Pretrained Event Classification Model for High Energy Physics Analysis

TL;DR

This paper presents a foundation model for event classification in high-energy physics using a Graph Neural Network trained on extensive simulated data, demonstrating improved performance and generalizability across diverse tasks.

Contribution

The introduction of a pretrained GNN-based foundation model tailored for high-energy physics event classification, with analysis of its internal representations and transfer capabilities.

Findings

Fine-tuning enhances classification accuracy, especially with limited data.

The model generalizes well to new physics processes and different simulation frameworks.

Representation analysis shows preserved encoders with altered message-passing layers after fine-tuning.

Abstract

We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes. The model is pretrained to learn a general and robust representation of collision data using challenging multiclass and multilabel classification tasks. Its performance is evaluated across seven event classification tasks, which include new physics processes not encountered during pretraining as well as ATLAS Open Data to demonstrate generalizability across different simulation frameworks, from Delphes fast simulation to full ATLAS detector simulation. Fine-tuning the pretrained model significantly improves classification performance, particularly in scenarios with limited training data, demonstrating gains in both accuracy and computational efficiency. To investigate the underlying mechanisms behind these performance improvements, we employ a representational similarity evaluation framework based on Centered Kernel Alignment. This analysis reveals that encoder-stage representations of the fine-tuned model remain similar to those of the baseline, while intermediate graph processing layers diverge substantially, indicating that fine-tuning preserves general-purpose encoders while developing fundamentally different message-passing pathways to arrive at superior task performance.