25–29 May 2026
Chulalongkorn University
Asia/Bangkok timezone

When Less is More: Towards Lightweight and Distilled Graph Neural Networks and for Efficient Particle Reconstruction in LHCb’s Next-Generation Calorimeter

28 May 2026, 14:03
18m
Chulalongkorn University

Chulalongkorn University

Oral Presentation Track 2 - Online and real-time computing Track 2 - Online and real-time computing

Speakers

Cilicia Uzziel Perez (La Salle, Ramon Llull University (ES)) Irvin Jadurier Umana Chacon (Consejo Nacional de Rectores (CONARE) (CR))

Description

Graph Neural Networks (GNNs) excel at modeling the complex, irregular geometry of modern calorimeters, but their computational cost poses challenges for real-time or resource-constrained environments. We present lightweight, attention-enhanced GNNs built on node-centric GarNet layers, which eliminate costly edge message passing and provide learnable, permutation-invariant aggregation optimized for fast inference and firmware deployment. Tailored for particle reconstruction in the proposed PicoCal for the LHCb Upgrade II, these architectures achieve up to 8× faster inference than traditional message-passing GNNs while maintaining superior energy-resolution performance compared to conventional reconstruction algorithms.
To further reduce latency, we evaluate two compressed variants: a compact GarNet student with ~40% fewer parameters that preserves the teacher’s performance, and a knowledge-distilled MLP trained on GarNet’s latent graph embeddings—a Graph(GarNet)-to-MLP approach—that provides an additional 2–6× speedup and even surpasses the GarNet teacher in energy resolution despite a ~95% reduction in model size. Together with ongoing firmware-level integration for real-time filtering in the LHCb trigger system, this work demonstrates a practical and scalable pathway for deploying high-performance, graph-based calorimeter reconstruction in future high-rate particle-detection pipelines.

Authors

Cilicia Uzziel Perez (La Salle, Ramon Llull University (ES)) Irvin Jadurier Umana Chacon (Consejo Nacional de Rectores (CONARE) (CR)) Francisco Siles (Consejo Nacional de Rectores (CONARE) (CR)) Miriam Calvo Gomez (La Salle, Ramon Llull University (ES)) Ronald Caravaca (Consejo Nacional de Rectores (CONARE) (CR)) Xavier Vilasis Cardona (La Salle, Ramon Llull University (ES))

Presentation materials

There are no materials yet.