Hierarchical Graph Neural Networks for Particle Track Reconstruction
This work addresses particle tracking in high-energy physics, offering incremental improvements in efficiency and robustness for domain-specific applications.
The paper tackles particle track reconstruction by introducing a Hierarchical Graph Neural Network (HGNN) with a learnable pooling algorithm and a new loss function, achieving better tracking efficiency, robustness against inefficient input graphs, and faster convergence compared to previous ML-based methods.
We introduce a novel variant of GNN for particle tracking called Hierarchical Graph Neural Network (HGNN). The architecture creates a set of higher-level representations which correspond to tracks and assigns spacepoints to these tracks, allowing disconnected spacepoints to be assigned to the same track, as well as multiple tracks to share the same spacepoint. We propose a novel learnable pooling algorithm called GMPool to generate these higher-level representations called "super-nodes", as well as a new loss function designed for tracking problems and HGNN specifically. On a standard tracking problem, we show that, compared with previous ML-based tracking algorithms, the HGNN has better tracking efficiency performance, better robustness against inefficient input graphs, and better convergence compared with traditional GNNs.