Corpus ID: 227247880

Graph Neural Networks for Particle Tracking and Reconstruction

  title={Graph Neural Networks for Particle Tracking and Reconstruction},
  author={Javier Mauricio Duarte and J. Vlimant},
  journal={arXiv: High Energy Physics - Phenomenology},
Machine learning methods have a long history of applications in high energy physics (HEP). Recently, there is a growing interest in exploiting these methods to reconstruct particle signatures from raw detector data. In order to benefit from modern deep learning algorithms that were initially designed for computer vision or natural language processing tasks, it is common practice to transform HEP data into images or sequences. Conversely, graph neural networks (GNNs), which operate on graph data… Expand
MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
MLPF, an end-to-end trainable machine-learned particle flow algorithm for reconstructing particle flow candidates based on parallelizable, computationally efficient, scalable graph neural networks and a multi-task objective is introduced. Expand
Physics and Computing Performance of the Exa.TrkX TrackML Pipeline
New developments needed to study the physics and computing performance of the Exa.TrkX pipeline on the full TrackML dataset are documents, a first step towards validating the pipeline using ATLAS and CMS data. Expand
Point cloud transformers applied to collider physics
A modified transformer network called point cloud transformer is applied as a method to incorporate the advantages of the transformer architecture to an unordered set of particles resulting from collision events to compare the performance with other strategies. Expand
Shared Data and Algorithms for Deep Learning in Fundamental Physics
A collection of datasets from fundamental physics research, containing hadronic top quarks, cosmic-ray induced air showers, phase transitions in hadronic matter, and generator-level histories are made public to simplify future work on cross-disciplinary machine learning and transfer learning in fundamental physics. Expand
Distributed Training and Optimization Of Neural Networks
The various ways to do the necessary computations in parallel in parallel are reviewed, and they are put in the context of high energy physics. Expand
Machine Learning scientific competitions and datasets
Four scientific competitions with the objective of discovering innovative techniques to perform typical High Energy Physics tasks, like event reconstruction, classification and new physics discovery are summarised in this chapter. Expand


Set2Graph: Learning graphs from sets, in Graph Representation Learning and Beyond
  • Workshop at the 37th International Conference on Machine Learning
  • 2020
A Living Review of Machine Learning for Particle Physics
This living review is a nearly comprehensive list of citations for those developing and applying deep learning approaches to experimental, phenomenological, or theoretical analyses, and will be updated as often as possible to incorporate the latest developments. Expand
Compressing deep neural networks on FPGAs to binary and ternary precision with HLS4ML
The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources, and shows how to balance between latency and accuracy by retaining full precision on a selected subset of network components. Expand
GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud
A novel neural network for point cloud is proposed, dubbed GAPNet, to learn local geometric representations by embedding graph attention mechanism within stacked Multi-Layer-Perceptron (MLP) layers and applies stacked MLP layers to attention features and local signature to fully extract local geometric structures. Expand
GPU coprocessors as a service for deep learning inference in high energy physics
A comprehensive exploration of the use of GPU-based hardware acceleration for deep learning inference within the data reconstruction workflow of high energy physics is presented. Expand
Graph Neural Networks in TensorFlow and Keras with Spektral
An overview of Spektral's features is presented and the performance of the methods implemented by the library in scenarios of node classification, graph classification, and graph regression is reported. Expand
Graph neural networks in particle physics
Various applications of graph neural networks in particle physics are reviewed, including different graph constructions, model architectures and learning objectives, as well as key open problems in particle science for which graph neural Networks are promising. Expand
On the Universality of Rotation Equivariant Point Cloud Networks
A first study of the approximation power of neural architectures that are invariant or equivariant to all three shape-preserving transformations of point clouds: translation, rotation, and permutation is presented. Expand
Towards a computer vision particle flow
In High Energy Physics experiments Particle Flow (PFlow) algorithms are designed to provide an optimal reconstruction of the nature and kinematic properties of the particles produced within theExpand
42 J
  • Duarte & J-R. Vlimant D. Rankin, T. Aarrestad, V. Loncar, M. Pierini, S. Summers, J. Ngadiuba, M. Liu, E. Kreinar, and Z. Wu, Accelerated charged particle tracking with graph neural networks on FPGAs, in 3rd Machine Learning and the Physical Sciences Workshop at the 34th Annual Conference on Neural
  • 2020