Scaling Graph Neural Networks for Particle Track Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917978968162304 |
|---|---|
| author | Tripathy, Alok Lazar, Alina Ju, Xiangyang Calafiura, Paolo Yelick, Katherine Buluc, Aydin |
| author_facet | Tripathy, Alok Lazar, Alina Ju, Xiangyang Calafiura, Paolo Yelick, Katherine Buluc, Aydin |
| contents | Particle track reconstruction is an important problem in high-energy physics (HEP), necessary to study properties of subatomic particles. Traditional track reconstruction algorithms scale poorly with the number of particles within the accelerator. The Exa.TrkX project, to alleviate this computational burden, introduces a pipeline that reduces particle track reconstruction to edge classification on a graph, and uses graph neural networks (GNNs) to produce particle tracks. However, this GNN-based approach is memory-prohibitive and skips graphs that would exceed GPU memory. We introduce improvements to the Exa.TrkX pipeline to train on samples of input particle graphs, and show that these improvements generalize to higher precision and recall. In addition, we adapt performance optimizations, introduced for GNN training, to fit our augmented Exa.TrkX pipeline. These optimizations provide a $2\times$ speedup over our baseline implementation in PyTorch Geometric. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04670 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scaling Graph Neural Networks for Particle Track Reconstruction Tripathy, Alok Lazar, Alina Ju, Xiangyang Calafiura, Paolo Yelick, Katherine Buluc, Aydin Machine Learning Computational Engineering, Finance, and Science Distributed, Parallel, and Cluster Computing Particle track reconstruction is an important problem in high-energy physics (HEP), necessary to study properties of subatomic particles. Traditional track reconstruction algorithms scale poorly with the number of particles within the accelerator. The Exa.TrkX project, to alleviate this computational burden, introduces a pipeline that reduces particle track reconstruction to edge classification on a graph, and uses graph neural networks (GNNs) to produce particle tracks. However, this GNN-based approach is memory-prohibitive and skips graphs that would exceed GPU memory. We introduce improvements to the Exa.TrkX pipeline to train on samples of input particle graphs, and show that these improvements generalize to higher precision and recall. In addition, we adapt performance optimizations, introduced for GNN training, to fit our augmented Exa.TrkX pipeline. These optimizations provide a $2\times$ speedup over our baseline implementation in PyTorch Geometric. |
| title | Scaling Graph Neural Networks for Particle Track Reconstruction |
| topic | Machine Learning Computational Engineering, Finance, and Science Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2504.04670 |