Explaining machine-learned particle-flow reconstruction

Abstract

The particle-flow (PF) algorithm is used in general-purpose particle detectors to reconstruct a comprehensive particle-level view of the collision by combining information from different subdetectors. A graph neural network (GNN) model, known as the machine-learned particle-flow (MLPF) algorithm, has been developed to substitute the rule-based PF algorithm. However, understanding the model's decision making is not straightforward, especially given the complexity of the set-to-set prediction task, dynamic graph building, and message-passing steps. In this paper, we adapt the layerwise-relevance propagation technique for GNNs and apply it to the MLPF algorithm to gauge the relevant nodes and features for its predictions. Through this process, we gain insight into the model's decision-making.

5 pages, 3 figures. Accepted to Machine Learning for Physical Sciences NeurIPS 2021 workshop

References in corpus (8)

• PYTHIA 6.4 Physics and Manual
• Fast Graph Representation Learning with PyTorch Geometric
• Particle-flow reconstruction and global event description with the CMS detector
• Description and performance of track and primary-vertex reconstruction with the CMS tracker
• Charged particle tracking via edge-classifying interaction networks
• HepSim: a repository with predictions for high-energy physics experiments
• Measurement of sigma(ppbar -> Z + X) Br(Z -> tau+tau-) at sqrt(s)=1.96 TeV
• Explainable machine learning of the underlying physics of high-energy particle collisions