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

2025-02-28

AI Summary

Developing particle flow reconstruction models for novel detector geometries in future colliders is time-consuming and computationally expensive. Method: We propose the first cross-detector transfer learning framework trained exclusively on full-simulation data, enabling efficient adaptation from CLICdet to FCC-ee/CLD. Our approach integrates deep learning, domain adaptation, and detector-geometry-aware feature alignment. Contribution/Results: Using only 100k simulated CLD events—90% fewer than required for training from scratch—the model achieves event-level performance comparable to conventional rule-based methods. Moreover, it matches the jet energy resolution and missing transverse momentum resolution of end-to-end models trained on one million events. This framework substantially accelerates detector design iteration cycles and establishes a new paradigm for transferable AI models in high-energy physics experiments.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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 pre-train 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 (FCC-ee). 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 resolution 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. These findings offer valuable insights towards building large physics models that can be fine-tuned across different detector designs and geometries, helping accelerate the development cycle for new detectors, and opening the door to rapid detector design and optimization using machine learning.

Problem

• Transfer learning for particle-flow reconstruction in new colliders.
• Fine-tuning models across different detector designs efficiently.
• Achieving high performance with fewer training samples.

Innovation

• Transfer learning for particle-flow reconstruction
• Cross-detector fine-tuning with minimal data
• Machine learning accelerates detector optimization