Reconstructing unstable heavy particles requires sophisticated techniques to
sift through the large number of possible permutations for assignment of
detector objects to partons. An approach based on a generalized attention
mechanism, symmetry preserving attention networks (SPANet), has been previously
applied to top quark pair decays at the Large Hadron Collider, which produce
six hadronic jets. Here we extend the SPANet architecture to consider multiple
input streams, such as leptons, as well as global event features, such as the
missing transverse momentum. In addition, we provide regression and
classification outputs to supplement the parton assignment. We explore the
performance of the extended capability of SPANet in the context of
semi-leptonic decays of top quark pairs as well as top quark pairs produced in
association with a Higgs boson. We find significant improvements in the power
of three representative studies: search for ttH, measurement of the top quark
mass and a search for a heavy Z' decaying to top quark pairs. We present
ablation studies to provide insight on what the network has learned in each
case.

通过扩展 SPANet 架构以考虑多个输入流和全局事件特征，并提供回归和分类输出以补充粒子分配，本研究探讨了 SPANet 扩展能力在半轻子衰变的顶夸克对以及与希格斯玻色子相关的顶夸克对的背景下的性能。在寻找 ttH、顶夸克质量测量和重 Z' 玻色子衰变为顶夸克对等三个代表性研究中，我们发现了显著的提高。此外，我们通过消融研究提供了有关网络在每种情况下学到的内容的见解。

扩展的对称保持注意力网络用于 LHC 分析

Extended Symmetry Preserving Attention Networks for LHC Analysis

In this paper, we propose generalized attention mechanism (GAM) by first
suggesting a new interpretation for self-attention mechanism of Vaswani et al.
. Following the interpretation, we provide description for different variants
of attention mechanism which together form GAM. Further, we propose a new
relative position representation within the framework of GAM. This
representation can be easily utilized for cases in which elements next to each
other in input sequence can be at random locations in actual dataset/corpus.

本文提出了广义注意力机制 (GAM)，揭示了 Vaswani 等人的自注意力机制的新解释，提供了不同变体注意力机制和 GAM 框架中的新相对位置表示，并可简单应用于不同数据集中元素的不同位置的情况。