IRIS-HEP Fellow: Ameya Thete
Fellowship dates: Jun – Aug, 2022
Home Institution: BITS, Pilani - K.K. Birla Goa Campus
Project: Equivariant Graph Neural Networks for Particle TrackingTracking devices, or trackers, at the LHC record hits of charged particles produced in a collision event. The task of track reconstruction involves clustering tracker hits to reconstruct the trajectories of these particles. The sparse nature of tracking data makes graph neural networks (GNNs) well-suited to particle tracking applications. The goal of this project is to develop a GNN for particle tracking by explicitly incorporating rotational equivariance into the model. Incorporating physically meaningful symmetries into the GNN can reduce the number of parameters and potentially reduce training and inference times for the model, while retaining the expressive power of non-equivariant GNNs.
More information: My project proposal
Savannah Thais (Princeton University)
Daniel Murnane (Lawrence Berkeley National Laboratory)
- 13 Jun 2022 - "Equivariant Graph Neural Networks for Particle Tracking", Ameya Thete, IRIS-HEP Fellows "Lightning" Talks
- 19 Oct 2022 - "Equivariant GNNs for Charged Particle Tracking", Ameya Thete, IRIS-HEP Fellows Presentations 2022 Recording: Equivariant GNNs for Charged Particle Tracking
May 2022 - Undergraduate student of Physics and Computer Science at BITS, Pilani - K.K. Birla Goa Campus.