Topological Reconstruction of Particle Physics Processes using Graph Neural Networks

Abstract

We present a new approach, the Topograph, which reconstructs underlying physics processes, including the intermediary particles, by leveraging underlying priors from the nature of particle physics decays and the flexibility of message passing graph neural networks. The Topograph not only solves the combinatoric assignment of observed final state objects, associating them to their original mother particles, but directly predicts the properties of intermediate particles in hard scatter processes and their subsequent decays. In comparison to standard combinatoric approaches or modern approaches using graph neural networks, which scale exponentially or quadratically, the complexity of Topographs scales linearly with the number of reconstructed objects. We apply Topographs to top quark pair production in the all hadronic decay channel, where we outperform the standard approach and match the performance of the state-of-the-art machine learning technique.

arXiv comment25 pages, 24 figures, 8 tables

References in corpus (39)

• A Comprehensive Survey on Graph Neural Networks
• The automated computation of tree-level and next-to-leading order differential cross sections, and their matching to parton shower simulations
• The anti-k_t jet clustering algorithm
• A Brief Introduction to PYTHIA 8.1
• FastJet user manual
• DELPHES 3, A modular framework for fast simulation of a generic collider experiment
• Tuning PYTHIA 8.1: the Monash 2013 Tune
• Automatic spin-entangled decays of heavy resonances in Monte Carlo simulations
• ParticleNet: Jet Tagging via Particle Clouds
• Measurement of the top quark mass using proton-proton data at sqrt(s) = 7 and 8 TeV
• Graph Neural Networks in Particle Physics
• JEDI-net: a jet identification algorithm based on interaction networks
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• Measurement of differential cross sections for top quark pair production using the lepton+jets final state in proton-proton collisions at 13 TeV
• A likelihood-based reconstruction algorithm for top-quark pairs and the KLFitter framework
• Measurement of the top quark mass in the $t\bar{t}\to$ lepton+jets channel from $\sqrt{s}=8$ TeV ATLAS data and combination with previous results
• Search for the Standard Model Higgs boson produced in association with top quarks and decaying into a $b\bar{b}$ pair in $pp$ collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector
• Measurements of normalized differential cross-sections for ttbar production in pp collisions at sqrt(s) = 7 TeV using the ATLAS detector
• Anomaly detection with Convolutional Graph Neural Networks
• Measurements of top-quark pair differential and double-differential cross-sections in the $\ell$+jets channel with $pp$ collisions at $\sqrt{s}=13$ TeV using the ATLAS detector
• Measurement of differential cross sections for the production of top quark pairs and of additional jets in lepton+jets events from pp collisions at $\sqrt{s}=$ 13 TeV
• Measurement of the top quark mass in the all-jets final state at $\sqrt{s}=$ 13 TeV and combination with the lepton+jets channel
• Evidence for single top-quark production in the $s$-channel in proton-proton collisions at $\sqrt{s}=$8 TeV with the ATLAS detector using the Matrix Element Method
• The Matrix Element Method and its Application to Measurements of the Top Quark Mass
• Measurement of the production cross sections for a Z boson and one or more b jets in pp collisions at sqrt(s) = 7 TeV
• Measurements of top-quark pair differential cross-sections in the lepton+jets channel in $pp$ collisions at $\sqrt{s}$=13 TeV using the ATLAS detector
• Determination of the top-quark pole mass using $t\bar{t}+1$-jet events collected with the ATLAS experiment in 7 TeV $pp$ collisions
• Measurement of differential $\text{t}\overline{\text{t}}$ production cross sections in the full kinematic range using lepton+jets events from proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Casting a graph net to catch dark showers
• Measurement of the top quark mass with lepton+jets final states using pp collisions at $\sqrt{s}=$ 13 TeV
• Measurement of the top-quark mass in $t\bar{t}+1$-jet events collected with the ATLAS detector in $pp$ collisions at $\sqrt{s}=8$ TeV
• Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
• Top-quark mass measurement in the all-hadronic $t\bar{t}$ decay channel at $\sqrt{s}$ = 8 TeV with the ATLAS detector
• SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention
• Measurements of top-quark pair single- and double-differential cross-sections in the all-hadronic channel in $pp$ collisions at $\sqrt{s}=13~\mbox{TeV}$ using the ATLAS detector
• Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
• The Boosted Higgs Jet Reconstruction via Graph Neural Network
• Measurement of spin correlations in t t-bar production using the matrix element method in the muon + jets final state in pp collisions at sqrt(s) = 8 TeV
• Secondary Vertex Finding in Jets with Neural Networks

Cited by in corpus (13)

• Constraints on the trilinear and quartic Higgs couplings from triple Higgs production at the LHC and beyond
• ${\nu }^2$-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows
• Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks
• Interplay of Traditional Methods and Machine Learning Algorithms for Tagging Boosted Objects
• Parton Labeling without Matching: Unveiling Emergent Labelling Capabilities in Regression Models
• Foundations of automatic feature extraction at LHC--point clouds and graphs
• Top-philic Machine Learning
• Reconstructing short-lived particles using hypergraph representation learning
• A search for R-parity-violating supersymmetry in final states containing many jets in $pp$ collisions at $\sqrt{s}=13\text{TeV}$ with the ATLAS detector
• Quantum-annealing-inspired algorithms for multijet clustering
• PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
• Countering adversarial perturbations in graphs using error correcting codes
• TIGER: A Topology-Agnostic, Hierarchical Graph Network for Event Reconstruction