Particle track reconstruction in high-density collider environments with an Evolving-Geometry Transformer
Abstract
Charged particle track reconstruction at the High-Luminosity Large Hadron Collider is challenged by dense hit environments and combinatorial ambiguities. Existing graph-based and Transformer approaches commonly rely on static geometric neighbourhoods, which cannot adapt as track-level representations evolve. We propose the Evolving-Geometry Transformer (EGT), a graph Transformer that reconstructs the hit-connectivity graph at successive encoder layers and incorporates relative hit coordinates as learnable attention biases. Across five simulation benchmarks spanning linear, helical, and reduced TrackML events with up to 200--500 simultaneous trajectories, EGT achieves the highest FitAccuracy on three of five settings under the shared benchmark protocol, reaching 79.6\% on the most complex setting and exceeding the strongest baseline by 1.6 percentage points. Replacing the evolving topology with a static graph reduces the perfect-track rate from 81\% to 29\%, while removing the geometric bias reduces it to 73\%. Under synthetic background injection equal to the number of signal hits, FitAccuracy decreases by 3.4 percentage points. The neural-network forward pass requires 31~ms per event on an NVIDIA A100 GPU. These results indicate that iterative refinement of hit associations improves complete-track recovery when local geometry alone is insufficient to determine trajectory membership.
Related
- Transformer-based machine learning using low-level calorimeter signals for collimated photon identification at collider experiments
- Machine-learned particle flow as a foundation model for collider physics
- A neural delta-f particle-in-cell method: evolving the background with learned backward flows
- Fast and Precise Learned Charged-Particle Trajectory Regression at the Large Hadron Collider
- Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion
BibTeX
@misc{ou2026particle,
title = {{Particle track reconstruction in high-density collider environments with an Evolving-Geometry Transformer}},
author = {Chenxiu Ou and Yan Wang and Mingjiang Liang and Man-Hong Yung and Qin Zhang and Zhaofeng Su},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.39196},
eprint = {2609.39196},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.39196},
}
RIS
TY - UNPB
TI - Particle track reconstruction in high-density collider environments with an Evolving-Geometry Transformer
AU - Chenxiu Ou
AU - Yan Wang
AU - Mingjiang Liang
AU - Man-Hong Yung
AU - Qin Zhang
AU - Zhaofeng Su
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.39196
UR - https://arxiv.org/abs/2609.39196
AB - Charged particle track reconstruction at the High-Luminosity Large Hadron Collider is challenged by dense hit environments and combinatorial ambiguities. Existing graph-based and Transformer approaches commonly rely on static geometric neighbourhoods, which cannot adapt as track-level representations evolve. We propose the Evolving-Geometry Transformer (EGT), a graph Transformer that reconstructs the hit-connectivity graph at successive encoder layers and incorporates relative hit coordinates as learnable attention biases. Across five simulation benchmarks spanning linear, helical, and reduced TrackML events with up to 200--500 simultaneous trajectories, EGT achieves the highest FitAccuracy on three of five settings under the shared benchmark protocol, reaching 79.6\% on the most complex setting and exceeding the strongest baseline by 1.6 percentage points. Replacing the evolving topology with a static graph reduces the perfect-track rate from 81\% to 29\%, while removing the geometric bias reduces it to 73\%. Under synthetic background injection equal to the number of signal hits, FitAccuracy decreases by 3.4 percentage points. The neural-network forward pass requires 31~ms per event on an NVIDIA A100 GPU. These results indicate that iterative refinement of hit associations improves complete-track recovery when local geometry alone is insufficient to determine trajectory membership.
ER -