In high-energy particle collisions, the primary collision products usually decay further resulting in tree-like, hierarchical structures with a priori unknown multiplicity. At the stable-particle level all decay products of a collision form permutation invariant sets of final state objects. The analogy to mathematical graphs gives rise to the idea that graph neural networks (GNNs), which naturally resemble these properties, should be best-suited to address many tasks related to high-energy particle physics. In this paper we describe a benchmark test of a typical GNN against neural networks of the well-established deep fully-connected feed-forward architecture. We aim at performing this comparison maximally unbiased in terms of nodes, hidden layers, or trainable parameters of the neural networks under study. As physics case we use the classification of the final state X produced in association with top quark-antiquark pairs in proton-proton collisions at the Large Hadron Collider at CERN, where X stands for a bottom quark-antiquark pair produced either non-resonantly or through the decay of an intermediately produced Z or Higgs boson.

翻译：在高能粒子对撞中，初级对撞产物通常会进一步衰变，形成具有先验未知多重性的树状分层结构。在稳定粒子层面，所有对撞衰变产物构成最终态物体的置换不变集合。与数学图的类比表明，天然符合这些性质的图神经网络（GNN）应最适合处理高能粒子物理中的许多任务。本文描述了对典型GNN与成熟的深度全连接前馈架构神经网络的基准测试。我们旨在以所研究神经网络的节点数、隐藏层数或可训练参数为基准，进行最大程度无偏的比较。物理案例采用欧洲核子研究中心大型强子对撞机质子-质子对撞中与顶夸克-反顶夸克对联合产生的最终态X的分类，其中X代表通过非共振方式或中间产生的Z或希格斯玻色子衰变产生的底夸克-反夸克对。