Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders

Abstract

We demonstrate transfer learning capabilities in a machine-learned algorithm trained for particle-flow reconstruction in high energy particle colliders. This paper presents a cross-detector fine-tuning study, where we initially pretrain the model on a large full simulation dataset from one detector design, and subsequently fine-tune the model on a sample with a different collider and detector design. Specifically, we use the Compact Linear Collider detector (CLICdet) model for the initial training set and demonstrate successful knowledge transfer to the CLIC-like detector (CLD) proposed for the Future Circular Collider in electron-positron mode. We show that with an order of magnitude less samples from the second dataset, we can achieve the same performance as a costly training from scratch, across particle-level and event-level performance metrics, including jet and missing transverse momentum resolution. Furthermore, we find that the fine-tuned model achieves comparable performance to the traditional rule-based particle-flow approach on event-level metrics after training on 100,000 CLD events, whereas a model trained from scratch requires at least 1 million CLD events to achieve similar reconstruction performance. To our knowledge, this represents the first full-simulation cross-detector transfer learning study for particle-flow reconstruction. These findings offer valuable insights towards building large foundation models that can be fine-tuned across different detector designs and geometries, helping to accelerate the development cycle for new detectors and opening the door to rapid detector design and optimization using machine learning.

20 pages, 13 figures

References in corpus (27)

• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Observation of a new boson at a mass of 125 GeV with the CMS experiment at the LHC
• The anti-k_t jet clustering algorithm
• FastJet user manual
• Particle-flow reconstruction and global event description with the CMS detector
• Observation of a new boson with mass near 125 GeV in pp collisions at sqrt(s) = 7 and 8 TeV
• Jet reconstruction and performance using particle flow with the ATLAS Detector
• The Pandora Software Development Kit for Pattern Recognition
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• Performance of Particle Flow Calorimetry at CLIC
• Symmetries, Safety, and Self-Supervision
• Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data
• Towards a Computer Vision Particle Flow
• Machine Learning Methods for Track Classification in the AT-TPC
• Measurement of sigma(ppbar -> Z + X) Br(Z -> tau+tau-) at sqrt(s)=1.96 TeV
• Reconstructing particles in jets using set transformer and hypergraph prediction networks
• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• A method to challenge symmetries in data with self-supervised learning
• Machine Learning for Particle Flow Reconstruction at CMS
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Solving Key Challenges in Collider Physics with Foundation Models
• Anomalies, Representations, and Self-Supervision
• Re-Simulation-based Self-Supervised Learning for Pre-Training Foundation Models
• Application of Transfer Learning to Neutrino Interaction Classification
• Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors
• Semi-visible jets, energy-based models, and self-supervision