JetParticle-JEPA: An Efficient Self-Supervised Representation Learning method for Jet Tagging in High-Energy Physics
For high-energy physics researchers, JP-JEPA provides a data-efficient and robust foundation-model approach to jet tagging, reducing reliance on massive simulated datasets.
JP-JEPA, a self-supervised Joint-Embedding Predictive Architecture, learns jet representations from continuous particle clouds without tokenization. It achieves performance comparable to fully supervised methods on JetClass, surpasses supervised baselines in low-label regimes, and shows robustness to missing detector information.
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 particles while preserving fine-grained kinematic correlations. On the JetClass benchmark, JP-JEPA achieves performance comparable to fully supervised state-of-the-art methods on the full dataset, surpasses supervised baselines in low-label regimes, and significantly outperforms existing SSL approaches. On Top Quark and Quark-Gluon Tagging benchmarks, it remains on par with supervised methods. The learned representations also exhibit strong robustness to missing detector information and improved uncertainty behavior, highlighting JP-JEPA as a promising foundation-model framework for robust and data-efficient jet physics at the LHC.