mlsanityData to 7 Oct 2026

Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking

arXiv 2103.06995 ↗First posted 11 Mar 2021physics.data-an cs.LG hep-excited by 29

Not on the map. Why?

Abstract (arXiv)

The Exa.TrkX project has applied geometric learning concepts such as metric learning and graph neural networks to HEP particle tracking. Exa.TrkX's tracking pipeline groups detector measurements to form track candidates and filters them. The pipeline, originally developed using the TrackML dataset (a simulation of an LHC-inspired tracking detector), has been demonstrated on other detectors, including DUNE Liquid Argon TPC and CMS High-Granularity Calorimeter. This paper documents new developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset, a first step towards validating the pipeline using ATLAS and CMS data. The pipeline achieves tracking efficiency and purity similar to production tracking algorithms. Crucially for future HEP applications, the pipeline benefits significantly from GPU acceleration, and its computational requirements scale close to linearly with the number of particles in the event.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 25 of its 70 references that are in the map. First posted on arXiv 11 Mar 2021.

Builds on

25 of 70 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Graph Attention Networkscited by 8,854
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2017Billion-scale similarity search with GPUscited by 2,477
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  7. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  8. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  9. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  10. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  11. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  12. 2018Horovod: fast and easy distributed deep learning in TensorFlowcited by 275
13 more
  1. 2018Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysiscited by 154
  2. 2017Smart Mining for Deep Metric Learningcited by 96
  3. 2021hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devicescited by 61
  4. 2019Dissecting the Graphcore IPU Architecture via Microbenchmarkingcited by 47
  5. 2019Learning representations of irregular particle-detector geometry with distance-weighted graph networkscited by 43
  6. 2021MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networkscited by 36
  7. 2020Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAscited by 23
  8. 2020Distributed Training of Graph Convolutional Networkscited by 14
  9. 2018TFLMS: Large Model Support in TensorFlow by Graph Rewritingcited by 12
  10. 2020Track Seeding and Labelling with Embedded-space Graph Neural Networkscited by 12
  11. 2020GPU coprocessors as a service for deep learning inference in high energy physicscited by 9
  12. 2020Beyond 4D Tracking: Using Cluster Shapes for Track Seedingcited by 2
  13. 2021Hashing and metric learning for charged particle trackingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 4; 2024: 9; 2025: 5; 2026: 4.

29 papers.

Sort:

By area:

  1. 2021Charged particle tracking via edge-classifying interaction networkscited by 19
  2. 2024Finetuning Foundation Models for Joint Analysis Optimizationcited by 18
  3. 2021Graph Neural Networks for Charged Particle Tracking on FPGAscited by 17
  4. 2021The Tracking Machine Learning challenge : Throughput phasecited by 12
  5. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  6. 2022LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physicscited by 12
  7. 2024A Language Model for Particle Trackingcited by 10
  8. 2023Hierarchical Graph Neural Networks for Particle Track Reconstructioncited by 7
  9. 2023High Pileup Particle Tracking with Object Condensationcited by 7
  10. 2022End-to-end multi-particle reconstruction in high occupancy imaging calorimeters with graph neural networkscited by 6
  11. 2023A General Framework for Robust G-Invariance in G-Equivariant Networkscited by 5
  12. 2025FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physicscited by 5
17 more
  1. 2024TrackFormers: In Search of Transformer-Based Particle Tracking for the High-Luminosity LHC Eracited by 4
  2. 2022Learning Tree Structures from Leaves For Particle Decay Reconstructioncited by 3
  3. 2024PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstructioncited by 3
  4. 2025ColliderML: The First Release of an OpenDataDetector High-Luminosity Physics Benchmark Datasetcited by 3
  5. 2023Graph Structure from Point Clouds: Geometric Attention is All You Needcited by 2
  6. 2024Graph Neural Network for Neutrino Physics Event Reconstructioncited by 2
  7. 2024Combined track finding with GNN & CKFcited by 1
  8. 2024Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learningcited by 1
  9. 2024EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstructioncited by 1
  10. 2025Comparative Analysis of FPGA and GPU Performance for Machine Learning-Based Track Reconstruction at LHCbcited by 1
  11. 2025Scaling Graph Neural Networks for Particle Track Reconstructioncited by 1
  12. 2025Locality-Sensitive Hashing-Based Efficient Point Transformer for Charged Particle Reconstructioncited by 1
  13. 2026Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Taskscited by 1
  14. 2024Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspectivecited by 0
  15. 2026HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstructioncited by 0
  16. 2026Learning Standard Model structure from LHC data with Riemannian flow matchingcited by 0
  17. 2026Goal-Persistent Coding Agents as Scientific Performance Engineers: A Fixed-Radius Nearest-Neighbor Case Studycited by 0