SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention

TL;DR

The paper introduces SPANet, a symmetry-preserving attention network that efficiently solves complex set-assignment problems in particle physics, outperforming existing methods in accuracy and speed by leveraging physical invariances.

Contribution

A novel symmetry-preserving attention mechanism for set assignment problems that scales to complex configurations and significantly improves performance in particle physics applications.

Findings

Improves reconstruction efficiency by 19-35% on benchmark problems.

Reduces inference time by 2-5 orders of magnitude for complex events.

Outperforms current methods in accuracy and scalability.

Abstract

The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics. Collisions typically produce variable-size sets of observed particles which have inherent ambiguities complicating the assignment of observed particles to the decay products of the heavy particles. Current strategies for tackling these challenges in the physics community ignore the physical symmetries of the decay products and consider all possible assignment permutations and do not scale to complex configurations. Attention based deep learning methods for sequence modelling have achieved state-of-the-art performance in natural language processing, but they lack built-in mechanisms to deal with the unique symmetries found in physical set-assignment problems. We introduce a novel method for constructing symmetry-preserving attention networks which reflect the problem's natural invariances to efficiently find assignments without evaluating all permutations. This general approach is applicable to arbitrarily complex configurations and significantly outperforms current methods, improving reconstruction efficiency between 19\% - 35\% on typical benchmark problems while decreasing inference time by two to five orders of magnitude on the most complex events, making many important and previously intractable cases tractable. A full code repository containing a general library, the specific configuration used, and a complete dataset release, are avaiable at https://github.com/Alexanders101/SPANet