Boosted Higgs boson jet reconstruction via a graph neural network
Jun Guo, Jinmian Li, Tianjun Li, Rao Zhang
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 $H+\text{jets}$ 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 boson in the event. We also demonstrate the signal and background discrimination capacity of the GCN by applying it to the $t\overline{t}$ process. Taking the outputs of the network as new features to complement the traditional jet substructure variables, the $t\overline{t}$ events can be separated further from the $H+\text{jets}$ events.