用异构图神经网络同时提升粒子事件重建速度与精度。
Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks
- 设计异构图网络，区分不同粒子关系并集成剪枝层
- 在多任务训练下实现顶点关联与图剪枝同步优化
- 推理时间随事件复杂度增长更平稳，适合高亮度对撞机
大型强子对撞机的亮度提升正给粒子碰撞事件的重建与分析带来挑战。粒子数量增多导致数据采集阶段延迟和存储压力加剧，同时背景噪声上升、顶点误关联频率增加。为此，需发展更全面且可扩展的重建方法，以利用机器学习最新进展。本文提出一种新型异构图神经网络（HGNN），具备针对不同粒子碰撞关系的独特表示，并集成图剪枝层以实现可扩展性。在模拟LHCb实验环境的多任务框架中训练，该HGNN显著提升了底夸克强子的重建性能。值得注意的是，其能在单一框架内同时完成粒子顶点关联与图剪枝。我们量化了重建与剪枝性能，验证了推理时间随事件复杂度增长的改进，且通过加权消息传递机制缓解了潜在性能损失。
原文摘要 · Abstract (English)
The growing luminosity frontier at the Large Hadron Collider is challenging the reconstruction and analysis of particle collision events. Increased particle multiplicities are straining latency and storage requirements at the data acquisition stage, while new complications are emerging, including higher background levels and more frequent particle vertex misassociations. This in turn necessitates the development of more holistic and scalable reconstruction methods that take advantage of recent advances in machine learning. We propose a novel Heterogeneous Graph Neural Network (HGNN) architecture featuring unique representations for diverse particle collision relationships and integrated graph pruning layers for scalability. Trained with a multi-task paradigm in an environment mimicking the LHCb experiment, this HGNN significantly improves beauty hadron reconstruction performance. Notably, it concurrently performs particle vertex association and graph pruning within a single framework. We quantify reconstruction and pruning performance, demonstrate enhanced inference time scaling with event complexity, and mitigate potential performance loss using a weighted message passing scheme.
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。