mlsanityData to 14 Oct 2026

MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks

arXiv 2101.08578 ↗First posted 21 Jan 2021physics.data-an cs.LG hep-excited by 36

Not on the map. Why?

Abstract (arXiv)

In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum. In view of the planned high-luminosity upgrade of the CERN Large Hadron Collider (LHC), it is necessary to revisit existing reconstruction algorithms and ensure that both the physics and computational performance are sufficient in an environment with many simultaneous proton-proton interactions (pileup). Machine learning may offer a prospect for computationally efficient event reconstruction that is well-suited to heterogeneous computing platforms, while significantly improving the reconstruction quality over rule-based algorithms for granular detectors. We introduce MLPF, a novel, end-to-end trainable, machine-learned particle-flow algorithm based on parallelizable, computationally efficient, and scalable graph neural networks optimized using a multi-task objective on simulated events. We report the physics and computational performance of the MLPF algorithm on a Monte Carlo dataset of top quark-antiquark pairs produced in proton-proton collisions in conditions similar to those expected for the high-luminosity LHC. The MLPF algorithm improves the physics response with respect to a rule-based benchmark algorithm and demonstrates computationally scalable particle-flow reconstruction in a high-pileup environment.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 28 of its 81 references that are in the map. First posted on arXiv 21 Jan 2021.

Builds on

28 of 81 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2020Reformer: The Efficient Transformercited by 1,668
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  10. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  11. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  12. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
16 more
  1. 2018Fast inference of deep neural networks in FPGAs for particle physicscited by 133
  2. 2018Energy Flow Networks: Deep Sets for Particle Jetscited by 84
  3. 2019ParticleNet: Jet Tagging via Particle Cloudscited by 64
  4. 2019Learning representations of irregular particle-detector geometry with distance-weighted graph networkscited by 43
  5. 2019Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physicscited by 42
  6. 2020Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physicscited by 34
  7. 2019How to GAN away Detector Effectscited by 28
  8. 2020Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image datacited by 24
  9. 2020Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAscited by 23
  10. 2020Jet Flavour Classification Using DeepJetcited by 16
  11. 2020Towards a Computer Vision Particle Flowcited by 15
  12. 2020Track Seeding and Labelling with Embedded-space Graph Neural Networkscited by 12
  13. 2020Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physicscited by 11
  14. 2020FPGAs-as-a-Service Toolkit (FaaST)cited by 10
  15. 2020GPU coprocessors as a service for deep learning inference in high energy physicscited by 9
  16. 2020Graph Highway Networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 11; 2023: 6; 2024: 4; 2025: 3; 2026: 4.

36 papers.

Sort:

  1. 2021A Living Review of Machine Learning for Particle Physicscited by 78
  2. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  3. 2021Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Trackingcited by 30
  4. 2021Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstructioncited by 20
  5. 2024Finetuning Foundation Models for Joint Analysis Optimizationcited by 18
  6. 2024Learning Long Range Dependencies on Graphs via Random Walkscited by 18
  7. 2021Graph Neural Networks for Charged Particle Tracking on FPGAscited by 17
  8. 2022Machine Learning for Particle Flow Reconstruction at CMScited by 14
  9. 2021The Tracking Machine Learning challenge : Throughput phasecited by 12
  10. 2021Explaining machine-learned particle-flow reconstructioncited by 12
  11. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  12. 2022Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learningcited by 10
24 more
  1. 2024A Language Model for Particle Trackingcited by 10
  2. 2025Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliderscited by 9
  3. 2022Explainable AI for High Energy Physicscited by 7
  4. 2023Progress towards an improved particle flow algorithm at CMS with machine learningcited by 7
  5. 2022End-to-end multi-particle reconstruction in high occupancy imaging calorimeters with graph neural networkscited by 6
  6. 2021Shared Data and Algorithms for Deep Learning in Fundamental Physicscited by 4
  7. 2022Do graph neural networks learn traditional jet substructure?cited by 4
  8. 2023Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectorscited by 4
  9. 2022Hyperparameter optimization of data-driven AI models on HPC systemscited by 3
  10. 2022Bias and Priors in Machine Learning Calibrations for High Energy Physicscited by 3
  11. 2022Data Science and Machine Learning in Educationcited by 3
  12. 2022Learning Tree Structures from Leaves For Particle Decay Reconstructioncited by 3
  13. 2023Graph Structure from Point Clouds: Geometric Attention is All You Needcited by 2
  14. 2025Double Descent and Overparameterization in Particle Physics Datacited by 2
  15. 2026End-to-end event reconstruction for precision physics at future colliderscited by 2
  16. 2026Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Taskscited by 2
  17. 2023Hyperparameter optimization, quantum-assisted model performance prediction, and benchmarking of AI-based High Energy Physics workloads using HPCcited by 1
  18. 2023Low Latency Edge Classification GNN for Particle Trajectory Tracking on FPGAscited by 1
  19. 2023Model Performance Prediction for Hyperparameter Optimization of Deep Learning Models Using High Performance Computing and Quantum Annealingcited by 1
  20. 2025Machine-learning based particle-flow algorithm in CMScited by 1
  21. 2026Machine-learned particle flow as a foundation model for collider physicscited by 1
  22. 2022Deep learning techniques for energy clustering in the CMS ECALcited by 0
  23. 2024Denoising Graph Super-Resolution towards Improved Collider Event Reconstructioncited by 0
  24. 2026HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstructioncited by 0