Probing stop pair production at the LHC with graph neural networks

• DOI: 10.1007/jhep08(2019)055
• Publication Date: 2019-08-10T05:42:45Z
• Authors: Murat Abdughani; Jie Ren; Lei Wu; Jin Min Yang
• Keywords: Pair production

A bstract Top-squarks (stops) play a crucial role for the naturalness of supersymmetry (SUSY). However, searching stops is tough task at LHC. To dig out huge LHC data, various expert-constructed kinematic variables or cutting-edge analysis techniques have been invented. In this paper, we propose to represent collision events as event graphs and use message passing neutral network (MPNN) analyze events. As proof-of-concept, our method in search stop pair production LHC, find that MPNN can efficiently discriminate signal back-ground comparison with other machine learning methods (e.g. DNN), enhance mass reach by several tens GeV over hundred GeV.