The Boosted Higgs Jet Reconstruction via Graph Neural Network

TL;DR

This paper introduces a graph neural network approach for Higgs jet reconstruction that outperforms traditional methods in efficiency and accuracy, and also enhances signal-background discrimination in collider events.

Contribution

The study applies a graph convolutional network with focal loss to Higgs jet reconstruction, demonstrating improved performance over traditional substructure-based methods and extending to signal-background discrimination.

Findings

Higher Higgs tagging efficiency achieved

Better reconstruction accuracy than traditional methods

Enhanced signal-background discrimination in collider events

Abstract

By representing each collider event as a point cloud, we adopt the Graphic Convolutional Network (GCN) with focal loss to reconstruct the Higgs jet in it. This method provides higher Higgs tagging efficiency and better reconstruction accuracy than the traditional methods which use jet substructure information. The GCN, which is trained on events of the $H$+jets process, is capable of detecting a Higgs jet in events of several different processes, even though the performance degrades when there are boosted heavy particles other than the Higgs in the event. We also demonstrate the signal and background discrimination capacity of the GCN by applying it to the $t\bar{t}$ process. Taking the outputs of the network as new features to complement the traditional jet substructure variables, the $t\bar{t}$ events can be separated further from the $H$+jets events.