Heterogeneous Graph Neural Network for Identifying Hadronically Decayed Tau Leptons at the High Luminosity LHC

TL;DR

This paper introduces a novel graph neural network approach that classifies jets from hadronic tau decays without reconstructing tau leptons, using heterogeneous graph representations of jets for improved identification at the High Luminosity LHC.

Contribution

The paper develops a new GNN-based algorithm that models jets as heterogeneous graphs with tracks and energy clusters, enhancing tau jet identification without explicit tau reconstruction.

Findings

Effective differentiation of tau jets from quark/gluon jets.

Utilization of heterogeneous graph representations improves classification accuracy.

Exploration of various GNN architectures and features enhances model performance.

Abstract

We present a new algorithm that identifies reconstructed jets originating from hadronic decays of tau leptons against those from quarks or gluons. No tau lepton reconstruction algorithm is used. Instead, the algorithm represents jets as heterogeneous graphs with tracks and energy clusters as nodes and trains a Graph Neural Network to identify tau jets from other jets. Different attributed graph representations and different GNN architectures are explored. We propose to use differential track and energy cluster information as node features and a heterogeneous sequentially-biased encoding for the inputs to final graph-level classification.