About
Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well-suited to address a variety of recon- struction problems in HEP. In particular, tracker events are naturally repre- sented as graphs by identifying hits as nodes and track segments as edges; given a set of hypothesized edges, edge-classifying GNNs predict which rep- resent real track segments. In this work, we adapt the physics-motivated Inter- action Network (IN) GNN to the problem of charged-particle tracking in the high-pileup conditions expected at the HL-LHC. We demonstrate the IN's ex- cellent edge-classification accuracy and tracking efficiency through a suite of measurements at each stage of GNN-based tracking: graph construction, edge- classification, and track building. Notably, the proposed IN architecture is sub- stantially smaller than previously studied GNN tracking architectures; this type of reduction in size critical for enabling GNN-based tracking in constrained computing environments. Furthermore, the IN is easily expressed as a set of matrix operations, making it a promising candidate for acceleration via hetero- geneous computing resources..
0:00:00 Slide 1
0:03:11 Slide 2
0:06:21 Slide 3
0:09:31 Slide 4
0:12:41 Slide 5
0:15:51 Slide 6
0:19:01 Slide 7
0:22:11 Slide 8
0:25:21 Slide 9
0:28:31 Slide 10
The talk
Credits and licence
- Institution
- CERN
- Department
- Conferences
- Speaker
- Gage DeZoort
- Year
- 2021
- Language
- English
- Subjects
- Physics, Computer science, Earth and environment
- Source
- CERN
- Licence
- CERN, as CERN states it. CERN's terms
- Attribution
- © CERN. CERN provides its audiovisual media free of charge for educational and informational use, credited to CERN; this lecture is shown in CERN's own player.
- Who can watch
- CERN gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed