Abstract
How to represent a jet is at the core of machine learning on jet physics. Inspired by the notion of point clouds, we propose a new approach that considers a jet as an unordered set of its constituent particles, effectively a "particle cloud". Such a particle cloud representation of jets is efficient in incorporating raw information of jets and also explicitly respects the permutation symmetry. Based on the particle cloud representation, we propose ParticleNet, a customized neural network architecture using Dynamic Graph Convolutional Neural Network for jet tagging problems. The ParticleNet architecture achieves state-of-the-art performance on two representative jet tagging benchmarks and is improved significantly over existing methods.
Highlights
A jet is one of the most ubiquitous objects in protonproton collision events at the LHC
The best performance is obtained by the ParticleNet model with particle identification (PID) inputs, achieving almost 15% improvement on the background rejection power compared to the Particle Flow Network (PFN)-Ex (PFN using experimentally realistic PID information) and P-Convolutional neural networks (CNNs) models
We present a new approach for machine learning on jets
Summary
A jet is one of the most ubiquitous objects in protonproton collision events at the LHC. Methods based on the QCD theory have been proposed and continuously improved for discriminating quark and gluon jets [1,2,3,4,5,6,7], tagging jets originating from high-momentum heavy particles [8,9,10,11,12,13,14,15,16,17,18], etc. Instead of organizing a jet’s constituent particles into an ordered structure (e.g., a sequence or a tree), we treat a jet as an unordered set of particles [57] This is very analogous to the point cloud representation of three-dimensional (3D) shapes used in computer vision, where each shape is represented by a set of points in space, and the points themselves are unordered. The ParticleNet architecture is evaluated on two jet tagging benchmarks and is found to achieve significant improvements over all existing methods
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
