TrackSorter: A Transformer-based sorting algorithm for track finding in High Energy Physics

TL;DR

TrackSorter introduces a Transformer-based approach to particle track finding, reformulating the problem as a sorting task, and demonstrates effective performance on the TrackML dataset.

Contribution

This paper presents the first Transformer-based end-to-end algorithm for track finding in High Energy Physics, framing pattern recognition as a sorting problem.

Findings

Effective track candidate sorting on TrackML dataset

Transformer model achieves competitive accuracy

Novel tokenization scheme for space points

Abstract

Track finding in particle data is a challenging pattern recognition problem in High Energy Physics. It takes as inputs a point cloud of space points and labels them so that space points created by the same particle have the same label. The list of space points with the same label is a track candidate. We argue that this pattern recognition problem can be formulated as a sorting problem, of which the inputs are a list of space points sorted by their distances away from the collision points and the outputs are the space points sorted by their labels. In this paper, we propose the TrackSorter algorithm: a Transformer-based algorithm for pattern recognition in particle data. TrackSorter uses a simple tokenization scheme to convert space points into discrete tokens. It then uses the tokenized space points as inputs and sorts the input tokens into track candidates. TrackSorter is a novel end-to-end track finding algorithm that leverages Transformer-based models to solve pattern recognition problems. It is evaluated on the TrackML dataset and has good track finding performance.