Charged particle tracking via edge-classifying interaction networks

TL;DR

This paper adapts a physics-inspired interaction network GNN for particle tracking in high-luminosity collider conditions, demonstrating high accuracy and efficiency with a smaller, versatile architecture suitable for constrained computing environments.

Contribution

The work introduces a smaller, efficient interaction network GNN architecture for particle tracking, suitable for high-luminosity collider environments, with promising acceleration strategies for real-time applications.

Findings

High edge-classification accuracy in simulated conditions

Reduced GNN architecture size compared to previous methods

Potential for accelerated implementation on heterogeneous hardware

Abstract

Recent work has demonstrated that geometric deep learning methods such as graph neural networks (GNNs) are well suited to address a variety of reconstruction problems in high energy particle physics. In particular, particle tracking data is naturally represented as a graph by identifying silicon tracker hits as nodes and particle trajectories as edges; given a set of hypothesized edges, edge-classifying GNNs identify those corresponding to real particle trajectories. In this work, we adapt the physics-motivated interaction network (IN) GNN toward the problem of particle tracking in pileup conditions similar to those expected at the high-luminosity Large Hadron Collider. Assuming idealized hit filtering at various particle momenta thresholds, we demonstrate the IN's excellent edge-classification accuracy and tracking efficiency through a suite of measurements at each stage of GNN-based tracking: graph construction, edge classification, and track building. The proposed IN architecture is substantially smaller than previously studied GNN tracking architectures; this is particularly promising as a reduction in size is critical for enabling GNN-based tracking in constrained computing environments. Furthermore, the IN may be represented as either a set of explicit matrix operations or a message passing GNN. Efforts are underway to accelerate each representation via heterogeneous computing resources towards both high-level and low-latency triggering applications.