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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mokhtar, Farouk, Pata, Joosep, Garcia, Dolores, Wulff, Eric, Zhang, Mengke, Kagan, Michael, Duarte, Javier
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913910976675840
author Mokhtar, Farouk
Pata, Joosep
Garcia, Dolores
Wulff, Eric
Zhang, Mengke
Kagan, Michael
Duarte, Javier
author_facet Mokhtar, Farouk
Pata, Joosep
Garcia, Dolores
Wulff, Eric
Zhang, Mengke
Kagan, Michael
Duarte, Javier
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00131
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders
Mokhtar, Farouk
Pata, Joosep
Garcia, Dolores
Wulff, Eric
Zhang, Mengke
Kagan, Michael
Duarte, Javier
High Energy Physics - Experiment
Machine Learning
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
Instrumentation and Detectors
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.
title Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders
topic High Energy Physics - Experiment
Machine Learning
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
Instrumentation and Detectors
url https://arxiv.org/abs/2503.00131