JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics
arXiv:2606.14813v1 Announce Type: cross Abstract: Jet tagging at the Large Hadron Collider increasingly relies on deep learning models trained on massive simulated datasets, leading to high computational costs and limited robustness to detector mismodeling. We introduce JetParticle-JEPA (JP-JEPA), a self-supervised Joint-Embedding Predictive Architecture that learns physically meaningful jet representations directly from continuous particle clouds without tokenization or reconstruction of raw inputs. Built on a Particle Transformer backbone, JP-JEPA predicts latent representations of masked pa
The increasing reliance on deep learning models in high-energy physics necessitates more efficient and robust methods for data processing and analysis.
This development offers a potential pathway to significantly reduce computational costs and improve the reliability of jet tagging in critical scientific research like high-energy physics.
Traditional deep learning limitations in high-energy physics are addressed through a self-supervised learning approach that bypasses tokenization and raw input reconstruction, leading to more efficient representation learning.
- · High-energy physics researchers
- · Particle accelerator facilities (e.g., CERN)
- · AI model developers for scientific applications
- · Traditional computationally intensive jet tagging methods
- · Developers of less robust deep learning models in physics
More efficient and accurate high-energy physics experiments become possible.
Reduced computing resource demands could free up capacity for other scientific AI endeavors.
The methodology could inspire similar self-supervised representation learning techniques in other complex scientific domains facing large dataset challenges.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI