Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors

Experiments at the High-Luminosity LHC and the Future Circular Collider need efficient algorithms to reconstruct granular events expected at such detectors with high fidelity. We study scalable machine learning models for event reconstruction in electron-positron collisions based on a full detector simulation. Particle-flow reconstruction can be formulated as a supervised learning task using tracks and calorimeter clusters. We compare a graph neural network and kernel-based transformer and demonstrate that we can avoid quadratic operations while achieving realistic reconstruction. We show that hyperparameter tuning significantly improves the performance of the models. The best graph neural network model shows improvement in the jet transverse momentum resolution by up to 50% compared to the rule-based algorithm. Accurate reconstruction can significantly improve future measurements at colliders. The resulting model is portable across Nvidia, AMD and Habana hardware. Our datasets and software are published following the findable, accessible, interoperable, and reusable principles.