发表机构
College of Computer Science and Software Engineering, Shenzhen University; School of Computer Science and Technology, University of Science and Technology of China; International Quantum Academy; Research Institute for Quantum Technology, The Hong Kong Polytechnic University（深圳大学计算机科学与技术学院; 中国科学技术大学计算机科学与技术学院; 国际量子科学院; 香港理工大学量子技术研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对高密度对撞机环境，提出演化几何Transformer（EGT），通过动态重建击中连接图并引入可学习几何偏置，在多个基准上提升径迹重建精度，最高达79.6%。
AI 中文摘要
高亮度大型强子对撞机中的带电粒子径迹重建面临密集击中环境和组合歧义的挑战。现有的基于图的方法和Transformer方法通常依赖静态几何邻域，这无法适应径迹级表示的演化。我们提出了演化几何Transformer（EGT），一种图Transformer，它在连续的编码器层重建击中连接图，并将相对击中坐标作为可学习的注意力偏置。在跨越线性、螺旋和简化TrackML事件的五个模拟基准中，最多包含200-500条同时轨迹，EGT在共享基准协议下的五个设置中的三个上取得了最高的拟合精度，在最复杂的设置上达到79.6%，超过最强基线1.6个百分点。将演化拓扑替换为静态图会使完美径迹率从81%降至29%，而移除几何偏置则使其降至73%。在合成背景注入等于信号击中数量的情况下，拟合精度下降3.4个百分点。神经网络前向传播在NVIDIA A100 GPU上每个事件需要31毫秒。这些结果表明，当局部几何本身不足以确定轨迹归属时，击中关联的迭代细化可提高完整径迹的恢复。
英文摘要
Charged particle track reconstruction at the High-Luminosity Large Hadron Collider is challenged by dense hit environments and combinatorial ambiguities. Existing graph-based and Transformer approaches commonly rely on static geometric neighbourhoods, which cannot adapt as track-level representations evolve. We propose the Evolving-Geometry Transformer (EGT), a graph Transformer that reconstructs the hit-connectivity graph at successive encoder layers and incorporates relative hit coordinates as learnable attention biases. Across five simulation benchmarks spanning linear, helical, and reduced TrackML events with up to 200--500 simultaneous trajectories, EGT achieves the highest FitAccuracy on three of five settings under the shared benchmark protocol, reaching 79.6\% on the most complex setting and exceeding the strongest baseline by 1.6 percentage points. Replacing the evolving topology with a static graph reduces the perfect-track rate from 81\% to 29\%, while removing the geometric bias reduces it to 73\%. Under synthetic background injection equal to the number of signal hits, FitAccuracy decreases by 3.4 percentage points. The neural-network forward pass requires 31~ms per event on an NVIDIA A100 GPU. These results indicate that iterative refinement of hit associations improves complete-track recovery when local geometry alone is insufficient to determine trajectory membership.
Comments25 pages, 6 figures
