Jet Flavour Classification with a Graph Neural Network (GNN) at the LHCb

This research explores the application of Graph Neural Networks (GNNs) for jet flavor classification at the LHCb experiment, focusing specifically on the identification of b-jets. Efficient jet flavour tagging is crucial for event reconstruction and particle analyses in high energy physics (HEP). GNNs excel in capturing complex relationships within graph-structured data, and we aim to enhance the classification of b-jets using this method of deep learning. The developed GNN model is able to identify b-jets with a versatile range of efficiencies and will be extended for further classification involving b-jets, c-jets, and fat jets with heavy flavor jets inside.