record/2888940.
  4. Atlas Collaboration, Atlas software and computing HL-LHC roadmap, Technical Report No. CERN-LHCC-2022-005, LHCC-G-182, CERN, Geneva, 2022, https://cds.cern.ch/record/2802918.
  5. C. O. Software and Computing, CMS Phase-2 computing model: Update document, Technical Report, CERN, Geneva, 2022.
  6. LHCb Collaboration, Measurement of the branching fraction ratios R(D+) and R(D*+) using muonic τ decays, Phys. Rev. Lett. 134, 061801 (2025).
  7. LHCb Collaboration, Measurement of the ratios of branching fractions R(D*) and R(D0), Phys. Rev. Lett. 131, 111802 (2023).
  8. LHCb Collaboration, Test of lepton flavor universality using B0→D*−τ+ντ decays with hadronic τ channels, Phys. Rev. D 108, 012018 (2023).
  9. LHCb Collaboration, Branching fraction measurements of the rare Bs0→ϕμ+μ− and Bs0→f2′(1525)μ+μ−- decays, Phys. Rev. Lett. 127, 151801 (2021).
  10. HEP Software Foundation Collaboration, A roadmap for HEP software and computing R&D for the 2020s, Comput. Software Big Sci. 3, 7 (2019).
  11. D. Müller, M. Clemencic, G. Corti, and M. Gersabeck, ReDecay: A novel approach to speed up the simulation at LHCb, Eur. Phys. J. C 78, 1009 (2018).
  12. S. Abdullin, P. Azzi, F. Beaudette, P. Janot, A. Perrotta (on behalf ofthe CMS Collaboration), The fast simulation of the CMS detector at LHC, J. Phys. Conf. Ser. 331, 032049 (2011).
  13. DELPHES 3 Collaboration, DELPHES 3, A modular framework for fast simulation of a generic collider experiment, J. High Energy Phys. 02 (2014) 057.
  14. G. A. Cowan, D. C. Craik, and M. D. Needham, RapidSim: An application for the fast simulation of heavy-quark hadron decays, Comput. Phys. Commun. 214, 239 (2017).
  15. LHCb Collaboration, Fast data-driven simulation of Cherenkov detectors using generative adversarial networks, J. Phys. Conf. Ser. 1525, 012097 (2020).
  16. A. Rogachev and F. Ratnikov, GAN with an auxiliary regressor for the fast simulation of the electromagnetic calorimeter response, J. Phys. Conf. Ser. 2438, 012086 (2023).
  17. M. Barbetti, Lamarr: LHCb ultra-fast simulation based on machine learning models deployed within Gauss, in 21th International Workshop on Advanced Computing and Analysis Techniques in Physics Research: AI meets Reality (2023).
  18. CMS Collaboration, Reweighting simulated events using machine-learning techniques in the CMS experiment, Eur. Phys. J. C 85, 495 (2025).
  19. CMS Collaboration, FlashSim: Accelerating HEP simulation with an end-to-end Machine Learning framework, EPJ Web Conf. 295, 09020 (2024).
  20. ATLAS Collaboration, AtlFast3: The next generation of fast simulation in ATLAS, Comput. Software Big Sci. 6, 7 (2022).
  21. Atlas Collaboration, Deep generative models for fast photon shower simulation in atlas, Comput. Software Big Sci. 8, 7 (2024).
  22. LHCb Collaboration, Observation of the doubly-charmed-baryon decay Ξcc++→Ξc0π+π+, J. High Energy Phys. 10 (2025) 136.
  23. LHCb Collaboration, Measurement of the CKM angle γ in B±→DK*(892)± decays, J. High Energy Phys. 02 (2025) 113.
  24. LHCb Collaboration, Measurement of CP violation observables in D+→K−K+π+ decays, Phys. Rev. Lett. 133, 251801 (2024).
  25. LHCb Collaboration, Search for the lepton-flavor violating decay Bs0→ϕμ±τ∓, Phys. Rev. D 110, 072014 (2024).
  26. LHCb Collaboration, First observation of the Λb0→D+D−Λ decay, J. High Energy Phys. 07 (2024) 140.
  27. LHCb Collaboration, Study of CP violation in B0→DK(892)0 decays with D→Kπ(ππ),ππ(ππ), and KK final states, J. High Energy Phys. 05 (2024) 025.
  28. T. Sjöstrand, S. Mrenna, and P. Skands, pythia 6.4 physics and manual, J. High Energy Phys. 05 (2006) 026.
  29. I. Belyaev et al., Handling of the generation of primary events in Gauss, the LHCb simulation framework, J. Phys. Conf. Ser. 331, 032047 (2011).
  30. D. J. Lange, The evtgen particle decay simulation package, Nucl. Instrum. Methods Phys. Res., Sect. A 462, 152 (2001).
  31. P. Golonka and Z. Was, photos Monte Carlo: A precision tool for QED corrections in Z and W decays, Eur. Phys. J. C 45, 97 (2006).
  32. N. Davidson, T. Przedzinski, and Z. Was, photos interface in C++: Technical and physics documentation, Comput. Phys. Commun. 199, 86 (2016).
  33. Geant4 Collaboration, geant4 developments and applications, IEEE Trans. Nucl. Sci. 53, 270 (2006).
  34. M. Clemencic G. Corti, S. Easo, C. R. Jones, S. Miglioranzi, M. Pappagallo, and P. Robbe, The LHCb simulation application, Gauss: Design, evolution and experience, J. Phys. Conf. Ser. 331, 032023 (2011).
  35. S. Tolk, J. Albrecht, F. Dettori, and A. Pellegrino, Data driven trigger efficiency determination at LHCb.
  36. M. De Cian, S. Farry, P. Seyfert, and S. Stahl, Fast neural-net based fake track rejection in the LHCb reconstruction.
  37. LHCb Collaboration, Design and performance of the LHCb trigger and full real-time reconstruction in Run 2 of the LHC, J. Instrum. 14, P04013 (2019).
  38. P. Billoir, M. De Cian, P. A. Günther, and S. Stemmle, A parametrized Kalman filter for fast track fitting at LHCb, Comput. Phys. Commun. 265, 108026 (2021).
  39. LHCb Collaboration, LHCb detector performance, Int. J. Mod. Phys. A 30, 1530022 (2015).
  40. J. Gavranovič and B. P. Kerševan, Systematic evaluation of generative machine learning capability to simulate distributions of observables at the large hadron collider, Eur. Phys. J. C 84, 911 (2024).
  41. M. Cacciari, M. Greco, and P. Nason, The pT spectrum in heavy-flavour hadroproduction, J. High Energy Phys. 05 (1998) 007.
  42. M. Cacciari, S. Frixione, N. Houdeau, M. L. Mangano, P. Nason, and G. Ridolfi, Theoretical predictions for charm and bottom production at the LHC, J. High Energy Phys. 10 (2012) 137.
  43. M. Fey and J. E. Lenssen, Fast graph representation learning with PyTorch geometric, arXiv:1903.02428.
  44. LHCb Collaboration, Adopting new technologies in the LHCb Gauss simulation framework, EPJ Web Conf. 214, 02004 (2019).
  45. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, Generative adversarial networks, Commun. ACM 63, 139 (2020).
  46. X. Yang, M. Yan, S. Pan, X. Ye, and D. Fan, Simple and efficient heterogeneous graph neural network, in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37 (2023), pp. 10816–10824.
  47. W. Sutcliffe, M. Calvi, S. Capelli, J. Eschle, J. García Pardiñas, A. Mathad et al., Scalable multi-task learning for particle collision event reconstruction with heterogeneous graph neural networks, Mach. Learn. Sci. Tech. 6, 045060 (2025).
  48. A. Huang, X. Ju, J. Lyons, D. Murnane, M. Pettee, and L. Reed, Heterogeneous graph neural network for identifying hadronically decayed tau leptons at the High Luminosity LHC, J. Instrum. 18, P07001 (2023).
  49. S. Caillou, C. Collard, C. Rougier, J. Stark, H. Torres, and A. Vallier, Novel fully-heterogeneous GNN designs for track reconstruction at the HL-LHC, EPJ Web Conf. 295, 09028 (2024).
  50. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, Graph attention networks, arXiv:1710.10903.
  51. T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, Improved techniques for training GANs, arXiv:1606.03498.
  52. L. Anderlini, A. Contu, C. R. Jones, S. S. Malde, D. Muller, S. Ogilvy et al., The PIDCalib package, 2016.
  53. LHCb Collaboration, Measurement of the branching fraction ratio RK at large dilepton invariant mass, J. High Energy Phys. 07 (2025) 198.
  54. LHCb Collaboration, Test of lepton universality in b→sℓ+ℓ− decays, Phys. Rev. Lett. 131, 051803 (2023).
  55. LHCb Collaboration, Test of lepton universality in beauty-quark decays, Nat. Phys. 18, 277 (2022).

Outline

Information

Phys. Rev. D 113, 012005– Published 13 January, 2026
  • Received 9 July 2025
  • Accepted 4 December 2025
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Funded by SCOAP3.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation