Learning Symmetry-Independent Jet Representations via Jet-Based Joint Embedding Predictive Architecture
This addresses the need for self-supervised learning models in high energy physics that are not reliant on labeled datasets or biased augmentations, though it appears incremental as it builds on existing SSL techniques.
The study tackled the problem of learning jet representations in high energy physics without hand-crafted augmentations by introducing a jet-based joint embedding predictive architecture (J-JEPA), which avoids biases and enables versatile applications across tasks.
In high energy physics, self-supervised learning (SSL) methods have the potential to aid in the creation of machine learning models without the need for labeled datasets for a variety of tasks, including those related to jets -- narrow sprays of particles produced by quarks and gluons in high energy particle collisions. This study introduces an approach to learning jet representations without hand-crafted augmentations using a jet-based joint embedding predictive architecture (J-JEPA), which aims to predict various physical targets from an informative context. As our method does not require hand-crafted augmentation like other common SSL techniques, J-JEPA avoids introducing biases that could harm downstream tasks. Since different tasks generally require invariance under different augmentations, this training without hand-crafted augmentation enables versatile applications, offering a pathway toward a cross-task foundation model. We finetune the representations learned by J-JEPA for jet tagging and benchmark them against task-specific representations.