Deep Sets for Flavor Tagging on the ATLAS Experiment

Flavour Tagging is a major client for tracking in particle physics experiments at high energy colliders, where it is used to identify the experimental signatures of heavy flavor production. Among other features, charm and beauty hadron decays produce jets containing several tracks with large impact parameter. This work introduces a new architecture for Flavour Tagging, based on Deep Sets, which models the jet as a set of tracks. Such approach is an evolution with respect to the Recurrent Neural Network (RNN) currently adopted in the ATLAS experiment, which treats track collections as a sequence. The Deep Sets algorithm uses track impact parameters and kinematics within a permutation-invariant architecture, leading to a significant decrease in training and evaluation time, and faster optimization. We compare the Deep Sets algorithm with current ATLAS Flavour Tagging benchmarks and provide an outlook on methods to explore and interpret the information learned by the network in the training process.