Oct 19 – 23, 2020
Europe/Zurich timezone

Graph Neural Network-based Event Classification for Measurement of the Higgs-Top Yukawa Interaction

Oct 22, 2020, 2:20 PM
Regular talk 1 ML for data reduction : Application of Machine Learning to data reduction, reconstruction, building/tagging of intermediate object Workshop


Ryan Roberts (Lawrence Berkeley National Lab. (US))


The measurement of the associated production of Higgs boson with a top-quark pair (ttH) at the LHC provides a direct determination of the Higgs-Top Yukawa interaction. The presence of a large number of objects in the final state makes the measurement very challenging. Multivariate Analysis methods such as Boosted Decision Trees (BDT) were used to enhance the analysis sensitivity. However, the sensitivity gain largely depends on physics-inspired input discriminating variables, which in practice require a significant amount of time to engineer carefully. In this presentation, we separate ttH signal from its main background using a Graph Neural Network (GNN), in which collision data are represented by graphs of nodes and edges. The graph representation and message passing of the GNN make the exploitation of relational information more effective between final state particles. We will report results using simulated events and compare GNN-based and BDT-based event classifiers. We will also examine how well the GNN model captures relational information in the event, which is challenging to represent in conventional BDT-based models.

Primary authors

Haichen Wang (Lawrence Berkeley National Lab. (US)) Xiangyang Ju (Lawrence Berkeley National Lab. (US)) Ryan Roberts (Lawrence Berkeley National Lab. (US)) Shuo Han (Lawrence Berkeley National Lab. (US)) Allison Lauren Xu (Lawrence Berkeley National Lab. (US)) Pamela Pajarillo (Lawrence Berkeley National Lab. (US))

Presentation materials