aiqbench analysis
This study presents a Graph Neural Network foundation model trained on over 120 million simulated proton-proton collisions to enhance event classification in high-energy physics. By demonstrating that fine-tuning preserves general-purpose encoders while optimizing message-passing pathways, the research offers significant gains in accuracy and efficiency for scenarios with limited training data. The work highlights a critical intersection where advanced machine learning techniques are directly applied to solve complex problems within fundamental particle physics simulations.
Pretrained Event Classification Model for High Energy Physics Analysis
arXiv:2412.10665v3 Announce Type: replace-cross 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.
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.
High Energy Physics - Phenomenology (hep-ph); Machine Learning (cs.LG)
arXiv:2412.10665 [hep-ph]
(or arXiv:2412.10665v3 [hep-ph] for this version)
Full text under the publisher's open licence · 196 words
Related coverage
Cross-Domain Transfer with Particle Physics Foundation Models: From Jets to Neutrino Interactions
arXiv · Aug 27, 2026
Machine Learning Meets High-Energy Nuclear Physics: From Pattern Recognition to Physics-Integrated Discovery
arXiv · Oct 10, 2026
Learning to bin: differentiable and Bayesian optimization for multi-dimensional discriminants in high-energy physics
arXiv · Sep 23, 2026
Evaluating Quantum Kernel Methods for Track-Based Classification in High-Energy Physics
arXiv · Aug 28, 2026