Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks

Abstract

The growing luminosity frontier at the Large Hadron Collider is challenging the reconstruction and analysis of particle collision events. Increased particle multiplicities are straining latency and storage requirements at the data acquisition stage, while new complications are emerging, including higher background levels and more frequent particle vertex misassociations. This in turn necessitates the development of more holistic and scalable reconstruction methods that take advantage of recent advances in machine learning. We propose a novel Heterogeneous Graph Neural Network (HGNN) architecture featuring unique representations for diverse particle collision relationships and integrated graph pruning layers for scalability. Trained with a multi-task paradigm in an environment mimicking the LHCb experiment, this HGNN significantly improves beauty hadron reconstruction performance. Notably, it concurrently performs particle vertex association and graph pruning within a single framework. We quantify reconstruction and pruning performance, demonstrate enhanced inference time scaling with event complexity, and mitigate potential performance loss using a weighted message passing scheme.

23 pages, 9 figures, 4 tables (revised for Machine Learning Science and Technology)

References in corpus (22)

• ParticleNet: Jet Tagging via Particle Clouds
• Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree
• Determination of the quark coupling strength $|V_{ub}|$ using baryonic decays
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Machine and Deep Learning Applications in Particle Physics
• Measurement of the CP-violating phase phi_s in the decay Bs->J/psi phi
• Design and performance of the LHCb trigger and full real-time reconstruction in Run 2 of the LHC
• The Full Event Interpretation -- An exclusive tagging algorithm for the Belle II experiment
• The LHCb upgrade I
• MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks
• A comprehensive real-time analysis model at the LHCb experiment
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• Graph Neural Networks for Charged Particle Tracking on FPGAs
• OmniJet-$\alpha$: The first cross-task foundation model for particle physics
• Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models
• A Method to Simultaneously Facilitate All Jet Physics Tasks
• Measurement of the branching fraction ratios $R(D^{+})$ and $R(D^{\ast +})$ using muonic $\tau$ decays
• New graph-neural-network flavor tagger for Belle II and measurement of $\sin 2{\varphi }_1$ in $B^0\to J/\psi K_{\text{S}}^0$ decays
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Heterogeneous Graph Neural Network for Identifying Hadronically Decayed Tau Leptons at the High Luminosity LHC
• A parametrized Kalman filter for fast track fitting at LHCb
• Graph Neural Network for Neutrino Physics Event Reconstruction

Cited by in corpus (2)

• Minimising Event Size, Maximising Physics: Inclusive Particle Isolation for LHCb's Run 3
• Towards replacing detector simulation with heterogeneous GNNs in flavour physics analyses