Jul 6 – 8, 2021
Europe/Zurich timezone

Pushing the limit of jet tagging with graph neural networks

Jul 7, 2021, 9:20 AM
20m

Speaker

Huilin Qu (CERN)

Description

Graph neural networks (GNNs) have shown a lot of potential for jet tagging. Recent GNN algorithms such as ParticleNet, ABCNet, and LundNet represent the state-of-the-art in various jet tagging tasks. In this talk, we present some new progress on GNN design for jet tagging. With the incorporation of edge features and optimized network architecture, the new algorithm achieves a significant performance improvement on the top tagging benchmark.

Affiliation CERN
Academic Rank Postdoctoral researcher

Primary author

Presentation materials