用分块层级注意力提升粒子喷注识别效率，兼顾精度与实时性。
Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging
- 结合几何消息传递与分块层级注意力，建模粒子局部结构与全局关系。
- 在四类基准上实现资源受限下的最高准确率与背景抑制效果。
- 适合高能物理实时触发系统，兼顾计算效率与分类性能。
实时喷注识别对大型强子对撞机中高通量探测器至关重要，因触发系统需在严格延迟与精度约束下决定保存哪些碰撞事件。尽管变压器架构在计算无限制时达到最高识别精度，但其二次复杂度的自注意力机制使推理难以满足触发预算。现有高效变体虽降低计算成本，却损害分类性能。为此，我们提出分块层级注意力变压器（PHAT-JeT），融合两种机制：基于物理启发的几何消息传递模块，编码局部探测器平面结构；以及分层分块注意力方案，在小粒子组内精确计算注意力，通过轻量级分块令牌通信保持全局上下文。在有限预算下，PHAT-JeT在四个基准（HLS4ML、JetClass、Top Tagging、Quark–Gluon）上实现所有资源受限模型中的最先进精度与背景拒识能力。代码已开源于 https://github.com/aaronw5/PHAT-JeT。
原文摘要 · Abstract (English)
Real-time jet tagging is critical for identifying short-lived particle decays in the high-throughput detectors of the Large Hadron Collider, where real-time trigger systems responsible for deciding which collision events to store impose strict latency and accuracy constraints. While transformer architectures achieve the highest jet tagging accuracy when compute is unconstrained, their quadratic self-attention cost makes inference restrictive on trigger budget. Existing efficient variants reduce the computational cost, but hinder the classification performance. To address this limitation, we introduce the Patch Hierarchical Attention Transformer (PHAT-JeT), which combines two mechanisms: a physics-inspired geometric message-passing module that encodes local detector-plane structure, and a hierarchical patch-based attention scheme that computes exact attention within small particle groups while preserving global context through lightweight patch-token communication. Within a restricted budget, PHAT-JeT achieves state-of-the-art accuracy and background rejection among all resource-constrained jet tagging models on four benchmarks (\textsc{hls4ml}, JetClass, Top Tagging, and Quark--Gluon). Our code is available at https://github.com/aaronw5/PHAT-JeT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。