Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging
This addresses deployment challenges in high-data-throughput environments like the CERN LHC, offering a more efficient solution for particle physics applications.
The paper tackled the high computational cost and latency of transformers in high-energy particle jet tagging by introducing the Spatially Aware Linear Transformer (SAL-T), which achieved classification results comparable to full-attention transformers while using fewer resources and lower latency.
Transformers are very effective in capturing both global and local correlations within high-energy particle collisions, but they present deployment challenges in high-data-throughput environments, such as the CERN LHC. The quadratic complexity of transformer models demands substantial resources and increases latency during inference. In order to address these issues, we introduce the Spatially Aware Linear Transformer (SAL-T), a physics-inspired enhancement of the linformer architecture that maintains linear attention. Our method incorporates spatially aware partitioning of particles based on kinematic features, thereby computing attention between regions of physical significance. Additionally, we employ convolutional layers to capture local correlations, informed by insights from jet physics. In addition to outperforming the standard linformer in jet classification tasks, SAL-T also achieves classification results comparable to full-attention transformers, while using considerably fewer resources with lower latency during inference. Experiments on a generic point cloud classification dataset (ModelNet10) further confirm this trend. Our code is available at https://github.com/aaronw5/SAL-T4HEP.