G. Paspalaki

Abstract The high instantaneous luminosity of the CERN Large Hadron Collider leads to multiple proton–proton interactions in the same or nearby bunch crossings (pileup). Advanced pileup mitigation algorithms are designed to remove this noise from pileup particles and improve the performance of crucial physics observables. This study implements a semi-supervised graph neural network for particle-level pileup noise removal, by identifying individual particles produced from pileup. The graph neural network is firstly trained on charged particles with known labels, which can be obtained from detector measurements on data or simulation, and then inferred on neutral particles for which such labels are missing. This semi-supervised approach does not depend on the neutral particle pileup label information from simulation, and thus allows us to perform training directly on experimental data. The performance of this approach is found to be consistently better than widely-used domain algorithms and comparable to the fully-supervised training using simulation truth information. The study serves as the first attempt at applying semi-supervised learning techniques to pileup mitigation, and opens up a new direction of fully data-driven machine learning pileup mitigation studies.

The identification of jets originated from b quarks is crucial for a broad range of physics analyses. Various b tagging algorithms exist at CMS and are further developed with the use of the machine learning techniques. Constant monitoring of the basic quantities provided to the high-level taggers is fundamental to ensure a good tagging performance and to spot potential issues in the data taking. We present a comparison between the proton-proton collision data collected by the CMS detector in 2016 and simulation. The comparison is between the input variables used by the heavy flavour tagging algorithms and the taggers distributions in several event topologies.