Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments

TL;DR

This paper enhances particle physics event classification by integrating physics-motivated features, including SM interaction strengths, into Transformer and graph neural network architectures, significantly improving background rejection and signal significance.

Contribution

It introduces energy-dependent SM interaction strengths into deep learning models, improving event classification performance in particle physics.

Findings

Background rejection improved by 10-40% over baselines.

Additional 9% gain from SM interaction matrix.

Enhanced architectures yield significant signal significance improvements.

Abstract

A major task in particle physics is the measurement of rare signal processes. Even modest improvements in background rejection, at a fixed signal efficiency, can significantly enhance the measurement sensitivity. Building on prior research by others that incorporated physical symmetries into neural networks, this work extends those ideas to include additional physics-motivated features. Specifically, we introduce energy-dependent particle interaction strengths, derived from leading-order SM predictions, into modern deep learning architectures, including Transformer Architectures (Particle Transformer), and Graph Neural Networks (Particle Net). These interaction strengths, represented as the SM interaction matrix, are incorporated into the attention matrix (transformers) and edges (graphs). Our results in event classification show that the integration of all physics-motivated features improves background rejection by $10\%-40\%$ over baseline models, with an additional gain of up to $9\%$ due to the SM interaction matrix. This study also provides one of the broadest comparisons of event classifiers to date, demonstrating how various architectures perform across this task. A simplified statistical analysis demonstrates that these enhanced architectures yield significant improvements in signal significance compared to a graph network baseline.